Intelligent monitoring system for wood shaving processing

Abstract

The invention discloses an intelligent monitoring system for wood shaving processing, which belongs to the field of intelligent monitoring systems and comprises a product quality acquisition module, a production data acquisition module, an environment data acquisition module, a data receiving module, a data analysis module and a visualization module. The product quality acquisition module comprises an image acquisition unit, a strength acquisition unit and a water content acquisition unit, the image acquisition unit acquires surface image information of the shaving board through a camera, and the strength acquisition unit acquires internal structural strength information of the shaving board through ultrasonic detection; and the water content acquisition unit acquires water content information in the shaving board through an electrical measurement method. The product quality, the production data and the environment data on the production line can be comprehensively monitored, the overall monitoring effect is improved, and then background workers are helped to more effectively know the overall state of the production line.

Description

Technical Field

[0001] The invention relates to the field of intelligent monitoring systems, in particular to an intelligent monitoring system for wood shavings processing. Background Art

[0002] Wood shavings processing is a multi-step process, mainly including raw material preparation, wood cutting, wood drying, shavings production, subsequent processing, and finally making particleboard. In addition, wood shavings processing is a complex and delicate process, which requires strict control of the quality and operation specifications of each link. With the continuous advancement of technology and changes in market demand, the wood shavings processing industry will continue to grow and develop, providing more high-quality and environmentally friendly shavings products for various fields.

[0003] The existing patent (publication number: CN118037649A) is a real-time monitoring method, terminal and medium for the cross-sectional density of particleboard during hot pressing, which belongs to the field of particleboard processing technology, including obtaining marked wood chips after being marked with different colors of spray paint; obtaining a slab with the marked wood chips evenly spread on one side; obtaining a photo set of marked wood chips on the side of the slab during hot pressing; extracting and processing the photo set of marked wood chips to obtain images of all marked wood chips in the photo set; identifying and processing the images of all marked wood chips through pre-built OpenCV image processing technology, and using self-built tracking and positioning technology to obtain the center of mass and displacement changes of the marked wood chips.

[0004] In order to improve the operation stability of the existing wood shavings processing production line, it is necessary to carry out intelligent monitoring of the production line. However, the traditional intelligent monitoring system is not comprehensive enough in monitoring the product quality, production data and environmental data on the production line, which makes the overall monitoring effect less than ideal and cannot help the back-end staff to more effectively understand the overall status of the production line.

[0005] Therefore, those skilled in the art provide an intelligent monitoring system for wood shavings processing to solve the problems raised in the above background technology. Summary of the invention

[0006] The purpose of the present invention is to provide an intelligent monitoring system for wood shavings processing, which can comprehensively monitor the product quality, production data and environmental data on the production line, improve the overall monitoring effect, and then help the backstage staff to more effectively understand the overall status of the production line, so as to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] An intelligent monitoring system for wood shavings processing, comprising a product quality acquisition module, a production data acquisition module, an environmental data acquisition module, a data receiving module, a data analysis module and a visualization module;

[0009] The product quality acquisition module includes an image acquisition unit, a strength acquisition unit, and a moisture content acquisition unit, wherein the image acquisition unit acquires the surface image information of the particleboard through a camera, the strength acquisition unit acquires the internal structural strength information of the particleboard through ultrasonic detection, and the moisture content acquisition unit acquires the internal moisture content information of the particleboard through electrical measurement; the production data acquisition module includes a personnel status acquisition unit, an equipment status acquisition unit, and a product status acquisition unit, wherein the personnel status acquisition unit acquires the image information of the staff on the production line through a camera, the equipment status acquisition unit is used to acquire the faulty equipment node information on the current production line, and the product status acquisition unit is used to acquire the processing time information of the final product of the current production line; the environmental data acquisition module is used to acquire the environmental information of the current production line, and the environmental information includes temperature and humidity, dust concentration and noise; the data receiving module is used to receive all the acquired information and send it to the data analysis module; the data analysis module is used to analyze all the received information and send the analysis results to the visualization module; the visualization module is used to visualize the analysis results to the background staff.

