CN119217474A

CN119217474A - A wood segmentation method based on machine vision

Info

Publication number: CN119217474A
Application number: CN202411755330.1A
Authority: CN
Inventors: 邓帅; 潘博; 胡昊; 刘建清
Original assignee: Sichuan Qingcheng Machinery Co Ltd
Current assignee: Sichuan Qingcheng Machinery Co Ltd
Priority date: 2024-12-03
Filing date: 2024-12-03
Publication date: 2024-12-31

Abstract

The invention discloses a timber cutting method based on machine vision, which comprises the following steps of S1, conveying timber into a vision scanner for recognition through a feeding table chain, S2, setting related timber cutting parameters by a user and determining timber corresponding values according to the set parameters, S3, determining timber cutting type priority and performing timber cutting. The invention can comprehensively analyze the wood sample through the visual scanner, realize the identification and detection of a plurality of targets such as wood types, quality, size and the like, greatly improve the efficiency and precision of wood processing, accurately identify and classify the wood, thereby realizing the optimization and the maximization of the value of the material in the furniture manufacturing process, and realizing the maximization of the wood utilization rate, thereby reducing the production cost and improving the production efficiency.

Description

Timber segmentation method based on machine vision

Technical Field

The invention relates to the technical field of machine vision, in particular to a timber segmentation method based on machine vision.

Background

In the current domestic sawing market, wood veneer removal and optimized sawing of boards are mainly realized by adopting a longitudinal preferential saw, the feeding problem of wood is the biggest problem puzzling each manufacturer, and the feeding modes adopted by most manufacturers at present are two, namely, manual feeding by workers, manual adjustment of laser scribing, manual alignment of the wood position and feeding into the preferential saw for sawing, and manual adjustment of laser scribing, manual alignment of the wood position and feeding into the preferential saw for sawing. Compared with the first mode, the second mode has the advantages that the labor amount is reduced without manual feeding, but the two modes still have great defects, such as manual intervention, wood alignment is carried out by naked eyes, and the processing precision is low and the efficiency is low.

Disclosure of Invention

The wood splitting method based on machine vision comprises the following steps of S1, conveying wood into a vision scanner through a feeding table chain for recognition, S2, setting related parameters of wood splitting by a user and determining corresponding values of the wood according to the set parameters, S3, determining priority of wood splitting types and splitting the wood, and equipment preparation step S0., setting and installing related equipment for achieving wood splitting, wherein in the S0 step, the related equipment concretely comprises the vision scanner, a feeding table, a numerical control positioning table, a longitudinal-section preferential saw and an upper computer, the vision scanner is used for collecting and analyzing patterns of the wood, the feeding table is used for conveying the wood, the numerical control positioning table is used for fixing the position of the wood and adjusting the position of the wood, a plurality of longitudinal-section preferential saws are used for splitting the wood according to the set parameters of the user, and the upper computer is used for setting a wood splitting scheme and monitoring the states of the vision scanner, the feeding table, the numerical control positioning table and the longitudinal-section preferential saw.

Further, the related parameters of wood splitting in the step S2 specifically include sawing width, required quantity, splitting priority, and whether quantity priority is enabled.

The method comprises the following steps of S3, namely determining a wood cutting scheme according to wood cutting related parameters set by a user and scanning data of a visual scanner, S32, feeding the wood into a numerical control positioning table for sawing positioning adjustment, S33, adjusting a movable saw blade to a cutting position by a longitudinal section preferential saw according to the wood cutting related parameters set by the user, and S34, transversely transmitting the wood into the longitudinal section preferential saw for preferential sawing.

Further, the step S31 specifically comprises the substeps of S311, starting a plurality of longitudinally-cut preferential saws, calculating the residual quantity of the divided timber, S312, selecting the combination with the smallest residual quantity, judging whether the quantity is started to be preferential, S313, calculating the sum of the corresponding values of the combinations with the smallest residual quantity, sequencing, and selecting the combination with the largest total value.

Further, the calculation formula of the allowance after the wood is divided is that the allowance=the clean width of the wood- (planning size 1+planning size 2+ & gt planning size n) - (longitudinal section preferred saw moving link 1+longitudinal section preferred saw moving link 2+ & gt longitudinal section preferred saw moving link n-1), wherein n represents the number of the adopted longitudinal section preferred saws.

