CN118068819A - Large model data management system for high quality diagnostics and decision making - Google Patents
Large model data management system for high quality diagnostics and decision making Download PDFInfo
- Publication number
- CN118068819A CN118068819A CN202410459967.XA CN202410459967A CN118068819A CN 118068819 A CN118068819 A CN 118068819A CN 202410459967 A CN202410459967 A CN 202410459967A CN 118068819 A CN118068819 A CN 118068819A
- Authority
- CN
- China
- Prior art keywords
- numerical control
- executed
- control instruction
- equipment
- production
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000013523 data management Methods 0.000 title claims abstract description 19
- 238000004519 manufacturing process Methods 0.000 claims abstract description 137
- 238000004458 analytical method Methods 0.000 claims abstract description 20
- 238000003745 diagnosis Methods 0.000 claims abstract description 12
- 238000011156 evaluation Methods 0.000 claims abstract description 10
- 230000035945 sensitivity Effects 0.000 claims description 27
- 238000012797 qualification Methods 0.000 claims description 18
- 230000006399 behavior Effects 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 12
- 230000007613 environmental effect Effects 0.000 claims description 10
- 238000012544 monitoring process Methods 0.000 claims description 6
- 239000012634 fragment Substances 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 230000002159 abnormal effect Effects 0.000 abstract description 17
- 238000012216 screening Methods 0.000 abstract description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0262—Confirmation of fault detection, e.g. extra checks to confirm that a failure has indeed occurred
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- General Factory Administration (AREA)
Abstract
The invention relates to the technical field of equipment data management, in particular to a large model data management system for high-quality diagnosis and decision, which comprises a production state acquisition module, an equipment numerical control instruction calling module, an instruction association influence analysis module, an instruction risk characteristic evaluation module and an instruction execution supervision module, wherein the instruction association influence analysis module is used for analyzing operation interference relations among numerical control instructions in a numerical control instruction set to be executed and also analyzing influence intervention relations among elements in a production process set and the numerical control instructions in the numerical control instruction set to be executed. According to the invention, the numerical control instruction set to be executed in the intelligent manufacturing process is collected and analyzed, the numerical control instruction which causes abnormal data to be generated is screened and locked in advance, and corresponding diagnosis and decision are carried out according to the screening result, so that the abnormal data in the intelligent manufacturing process is restrained, the influence of the abnormal data on the production of products of equipment is reduced, and the effective supervision of the abnormal data is realized.
Description
Technical Field
The invention relates to the technical field of equipment data management, in particular to a large model data management system for high-quality diagnosis and decision.
Background
Along with the continuous development of science and technology, the requirements of people on manufacturing industry are higher and higher, the traditional manufacturing mode can not meet the actual demands of the market, and further intelligent manufacturing is generated, so that the labor is saved, and meanwhile, the production efficiency and the product quality of a product can be effectively improved.
However, in the intelligent manufacturing process, abnormal data may cause abnormal production conditions of production equipment, and further result in the influence of quality of products, so that monitoring, diagnosis and decision of the abnormal data are important links in the intelligent manufacturing process.
The existing large model data management system for high-quality diagnosis and decision-making generally adopts a timely alarm mode, namely, monitoring data of corresponding equipment at each position in the intelligent manufacturing process is monitored in real time through a sensor, and the obtained data is compared with a preset sensor monitoring normal interval to realize real-time alarm of abnormal data; however, the method has a large defect, the existing method is to perform diagnosis and decision (alarm) only when abnormal data are already generated, the generated abnormal data still have influence on products remained in the equipment, the abnormal data cannot be prejudged in advance, and the corresponding diagnosis and decision are performed according to the prejudgment result.
Disclosure of Invention
The present invention is directed to a large model data management system for high quality diagnosis and decision making to solve the above-mentioned problems set forth in the background art.
In order to solve the technical problems, the invention provides the following technical scheme: a large model data management system for high quality diagnosis and decision, which comprises a production state acquisition module, a device numerical control instruction calling module, an instruction association influence analysis module, an instruction risk characteristic evaluation module and an instruction execution supervision module,
The production state acquisition module is used for acquiring the running state information of the equipment at the current time, wherein the running state information of the equipment comprises the types of the produced products, the production processes of the produced products in the equipment at the current time and the corresponding production process sets of the corresponding product types in the equipment;
the equipment numerical control instruction calling module is used for obtaining a numerical control instruction set to be executed, which is received by the equipment numerical control panel based on the current time;
The instruction association influence analysis module is used for analyzing operation interference relations among all numerical control instructions in the numerical control instruction set to be executed and also analyzing influence intervention relations among all elements in the production flow set and all numerical control instructions in the numerical control instruction set to be executed respectively;
The instruction risk feature evaluation module acquires an analysis result of the instruction association influence analysis module, and combines environmental feature information in an equipment area corresponding to each element in the numerical control instruction set to be executed in the current time equipment and user instruction operation information corresponding to corresponding equipment in the historical data to acquire operation risk feature influence values corresponding to each element in the numerical control instruction set to be executed respectively;
And the instruction execution supervision module generates priorities of numerical control instructions corresponding to the elements in the numerical control instruction set to be executed according to the operation risk characteristic influence values respectively corresponding to the elements in the numerical control instruction set to be executed, and manages and pre-warns the numerical control instructions in the numerical control instruction set to be executed by combining the obtained instruction priorities so as to assist a user in diagnosing and deciding the execution condition of the numerical control instructions in the numerical control instruction set to be executed.