[0010] As a further solution of the present invention: the specific process of the data analysis module analyzing the information collected by the product quality collection module is:

[0011] S101: performing image recognition on the collected particle board surface image, identifying cracks on the particle board surface, and marking the identified cracks as Ai, i=1···k, where k is a natural number;

[0012] S102: k and a preset value K 预设 Perform comparison, if k ≥ K 预设 , it means that the cracks in the particleboard are abnormal. If k<K 预设 , then proceed to step S103;

[0013] S103: Count the total length of all Ai and mark it as b, then compare b with the preset value B 预设 Compare, if b ≥ B 预设 , it means that the cracks in the particleboard are abnormal. If b<B 预设 , then proceed to step S104;

[0014] S104: construct a structural strength analysis model to analyze and determine whether there is an abnormality in the internal structural strength of the particleboard;

[0015] S105: construct a moisture content analysis model to analyze and determine whether there is an abnormality in the moisture content inside the particleboard.

[0016] As a further solution of the present invention: the specific analysis process of the structural strength analysis model is:

[0017] S201: Divide the surface of the particle board into a plurality of regions, and mark them as Ci, i=1···n, where n is a positive integer;

[0018] S202: If there is a crack Ai in the region Ci, plan Ci to the first sequence; if there is no crack Ai in the region Ci, plan Ci to the second sequence;

[0019] S203: collecting internal structural strength information of all regions of the particleboard through ultrasonic testing, wherein the internal structural strength information includes ultrasonic propagation velocity and ultrasonic attenuation coefficient;

[0020] S204: Mark the average ultrasonic propagation speed corresponding to all Ci in the first sequence collected as V1, and then mark the average ultrasonic propagation speed corresponding to all Ci in the second sequence collected as V2. If (V1-V2) is greater than the preset speed, it means that the internal structural strength of the particleboard is abnormal. If (V1-V2) is less than or equal to the preset speed, enter step S205;

[0021] S205: Mark the average ultrasonic attenuation coefficient corresponding to all Ci in the first sequence collected as D1, and then mark the average ultrasonic attenuation coefficient corresponding to all Ci in the second sequence collected as D2. If (D2-D1) is greater than the preset attenuation coefficient, it means that there is an abnormality in the internal structural strength of the particleboard. If (D2-D1) is less than or equal to the preset attenuation coefficient, enter step S206;

[0022] S206: Calculate the comprehensive structural strength weight value s of the particle board = (V2 / D2). If s is greater than the preset structural strength weight value, it means that the internal structural strength of the particle board is normal. If s is less than or equal to the preset structural strength weight value, it means that the internal structural strength of the particle board is abnormal.

[0023] As a further solution of the present invention: the specific analysis process of the moisture content analysis model is:

[0024] S301: collecting the internal moisture content of all regions of the particleboard by electrical measurement and marking it as Ei, i=1···n;

[0025] S302: If Ei is within the preset interval, the area corresponding to Ei is planned to the third sequence; if Ei is not within the preset interval, the area corresponding to Ei is planned to the fourth sequence;

[0026] S303: Count the number of regions in the fourth sequence and mark them as F, and then count the number of repeated regions in the fourth sequence and the first sequence and mark them as G;

[0027] S304: Compare F with the preset value f, and compare G with the preset value g. If F>f and G>g, it means that there is a third-level abnormality in the moisture content inside the particleboard; if F≤f and G>g, it means that there is a second-level abnormality in the moisture content inside the particleboard; if F>f and G≤g, it means that there is a first-level abnormality in the moisture content inside the particleboard; if F≤f and G≤g, it means that the moisture content inside the particleboard is normal.

[0028] As a further solution of the present invention: the specific process of the data analysis module analyzing the information collected by the production data collection module is:

[0029] S401: Mark the collected processing time of the final product of the current production line as T;

[0030] S402: Compare T with the preset time t. If T>t, it means that the processing time of the product is abnormal. If T≤t, go to step S403;

[0031] S403: by performing image recognition on the collected image information of the workers on the production line, determining whether the workers' sight is focused on the products at their workstations when the products flow through the workers, if so, the workers are arranged to the fifth sequence, if not, the workers are arranged to the sixth sequence, and the length of time the workers' sight is away from the products at their workstations is counted;

[0032] S404: Count the total number of workers in the sixth sequence and mark it as X, then select the maximum time that the workers in the sixth sequence have their sight away from the product at their workstation and mark it as Y;

[0033] S405: Compare X with a preset value x, and compare Y with a preset value y. If any of X>x and Y>y occurs, it indicates that the status of the personnel on the production line is abnormal. If X≤x and Y≤y, proceed to step S406;

[0034] S406: Construct an equipment failure analysis model to analyze and determine whether there is an abnormality in the equipment failure on the production line.