Further, the step S312 specifically includes counting and sorting the required number of each size in the combinations with the smallest margin when the number of activated priorities is higher, selecting the combination with the smallest required number, and executing the step S313 when the number of deactivated priorities is higher.

The invention provides a timber segmentation method based on machine vision, which has the following beneficial effects:

The invention can comprehensively analyze the wood sample through the visual scanner, realize the identification and detection of a plurality of targets such as wood types, quality, size and the like, greatly improve the efficiency and precision of wood processing, accurately identify and classify the wood, thereby realizing the optimization and the maximization of the value of the material in the furniture manufacturing process, and realizing the maximization of the wood utilization rate, thereby reducing the production cost and improving the production efficiency.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to the structures shown in these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method provided by the invention.

Detailed Description

It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.

The following detailed description of embodiments of the invention, taken in conjunction with the accompanying drawings, illustrates only some, but not all embodiments, and for the sake of clarity, illustration and description not related to the invention is omitted in the drawings and description.

The technical scheme of the present invention is selected from the following detailed description in order to more clearly understand the technical features, objects and advantageous effects of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention and should not be construed as limiting the scope of the invention which can be practiced. All other embodiments, which can be made by a person of ordinary skill in the art based on the embodiments of the present invention without making any inventive effort, are within the scope of the present invention.

The invention provides a timber cutting method based on machine vision, which is shown in fig. 1 and comprises the following steps of S1, conveying timber into a vision scanner for recognition through a feeding table chain, S2, setting related timber cutting parameters by a user, determining timber corresponding values according to the setting parameters, S3, determining timber cutting type priority and performing timber cutting, and equipment preparation step S0., setting and installing related equipment for realizing timber cutting, wherein in the S0 step, the related equipment concretely comprises the vision scanner, a feeding table, a numerical control positioning table, a longitudinal section preferential saw and an upper computer, the vision scanner is used for collecting and analyzing patterns of the timber, the feeding table is used for conveying the timber, the numerical control positioning table is used for fixing the position of the timber and adjusting the position of the timber, a plurality of longitudinal section preferential saws are arranged for cutting the timber according to the setting parameters of the user, and the upper computer is used for setting a timber cutting scheme and monitoring the states of the vision scanner, the feeding table, the numerical control positioning table and the longitudinal section preferential saw.

The related parameters of wood splitting in the step S2 comprise sawing width, required quantity, splitting priority and whether quantity priority is started or not.

S3, determining a wood cutting scheme according to wood cutting related parameters set by a user and scanning data of a visual scanner, S32, feeding the wood into a numerical control positioning table for sawing positioning adjustment, S33, adjusting a movable saw blade to a cutting position by a longitudinal section preferential saw according to the wood cutting related parameters set by the user, and S34, transversely transmitting the wood into the longitudinal section preferential saw for preferential sawing.

S31, specifically, starting a plurality of longitudinally-cut preferential saws, calculating the residual quantity of the divided timber, S312, selecting the combination with the minimum residual quantity, judging whether the quantity is started to give priority, S313, calculating the sum of the corresponding values of the combination with the minimum residual quantity, sequencing, and selecting the combination with the maximum total value.

The calculation formula of the allowance after the wood is divided is that the allowance = wood clear width- (planning dimension 1+planning dimension 2+ & planning dimension n) - (longitudinal section preferred saw moving link 1+longitudinal section preferred saw moving link 2+ & longitudinal section preferred saw moving link n-1), wherein n represents the number of adopted longitudinal section preferred saws.

The step S312 specifically includes counting and sorting the required number of each size in the combination with the smallest margin when the number of the activated sets is prioritized, selecting the combination with the smallest required number, and executing the step S313 when the number of the activated sets is not prioritized.

The embodiment of the method for analyzing and optimizing the sawing of the wood sample based on the machine vision comprises a vision scanner, a feeding table, a numerical control positioning table and a longitudinal section optimizing saw, and mainly comprises the following steps:

Step one, wood is conveyed into a visual scanner through a feeding table chain to prepare for identification work.

And secondly, collecting patterns of the wood sample and analyzing the images.

