CN116380816A - Method, program and storage medium for judging faults of coal quality online detection system - Google Patents
Method, program and storage medium for judging faults of coal quality online detection system Download PDFInfo
- Publication number
- CN116380816A CN116380816A CN202211624465.5A CN202211624465A CN116380816A CN 116380816 A CN116380816 A CN 116380816A CN 202211624465 A CN202211624465 A CN 202211624465A CN 116380816 A CN116380816 A CN 116380816A
- Authority
- CN
- China
- Prior art keywords
- coal quality
- target element
- detection system
- online
- spectrum intensity
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
- G01N2021/0106—General arrangement of respective parts
- G01N2021/0112—Apparatus in one mechanical, optical or electronic block
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
Description
技术领域technical field
本发明属于故障检测技术领域，具体涉及一种煤质在线检测系统故障判定方法、程序以及存储介质。The invention belongs to the technical field of fault detection, and in particular relates to a fault judgment method, program and storage medium of an online coal quality detection system.
背景技术Background technique
激光探针，又称激光诱导击穿光谱(Laser-induced Breakdown Spectroscopy，LIBS)，是一种以激光作为等离子体激发源的原子发射光谱分析技术。因受激光器、光谱仪、光电探测器件等关键设备性能的限制，这一技术在其诞生初期发展缓慢。近年来，随着上述关键设备的快速发展，在煤质在线监测领域得到了快速的发展。Laser probe, also known as laser-induced breakdown spectroscopy (LIBS), is an atomic emission spectroscopic analysis technique that uses laser as the plasma excitation source. Due to the limitation of the performance of key equipment such as lasers, spectrometers, and photodetection devices, this technology developed slowly in its early days. In recent years, with the rapid development of the above-mentioned key equipment, the field of online monitoring of coal quality has developed rapidly.
为了实现采用基于LIBS的煤质检测系统对煤质的检测，在授权发明专利授权公告号CN111044504B《一种考虑激光诱导击穿光谱不确定性的煤质分析方法》通过将每个煤样的多幅原始光谱平均分为多组后，在组内求平均，得到每个煤样对应多幅平均光谱，然后用这些平均光谱基于多变量分析方法建立煤质定量分析模型，对煤质指标进行分析，该方法可以有效表征LIBS数据的不确定性，同一煤样的LIBS数据即使在一定范围内波动，该方法依然能够准确计算对应的煤质指标值，但是却没有根据激光色谱的监测情况的分析，实现对煤质监测系统的故障诊断，在实际的工作过程中，由于工作环境较为恶劣，若不能实时发现煤质监测系统的故障情况，会导致对煤质的监测结果产生错误的判断，进而影响最终的燃烧调节，严重时甚至会造成非计划的非计划的锅炉熄火事故的发生。In order to realize the detection of coal quality by using LIBS-based coal quality detection system, in the authorized invention patent authorization announcement number CN111044504B "A Coal Quality Analysis Method Considering the Uncertainty of Laser-Induced Breakdown Spectrum" by combining multiple After the original spectrum is divided into multiple groups on average, the average is calculated within the group to obtain multiple average spectra corresponding to each coal sample, and then these average spectra are used to establish a coal quality quantitative analysis model based on the multivariate analysis method to analyze the coal quality indicators , this method can effectively characterize the uncertainty of LIBS data. Even if the LIBS data of the same coal sample fluctuates within a certain range, this method can still accurately calculate the corresponding coal quality index value, but it does not analyze according to the monitoring situation of laser chromatography. , to realize the fault diagnosis of the coal quality monitoring system. In the actual working process, due to the harsh working environment, if the fault of the coal quality monitoring system cannot be found in real time, it will lead to wrong judgments on the coal quality monitoring results, and then It will affect the final combustion adjustment, and even cause unplanned and unplanned boiler flameout accidents in severe cases.
基于上述技术问题，需要设计及一种煤质在线检测系统故障判定方法、程序以及存储介质。Based on the above technical problems, it is necessary to design and design a method, program and storage medium for fault determination of an online coal quality detection system.
发明内容Contents of the invention
本发明的目的是提供一种煤质在线检测系统故障判定方法、程序以及存储介质。The object of the present invention is to provide a method, program and storage medium for fault determination of an online coal quality detection system.
为了解决上述技术问题，本发明第一方面提供了一种煤质在线检测系统故障判定方法，包括：In order to solve the above technical problems, the first aspect of the present invention provides a fault determination method for an online coal quality detection system, including:
S11提取煤质在线检测系统的光谱强度信号，并基于指定元素的光谱强度信号构建得到基于指定元素内标后的目标元素的光谱强度；S11 extracts the spectral intensity signal of the coal quality online detection system, and constructs the spectral intensity of the target element based on the internal standard of the specified element based on the spectral intensity signal of the specified element;
S12基于所述目标元素的光谱强度，提取在同等煤质下的目标元素的历史光谱强度，判断两者的差值的绝对值大于第一光谱强度差值的目标元素的数量是否大于第一阈值，若是，则确定所述煤质在线检测系统存在可疑故障，并进入步骤S13；若否，S12 Based on the spectral intensity of the target element, extract the historical spectral intensity of the target element under the same coal quality, and judge whether the number of target elements whose absolute value of the difference between the two is greater than the first spectral intensity difference is greater than the first threshold , if so, then determine that there is a suspicious fault in the coal quality online detection system, and enter step S13; if not,
则所述煤质在线检测系统不存在异常；Then there is no abnormality in the coal quality online detection system;
S13采用所述煤质在线检测系统得到多次基于指定元素内标后的目标元素的光谱强度，并求得所述多次基于指定元素内标后的目标元素的光谱强度的平均值，基于所述光谱强度的平均值得到煤质检测结果；S13 uses the coal quality online detection system to obtain the spectral intensity of the target element based on the internal standard of the specified element multiple times, and obtains the average value of the spectral intensity of the target element based on the internal standard of the specified element multiple times, based on the specified element The average value of the above spectral intensity is used to obtain the coal quality detection result;
S14基于煤质入厂试验室测定结果与所述煤质检测结果的差值，确定所述煤质在线检测系统是否存在异常。S14 Determine whether there is an abnormality in the coal quality online detection system based on the difference between the measurement result of the incoming coal quality laboratory and the coal quality detection result.