[0035] As a further solution of the present invention: the specific analysis process of the equipment failure analysis model is:

[0036] S501: Collecting the locations of all faulty device nodes on the current production line, and connecting the adjacent locations of the faulty device nodes on the production line into a line segment;

[0037] S502: If there are two faulty device node locations on the line segment, the line segment is planned to the seventh sequence; if there are three faulty device node locations on the line segment, the line segment is planned to the eighth sequence; if there are more than three faulty device node locations on the line segment, the line segment is planned to the ninth sequence;

[0038] S503: Count the number of line segments in the seventh sequence, the eighth sequence, and the ninth sequence, and mark them as q1, q2, and q3 respectively;

[0039] S504: Calculate the fault criticality weight value W=30%*q1+50%*q2+90%*q3;

[0040] S505: Compare W with a preset weight value w. If W>w, it indicates that there is an abnormality in the equipment failure on the production line. If W≤w, it indicates that there is no abnormality in the equipment failure on the production line.

[0041] As a further solution of the present invention: the specific process of the data analysis module analyzing the information collected by the environmental data collection module is:

[0042] S601: Mark the collected temperature information as M1, the collected humidity information as M2, the collected dust concentration information as M3, and the collected noise volume information as M4;

[0043] S602: Generate a radar chart P based on M1, M2, M3, and M4, and then mark the preset radar chart as p;

[0044] S603: P and p are compared for similarity. If the similarity between the two is greater than a preset similarity, it indicates that the environment of the production line is normal. If the similarity between the two is less than or equal to the preset similarity, it indicates that the environment of the production line is abnormal.

[0045] As a further solution of the present invention: the visualization module includes a display screen, and the display area of ​​the display screen is divided into three areas, which respectively correspond to the analysis results of the data collected by the product quality collection module, the production data collection module, and the environmental data collection module.

[0046] As a further solution of the present invention: when the data collected by the product quality collection module, the production data collection module, and the environmental data collection module are analyzed to be abnormal, the display area boundary of the corresponding display screen flashes red.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] This application can comprehensively monitor the product quality, production data and environmental data on the production line, improve the overall monitoring effect, and then help the back-end staff to more effectively understand the overall status of the production line. Among them, the product quality is analyzed from multiple angles from the surface cracks of the particleboard, the internal structure strength and the moisture content, and the production data is analyzed from three aspects: the length of time it takes to complete the product, the sight of the staff, and the equipment failure point. Finally, the entire wood particle processing production line is efficiently monitored, and timely warnings are issued when abnormalities occur, effectively improving the stability of the production line operation.

[0049] When analyzing product quality, this application first analyzes whether the cracks on the product surface are abnormal, and then combines the identified cracks with the constructed structural strength analysis model and moisture content analysis model for analysis, thereby quickly and accurately determining whether the particleboard product quality is abnormal. When analyzing production data, the line of sight of the workers on the production line is captured to analyze whether the workers are focused, and for faulty equipment, by counting the correlation between the locations of these equipment, it is quickly analyzed whether the hazards caused by these faulty equipment are abnormal. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 The block diagram of the intelligent monitoring system for wood shavings processing;

[0051] Figure 2 Schematic diagram of radar chart P in the intelligent monitoring system for wood shavings processing. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] As mentioned in the background technology of this application, research has found that the existing intelligent monitoring system is not comprehensive enough in monitoring product quality, production data and environmental data on the production line, resulting in less than ideal overall monitoring effect. It is unable to help back-end staff more effectively understand the overall status of the production line and has certain defects.

[0054] In order to solve the above-mentioned defects, the present application discloses an intelligent monitoring system for wood shavings processing, which can comprehensively monitor the product quality, production data and environmental data on the production line, improve the overall monitoring effect, and thus help backstage staff to more effectively understand the overall status of the production line.

[0055] The following will describe in detail how the solution of the present application solves the above technical problems in conjunction with the accompanying drawings.