Further, each production flow to which the production product belongs in the current time equipment represents each production flow which is running in the current time equipment and contains the production product;
The corresponding production flow set of the corresponding product type in the equipment is a set formed by all production flows required to be executed in the current equipment in the production cycle of the corresponding product type;
In the running state information of the current time equipment, the set formed by each production flow to which the production product belongs in the current time equipment is a subset of the corresponding production flow set of the corresponding product type in the equipment.
In the invention, in the production process of the equipment, not every production flow area keeps an open running state, or the production flow area which possibly keeps the running state does not have corresponding products in production, so that each production flow to which the produced products belong in the equipment at the current time and a corresponding production flow set of the corresponding product types in the equipment are required to be distinguished.
Further, the to-be-executed numerical control instruction set received by the numerical control panel based on the current time equipment represents a set formed by receiving and sending all control instructions which are not executed by the equipment and are sent by the equipment under the operation of a user;
the numerical control instruction set to be executed, which is received by the numerical control panel of the current time equipment, comprises zero, one or a plurality of elements.
Further, when the instruction association influence analysis module analyzes the operation interference relation among the numerical control instructions in the numerical control instruction set to be executed, which is received by the numerical control panel and is received by the current time equipment, is obtained and marked as A; the numerical control instruction corresponding to the i-th element in A is marked as Ai;
Taking Ai as a reference node, judging whether the reference node has an operation sensitivity influence on each element after the reference node, wherein i epsilon [1, i1], and i1 represents the total number of elements in A;
when the reference node affects the operation sensitivity formed by each element after the reference node, extracting a to-be-executed numerical control instruction interference sequence segment formed by the reference node and each element after the reference node, and judging that an operation interference relationship exists among each numerical control instruction in the to-be-executed numerical control instruction interference sequence segment in the to-be-executed numerical control instruction set;
When the reference node has the condition that the elements behind the reference node do not form the operation sensitivity influence, the reference node is changed, the first element which does not form the operation sensitivity influence after the original reference node is taken as a new reference node, and whether the new reference node forms the operation sensitivity influence on the elements behind the new reference node is judged again;
If the new reference node is Ai1, judging that the operation interference relation among all numerical control instructions in the numerical control instruction set to be executed does not exist and the corresponding numerical control instruction interference sequence segment to be executed is empty;
When judging whether the reference node Ai has an operation sensitivity influence on the following element Ai2, i2 epsilon [1, i1] is carried out, acquiring distribution position areas corresponding to Ai and Ai2 in the numerical control panel, and judging that Ai has an operation sensitivity influence on Ai2 if the intersection of the distribution position areas corresponding to Ai and Ai2 is an empty set; otherwise, it is determined that Ai does not constitute an operation sensitivity influence on Ai 2.
The invention acquires the interference sequence segment of the numerical control instruction to be executed, and considers that the numerical control instruction sent by a user in the process of generating the numerical control instruction on the numerical control panel is possibly not all required by the user, and also can be generated due to the fact that the user touches the numerical control panel by mistake due to the sensitivity problem of the numerical control panel, and in general, abnormal data can be generated due to the fact that the numerical control instruction generated by touching the numerical control panel by mistake is an error instruction.
Further, when the instruction association influence analysis module analyzes influence intervention relations between each element in the production flow set and each numerical control instruction in the numerical control instruction set to be executed respectively, each element in the production flow set is obtained, the j element in the generation flow set is marked as Lj,
Judging the intersection of the equipment execution area corresponding to Ai and the equipment area corresponding to Lj, and when the obtained intersection is not empty, adding the execution Ai in the obtained intersection area as a new production condition into the original production condition TYLj in the equipment area corresponding to Lj to obtain a new production condition corresponding to Lj, and marking as TXLj; the production conditions of the production processes except for Lj in the matching history data are unchanged, and the corresponding product qualification rate is marked as a first qualification rate when the production conditions are TXLj in all products processed in the equipment area corresponding to Lj; the production conditions of the production processes except for Lj in the matching history data are unchanged, and in all products processed by the equipment area corresponding to Lj, the corresponding product qualification rate is recorded as a second qualification rate when the production conditions are TYLj;
If the difference value between the second qualification rate and the first qualification rate is greater than or equal to a preset value, judging that the production flows respectively corresponding to each element in the production flow set Lj and the subsequent elements are influenced by the intervention of Ai, and inputting the production flows respectively corresponding to each element in the production flow set Lj and the subsequent elements in sequence into a blank set one by one to generate an intervention influence flow sequence set corresponding to Ai, wherein the elements in the intervention influence flow sequence set corresponding to Ai and Ai have influence intervention relations; otherwise, the interventional influence procedure sequence set corresponding to Ai is empty.