通过基于与历史光谱强度的差值的确定，从而实现对存在疑似故障的煤质在线检测系统的识别，不仅较为直观直接，而且具有较好的重复性和一致性，使得识别结果较为准确。Based on the determination of the difference with the historical spectral intensity, the identification of the coal quality online detection system with suspected faults is realized, which is not only intuitive and direct, but also has good repeatability and consistency, making the identification results more accurate.
通过首先判断存在可疑故障的煤质在线检测系统之后，再求得多次基于指定元素内标后的光谱强度的平均值，不仅节省了电能，而且通过平均值的计算，也使得最终的煤质检测结果变得更加精确。By first judging the coal quality online detection system with suspicious faults, and then obtaining the average value of the spectral intensity based on the internal standard of the specified element for many times, it not only saves electric energy, but also makes the final coal quality Detection results become more precise.
通过采用煤质入厂试验室测定结果以及煤质检测结果的差值，对煤质在线监测系统的异常状态进行确认，从而进一步提升了判断的准确性，防止由于煤质的变动导致的误判情况的出现，从两方面实现对异常状态的确认，保证了能够准确识别得到煤质在线检测系统的故障。The abnormal state of the coal quality online monitoring system is confirmed by using the difference between the test results of the coal quality entering the factory and the coal quality detection results, thereby further improving the accuracy of judgment and preventing misjudgment caused by changes in coal quality The emergence of the situation realizes the confirmation of the abnormal state from two aspects, ensuring that the fault of the coal quality online detection system can be accurately identified.
进一步的技术方案在于，所述指定元素根据历史煤质检测结果中内标的指定元素确定，对于不同的煤质测量维度采用不同的指定元素。A further technical solution is that the designated elements are determined according to the designated elements of the internal standard in the historical coal quality detection results, and different designated elements are used for different coal quality measurement dimensions.
进一步的技术方案在于，确定所述煤质在线检测系统存在疑似故障的具体步骤为：A further technical solution is that the specific steps for determining that there is a suspected fault in the coal quality online detection system are:
S21基于所述目标元素的光谱强度以及在同等煤质下的所述目标元素的历史光谱强度，确定是否存在所述两者的差值的绝对值大于第一光谱强度差值的目标元素的数量大于第一阈值，若是，则进入步骤S22；S21 Based on the spectral intensity of the target element and the historical spectral intensity of the target element under the same coal quality, determine whether there is a quantity of the target element whose absolute value of the difference between the two is greater than the first spectral intensity difference greater than the first threshold, if so, enter step S22;
S22利用煤质在线监测系统，提取多次所述目标元素的光谱强度并求得平均值，构成所述目标元素的平均光谱强度，并判断所述目标元素的平均光谱强度与所述目标元素的历史光谱强度的差值的绝对值大于第一光谱强度差值的目标元素的数量是否大于第一阈值并将其作为超标目标元素，若是，则进入步骤S23；S22 Use the coal quality online monitoring system to extract the spectral intensity of the target element multiple times and obtain the average value to form the average spectral intensity of the target element, and judge the difference between the average spectral intensity of the target element and the Whether the absolute value of the difference of historical spectral intensity is greater than the quantity of the target element of the first spectral intensity difference is greater than the first threshold and it is used as the target element exceeding the standard, if so, then enter step S23;
S23根据所述超标目标元素得到所述超标目标元素反应的煤质维度，并判断所述超标元素反应的煤质维度的数量是否大于第二阈值，若是，则进入步骤S24；S23 Obtain the coal quality dimension of the reaction of the exceeding standard target element according to the exceeding standard target element, and judge whether the quantity of the coal quality dimension of the reaction of the exceeding standard element is greater than the second threshold, and if so, enter step S24;
S24确定所述煤质在线检测系统存在疑似故障。S24 determines that there is a suspected fault in the online coal quality detection system.
通过首先基于单次的误差进行判断，在此基础上存在异常时再通过平均值求得平均光谱强度，当平均光谱强度同样存在异常时，再根据超标目标元素反应的煤质维度，由于煤质维度往往具有多种，具体的可以为灰分、挥发分等多种，因此只有存在多种反应煤质维度的超标目标元素存在异常时，才能确定此时的煤质在线检测系统存在疑似故障，通过分步骤的判断，使得最终的判断结果变得更加的准确可靠的同时，也避免了不必要的电能消耗以及算力的浪费。By first making a judgment based on a single error, on this basis, when there is an abnormality, the average spectral intensity is obtained by the average value. There are often multiple dimensions, specifically ash content, volatile content, etc. Therefore, only when there are abnormalities in the excessive target elements that reflect multiple dimensions of coal quality, can it be confirmed that there is a suspected fault in the coal quality online detection system at this time. The step-by-step judgment makes the final judgment result more accurate and reliable, and at the same time avoids unnecessary power consumption and waste of computing power.
进一步的技术方案在于，所述煤质维度为热值、挥发分、灰分、碳含量，第二阈值根据煤质维度的数量确定，取2或者以上的数量。A further technical solution is that the coal quality dimensions are calorific value, volatile matter, ash content, and carbon content, and the second threshold is determined according to the number of coal quality dimensions, which is 2 or more.