[0056] Embodiment 1:

[0057] See also Figure 1 In the embodiment of the present invention, it includes a product quality acquisition module, a production data acquisition module, an environmental data acquisition module, a data receiving module, a data analysis module and a visualization module; the product quality acquisition module includes an image acquisition unit, a strength acquisition unit and a moisture content acquisition unit, wherein the image acquisition unit acquires the surface image information of the particle board through a camera, the strength acquisition unit acquires the internal structural strength information of the particle board through ultrasonic detection, and the moisture content acquisition unit acquires the internal moisture content information of the particle board through an electrical measurement method; the production data acquisition module includes a personnel status acquisition unit, an equipment status acquisition unit and a product status acquisition unit, wherein the personnel status acquisition unit acquires the image information of the staff on the production line through a camera, the equipment status acquisition unit is used to acquire the faulty equipment node information on the current production line, and the product status acquisition unit is used to acquire the processing time information of the final product of the current production line; the environmental data acquisition module is used to acquire the environmental information of the current production line, wherein the environmental information includes temperature and humidity, dust concentration and noise; the data receiving module is used to receive all the acquired information and send it to the data analysis module; the data analysis module is used to analyze all the received information and send the analysis results to the visualization module; the visualization module is used to visualize the analysis results to the background staff. This application can comprehensively monitor the product quality, production data and environmental data on the production line, improve the overall monitoring effect, and then help the back-end staff to more effectively understand the overall status of the production line.

[0058] In this embodiment, the specific process of the data analysis module analyzing the information collected by the product quality collection module is as follows: S101: performing image recognition on the collected particle board surface image, identifying the cracks on the particle board surface, and marking the identified cracks as Ai, i = 1...k, where k is a natural number; S102: comparing k with the preset value K 预设 Compare, if k ≥ K 预设 , it means that the cracks in the particleboard are abnormal. If k<K 预设 , then go to step S103; S103: count the total length of all Ai, and mark it as b, then compare b with the preset value B 预设 Compare, if b ≥ B 预设 , it means that the cracks in the particleboard are abnormal. If b<B 预设, then enter step S104; S104: construct a structural strength analysis model to analyze and determine whether there is an abnormality in the internal structural strength of the particleboard; S105: construct a moisture content analysis model to analyze and determine whether there is an abnormality in the internal moisture content of the particleboard. Image recognition refers to the technology of using a computer to process, analyze and understand the input image to identify various target objects in the image and extract relevant information. It is a core task in the field of computer vision, which aims to enable computers to have the ability to understand and judge the content of the image like humans. Image recognition technology is based on the main features of the image. Each image has its own features, such as color, texture, shape, etc., which play a key role in the image recognition process. The core of image recognition technology is to extract these features from the image through algorithms and models, and match them with known patterns to identify the target object in the image. Image recognition is used to identify surface cracks on particleboard. Surface cracks on particleboard directly affect its appearance, making the surface of the board look uneven and imperfect, which may reduce the overall visual effect of furniture or decoration materials. Although surface cracks do not necessarily cause the particleboard to break immediately, they may weaken the local strength of the board. Cracks may become areas of stress concentration, making them more susceptible to fracture or breakage when subjected to external forces.

[0059] In this embodiment, the specific analysis process of the structural strength analysis model is as follows: S201: divide the surface of the particle board into several areas and mark them as Ci, i=1···n, where n is a positive integer; S202: if there is a crack Ai in the area Ci, Ci is planned to the first sequence, and if there is no crack Ai in the area Ci, Ci is planned to the second sequence; S203: collect the internal structural strength information of all areas of the particle board through ultrasonic detection, wherein the internal structural strength information includes ultrasonic propagation velocity and ultrasonic attenuation coefficient; S204: mark the average ultrasonic propagation velocity corresponding to all Ci in the first sequence collected as V1, and then mark the average ultrasonic propagation velocity corresponding to all Ci in the second sequence collected as V2. If (V1-V2) is greater than the preset velocity, then the average ultrasonic propagation velocity is V1. degree, it indicates that the internal structural strength of the particleboard is abnormal. If (V1-V2) is less than or equal to the preset speed, the process proceeds to step S205; S205: the average ultrasonic attenuation coefficient corresponding to all Ci in the first sequence collected is marked as D1, and the average ultrasonic attenuation coefficient corresponding to all Ci in the second sequence collected is marked as D2. If (D2-D1) is greater than the preset attenuation coefficient, it indicates that the internal structural strength of the particleboard is abnormal. If (D2-D1) is less than or equal to the preset attenuation coefficient, the process proceeds to step S206; S206: calculate the comprehensive structural strength weight value s=(V2 / D2) of the particleboard. If s is greater than the preset structural strength weight value, it indicates that the internal structural strength of the particleboard is normal. If s is less than or equal to the preset structural strength weight value, it indicates that the internal structural strength of the particleboard is abnormal.