And thirdly, giving the analysis result to an upper computer, and carrying out process treatment such as value optimization, quantity optimization, grade optimization, maximum yield optimization and the like according to the needs of clients. The customer firstly inputs the size, the number and the priority of the saw cutting at the master control end, and whether the number priority is started or not.

And (3) according to the list of users, arranging and combining, searching an optimal cutting scheme, and ensuring the highest value under the condition of ensuring the maximum material output. The analysis identifies that the current wood clear width is W (after the edge skin is removed), the upper computer automatically searches for the combination which meets the requirements and is generated under the conditions of starting 1 movable saw (namely, longitudinally slitting the optimized saw), starting 2 movable saws, starting 3 movable saws and starting 4 movable saws, and respectively calculates the allowance of the combination.

1 Moving saw (without consideration of saw path) is activated, margin = wood clear width W-planned dimension 1.

2 Mobile saws (consider 1 st mobile saw cut) were activated with margin = wood clearance W-planned dimension 1-planned dimension 2-1 st mobile saw cut.

3 Mobile saws (1 st and 2 nd mobile saw kerfs are considered) are started, and the allowance = wood clear width W-planned size 1-planned size 2-planned size 3-1 st mobile saw kerf-2 nd mobile saw kerf.

4 Mobile saws (1 st, 2 nd and 3 rd mobile saw paths are considered) are started, and the allowance=the wood clear width W-the planning size 1-the planning size 2-the planning size 3-the planning size 4-the 1 st mobile saw path-the 2 nd mobile saw path-the 3 rd mobile saw path.

By comparing the sizes of the margins, the combination with the smallest margin is found, and the combination with the smallest margin can be 1 or more combinations (the step ensures the largest wood output and reduces the wood waste). And then taking out the combination with the smallest allowance for the next operation.

After the combination with the minimum allowance is obtained, judging whether the quantity priority mode is started, if the quantity priority mode is not started, calculating the value sum corresponding to the combination with the minimum allowance, sequencing the total value, and selecting the combination with the maximum total value for sawing. The value is calculated by customizing the plates with different grades according to the user, and the value of the corresponding size can be improved by improving the priority.

If the quantity priority mode is started, counting the required quantity of each size in the combination with the minimum allowance, sequencing the required quantity, and selecting the sawing with the minimum required quantity.

For example, recognizing that the current wood width is 187mm (after the edge skin is removed), the upper computer automatically finds the combination of 140+0+0+0, the remainder being 47mm, which is obtained in the case of using 1 moving saw.

The combination obtained in the case of using 2 moving saws (3 mm for the middle moving saw kerf) was 130+50+0+0+3, the remainder being 4mm, 120+60+0+0+3, the remainder being 4mm, 110+70+0+0+3, the remainder being 4mm, 100+80+0+0+3, the remainder being 4mm, 90+90+0+0+3, the remainder being 4mm.

In the case of using 3 moving saws (the middle moving saw path is 3mm+3mm), 80+50+50+0+3+3, the remainder is 1mm, 70+60+50+0+3+3, the remainder is 1mm, 60+60+60+0+3+3, and the remainder is 1mm.

In the case of using 4 moving saws (the middle moving saw path is 3mm+3mm+3mm), no satisfactory combination can be found, and when the minimum combination is 50+50+50+3+3+3 and the net width of the timber is at least 209mm, the 4 moving saws can be used for sawing.

The combination with the smallest margin is obtained by comparison, namely 80+50+50+0+3+3, the margin is 1mm, 70+60+50+0+3+3, the margin is 1mm, 60+60+60+0+3+3, and the margin is 1mm.

Then judging whether the quantity priority mode is started or not, if the quantity priority mode is not started, continuing to calculate the total value corresponding to the 3 combinations with the smallest margin, namely 80+50+50+3+3:1068+760+760=2588, 70+60+50+3:972+852+760=2584, 60+60+60+3:852+852+852+2556.

And sorting the total values, selecting the combination with the highest value, namely selecting the combination of 80+50+50+3+3, sawing by using 3 movable saws, and finally sawing 1 sheet of plate with the width of 80mm and 2 sheets of 50mm.