进一步的技术方案在于，所述第一光谱强度差值根据所述目标元素的基础光谱强度、目标元素反应的煤质维度的数量、目标元素反应的煤质维度的重要程度确定，其具体的计算公式为：A further technical solution is that the first spectral intensity difference is determined according to the basic spectral intensity of the target element, the number of coal quality dimensions reacted by the target element, and the importance of the coal quality dimension reacted by the target element, and its specific calculation The formula is:
其中K1、K2、K3、K4为常数,Q、S、J为目标元素的基础光谱强度、目标元素反应的煤质维度的数量、目标元素反应的煤质维度的重要程度，其中J根据专家打分的方式确定，取值范围在0到1之间。Among them, K 1 , K 2 , K 3 , and K 4 are constants, Q, S, and J are the basic spectral intensity of the target element, the number of coal quality dimensions of the target element response, and the importance of the coal quality dimension of the target element response. J is determined according to the method of scoring by experts, and the value range is between 0 and 1.
进一步的技术方案在于，所述第一阈值根据所述目标元素的数量、煤质测量的精准度要求、在线煤质测量系统历史故障次数确定，其具体的计算公式为：A further technical solution is that the first threshold is determined according to the quantity of the target element, the accuracy requirement of coal quality measurement, and the number of historical failures of the online coal quality measurement system, and its specific calculation formula is:
其中T、P、S1分别为煤质测量的精准度要求、在线煤质测量系统历史故障次数、目标元素的数量，K5、K6、K7为权值。Among them, T, P, and S 1 are the accuracy requirements of coal quality measurement, the number of historical failures of the online coal quality measurement system, and the number of target elements, respectively, and K 5 , K 6 , and K 7 are weights.
进一步的技术方案在于，基于所述光谱强度的平均值得到煤质检测结果的具体步骤为：A further technical solution is that the specific steps for obtaining the coal quality detection result based on the average value of the spectral intensity are:
S31基于PLS算法的煤质回归模型，以所述目标元素的光谱强度的平均值为输入量，求得所述目标元素对预测结果的贡献度因子；S31 is based on the coal quality regression model of the PLS algorithm, using the average value of the spectral intensity of the target element as an input to obtain the contribution factor of the target element to the prediction result;
S32提取得到所述贡献度因子大于第一贡献度阈值的目标元素并将其作为最优目标元素，将所述最优目标元素送入到基于ANN算法的解析模型之中，得到ANN煤质检测结果；S32 Extract the target element whose contribution factor is greater than the first contribution threshold and use it as the optimal target element, send the optimal target element into the analytical model based on the ANN algorithm, and obtain the ANN coal quality detection result;
S33基于历史数据构建非线性回归模型，以所述目标元素的光谱强度的平均值作为输入量，得到回归煤质检测结果；S33 constructing a nonlinear regression model based on historical data, using the average value of the spectral intensity of the target element as an input to obtain a regression coal quality detection result;
S34基于所述回归煤质检测结果以及所述ANN煤质检测结果得到煤质检测结果。S34 Obtain a coal quality detection result based on the regression coal quality detection result and the ANN coal quality detection result.
通过首先基于PLS算法的煤质回归模型，从而将贡献度因子较低的目标元素筛选出去，从而进一步提升了最终的ANN煤质检测结果的检测效率和准确度，并进一步通过非线性回归模型的构建，实现了从两个角度对煤质检测结果的确定，进一步保证了最终的煤质检测结果的准确性，也为进一步对在线煤质检测系统的故障的准确诊断奠定了基础。Through the coal quality regression model based on the PLS algorithm, the target elements with low contribution factors are screened out, thereby further improving the detection efficiency and accuracy of the final ANN coal quality detection results, and further through the nonlinear regression model The construction realizes the determination of the coal quality detection results from two angles, further ensures the accuracy of the final coal quality detection results, and also lays the foundation for further accurate diagnosis of the faults of the online coal quality detection system.
进一步的技术方案在于，将所述煤质入厂试验室测定结果与所述煤质检测结果的差值作为煤质偏差量，当所述煤质偏差量大于第一差值阈值时，确定所述煤质在线检测系统存在故障，并根据所述煤质偏差量对应的煤质维度的数量以及煤质偏差量的大小，确定煤质在线检测系统的故障情况。A further technical solution is to use the difference between the measurement result of the coal quality entering the factory laboratory and the coal quality detection result as the coal quality deviation, and when the coal quality deviation is greater than the first difference threshold, determine the There is a fault in the online coal quality detection system, and according to the number of coal quality dimensions corresponding to the coal quality deviation and the size of the coal quality deviation, the fault situation of the coal quality online detection system is determined.
另一方面，本申请实施例中提供一种计算机可读存储介质，其上存储有计算机程序，当所述计算机程序在计算机中执行时，令计算机执行上述的一种煤质在线检测系统故障判定方法。On the other hand, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed in a computer, the computer is instructed to perform the above-mentioned failure determination of an online coal quality detection system. method.
另一方面，本申请实施例中提供一种计算机程序产品，其特征在于，所述计算机程序产品存储有指令，所述指令在由计算机执行时，使得所述计算机实施上述的一种煤质在线检测系统故障判定方法。On the other hand, an embodiment of the present application provides a computer program product, which is characterized in that the computer program product stores instructions, and when the instructions are executed by a computer, the computer implements the above-mentioned coal quality online Detection system fault determination method.
其他特征和优点将在随后的说明书中阐述，并且，部分地从说明书中变得显而易见，或者通过实施本发明而了解。本发明的目的和其他优点在说明书以及附图中所特别指出的结构来实现和获得。Additional features and advantages will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and appended drawings.
为使本发明的上述目的、特征和优点能更明显易懂，下文特举较佳实施例，并配合所附附图，作详细说明如下。In order to make the above-mentioned objects, features and advantages of the present invention more comprehensible, preferred embodiments will be described in detail below together with the accompanying drawings.