[0060] In this embodiment, the present application selects a particleboard for ultrasonic testing, wherein the average ultrasonic propagation velocity V1 corresponding to all Ci in the first sequence is 1200 m / s, the average ultrasonic propagation velocity V2 corresponding to all Ci in the second sequence is 800 m / s, the average ultrasonic attenuation coefficient D1 corresponding to all Ci in the first sequence is 0.06, and the average ultrasonic attenuation coefficient D2 corresponding to all Ci in the second sequence is 0.19. The basic principle of ultrasonic non-destructive testing is to use the propagation characteristics of ultrasonic waves in materials, and to detect the reflection, refraction and other phenomena of ultrasonic waves inside the material to determine whether there are defects or structural abnormalities inside the material, and then evaluate its structural strength. Through ultrasonic testing, the internal structural strength of the board can be non-destructively evaluated to find potential defects and damage. This method has the advantages of high resolution, high accuracy, and applicability to various types of materials, and has broad application prospects in the field of board quality control and testing. By measuring parameters such as ultrasonic propagation velocity and attenuation at different positions of the board, the overall strength information of the board can be indirectly obtained.

[0061] In this embodiment, the specific analysis process of the moisture content analysis model is as follows: S301: collect the internal moisture content of all areas of the particleboard by electrical measurement method, and mark it as Ei, i=1···n; S302: if Ei is within the preset interval, the area corresponding to Ei is planned to the third sequence, if Ei is not within the preset interval, the area corresponding to Ei is planned to the fourth sequence; S303: count the number of areas in the fourth sequence and mark it as F, and then count the number of repeated areas in the fourth sequence and the first sequence and mark it as G; S304: compare F with the preset value f, and compare G with the preset value g. If F>f, and G>g, it means that there is a third-level abnormality in the moisture content inside the particleboard; if F≤f, and G>g, it means that there is a second-level abnormality in the moisture content inside the particleboard; if F>f, and G≤g, it means that there is a first-level abnormality in the moisture content inside the particleboard; if F≤f, and G≤g, it means that the moisture content inside the particleboard is normal.

[0062] In this embodiment, the present application selects a particle board for moisture content analysis, wherein the number of regions in the fourth sequence is F=21, the number of repeated regions in the fourth sequence and the first sequence is G=16, the preset value is f=18, and the preset value is g=12. Through the above analysis process, it can be seen that F>f, and G>g, and the moisture content inside the particle board has three levels of abnormality. There are many methods for measuring the moisture content of wood, including drying method, electrical measurement method, distillation method, titration method, humidity method, as well as ray method and microwave method. Among them, the drying method is the most commonly used method, which measures the moisture content of the tested wood by drying the moisture content test piece until it is completely dry. The electrical measurement method uses the relationship between the conductivity of wood and the moisture content to determine the moisture content. The ray method and microwave method have the advantages of fast detection speed and large detection range, but the equipment is expensive and there is radiation hazard.

[0063] In this embodiment, the specific process of the data analysis module analyzing the information collected by the production data collection module is as follows: S401: mark the collected processing time of the final product of the current production line as T; S402: compare T with the preset time t, if T>t, it means that the processing time of the product is abnormal, if T≤t, then enter step S403; S403: perform image recognition on the collected image information of the staff on the production line to determine whether the staff's line of sight is fixed on the product at the workstation when the product flows through the staff, if so, the staff is planned to the fifth sequence, if not, the workstation is moved to the fifth sequence. The workers are planned to the sixth sequence, and the length of time that the workers' sight is away from the products at their workstations is counted; S404: the total number of workers in the sixth sequence is counted and marked as X, and then the maximum length of time that the workers' sight is away from the products at their workstations in the sixth sequence is screened and marked as Y; S405: X is compared with the preset value x, and Y is compared with the preset value y. If any of X>x and Y>y occurs, it means that the status of the personnel on the production line is abnormal. If X≤x and Y≤y, proceed to step S406; S406: construct an equipment failure analysis model to analyze and determine whether there is an abnormality in the equipment failure on the production line.