If the number priority mode is started, the sawing is preferably performed with the smallest size requirement in the combination under the condition of the smallest judging allowance, wherein the combination of 80+50+50+3+3 is selected if the required number of the size 80 is smallest, the combination of 70+60+50+3+3 is selected if the required number of the size 70 is smallest, the combination of 60+60+60+3+3 is selected if the required number of the size 60 is smallest, and the combination of 80+50+50+3+3 is selected if the required number of the size 50 is smallest.

And finally, outputting a preferred result by the main control, and positioning the movable saw blade.

And fourthly, identifying that the completed timber enters a rear numerical control positioning table for sawing positioning adjustment. Wherein, the positioning accuracy of the latter positioning system is 0.1mm.

And fifthly, adjusting and moving the saw blade to a corresponding position by the longitudinal section preferential saw according to the preferential result. Wherein, saw blade movement accuracy is 0.1mm.

And step six, after the adjustment is finished, the timber is transversely conveyed into a longitudinal section preferential sawing device for preferential sawing.

The foregoing is merely a preferred embodiment of the invention, and it is to be understood that the invention is not limited to the form disclosed herein but is not to be construed as excluding other embodiments, but is capable of numerous other combinations, modifications and environments and is capable of modifications within the scope of the inventive concept, either as taught or as a matter of routine skill or knowledge in the relevant art. And that modifications and variations which do not depart from the spirit and scope of the invention are intended to be within the scope of the appended claims.

Claims

1. A wood segmentation method based on machine vision, characterized in that it comprises the following steps:

S1. The wood is transported through the loading platform chain into the visual scanner for identification;

S2. The user sets the parameters related to wood segmentation and determines the corresponding value of the wood according to the set parameters;

S3. Determine the priority of wood segmentation type and perform wood segmentation;

It also includes equipment preparation steps: S0. Setting and installing relevant equipment to achieve wood splitting;

The relevant equipment in step S0 specifically includes: a visual scanner, a loading table, a CNC positioning table, a longitudinal sectioning optimization saw, and a host computer;

The visual scanner is used to collect and analyze the pattern of wood;

The loading platform is used to transport wood;

The numerical control positioning table is used to fix the position of the wood and adjust the position of the wood;

The longitudinal splitting preferred saw has multiple parts, which are used to split the wood according to the parameters set by the user;

The host computer is used to set the wood splitting plan and monitor the status of the visual scanner, the loading platform, the CNC positioning platform, and the longitudinal splitting optimal saw.

2. The method for wood segmentation based on machine vision according to claim 1 is characterized in that the wood segmentation related parameters in step S2 specifically include: sawing width, required quantity, segmentation priority, and whether quantity priority is enabled.

3. The wood segmentation method based on machine vision according to claim 1, characterized in that the step S3 specifically includes the following sub-steps:

S31. Determine the wood segmentation scheme according to the wood segmentation parameters set by the user and the visual scanner scan data;

S32. The wood is fed into the CNC positioning table for sawing positioning adjustment;

S33. The longitudinal cutting optimal saw adjusts the moving saw blade to the splitting position according to the wood splitting related parameters set by the user;

S34. The wood is transferred transversely to the longitudinal cutting optimization saw for optimal sawing.

4. The wood segmentation method based on machine vision according to claim 3 is characterized in that the step S31 specifically includes the following sub-steps:

S311. Start multiple longitudinal cutting optimal saws and calculate the remaining amount of wood after splitting;

S312. Select the combination with the smallest margin and determine whether to enable quantity priority;

S313. Calculate the sum of the corresponding values of the combinations with the smallest remainder and sort them, and select the combination with the largest total value.

5. According to the machine vision-based wood segmentation method of claim 4, it is characterized in that the calculation formula for the remainder of the wood after segmentation is: remainder = net width of wood - (planned size 1 + planned size 2 +... + planned size n) - (longitudinal sectioning preferred saw mobile link 1 + longitudinal sectioning preferred saw mobile link 2 +... + longitudinal sectioning preferred saw mobile link n-1), where n represents the number of longitudinal sectioning preferred saws used.

6. The machine vision-based wood segmentation method according to claim 4 is characterized in that the step S312 specifically includes: when quantity priority is enabled, counting the required quantity of each size in the combination with the smallest margin and sorting them, and selecting the combination with the smallest required quantity; when quantity priority is not enabled, executing step S313.