附图说明Description of drawings
为了更清楚地说明本发明具体实施方式或现有技术中的技术方案，下面将对具体实施方式或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施方式，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the specific implementation of the present invention or the technical solutions in the prior art, the following will briefly introduce the accompanying drawings that need to be used in the specific implementation or description of the prior art. Obviously, the accompanying drawings in the following description The drawings show some implementations of the present invention, and those skilled in the art can obtain other drawings based on these drawings without any creative effort.
图1为实施例1中的一种煤质在线检测系统故障判定方法的流程图；Fig. 1 is the flow chart of a kind of coal quality on-line detection system failure judging method in embodiment 1;
图2为实施例1中的确定所述煤质在线检测系统存在疑似故障的具体步骤的流程图；Fig. 2 is the flow chart of the specific steps of determining that there is a suspected fault in the coal quality online detection system in embodiment 1;
图3为实施例1中的基于所述光谱强度的平均值得到煤质检测结果的具体步骤的流程图。Fig. 3 is a flow chart of the specific steps of obtaining the coal quality detection result based on the average value of the spectral intensity in embodiment 1.
具体实施方式Detailed ways
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合附图对本发明的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. the embodiment. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
由于煤质在线检测系统的现场工作环境较为恶劣，若不能实时发现煤质监测系统的故障情况，会导致对煤质的监测结果产生错误的判断，进而影响最终的燃烧调节，严重时甚至会造成非计划的非计划的锅炉熄火事故的发生，从而造成巨大的经济损失。Due to the harsh on-site working environment of the coal quality online detection system, if the failure of the coal quality monitoring system cannot be found in real time, it will lead to wrong judgments on the coal quality monitoring results, which will affect the final combustion adjustment, and even cause serious damage. The occurrence of unplanned and unplanned boiler flameout accidents will cause huge economic losses.
实施例1Example 1
为解决上述的技术问题，图1是本发明所涉及的一种煤质在线检测系统故障判定方法，包括：In order to solve the above-mentioned technical problems, Fig. 1 is a kind of coal quality on-line detection system fault judgment method involved in the present invention, comprising:
S11提取煤质在线检测系统的光谱强度信号，并基于指定元素的光谱强度信号构建得到基于指定元素内标后的目标元素的光谱强度；S11 extracts the spectral intensity signal of the coal quality online detection system, and constructs the spectral intensity of the target element based on the internal standard of the specified element based on the spectral intensity signal of the specified element;
具体的举个例子，指定元素可以为Al，目标元素可以为H、C、CN等。Specifically, for example, the specified element can be Al, and the target element can be H, C, CN, etc.
S12基于所述目标元素的光谱强度，提取在同等煤质下的目标元素的历史光谱强度，判断两者的差值的绝对值大于第一光谱强度差值的目标元素的数量是否大于第一阈值，若是，则确定所述煤质在线检测系统存在可疑故障，并进入步骤S13；若否，则所述煤质在线检测系统不存在异常；S12 Based on the spectral intensity of the target element, extract the historical spectral intensity of the target element under the same coal quality, and judge whether the number of target elements whose absolute value of the difference between the two is greater than the first spectral intensity difference is greater than the first threshold , if yes, then determine that there is a suspicious fault in the coal quality online detection system, and enter step S13; if not, then there is no abnormality in the coal quality online detection system;
具体的举个例子，第一光谱强度差值为200a.u.,若两者的差值的绝对值为500a.u.的目标元素的数量为10个，第一阈值为5，则确定所述煤质在线检测系统存在可疑故障。Specifically, for example, the first spectral intensity difference is 200a.u., if the number of target elements whose absolute value of the difference is 500a.u. is 10, and the first threshold is 5, then determine the Suspicious faults exist in the coal quality online detection system.
S13采用所述煤质在线检测系统得到多次基于指定元素内标后的目标元素的光谱强度，并求得所述多次基于指定元素内标后的目标元素的光谱强度的平均值，基于所述光谱强度的平均值得到煤质检测结果；S13 uses the coal quality online detection system to obtain the spectral intensity of the target element based on the internal standard of the specified element multiple times, and obtains the average value of the spectral intensity of the target element based on the internal standard of the specified element multiple times, based on the specified element The average value of the above spectral intensity is used to obtain the coal quality detection result;
S14基于煤质入厂试验室测定结果与所述煤质检测结果的差值，确定所述煤质在线检测系统是否存在异常。S14 Determine whether there is an abnormality in the coal quality online detection system based on the difference between the measurement result of the incoming coal quality laboratory and the coal quality detection result.
具体的举个例子，若煤质检测结果中的热值的1.11MJ/Kg，入厂试验室测定结果为0.8MJ/Kg，则确定所述煤质在线检测系统存在异常，若煤质检测结果中的热值的0.78MJ/Kg，则所述煤质在线监测系统不存在异常。Specifically, for example, if the calorific value in the coal quality detection result is 1.11MJ/Kg, and the measurement result of the incoming laboratory is 0.8MJ/Kg, it is determined that there is an abnormality in the coal quality online detection system. If the coal quality detection result If the calorific value is 0.78MJ/Kg, there is no abnormality in the coal quality online monitoring system.