[0064] In this embodiment, the present application analyzes the staff on a production line in real time, wherein the processing time of the final product of the current production line is T=1.5h, the preset time is t=2.0h, the total number of staff in the sixth sequence is X=5, the maximum time that the staff's line of sight is away from the product at the workstation in the sixth sequence is Y=3s, the preset value x=10, and the preset value y=10s. When the product flows through the staff, if the staff's line of sight is not focused on the product at the workstation, it means that the staff is not focused enough, and the staff's lack of concentration in the production workshop may lead to a series of serious consequences, which not only affect production efficiency and product quality, but also may pose a threat to the safety of the staff themselves and the surrounding environment.

[0065] In this embodiment, the specific analysis process of the equipment failure analysis model is as follows: collect the positions of all faulty equipment nodes on the current production line, and connect the adjacent faulty equipment node positions on the production line into a line segment; if there are two faulty equipment node positions on the line segment, plan the line segment to the seventh sequence; if there are three faulty equipment node positions on the line segment, plan the line segment to the eighth sequence; if there are more than three faulty equipment node positions on the line segment, plan the line segment to the ninth sequence; S503: count the number of line segments in the seventh sequence, the eighth sequence, and the ninth sequence, and mark them as q1, q2, and q3 respectively; S504: calculate the fault hazard weight value W=30%*q1+50%*q2+90%*q3; S505: compare W with the preset weight value w, if W>w, it means that there is an abnormality in the equipment failure on the production line, if W≤w, it means that there is no abnormality in the equipment failure on the production line.

[0066] In this embodiment, the present application analyzes the equipment failure on a production line in real time, wherein the number of line segments in the seventh sequence of the current production line is q1=5, the number of line segments in the eighth sequence is q2=3, and the number of line segments in the ninth sequence is q3=1, then the fault hazard weight value W=30%*q1+50%*q2+90%*q3=3.9, the preset weight value w=0.5, W>w, and the equipment failure on the production line is abnormal. When the faults on the production line are connected together, the following effects may occur: production line stagnation (if multiple faults occur at the same time or are interrelated, the production line cannot continue to operate, which will directly affect the production schedule and output), chain reaction (one fault may trigger another fault, forming a chain reaction, making the problem more complicated and difficult to solve), and economic loss (long-term shutdown and increased maintenance costs will bring greater economic losses to the enterprise). However, the fault usually only affects a part or a link of the production line, and will not have a comprehensive impact on the entire production line. Since the faults are dispersed, the troubleshooting and repair work may be relatively easy, and production can be resumed faster.

[0067] In this embodiment, the specific process of the data analysis module analyzing the information collected by the environmental data collection module is: marking the collected temperature information as M1, the collected humidity information as M2, the collected dust concentration information as M3, and the collected noise amount information as M4; S602: generating a radar chart P based on M1, M2, M3, and M4, such as Figure 2 As shown, the preset radar chart is marked as p; P and p are compared for similarity. If the similarity between the two is greater than the preset similarity, it means that the environment of the production line is normal. If the similarity between the two is less than or equal to the preset similarity, it means that the environment of the production line is abnormal.

[0068] In this embodiment, the visualization module includes a display screen, and the display area of ​​the display screen is divided into three areas, corresponding to the analysis results of the data collected by the product quality acquisition module, the production data acquisition module, and the environmental data acquisition module. This setting can facilitate the background staff to quickly and intuitively understand the analysis results. A radar chart is a graphical method for displaying multiple quantitative variables, and is usually used to display multidimensional data of performance or quality indicators. In a radar chart, each variable (or dimension) is represented as an axis radiating outward from a center point, and the scale on each axis represents the value of the variable. Therefore, a radar chart can effectively display the performance of an entity in different aspects.

[0069] In this embodiment, when the data collected by the product quality collection module, the production data collection module, and the environmental data collection module are analyzed to be abnormal, the display area boundary of the corresponding display screen flashes red to remind the staff.