Further, when the instruction risk feature evaluation module obtains the operation risk feature influence values respectively corresponding to the elements in the to-be-executed numerical control instruction set, environmental feature information in the equipment area corresponding to the elements in the to-be-executed numerical control instruction set in the current time equipment is obtained, and the equipment area corresponding to the i-th element in the to-be-executed numerical control instruction set in the current time equipment is marked as QAi; the environmental characteristic information corresponding to the QAi is recorded as H QAi; the environmental characteristic information comprises sensor monitoring values corresponding to all indexes in production conditions, wherein the production conditions comprise all monitored indexes and all executing instructions, and the production conditions comprise the monitored indexes comprising temperature and humidity;
Acquiring user instruction operation information corresponding to the environment characteristic information in the corresponding equipment area in the historical data respectively in the error range, wherein the user instruction operation information comprises instruction sequences formed by continuous numerical control instructions when the environment characteristic information in the corresponding equipment area is in the error range, and discontinuous time slices in the historical data correspond to different instruction sequences; extracting all instruction sequences comprising to-be-executed numerical control instruction interference sequence fragments from each obtained instruction sequence, and marking the set as a first instruction sequence set; marking elements which are contained in the first instruction sequence set and aim at misoperation behaviors of the numerical control instruction interference sequence segment to be executed; if the operation behavior corresponding to the subsequent first numerical control instruction of the numerical control instruction interference sequence segment to be executed contained in the element in the first instruction sequence set is a return operation, judging that the element in the first instruction sequence set contains misoperation behaviors aiming at the numerical control instruction interference sequence segment to be executed; otherwise, judging that the element in the first instruction sequence set does not contain misoperation behaviors aiming at the numerical control instruction interference sequence segment to be executed;
the error ranges of the indexes corresponding to different production conditions in the environment characteristic information are different, and the error ranges of the indexes corresponding to the production conditions are preset in a database;
Acquiring operation risk characteristic influence values corresponding to elements in a numerical control instruction set to be executed respectively, and marking the operation risk characteristic influence value corresponding to an i-th element in the numerical control instruction set to be executed as Bi;
，
Wherein Mi represents the number of elements in an intersection of a set formed by each production flow to which a product belongs in the current time equipment and an intervention influence flow sequence set corresponding to Ai;
PGi denotes a deviation interference coefficient corresponding to Ai, and PGi =0 when Ai does not belong to a numerical control instruction interference sequence segment to be executed; when Ai belongs to the section of the numerical control instruction interference sequence to be executed, Wherein Ei h represents the total number of elements in the h to-be-executed numerical control instruction interference sequence segment containing Ai; HEi h represents the corresponding position serial number of Ai in the h to-be-executed numerical control instruction interference sequence segment containing Ai;
fi represents the ratio of the number of marked elements in the first instruction sequence set to the total number of elements in the first instruction sequence set.
According to the method, the numerical control instruction to be executed corresponding to the user is comprehensively evaluated from multiple angles, the corresponding operation risk (operation risk characteristic influence value) of the numerical control instruction corresponding to each element in the numerical control instruction set to be executed is quantized, the numerical control instruction which causes abnormal data to be generated in the subsequent step is conveniently screened, and data support is provided for generating the priority of the numerical control instruction corresponding to each element in the numerical control instruction set to be executed in the subsequent step.
Further, when the instruction execution supervision module generates the priorities of the numerical control instructions corresponding to the elements in the numerical control instruction set to be executed, the elements in the numerical control instruction set to be executed are ordered according to the order of the influence values of the corresponding operation risk characteristics from large to small, so as to obtain a first sequence, and the priorities corresponding to the elements in the first sequence are equal to the serial numbers of the corresponding elements in the first sequence.
Further, when the instruction execution supervision module manages and pre-warns the numerical control instructions in the numerical control instruction set to be executed, the elements in the numerical control instruction set to be executed are ordered from big to small according to the sequence, and sequence numbers of the elements in the numerical control instruction set to be executed are obtained; judging whether the element serial number corresponding to each element in the numerical control instruction set to be executed is equal to the corresponding priority in value or not;
Extracting each element with the element serial numbers which are different from the corresponding priority in numerical values and correspond to the element serial numbers in the numerical control instruction set to be executed, feeding back the element serial numbers extracted in the numerical control instruction set to be executed and the element serial numbers which are behind the element serial numbers to be executed to the user, carrying out early warning on the user, and after the user confirms that the feedback content is correct, sequentially executing each numerical control instruction to be executed; otherwise, judging that each feedback numerical control instruction to be executed is invalid.
Compared with the prior art, the invention has the following beneficial effects: according to the invention, through collecting and analyzing the numerical control instruction set to be executed in the intelligent manufacturing process, screening and locking are carried out on numerical control instructions which cause abnormal data to be generated in advance, corresponding diagnosis and decision are carried out according to screening results, the generation of the abnormal data in the intelligent manufacturing process is restrained from the root place (artificial misoperation), the influence of the abnormal data on the production products of equipment is reduced, and effective supervision of the abnormal data is realized.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of the architecture of a large model data management system for high quality diagnostics and decision making of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides the following technical solutions: a large model data management system for high quality diagnosis and decision, which comprises a production state acquisition module, a device numerical control instruction calling module, an instruction association influence analysis module, an instruction risk characteristic evaluation module and an instruction execution supervision module,
The production state acquisition module is used for acquiring the running state information of the equipment at the current time, wherein the running state information of the equipment comprises the types of the produced products, the production processes of the produced products in the equipment at the current time and the corresponding production process sets of the corresponding product types in the equipment;
In this embodiment, each production device includes a plurality of production processes, and different production processes are all regulated and controlled by corresponding numerical control panels of the devices; at the same time, the operating states of different production flows of the same equipment may be different, i.e., some production flows may remain on, while some production flows may remain off.