首先通过煤质在线检测系统可以得到在指定元素内标后的的目标元素的光谱强度，并根据目标元素的光谱强度以及目标元素的历史光谱强度的差值，当两者偏差较大时，则说明存在可疑故障，并在此基础上通过煤质检测结果的差值的确定，从而进一步实现了对煤质在线检测系统的故障的判定，解决了原来的无法实时发现煤质监测系统的故障情况的技术问题，从而使得测量的准确性和稳定性都得到了进一步的提升。First, through the coal quality online detection system, the spectral intensity of the target element after the internal standard of the specified element can be obtained, and according to the difference between the spectral intensity of the target element and the historical spectral intensity of the target element, when the deviation between the two is large, then It shows that there is a suspicious fault, and on this basis, through the determination of the difference of the coal quality detection results, the fault judgment of the coal quality online detection system is further realized, and the original fault situation that the coal quality monitoring system cannot be found in real time is solved Therefore, the accuracy and stability of the measurement have been further improved.
通过基于与历史光谱强度的差值的确定，从而实现对存在疑似故障的煤质在线检测系统的识别，不仅较为直观直接，而且具有较好的重复性和一致性，使得识别结果较为准确。Based on the determination of the difference with the historical spectral intensity, the identification of the coal quality online detection system with suspected faults is realized, which is not only intuitive and direct, but also has good repeatability and consistency, making the identification results more accurate.
通过首先判断存在可疑故障的煤质在线检测系统之后，再求得多次基于指定元素内标后的光谱强度的平均值，不仅节省了电能，而且通过平均值的计算，也使得最终的煤质检测结果变得更加精确。By first judging the coal quality online detection system with suspicious faults, and then obtaining the average value of the spectral intensity based on the internal standard of the specified element for many times, it not only saves electric energy, but also makes the final coal quality Detection results become more precise.
通过采用煤质入厂试验室测定结果以及煤质检测结果的差值，对煤质在线监测系统的异常状态进行确认，从而进一步提升了判断的准确性，防止由于煤质的变动导致的误判情况的出现，从两方面实现对异常状态的确认，保证了能够准确识别得到煤质在线检测系统的故障。The abnormal state of the coal quality online monitoring system is confirmed by using the difference between the test results of the coal quality entering the factory and the coal quality detection results, thereby further improving the accuracy of judgment and preventing misjudgment caused by changes in coal quality The emergence of the situation realizes the confirmation of the abnormal state from two aspects, ensuring that the fault of the coal quality online detection system can be accurately identified.
在另外一种可能的实施例中，所述指定元素根据历史煤质检测结果中内标的指定元素确定，对于不同的煤质测量维度采用不同的指定元素。In another possible embodiment, the designated elements are determined according to the designated elements of the internal standard in the historical coal quality detection results, and different designated elements are used for different coal quality measurement dimensions.
具体的举个例子，对于灰分、挥发分采用不同的指定元素进行内标。For example, for ash and volatile matter, different designated elements are used as internal standards.
在另外一种可能的实施例中，确定所述煤质在线检测系统存在疑似故障的具体步骤为：In another possible embodiment, the specific steps for determining that there is a suspected fault in the online coal quality detection system are:
S21基于所述目标元素的光谱强度以及在同等煤质下的所述目标元素的历史光谱强度，确定是否存在所述两者的差值的绝对值大于第一光谱强度差值的目标元素的数量大于第一阈值，若是，则进入步骤S22；S21 Based on the spectral intensity of the target element and the historical spectral intensity of the target element under the same coal quality, determine whether there is a quantity of the target element whose absolute value of the difference between the two is greater than the first spectral intensity difference greater than the first threshold, if so, enter step S22;
S22利用煤质在线监测系统，提取多次所述目标元素的光谱强度并求得平均值，构成所述目标元素的平均光谱强度，并判断所述目标元素的平均光谱强度与所述目标元素的历史光谱强度的差值的绝对值大于第一光谱强度差值的目标元素的数量是否大于第一阈值并将其作为超标目标元素，若是，则进入步骤S23；S22 Use the coal quality online monitoring system to extract the spectral intensity of the target element multiple times and obtain the average value to form the average spectral intensity of the target element, and judge the difference between the average spectral intensity of the target element and the Whether the absolute value of the difference of historical spectral intensity is greater than the quantity of the target element of the first spectral intensity difference is greater than the first threshold and it is used as the target element exceeding the standard, if so, then enter step S23;
S23根据所述超标目标元素得到所述超标目标元素反应的煤质维度，并判断所述超标元素反应的煤质维度的数量是否大于第二阈值，若是，则进入步骤S24；S23 Obtain the coal quality dimension of the reaction of the exceeding standard target element according to the exceeding standard target element, and judge whether the quantity of the coal quality dimension of the reaction of the exceeding standard element is greater than the second threshold, and if so, enter step S24;
具体的举个例子，还需要对反应煤质维度的目标元素进行筛选，可以采用基于PCA算法与PLS算法相结合的方式，筛选得到贡献度大于一定阈值的目标元素并将其作为预测目标元素，根据预测目标元素的光谱强度与历史光谱强度的差值超过阈值的情况以及超过阈值的预测目标元素反应的煤质维度的数量，当数量大于一定的阈值的基础上，再进入步骤S24,确定所述煤质在线检测系统存在疑似故障。To give a specific example, it is also necessary to screen the target elements that reflect the dimension of coal quality. The method based on the combination of PCA algorithm and PLS algorithm can be used to screen the target elements whose contribution is greater than a certain threshold and use them as predicted target elements. According to the situation that the difference between the spectral intensity of the predicted target element and the historical spectral intensity exceeds the threshold and the number of coal quality dimensions that the predicted target element reacts exceeds the threshold, when the number is greater than a certain threshold, then enter step S24 to determine the There is a suspected fault in the coal quality online detection system.
S24确定所述煤质在线检测系统存在疑似故障。S24 determines that there is a suspected fault in the online coal quality detection system.