[0070] The present invention can comprehensively monitor the product quality, production data and environmental data on the production line, improve the overall monitoring effect, and then help the backstage staff to more effectively understand the overall status of the production line. Among them, the product quality is analyzed from multiple angles from the surface cracks of the particleboard, the internal structural strength and the water content, and the production data is analyzed from three aspects: the product completion time, the staff's line of sight, and the equipment failure point. Finally, the entire wood shavings processing production line is efficiently monitored, and timely warnings are issued when abnormalities occur, effectively improving the operation stability of the production line. Among them, when analyzing the product quality, the present application first analyzes whether the surface cracks of the product are abnormal, and then combines the identified cracks with the constructed structural strength analysis model and the moisture content analysis model for analysis, so as to quickly and accurately determine whether the particleboard product quality is abnormal. When analyzing the production data, the line of sight of the staff on the production line is captured to analyze whether the staff's attention is focused, and for the faulty equipment, by statistically analyzing the correlation between the positions of these equipment, it is quickly analyzed whether the hazards caused by these faulty equipment are abnormal.

[0071] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0072] What is described above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. Intelligent monitoring system for wood shavings processing, characterized in that: It includes product quality acquisition module, production data acquisition module, environmental data acquisition module, data receiving module, data analysis module and visualization module; The product quality acquisition module includes an image acquisition unit, a strength acquisition unit, and a moisture content acquisition unit. The image acquisition unit acquires the surface image information of the particle board through a camera, the strength acquisition unit acquires the internal structural strength information of the particle board through ultrasonic detection, and the moisture content acquisition unit acquires the internal moisture content information of the particle board through electrical measurement; the production data acquisition module includes a personnel status acquisition unit, an equipment status acquisition unit, and a product status acquisition unit. The personnel status acquisition unit acquires the image information of the staff on the production line through a camera, the equipment status acquisition unit is used to acquire the faulty equipment node information on the current production line, and the product status acquisition unit is used to acquire the processing time information of the final product of the current production line; the environmental data acquisition module is used to acquire the environmental information of the current production line, and the environmental information includes temperature and humidity, dust concentration and noise; the data receiving module is used to receive all the acquired information and send it to the data analysis module; The data analysis module is used to analyze all received information and send the analysis results to the visualization module; the visualization module is used to visualize the analysis results to the back-end staff.

2. The intelligent monitoring system for wood shavings processing according to claim 1 is characterized in that: The specific process of the data analysis module analyzing the information collected by the product quality collection module is as follows: S101: performing image recognition on the collected particle board surface image, identifying cracks on the particle board surface, and marking the identified cracks as Ai, i=1···k, where k is a natural number; S102: k and a preset value K 预设 Perform comparison, if k ≥ K 预设 , it means that the cracks in the particleboard are abnormal. If k<K 预设 , then proceed to step S103; S103: Count the total length of all Ai and mark it as b, then compare b with the preset value B 预设 Compare, if b ≥ B 预设 , it means that the cracks in the particleboard are abnormal. If b<B 预设 , then proceed to step S104; S104: construct a structural strength analysis model to analyze and determine whether there is an abnormality in the internal structural strength of the particleboard; S105: construct a moisture content analysis model to analyze and determine whether there is an abnormality in the moisture content inside the particleboard.

3. The intelligent monitoring system for wood shavings processing according to claim 2 is characterized in that: The specific analysis process of the structural strength analysis model is as follows: S201: Divide the surface of the particle board into a plurality of regions, and mark them as Ci, i=1···n, where n is a positive integer; S202: If there is a crack Ai in the region Ci, plan Ci to the first sequence; if there is no crack Ai in the region Ci, plan Ci to the second sequence; S203: collecting internal structural strength information of all regions of the particleboard through ultrasonic testing, wherein the internal structural strength information includes ultrasonic propagation velocity and ultrasonic attenuation coefficient; S204: Mark the average ultrasonic propagation speed corresponding to all Ci in the first sequence collected as V1, and then mark the average ultrasonic propagation speed corresponding to all Ci in the second sequence collected as V2. If (V1-V2) is greater than the preset speed, it means that the internal structural strength of the particleboard is abnormal. If (V1-V2) is less than or equal to the preset speed, enter step S205; S205: Mark the average ultrasonic attenuation coefficient corresponding to all Ci in the first sequence collected as D1, and then mark the average ultrasonic attenuation coefficient corresponding to all Ci in the second sequence collected as D2. If (D2-D1) is greater than the preset attenuation coefficient, it means that there is an abnormality in the internal structural strength of the particleboard. If (D2-D1) is less than or equal to the preset attenuation coefficient, enter step S206; S206: Calculate the comprehensive structural strength weight value s of the particle board = (V2 / D2). If s is greater than the preset structural strength weight value, it means that the internal structural strength of the particle board is normal. If s is less than or equal to the preset structural strength weight value, it means that the internal structural strength of the particle board is abnormal.