Each production flow to which the production product belongs in the current time equipment represents each production flow which is running in the current time equipment and contains the production product;
The corresponding production flow set of the corresponding product type in the equipment is a set formed by all production flows required to be executed in the current equipment in the production cycle of the corresponding product type;
In the running state information of the current time equipment, the set formed by each production flow to which the production product belongs in the current time equipment is a subset of the corresponding production flow set of the corresponding product type in the equipment.
The equipment numerical control instruction calling module is used for obtaining a numerical control instruction set to be executed, which is received by the equipment numerical control panel based on the current time;
the to-be-executed numerical control instruction set received by the numerical control panel based on the current time equipment represents a set formed by receiving and sending all control instructions which are not executed by the equipment and are sent by the equipment under the operation of a user;
the numerical control instruction set to be executed, which is received by the numerical control panel of the current time equipment, comprises zero, one or a plurality of elements.
The instruction association influence analysis module is used for analyzing operation interference relations among all numerical control instructions in the numerical control instruction set to be executed and also analyzing influence intervention relations among all elements in the production flow set and all numerical control instructions in the numerical control instruction set to be executed respectively;
When the instruction association influence analysis module analyzes the operation interference relation among all numerical control instructions in the numerical control instruction set to be executed, acquiring the numerical control instruction set to be executed, which is received by the numerical control panel, of the current time equipment and is marked as A; the numerical control instruction corresponding to the i-th element in A is marked as Ai;
Taking Ai as a reference node, judging whether the reference node has an operation sensitivity influence on each element after the reference node, wherein i epsilon [1, i1], and i1 represents the total number of elements in A;
when the reference node affects the operation sensitivity formed by each element after the reference node, extracting a to-be-executed numerical control instruction interference sequence segment formed by the reference node and each element after the reference node, and judging that an operation interference relationship exists among each numerical control instruction in the to-be-executed numerical control instruction interference sequence segment in the to-be-executed numerical control instruction set;
When the reference node has the condition that the elements behind the reference node do not form the operation sensitivity influence, the reference node is changed, the first element which does not form the operation sensitivity influence after the original reference node is taken as a new reference node, and whether the new reference node forms the operation sensitivity influence on the elements behind the new reference node is judged again;
If the new reference node is Ai1, judging that the operation interference relation among all numerical control instructions in the numerical control instruction set to be executed does not exist and the corresponding numerical control instruction interference sequence segment to be executed is empty;
When judging whether the reference node Ai has an operation sensitivity influence on the following element Ai2, i2 epsilon [1, i1] is carried out, acquiring distribution position areas corresponding to Ai and Ai2 in the numerical control panel, and judging that Ai has an operation sensitivity influence on Ai2 if the intersection of the distribution position areas corresponding to Ai and Ai2 is an empty set; otherwise, it is determined that Ai does not constitute an operation sensitivity influence on Ai 2.
In this embodiment, if the numerical control instruction set a to be executed includes four numerical control instructions, A1, A2, A3, and A4 are respectively in sequence;
If the distribution position area of A1 in the numerical control panel and the distribution position area of A2 in the numerical control panel do not have intersection, the distribution position area of A1 in the numerical control panel and the distribution position area of A3 in the numerical control panel have intersection, and the distribution position area of A1 in the numerical control panel and the distribution position area of A4 in the numerical control panel do not have intersection;
If the intersection exists between the distribution position area of A2 in the numerical control panel and the distribution position area of A3 in the numerical control panel, the intersection exists between the distribution position area of A2 in the numerical control panel and the distribution position area of A4 in the numerical control panel;
If the intersection does not exist between the distribution position area of A3 in the numerical control panel and the distribution position area of A4 in the numerical control panel;
in the process of acquiring the interference sequence segment of the numerical control instruction to be executed,
Firstly taking A1 as a reference node, judging whether the reference node A1 forms operation sensitivity influence on each element (A2, A3 and A4) after the reference node A1, wherein the distribution position area of A1 in the numerical control panel and the distribution position area of A2 in the numerical control panel do not have intersection, the distribution position area of A1 in the numerical control panel and the distribution position area of A4 in the numerical control panel do not have intersection, the reference node is required to be updated, and the A2 is taken as a new reference node because the position of A2 in the numerical control instruction set A to be executed is more advanced than that of A4,
Because the intersection exists between the distribution position area of A2 in the numerical control panel and the distribution position area of A3 in the numerical control panel, the intersection exists between the distribution position area of A2 in the numerical control panel and the distribution position area of A4 in the numerical control panel, the reference node A2 forms the operation sensitivity influence on each element (A3 and A4) after the reference node A2, and the numerical control instruction interference sequence segments { A2, A3 and A4} to be executed are further obtained.