通过首先基于单次的误差进行判断，在此基础上存在异常时再通过平均值求得平均光谱强度，当平均光谱强度同样存在异常时，再根据超标目标元素反应的煤质维度，由于煤质维度往往具有多种，具体的可以为灰分、挥发分等多种，因此只有存在多种反应煤质维度的超标目标元素存在异常时，才能确定此时的煤质在线检测系统存在疑似故障，通过分步骤的判断，使得最终的判断结果变得更加的准确可靠的同时，也避免了不必要的电能消耗以及算力的浪费。By first making a judgment based on a single error, on this basis, when there is an abnormality, the average spectral intensity is obtained by the average value. There are often multiple dimensions, specifically ash content, volatile content, etc. Therefore, only when there are abnormalities in the excessive target elements that reflect multiple dimensions of coal quality, can it be confirmed that there is a suspected fault in the coal quality online detection system at this time. The step-by-step judgment makes the final judgment result more accurate and reliable, and at the same time avoids unnecessary power consumption and waste of computing power.
在另外一种可能的实施例中，所述煤质维度为热值、挥发分、灰分、碳含量，第二阈值根据煤质维度的数量确定，取2或者以上的数量。In another possible embodiment, the coal quality dimension is calorific value, volatile matter, ash content, and carbon content, and the second threshold is determined according to the quantity of the coal quality dimension, which is 2 or more.
在另外一种可能的实施例中，所述第一光谱强度差值根据所述目标元素的基础光谱强度、目标元素反应的煤质维度的数量、目标元素反应的煤质维度的重要程度确定，其具体的计算公式为：In another possible embodiment, the first spectral intensity difference is determined according to the basic spectral intensity of the target element, the number of coal quality dimensions of the target element response, and the importance of the coal quality dimension of the target element response, Its specific calculation formula is:
其中K1、K2、K3、K4为常数,Q、S、J为目标元素的基础光谱强度、目标元素反应的煤质维度的数量、目标元素反应的煤质维度的重要程度，其中J根据专家打分的方式确定，取值范围在0到1之间。Among them, K 1 , K 2 , K 3 , and K 4 are constants, Q, S, and J are the basic spectral intensity of the target element, the number of coal quality dimensions of the target element response, and the importance of the coal quality dimension of the target element response. J is determined according to the method of scoring by experts, and the value range is between 0 and 1.
在另外一种可能的实施例中，所述第一阈值根据所述目标元素的数量、煤质测量的精准度要求、在线煤质测量系统历史故障次数确定，其具体的计算公式为：In another possible embodiment, the first threshold is determined according to the quantity of the target element, the accuracy requirement of coal quality measurement, and the number of historical failures of the online coal quality measurement system, and its specific calculation formula is:
其中T、P、S1分别为煤质测量的精准度要求、在线煤质测量系统历史故障次数、目标元素的数量，K5、K6、K7为权值。Among them, T, P, and S 1 are the accuracy requirements of coal quality measurement, the number of historical failures of the online coal quality measurement system, and the number of target elements, respectively, and K 5 , K 6 , and K 7 are weights.
在另外一种可能的实施例中，基于所述光谱强度的平均值得到煤质检测结果的具体步骤为：In another possible embodiment, the specific steps for obtaining the coal quality detection result based on the average value of the spectral intensity are:
S31基于PLS算法的煤质回归模型，以所述目标元素的光谱强度的平均值为输入量，求得所述目标元素对预测结果的贡献度因子；S31 is based on the coal quality regression model of the PLS algorithm, using the average value of the spectral intensity of the target element as an input to obtain the contribution factor of the target element to the prediction result;
具体的举个例子，偏最小二乘法(PLS)作为常用的多元回归分析方法之一，已广泛应用于光谱技术分析测量之中。采用PLS方法，以内标处理后的平均光谱数据为模型输入变量。通过优化模型的输入变量，选择最优的PLS因子数量，分别建立具有良好预测性能的煤炭灰分、挥发分和发热量定量分析模型。As a specific example, partial least squares (PLS), as one of the commonly used multiple regression analysis methods, has been widely used in spectroscopic analysis and measurement. The PLS method was adopted, and the average spectral data processed by the internal standard was used as the input variable of the model. By optimizing the input variables of the model and selecting the optimal number of PLS factors, the quantitative analysis models of coal ash, volatile matter and calorific value with good predictive performance were respectively established.
试验中获取的每个光谱包含了7912个波长点，波长在220～860nm。光谱不仅含有煤中元素的多条特征谱线，还包含了背景与噪声波段。若以全谱作为模型的输入变量，不仅会降低模型的分析效果，还会增加模型的计算量。优化输入变量一方面是将与煤质特性无关的背景及噪声波段剔除，另一方面是确定与煤质特性指标密切相关的光谱波段。首先以全波段光谱数据作为输入变量，分别以灰分、挥发分、发热量为因变量，建立以全谱为输入变量的PLS模型。然后根据模型结果中各输入变量的贡献度因子，剔除贡献度因子低的波段，保留贡献度因子高的波段，得到优化后的模型输入变量波段。Each spectrum obtained in the experiment contains 7912 wavelength points, and the wavelength is between 220 and 860nm. The spectrum not only contains multiple characteristic spectral lines of elements in coal, but also includes background and noise bands. If the full spectrum is used as the input variable of the model, it will not only reduce the analysis effect of the model, but also increase the calculation amount of the model. Optimizing the input variables is to eliminate the background and noise bands that have nothing to do with coal quality characteristics on the one hand, and to determine the spectral bands that are closely related to coal quality characteristics indicators on the other hand. First, the full-band spectral data was used as the input variable, and the ash, volatile matter, and calorific value were respectively used as the dependent variables to establish a PLS model with the full spectrum as the input variable. Then, according to the contribution factors of each input variable in the model results, the bands with low contribution factors are eliminated, and the bands with high contribution factors are retained to obtain the optimized model input variable bands.