4. The intelligent monitoring system for wood shavings processing according to claim 3 is characterized in that: The specific analysis process of the moisture content analysis model is as follows: S301: collecting the internal moisture content of all regions of the particleboard by electrical measurement and marking it as Ei, i=1···n; S302: If Ei is within the preset interval, the area corresponding to Ei is planned to the third sequence; if Ei is not within the preset interval, the area corresponding to Ei is planned to the fourth sequence; S303: Count the number of regions in the fourth sequence and mark them as F, and then count the number of repeated regions in the fourth sequence and the first sequence and mark them as G; S304: Compare F with the preset value f, and compare G with the preset value g. If F>f and G>g, it means that there is a third-level abnormality in the moisture content inside the particleboard; if F≤f and G>g, it means that there is a second-level abnormality in the moisture content inside the particleboard; if F>f and G≤g, it means that there is a first-level abnormality in the moisture content inside the particleboard; if F≤f and G≤g, it means that the moisture content inside the particleboard is normal.

5. The intelligent monitoring system for wood shavings processing according to claim 4 is characterized in that: The specific process of the data analysis module analyzing the information collected by the production data collection module is as follows: S401: Mark the collected processing time of the final product of the current production line as T; S402: Compare T with the preset time t. If T>t, it means that the processing time of the product is abnormal. If T≤t, go to step S403; S403: by performing image recognition on the collected image information of the workers on the production line, determining whether the workers' sight is focused on the products at their workstations when the products flow through the workers, if so, the workers are arranged to the fifth sequence, if not, the workers are arranged to the sixth sequence, and the length of time the workers' sight is away from the products at their workstations is counted; S404: Count the total number of workers in the sixth sequence and mark it as X, then select the maximum time that the workers in the sixth sequence have their sight away from the product at their workstation and mark it as Y; S405: Compare X with a preset value x, and compare Y with a preset value y. If any of X>x and Y>y occurs, it indicates that the status of the personnel on the production line is abnormal. If X≤x and Y≤y, proceed to step S406; S406: Construct an equipment failure analysis model to analyze and determine whether there is an abnormality in the equipment failure on the production line.

6. The intelligent monitoring system for wood shavings processing according to claim 5, characterized in that: The specific analysis process of the equipment failure analysis model is as follows: S501: Collecting the locations of all faulty device nodes on the current production line, and connecting the adjacent locations of the faulty device nodes on the production line into a line segment; S502: If there are two faulty device node locations on the line segment, the line segment is planned to the seventh sequence; if there are three faulty device node locations on the line segment, the line segment is planned to the eighth sequence; if there are more than three faulty device node locations on the line segment, the line segment is planned to the ninth sequence; S503: Count the number of line segments in the seventh sequence, the eighth sequence, and the ninth sequence, and mark them as q1, q2, and q3 respectively; S504: Calculate the fault criticality weight value W=30%*q1+50%*q2+90%*q3; S505: Compare W with a preset weight value w. If W>w, it indicates that there is an abnormality in the equipment failure on the production line. If W≤w, it indicates that there is no abnormality in the equipment failure on the production line.

7. The intelligent monitoring system for wood shavings processing according to claim 6, characterized in that: The specific process of the data analysis module analyzing the information collected by the environmental data collection module is as follows: S601: Mark the collected temperature information as M1, the collected humidity information as M2, the collected dust concentration information as M3, and the collected noise volume information as M4; S602: Generate a radar chart P based on M1, M2, M3, and M4, and then mark the preset radar chart as p; S603: P and p are compared for similarity. If the similarity between the two is greater than a preset similarity, it indicates that the environment of the production line is normal. If the similarity between the two is less than or equal to the preset similarity, it indicates that the environment of the production line is abnormal.

8. The intelligent monitoring system for wood shavings processing according to claim 7, characterized in that: The visualization module includes a display screen, and the display area of ​​the display screen is divided into three areas, which respectively correspond to the analysis results of the data collected by the product quality collection module, the production data collection module, and the environmental data collection module.

9. The intelligent monitoring system for wood shavings processing according to claim 8, characterized in that: When the data collected by the product quality collection module, the production data collection module, and the environmental data collection module are analyzed to be abnormal, the display area boundary of the corresponding display screen flashes red.

Images