The instruction association influence analysis module is used for acquiring each element in the production flow set and marking the j element in the generation flow set as Lj when analyzing influence intervention relations between each element in the production flow set and each numerical control instruction in the numerical control instruction set to be executed respectively,
Judging the intersection of the equipment execution area corresponding to Ai and the equipment area corresponding to Lj, and when the obtained intersection is not empty, adding the execution Ai in the obtained intersection area as a new production condition into the original production condition TYLj in the equipment area corresponding to Lj to obtain a new production condition corresponding to Lj, and marking as TXLj; the production conditions of the production processes except for Lj in the matching history data are unchanged, and the corresponding product qualification rate is marked as a first qualification rate when the production conditions are TXLj in all products processed in the equipment area corresponding to Lj; the production conditions of the production processes except for Lj in the matching history data are unchanged, and in all products processed by the equipment area corresponding to Lj, the corresponding product qualification rate is recorded as a second qualification rate when the production conditions are TYLj;
If the difference value between the second qualification rate and the first qualification rate is greater than or equal to a preset value, judging that the production flows respectively corresponding to each element in the production flow set Lj and the subsequent elements are influenced by the intervention of Ai, and inputting the production flows respectively corresponding to each element in the production flow set Lj and the subsequent elements in sequence into a blank set one by one to generate an intervention influence flow sequence set corresponding to Ai, wherein the elements in the intervention influence flow sequence set corresponding to Ai and Ai have influence intervention relations; otherwise, the interventional influence procedure sequence set corresponding to Ai is empty.
The instruction risk feature evaluation module acquires an analysis result of the instruction association influence analysis module, and combines environmental feature information in an equipment area corresponding to each element in the numerical control instruction set to be executed in the current time equipment and user instruction operation information corresponding to corresponding equipment in the historical data to acquire operation risk feature influence values corresponding to each element in the numerical control instruction set to be executed respectively;
When the instruction risk feature evaluation module obtains operation risk feature influence values respectively corresponding to elements in the to-be-executed numerical control instruction set, environment feature information in equipment areas corresponding to the elements in the to-be-executed numerical control instruction set in the current time equipment is obtained, and the equipment area corresponding to the i-th element in the to-be-executed numerical control instruction set in the current time equipment is marked as QAi; the environmental characteristic information corresponding to the QAi is recorded as H QAi; the environmental characteristic information comprises sensor monitoring values corresponding to all indexes in production conditions, wherein the production conditions comprise all monitored indexes and all executing instructions, and the production conditions comprise the monitored indexes comprising temperature and humidity;
Acquiring user instruction operation information corresponding to the environment characteristic information in the corresponding equipment area in the historical data respectively in the error range, wherein the user instruction operation information comprises instruction sequences formed by continuous numerical control instructions when the environment characteristic information in the corresponding equipment area is in the error range, and discontinuous time slices in the historical data correspond to different instruction sequences; extracting all instruction sequences comprising to-be-executed numerical control instruction interference sequence fragments from each obtained instruction sequence, and marking the set as a first instruction sequence set; marking elements which are contained in the first instruction sequence set and aim at misoperation behaviors of the numerical control instruction interference sequence segment to be executed; if the operation behavior corresponding to the subsequent first numerical control instruction of the numerical control instruction interference sequence segment to be executed contained in the element in the first instruction sequence set is a return operation, judging that the element in the first instruction sequence set contains misoperation behaviors aiming at the numerical control instruction interference sequence segment to be executed; otherwise, judging that the element in the first instruction sequence set does not contain misoperation behaviors aiming at the numerical control instruction interference sequence segment to be executed;
the error ranges of the indexes corresponding to different production conditions in the environment characteristic information are different, and the error ranges of the indexes corresponding to the production conditions are preset in a database;
Acquiring operation risk characteristic influence values corresponding to elements in a numerical control instruction set to be executed respectively, and marking the operation risk characteristic influence value corresponding to an i-th element in the numerical control instruction set to be executed as Bi;
，
Wherein Mi represents the number of elements in an intersection of a set formed by each production flow to which a product belongs in the current time equipment and an intervention influence flow sequence set corresponding to Ai;
PGi denotes a deviation interference coefficient corresponding to Ai, and PGi =0 when Ai does not belong to a numerical control instruction interference sequence segment to be executed; when Ai belongs to the section of the numerical control instruction interference sequence to be executed, Wherein Ei h represents the total number of elements in the h to-be-executed numerical control instruction interference sequence segment containing Ai; HEi h represents the corresponding position serial number of Ai in the h to-be-executed numerical control instruction interference sequence segment containing Ai;
fi represents the ratio of the number of marked elements in the first instruction sequence set to the total number of elements in the first instruction sequence set.
And the instruction execution supervision module generates priorities of numerical control instructions corresponding to the elements in the numerical control instruction set to be executed according to the operation risk characteristic influence values respectively corresponding to the elements in the numerical control instruction set to be executed, and manages and pre-warns the numerical control instructions in the numerical control instruction set to be executed by combining the obtained instruction priorities so as to assist a user in diagnosing and deciding the execution condition of the numerical control instructions in the numerical control instruction set to be executed.
When the instruction execution supervision module generates the priority of the numerical control instruction corresponding to each element in the numerical control instruction set to be executed, sequencing each element in the numerical control instruction set to be executed according to the sequence from the big to the small of the influence value of the corresponding operation risk characteristic to obtain a first sequence, wherein the priority corresponding to each element in the first sequence is equal to the sequence number of the corresponding element in the first sequence.