经优化后输入模型中的主要光谱波段为250～840nm，在该波段内包含了煤中主要元素的特征谱线、CN分子波段和C2分子波段。从煤化学理论分析，该波段反映出的元素信息与煤炭灰分、挥发分及发热量密切相关。After optimization, the main spectral bands input into the model are 250-840nm, which include the characteristic spectral lines of the main elements in coal, CN molecular bands and C 2 molecular bands. From the theoretical analysis of coal chemistry, the elemental information reflected in this band is closely related to coal ash, volatile matter and calorific value.
为了实现对PLS模型结果的验证，采用定标集的回归系数R2、均方根误差和预测集的均方根误差、平均绝对误差作为验证指标，可分别由下式计算得到。In order to verify the results of the PLS model, the regression coefficient R 2 and the root mean square error of the calibration set and the root mean square error and the average absolute error of the prediction set are used as verification indicators, which can be calculated by the following formula respectively.
S32提取得到所述贡献度因子大于第一贡献度阈值的目标元素并将其作为最优目标元素，将所述最优目标元素送入到基于ANN算法的解析模型之中，得到ANN煤质检测结果；S32 Extract the target element whose contribution factor is greater than the first contribution threshold and use it as the optimal target element, send the optimal target element into the analytical model based on the ANN algorithm, and obtain the ANN coal quality detection result;
人工神经网络(Artificial Neural Network，ANN)最初是用于解决计算领域人工智能的问题。其原理是通过模拟生物神经元之间工作的流程，用数学表达式的形式表达神经元之间的信息传递，通过建立包含输入层、隐含层和输出层的神经网络结构，用于对数据的回归与预测等问题。Artificial Neural Network (ANN) was originally used to solve artificial intelligence problems in the computing field. Its principle is to simulate the working process between biological neurons, express the information transmission between neurons in the form of mathematical expressions, and establish a neural network structure including input layer, hidden layer and output layer for data processing. regression and forecasting issues.
假设人工神经网络输入层、隐含层和输出层的维度分别为m0、m1、m2、…、mk，则神经网络结构中输入层、隐含层和输出层的向量数学表达式可以用下式表示：Assuming that the dimensions of the input layer, hidden layer and output layer of the artificial neural network are m 0 , m 1 , m 2 , ..., m k respectively, the vector mathematical expressions of the input layer, hidden layer and output layer in the neural network structure Can be represented by the following formula:
输入层:
隐含层1:
隐含层
输出层：
而在神经网络结构中，第n个神经元接收前m个神经元的输入信号，是通过带权重形式进行传递的，因此，每一层的权重和偏执项(bias)可以用如下矩阵形式表示：In the neural network structure, the nth neuron receives the input signal of the first m neurons, which is transmitted in a weighted form. Therefore, the weight and bias item (bias) of each layer can be expressed in the following matrix form :
神经元接受到所有带权重和偏执项得到总的输入信号，通过和神经元的阈值相比较，利用激活函数f去决定最终神经元的输出信号，其数学表达式为：The neuron receives all the weighted and biased items to obtain the total input signal. By comparing with the threshold of the neuron, the activation function f is used to determine the output signal of the final neuron. The mathematical expression is:
NET(k)＝W(k)X(k-1)+b(k)NET(k)=W(k)X(k-1)+b(k)
为了使输出值与目标值存在最小的误差，人工神经网络(ANN)基于误差反分析法的网络更新思想，通过调节权重W和偏执项b参数实现误差最小。首先，假定输出向量的均方误差为损失函数L，表达式如下：In order to minimize the error between the output value and the target value, the artificial neural network (ANN) is based on the network update idea of the error back analysis method, and achieves the minimum error by adjusting the weight W and the paranoid b parameter. First, assume that the mean square error of the output vector is the loss function L, the expression is as follows:
式中：Xi(k)为第i个输出向量；Ti为第i个目标向量。Where: Xi(k) is the i-th output vector; Ti is the i-th target vector.
为了使损失函数L的值最小，可以对权重W和偏执项b求导，使其求导后的值为0，而在实际应用中，通过数学求解是很难实现的。因此，基于计算机机器学习的优势，可以利用“梯度下降法”实现该过程。其表达式如下：In order to minimize the value of the loss function L, the weight W and the bias term b can be derived to make the value of the derivative 0, but in practical applications, it is difficult to achieve mathematical solutions. Therefore, based on the advantages of computer machine learning, the "gradient descent method" can be used to realize the process. Its expression is as follows:
S33基于历史数据构建非线性回归模型，以所述目标元素的光谱强度的平均值作为输入量，得到回归煤质检测结果；S33 constructing a nonlinear regression model based on historical data, using the average value of the spectral intensity of the target element as an input to obtain a regression coal quality detection result;
S34基于所述回归煤质检测结果以及所述ANN煤质检测结果得到煤质检测结果。S34 Obtain a coal quality detection result based on the regression coal quality detection result and the ANN coal quality detection result.
通过首先基于PLS算法的煤质回归模型，从而将贡献度因子较低的目标元素筛选出去，从而进一步提升了最终的ANN煤质检测结果的检测效率和准确度，并进一步通过非线性回归模型的构建，实现了从两个角度对煤质检测结果的确定，进一步保证了最终的煤质检测结果的准确性，也为进一步对在线煤质检测系统的故障的准确诊断奠定了基础。Through the coal quality regression model based on the PLS algorithm, the target elements with low contribution factors are screened out, thereby further improving the detection efficiency and accuracy of the final ANN coal quality detection results, and further through the nonlinear regression model The construction realizes the determination of the coal quality detection results from two angles, further ensures the accuracy of the final coal quality detection results, and also lays the foundation for further accurate diagnosis of the faults of the online coal quality detection system.