When the instruction execution supervision module manages and controls the numerical control instructions in the numerical control instruction set to be executed and early warns, the elements in the numerical control instruction set to be executed are ordered from big to small according to the sequence, and the sequence numbers of the elements in the numerical control instruction set to be executed are obtained; judging whether the element serial number corresponding to each element in the numerical control instruction set to be executed is equal to the corresponding priority in value or not;
Extracting each element with the element serial numbers which are different from the corresponding priority in numerical values and correspond to the element serial numbers in the numerical control instruction set to be executed, feeding back the element serial numbers extracted in the numerical control instruction set to be executed and the element serial numbers which are behind the element serial numbers to be executed to the user, carrying out early warning on the user, and after the user confirms that the feedback content is correct, sequentially executing each numerical control instruction to be executed; otherwise, judging that each feedback numerical control instruction to be executed is invalid.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A large model data management system for high quality diagnosis and decision is characterized in that the system comprises a production state acquisition module, a device numerical control instruction calling module, an instruction association influence analysis module, an instruction risk characteristic evaluation module and an instruction execution supervision module,
The production state acquisition module is used for acquiring the running state information of the equipment at the current time, wherein the running state information of the equipment comprises the types of the produced products, the production processes of the produced products in the equipment at the current time and the corresponding production process sets of the corresponding product types in the equipment;
the equipment numerical control instruction calling module is used for obtaining a numerical control instruction set to be executed, which is received by the equipment numerical control panel based on the current time;
The instruction association influence analysis module is used for analyzing operation interference relations among all numerical control instructions in the numerical control instruction set to be executed and also analyzing influence intervention relations among all elements in the production flow set and all numerical control instructions in the numerical control instruction set to be executed respectively;
The instruction risk feature evaluation module acquires an analysis result of the instruction association influence analysis module, and combines environmental feature information in an equipment area corresponding to each element in the numerical control instruction set to be executed in the current time equipment and user instruction operation information corresponding to corresponding equipment in the historical data to acquire operation risk feature influence values corresponding to each element in the numerical control instruction set to be executed respectively;
And the instruction execution supervision module generates priorities of numerical control instructions corresponding to the elements in the numerical control instruction set to be executed according to the operation risk characteristic influence values respectively corresponding to the elements in the numerical control instruction set to be executed, and manages and pre-warns the numerical control instructions in the numerical control instruction set to be executed by combining the obtained instruction priorities so as to assist a user in diagnosing and deciding the execution condition of the numerical control instructions in the numerical control instruction set to be executed.
2. The large model data management system for high quality diagnostics and decision according to claim 1 wherein: each production flow to which the production product belongs in the current time equipment represents each production flow which is running in the current time equipment and contains the production product;
The corresponding production flow set of the corresponding product type in the equipment is a set formed by all production flows required to be executed in the current equipment in the production cycle of the corresponding product type;
In the running state information of the current time equipment, the set formed by each production flow to which the production product belongs in the current time equipment is a subset of the corresponding production flow set of the corresponding product type in the equipment.
3. The large model data management system for high quality diagnostics and decision according to claim 1 wherein: the to-be-executed numerical control instruction set received by the numerical control panel based on the current time equipment represents a set formed by receiving and sending all control instructions which are not executed by the equipment and are sent by the equipment under the operation of a user;
the numerical control instruction set to be executed, which is received by the numerical control panel of the current time equipment, comprises zero, one or a plurality of elements.
4. The large model data management system for high quality diagnostics and decision according to claim 1 wherein: when the instruction association influence analysis module analyzes the operation interference relation among all numerical control instructions in the numerical control instruction set to be executed, acquiring the numerical control instruction set to be executed, which is received by the numerical control panel, of the current time equipment and is marked as A; the numerical control instruction corresponding to the i-th element in A is marked as Ai;
Taking Ai as a reference node, judging whether the reference node has an operation sensitivity influence on each element after the reference node, wherein i epsilon [1, i1], and i1 represents the total number of elements in A;
when the reference node affects the operation sensitivity formed by each element after the reference node, extracting a to-be-executed numerical control instruction interference sequence segment formed by the reference node and each element after the reference node, and judging that an operation interference relationship exists among each numerical control instruction in the to-be-executed numerical control instruction interference sequence segment in the to-be-executed numerical control instruction set;
When the reference node has the condition that the elements behind the reference node do not form the operation sensitivity influence, the reference node is changed, the first element which does not form the operation sensitivity influence after the original reference node is taken as a new reference node, and whether the new reference node forms the operation sensitivity influence on the elements behind the new reference node is judged again;
If the new reference node is Ai1, judging that the operation interference relation among all numerical control instructions in the numerical control instruction set to be executed does not exist and the corresponding numerical control instruction interference sequence segment to be executed is empty;
When judging whether the reference node Ai has an operation sensitivity influence on the following element Ai2, i2 epsilon [1, i1] is carried out, acquiring distribution position areas corresponding to Ai and Ai2 in the numerical control panel, and judging that Ai has an operation sensitivity influence on Ai2 if the intersection of the distribution position areas corresponding to Ai and Ai2 is an empty set; otherwise, it is determined that Ai does not constitute an operation sensitivity influence on Ai 2.
5. The large model data management system for high quality diagnostics and decision according to claim 4 wherein: the instruction association influence analysis module is used for acquiring each element in the production flow set and marking the j element in the generation flow set as Lj when analyzing influence intervention relations between each element in the production flow set and each numerical control instruction in the numerical control instruction set to be executed respectively,
Judging the intersection of the equipment execution area corresponding to Ai and the equipment area corresponding to Lj, and when the obtained intersection is not empty, adding the execution Ai in the obtained intersection area as a new production condition into the original production condition TYLj in the equipment area corresponding to Lj to obtain a new production condition corresponding to Lj, and marking as TXLj; the production conditions of the production processes except for Lj in the matching history data are unchanged, and the corresponding product qualification rate is marked as a first qualification rate when the production conditions are TXLj in all products processed in the equipment area corresponding to Lj; the production conditions of the production processes except for Lj in the matching history data are unchanged, and in all products processed by the equipment area corresponding to Lj, the corresponding product qualification rate is recorded as a second qualification rate when the production conditions are TYLj;
If the difference value between the second qualification rate and the first qualification rate is greater than or equal to a preset value, judging that the production flows respectively corresponding to each element in the production flow set Lj and the subsequent elements are influenced by the intervention of Ai, and inputting the production flows respectively corresponding to each element in the production flow set Lj and the subsequent elements in sequence into a blank set one by one to generate an intervention influence flow sequence set corresponding to Ai, wherein the elements in the intervention influence flow sequence set corresponding to Ai and Ai have influence intervention relations; otherwise, the interventional influence procedure sequence set corresponding to Ai is empty.
6. The large model data management system for high quality diagnostics and decision according to claim 5 wherein: when the instruction risk feature evaluation module obtains operation risk feature influence values respectively corresponding to elements in the to-be-executed numerical control instruction set, environment feature information in equipment areas corresponding to the elements in the to-be-executed numerical control instruction set in the current time equipment is obtained, and the equipment area corresponding to the i-th element in the to-be-executed numerical control instruction set in the current time equipment is marked as QAi; the environmental characteristic information corresponding to the QAi is recorded as H QAi; the environmental characteristic information comprises sensor monitoring values corresponding to all indexes in production conditions, wherein the production conditions comprise all monitored indexes and all executing instructions, and the production conditions comprise the monitored indexes comprising temperature and humidity;
Acquiring user instruction operation information corresponding to the environment characteristic information in the corresponding equipment area in the historical data respectively in the error range, wherein the user instruction operation information comprises instruction sequences formed by continuous numerical control instructions when the environment characteristic information in the corresponding equipment area is in the error range, and discontinuous time slices in the historical data correspond to different instruction sequences; extracting all instruction sequences comprising to-be-executed numerical control instruction interference sequence fragments from each obtained instruction sequence, and marking the set as a first instruction sequence set; marking elements which are contained in the first instruction sequence set and aim at misoperation behaviors of the numerical control instruction interference sequence segment to be executed; if the operation behavior corresponding to the subsequent first numerical control instruction of the numerical control instruction interference sequence segment to be executed contained in the element in the first instruction sequence set is a return operation, judging that the element in the first instruction sequence set contains misoperation behaviors aiming at the numerical control instruction interference sequence segment to be executed; otherwise, judging that the element in the first instruction sequence set does not contain misoperation behaviors aiming at the numerical control instruction interference sequence segment to be executed;
the error ranges of the indexes corresponding to different production conditions in the environment characteristic information are different, and the error ranges of the indexes corresponding to the production conditions are preset in a database;
Acquiring operation risk characteristic influence values corresponding to elements in a numerical control instruction set to be executed respectively, and marking the operation risk characteristic influence value corresponding to an i-th element in the numerical control instruction set to be executed as Bi;
，
Wherein Mi represents the number of elements in an intersection of a set formed by each production flow to which a product belongs in the current time equipment and an intervention influence flow sequence set corresponding to Ai;
PGi denotes a deviation interference coefficient corresponding to Ai, and PGi =0 when Ai does not belong to a numerical control instruction interference sequence segment to be executed; when Ai belongs to the section of the numerical control instruction interference sequence to be executed, Wherein Ei h represents the total number of elements in the h to-be-executed numerical control instruction interference sequence segment containing Ai; HEi h represents the corresponding position serial number of Ai in the h to-be-executed numerical control instruction interference sequence segment containing Ai;
fi represents the ratio of the number of marked elements in the first instruction sequence set to the total number of elements in the first instruction sequence set.
7. The large model data management system for high quality diagnostics and decision according to claim 1 wherein: when the instruction execution supervision module generates the priority of the numerical control instruction corresponding to each element in the numerical control instruction set to be executed, sequencing each element in the numerical control instruction set to be executed according to the sequence from the big to the small of the influence value of the corresponding operation risk characteristic to obtain a first sequence, wherein the priority corresponding to each element in the first sequence is equal to the sequence number of the corresponding element in the first sequence.