在另外一种可能的实施例中，将所述煤质入厂试验室测定结果与所述煤质检测结果的差值作为煤质偏差量，当所述煤质偏差量大于第一差值阈值时，确定所述煤质在线检测系统存在故障，并根据所述煤质偏差量对应的煤质维度的数量以及煤质偏差量的大小，确定煤质在线检测系统的故障情况。In another possible embodiment, the difference between the measurement result of the coal quality entering the factory laboratory and the coal quality detection result is used as the coal quality deviation amount, when the coal quality deviation amount is greater than the first difference threshold , it is determined that there is a fault in the online coal quality detection system, and the fault condition of the online coal quality detection system is determined according to the number of coal quality dimensions corresponding to the coal quality deviation and the size of the coal quality deviation.
实施例2Example 2
本申请实施例中提供一种计算机可读存储介质，其上存储有计算机程序，当所述计算机程序在计算机中执行时，令计算机执行上述的一种煤质在线检测系统故障判定方法。An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed in a computer, the computer is made to execute the above-mentioned fault determination method for an online coal quality detection system.
实施例3Example 3
本申请实施例中提供一种计算机程序产品，其特征在于，所述计算机程序产品存储有指令，所述指令在由计算机执行时，使得所述计算机实施上述的一种煤质在线检测系统故障判定方法。An embodiment of the present application provides a computer program product, which is characterized in that the computer program product stores instructions, and when the instructions are executed by a computer, the computer implements the above-mentioned online coal quality detection system fault judgment method.
另外，在本发明各个实施例中的各功能模块可以集成在一起形成一个独立的部分，也可以是各个模块单独存在，也可以两个或两个以上模块集成形成一个独立的部分。In addition, each functional module in each embodiment of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.
功能如果以软件功能模块的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本发明各个实施例方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、移动存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods in various embodiments of the present invention. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), mobile access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes. .
以上述依据本发明的理想实施例为启示，通过上述的说明内容，相关工作人员完全可以在不偏离本项发明技术思想的范围内，进行多样的变更以及修改。本项发明的技术性范围并不局限于说明书上的内容，必须要根据权利要求范围来确定其技术性范围。Inspired by the above-mentioned ideal embodiment according to the present invention, through the above-mentioned description content, relevant workers can make various changes and modifications within the scope of not departing from the technical idea of the present invention. The technical scope of the present invention is not limited to the content in the specification, but must be determined according to the scope of the claims.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211624465.5A CN116380816A (en) | 2022-12-16 | 2022-12-16 | Method, program and storage medium for judging faults of coal quality online detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211624465.5A CN116380816A (en) | 2022-12-16 | 2022-12-16 | Method, program and storage medium for judging faults of coal quality online detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116380816A true CN116380816A (en) | 2023-07-04 |
Family
ID=86969920
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211624465.5A Pending CN116380816A (en) | 2022-12-16 | 2022-12-16 | Method, program and storage medium for judging faults of coal quality online detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116380816A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117110975A (en) * | 2023-10-23 | 2023-11-24 | 石家庄科林电力设计院有限公司 | A misalignment detection method and device for a multi-channel electric energy metering device |
-
2022
- 2022-12-16 CN CN202211624465.5A patent/CN116380816A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117110975A (en) * | 2023-10-23 | 2023-11-24 | 石家庄科林电力设计院有限公司 | A misalignment detection method and device for a multi-channel electric energy metering device |
| CN117110975B (en) * | 2023-10-23 | 2024-02-09 | 石家庄科林电力设计院有限公司 | A misalignment detection method and device for a multi-channel electric energy metering device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117391459B (en) | Power operation risk early warning method and system based on deep learning | |
| CN118779831B (en) | Main transformer fault prediction method based on multivariable data fusion | |
| CN118757347B (en) | Intelligent identification method and system for wind generating set | |
| CN119622538B (en) | Equipment state sensing system based on peak staggering and dangerous situation sensing | |
| Giner‐Bosch et al. | An EWMA control chart for the multivariate coefficient of variation | |
| CN110865260A (en) | A method for monitoring and evaluating the actual state of MOV based on outlier detection | |
| CN118211837A (en) | A performance evaluation method and device for smart electric meter | |
| CN114004162A (en) | Modeling method for smelting load harmonic emission level under multi-working-condition scene | |
| CN117422167A (en) | Electric power carbon emission predictive analysis method based on tree model | |
| CN118482817B (en) | Digital textile equipment management method and system based on data analysis | |
| CN117977536A (en) | A method for identifying loads in smart grid | |
| CN118761522A (en) | Production quality prediction method based on kernel principal component analysis and multivariate linear regression | |
| CN116910668A (en) | A lightning arrester failure early warning method, device, equipment and storage medium | |
| CN116380816A (en) | Method, program and storage medium for judging faults of coal quality online detection system | |
| CN113269327A (en) | Flow anomaly prediction method based on machine learning | |
| CN120375969A (en) | Artificial intelligence-based dairy product quality safety detection method and system | |
| CN114611865A (en) | Instrument control platform-based health assessment method for industrial control station instrument | |
| CN118734036A (en) | Real-time drilling speed prediction method for drilling rig based on Transformer framework | |
| CN119622509A (en) | A gas mixture detection model construction method and a gas mixture detection method | |
| Abolmohammadi et al. | Effect of Linex loss function on the VSIX control chart | |
| CN114046179B (en) | A method to intelligently identify and predict underground safety accidents based on CO monitoring data | |
| Trappey et al. | Integrating real-time monitoring and asset health prediction for power transformer intelligent maintenance and decision support | |
| Liu et al. | Research on health state classification and maintenance strategy optimisation of manufacturing equipment based on brittleness | |
| Saiepour et al. | Development and assessment of predictive emission monitoring systems (PEMS) models in the steel industry | |
| He et al. | A novel soft sensor model based on stacking ensemble learning framework |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20230704 |