8. The large model data management system for high quality diagnostics and decision according to claim 7 wherein: when the instruction execution supervision module manages and controls the numerical control instructions in the numerical control instruction set to be executed and early warns, the elements in the numerical control instruction set to be executed are ordered from big to small according to the sequence, and the sequence numbers of the elements in the numerical control instruction set to be executed are obtained; judging whether the element serial number corresponding to each element in the numerical control instruction set to be executed is equal to the corresponding priority in value or not;
Extracting each element with the element serial numbers which are different from the corresponding priority in numerical values and correspond to the element serial numbers in the numerical control instruction set to be executed, feeding back the element serial numbers extracted in the numerical control instruction set to be executed and the element serial numbers which are behind the element serial numbers to be executed to the user, carrying out early warning on the user, and after the user confirms that the feedback content is correct, sequentially executing each numerical control instruction to be executed; otherwise, judging that each feedback numerical control instruction to be executed is invalid.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410459967.XA CN118068819B (en) | 2024-04-17 | 2024-04-17 | Large model data management system for high quality diagnostics and decision making |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410459967.XA CN118068819B (en) | 2024-04-17 | 2024-04-17 | Large model data management system for high quality diagnostics and decision making |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118068819A true CN118068819A (en) | 2024-05-24 |
| CN118068819B CN118068819B (en) | 2024-07-12 |
Family
ID=91106026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410459967.XA Active CN118068819B (en) | 2024-04-17 | 2024-04-17 | Large model data management system for high quality diagnostics and decision making |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118068819B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751288A (en) * | 2008-12-12 | 2010-06-23 | 中国移动通信集团山东有限公司 | Method, device and system applying process scheduler |
| US20120259585A1 (en) * | 2011-04-07 | 2012-10-11 | Leon Ericson Haynes | Methods and systems for monitoring operation of equipment |
| CN104678991A (en) * | 2014-12-26 | 2015-06-03 | 广东美的厨房电器制造有限公司 | Method and system for diagnosing abnormity of household appliance, server and household appliance |
| CN112204631A (en) * | 2018-04-04 | 2021-01-08 | 施耐德电气美国股份有限公司 | System and method for managing smart alerts |
| CN113614666A (en) * | 2019-03-25 | 2021-11-05 | 施耐德电子系统美国股份有限公司 | System and method for detecting and predicting faults in an industrial process automation system |
| CN116668482A (en) * | 2023-06-02 | 2023-08-29 | 南京国铁电气有限责任公司 | Intelligent building two-bus monitoring system and method based on artificial intelligence |
| CN116880396A (en) * | 2023-07-19 | 2023-10-13 | 北京红山信息科技研究院有限公司 | Intelligent factory dynamic cooperative scheduling method |
| US20240085896A1 (en) * | 2021-01-29 | 2024-03-14 | Omron Corporation | Quality improvement assisting device and quality improvement assisting system |
-
2024
- 2024-04-17 CN CN202410459967.XA patent/CN118068819B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751288A (en) * | 2008-12-12 | 2010-06-23 | 中国移动通信集团山东有限公司 | Method, device and system applying process scheduler |
| US20120259585A1 (en) * | 2011-04-07 | 2012-10-11 | Leon Ericson Haynes | Methods and systems for monitoring operation of equipment |
| CN104678991A (en) * | 2014-12-26 | 2015-06-03 | 广东美的厨房电器制造有限公司 | Method and system for diagnosing abnormity of household appliance, server and household appliance |
| CN112204631A (en) * | 2018-04-04 | 2021-01-08 | 施耐德电气美国股份有限公司 | System and method for managing smart alerts |
| CN113614666A (en) * | 2019-03-25 | 2021-11-05 | 施耐德电子系统美国股份有限公司 | System and method for detecting and predicting faults in an industrial process automation system |
| US20240085896A1 (en) * | 2021-01-29 | 2024-03-14 | Omron Corporation | Quality improvement assisting device and quality improvement assisting system |
| CN116668482A (en) * | 2023-06-02 | 2023-08-29 | 南京国铁电气有限责任公司 | Intelligent building two-bus monitoring system and method based on artificial intelligence |
| CN116880396A (en) * | 2023-07-19 | 2023-10-13 | 北京红山信息科技研究院有限公司 | Intelligent factory dynamic cooperative scheduling method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118068819B (en) | 2024-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117393076B (en) | Intelligent monitoring method and system for heat-resistant epoxy resin production process | |
| CN115630839B (en) | Intelligent feedback production regulation and control system based on data mining | |
| CN118707914A (en) | A workshop production equipment operation monitoring system based on distributed control | |
| CN116991130B (en) | An intelligent automation control system and method for petrochemical production | |
| CN109634233A (en) | Industrial big data intellectual analysis decision-making technique, readable storage medium storing program for executing and terminal | |
| CN116997915A (en) | Production process improvements induced by shared data | |
| CN119048063A (en) | Digital twin visual data processing system for intelligent park | |
| US6885975B2 (en) | Method and apparatus for managing process transitions | |
| CN116227754B (en) | Production self-adaptive optimization control method and system for rubber gloves | |
| CN118068819B (en) | Large model data management system for high quality diagnostics and decision making | |
| CN120180373A (en) | Intelligent fault early warning analysis system and method for electrical equipment based on artificial intelligence | |
| CN118968379B (en) | Monitoring data analysis system based on deep learning | |
| CN119620719A (en) | An intelligent chemical production patrol control system | |
| CN119814119A (en) | Satellite-ground integrated full-process data intelligent monitoring and early warning method and system | |
| CN119511869A (en) | An intelligent monitoring and adjustment method, system and device based on digital twin technology | |
| CN119199702A (en) | Analysis system based on metering model | |
| CN118114858A (en) | STM process tracing and error-proofing intelligent production management system | |
| CN110263949B (en) | Data processing method and system integrating machine mechanism and artificial intelligence algorithm system | |
| CN119150109B (en) | A method for producing a composite water treatment agent | |
| CN120928758B (en) | Remote control management system and method applied to cleaning equipment | |
| CN118921983B (en) | Abnormal data management system and method for chip mounter based on data analysis | |
| CN119806095B (en) | A large-scale data mining method, system and storage medium for manufacturing process | |
| CN121168761B (en) | An efficient changeover scheduling method, medium, and system based on AI multi-agent dynamic negotiation | |
| Yélamos et al. | Fault diagnosis based on support vector machines and systematic comparison to existing approaches | |
| CN119292209A (en) | Intelligent control method and system for vegetarian meat powder production line |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |