Visual management system and method for wire harness production workshop

Abstract

The invention relates to the technical field of production management, in particular to a visual management system and method for a wire harness production workshop, and the method comprises the steps: obtaining the visual display content of a target workshop, constructing a visual display strategy of the target workshop, and managing the visual display content, the display authority and the display oriented object; corresponding visual display contents are pushed for different display faces; the display object carries out production problem causal analysis and personnel and equipment cooperation based on the obtained visual display content; the visual display strategy comprises a front-end visual strategy and a rear-end visual strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of production management, and in particular to a visual management system and method for a wire harness production workshop. Background Art

[0002] A wire harness is an integrated assembly of multiple cables used to transmit power or signals in an electrical system. It is widely used in automobiles, home appliances, industrial equipment, and other fields. Its production process involves multiple precision steps, including: wire splitting, terminal crimping, subassembly and pre-assembly, final assembly, testing, and inspection. Wire harness production workshops typically have workstations and equipment corresponding to each process step. To improve production efficiency and monitor process status and equipment operating conditions, most existing wire harness production workshops have implemented visual management.

[0003] However, existing visual management processes mostly focus on equipment management, checking whether equipment operating status meets production plan completion and ensuring efficient completion of production plans by optimizing equipment operating hours, the number and type of equipment activated, and other factors. This approach fails to consider how, in some scenarios, the skill level of staff and the compatibility between staff and equipment can affect equipment operating status and production efficiency. Summary of the Invention

[0004] The present invention collaboratively manages staff and equipment through a human-machine management matrix to ensure the matching degree between staff and equipment.

[0005] The technical solution proposed by the present invention is: a visual management method for a wire harness production workshop, the method comprising:

[0006] Obtain visual display content of the target workshop;

[0007] Build visualization display strategies for target workshops, manage visualization display content, display permissions, and display object orientation;

[0008] Push corresponding visual display content to different display-oriented objects; based on the obtained visual display content, the display-oriented objects conduct causal analysis of production problems and coordination of personnel and equipment;

[0009] The visualization display strategy includes a front-end visualization strategy and a back-end visualization strategy.

[0010] Preferably, the obtaining of the visual display content of the target workshop includes:

[0011] Obtain the production plan information, workstation information, and staff information of the target workshop to form a basic visualization data set;

[0012] Obtain the operation image data of each worker at each workstation and the process parameters of the production equipment operated by the corresponding worker to form an analysis data set;

[0013] Based on the analysis data set, conduct operational process compliance analysis and output analysis results;

[0014] Build a human-machine management matrix based on basic visualization data sets and analysis results;

[0015] Generate visualization content using the analysis results of the human-machine management matrix and process compliance analysis;

[0016] The production plan information includes production process, production tasks, and production material information; the workstation information includes the workstation ID, the production equipment ID in the workstation, and the process parameter information corresponding to each production equipment ID; the staff information includes the staff ID and the skill level information corresponding to the staff ID.

[0017] Preferably, performing operational process compliance analysis based on the analysis data set and outputting analysis results includes:

[0018] Synchronize the timestamps of workers’ operation image data and process parameters of production equipment;

[0019] Recognize the operation image data through the pre-trained visual action recognition model and output the action classification result, wherein the action classification result includes correct actions and incorrect actions;

[0020] The visual action recognition model is built based on 3D convolutional neural network and LSTM model, and the loss function is Among them, y i Represents the output of the model based on the i-th frame image, p i represents the motion vector of the i-th frame image, λ represents the smoothing coefficient, and p t represents the action vector at the tth time point in the i-th frame image; p t-1 Represents the action vector at the t-1th time point in the i-th frame image;

[0021] After preprocessing the acquired process parameters of the production equipment, a process parameter vector is constructed. Among them, a i represents the i-th process parameter, and n represents the number of process parameters; the process parameters include one or more of pressure, temperature, displacement, voltage, and current;

[0022] Calculate the Mahalanobis distance of process parameters Where μ represents the standard process parameter matrix; if If the process is abnormal, the process is judged to be abnormal and the process abnormality alarm information is output; otherwise, the process is judged to be normal and the process normal information is output; where D0 is the process alarm threshold;

[0023] Constructing the compliance analysis model H=ωv ·S v +ω p ·S p ; Where H represents the compliance score; S v 、S p Represent the confidence of visual action and the normal probability of process parameters respectively; ω v 、ω p Represent visual weight and process parameter weight respectively, S v ∈(0,1),S p Obtained by mapping the Mahalanobis distance into the (0, 1) interval;

[0024] If H≥H0=0.8, the operator's operation is judged to be compliant and the operation compliance information is output; otherwise, the operation non-compliant information is output; where H0 is the compliance threshold;

[0025] The normal process information, abnormal process alarm information, operation compliance information and operation non-compliance information constitute the compliance result data set.

[0026] Preferably, the constructing of a human-machine management matrix based on the basic visualization data set and analysis results includes:

[0027] Obtain the staff ID and production equipment ID; construct the staff sequence and production equipment sequence;

[0028] Human-machine management matrix Among them, m nm It represents the comprehensive performance score of the nth worker in the worker sequence on the mth production equipment in the production equipment sequence;

[0029] m nm =α1A m +α2B m +α3C m , where α1, α2, and α3 represent score weights; A m 、B m 、C m They represent the staff's operational compliance rate, production efficiency and equipment efficiency improvement rate respectively.

[0030] Preferably, the generating of visualization content using the analysis results of the human-machine management matrix and process compliance analysis includes:

[0031] Generate an operation compliance progress bar based on the current compliance score and compliance threshold, and perform color mapping. That is, when H < H0, the progress bar color is red; otherwise, it is green.

[0032] Generate an operating parameter dashboard based on the process parameter vector and the Mahalanobis distance of the process parameters to display real-time process parameters and alarm status. When a process abnormality is detected, the operating parameter dashboard is highlighted.

[0033] Generate a heat map of the human-machine management matrix based on the staff sequence, equipment sequence, and the human-machine management matrix. Specifically, the staff sequence is arranged according to the staff skill level to form the rows of the heat map of the human-machine management matrix; the equipment sequence is arranged according to the equipment complexity to form the columns of the heat map of the human-machine management matrix.

[0034] Color mapping is performed on each element in the heat map of the human-machine management matrix. Specifically, the color of each element Color(M) = HSL(120°×m ij ,100%,50%); where m ij Indicates the element value of the corresponding position in the human-machine management matrix corresponding to each element of the human-machine management matrix heat map;

[0035] Generate a scatter plot of multimodal data association, specifically:

[0036] The Mahalanobis distance is the X-axis and the visual confidence is the Y-axis;

[0037] Perform cluster analysis on all data points in the multimodal data association scatter plot to identify abnormal areas, namely D 2 >3 and S v <0.6.

[0038] Preferably, the construction of a visualization display strategy for the target workshop, management of visualization display content, display authority, and display object orientation includes:

[0039] Build a front-end visualization display strategy, including:

[0040] Set the front-end display content whitelist;

[0041] Verify the roles and display permissions of all members in the front-end display content whitelist, that is, calculate the front-end verification value If the verification value Access(c,d) of the member in the whitelist is 1, the whitelist member passes the verification, otherwise it fails the verification; max They respectively represent the member role classification, member display permissions, and switching permission thresholds in the front-end display content whitelist;

[0042] Build backend visualization display strategies, including:

[0043] Set up a whitelist of backend display content;

[0044] Verify the roles and display permissions of all members in the backend display content whitelist, that is, calculate the backend verification value u′ represents the role level of members in the backend display content whitelist;

[0045] If the verification value Access′ of the member in the whitelist is 1, the backend displays the content that the whitelist member has passed the verification, otherwise it enters the frontend visual display strategy.

[0046] Preferably, the pushing of corresponding visual display content for different display-oriented objects includes:

[0047] Push the operation compliance progress bar and operation parameter dashboard to members on the verified front-end display content whitelist;

[0048] Push the human-machine management matrix heat map, multimodal data association scatter plot, and abnormal areas of the multimodal data association scatter plot to verified backend display content whitelist members;

[0049] The display-oriented objects include members of a front-end display content whitelist and members of a back-end display content whitelist.

[0050] Preferably, the object-oriented display performs causal analysis of production problems and personnel and equipment collaboration based on the acquired visual display content, including:

[0051] Obtain process parameter deviations and visual confidence levels for all data within the abnormal area;

[0052] Calculate Pearson correlation coefficient Among them, D i represents the Mahalanobis distance of the i-th process parameter vector, S v_i represents the visual confidence corresponding to the i-th process parameter vector; represents the average visual confidence; represents the average Mahalanobis distance; N represents the number of process parameter vectors;

[0053] If |γ|>0.7, it is judged that the process is strongly correlated with the operation and personnel optimization is needed;

[0054] Obtain the workstation ID, production equipment ID, and staff member ID corresponding to the data points in the abnormal area, generate staff replacement suggestion information, and obtain operation guidance video data;

[0055] Constructing the human-machine management matrix heat map visualization interaction rules:

[0056] Manage matrix heatmaps to display the value of each element on hover;

[0057] After clicking on the heat map of the human-machine management matrix, the Hungarian algorithm is activated to optimize the arrangement and obtain the optimized scheduling plan for personnel and equipment coordination;

[0058] Generate an optimal allocation table based on the optimized scheduling plan and convert the optimal allocation table into scheduling instructions executable by MES;

[0059] The MES system obtains scheduling instructions through the API interface, updates the original schedule, and re-matches staff and equipment;

[0060] The Hungarian algorithm is started to optimize the arrangement and obtain the optimized scheduling plan, including:

[0061] Find the solution to the following equation:

[0062] where X ij Represents the elements in the allocation matrix X, X ij =1 means that worker i is assigned to production equipment j; X ij =0 means no allocation.

[0063] The present invention also provides a visual management system for a wire harness production workshop, wherein the system is used to execute the visual management method for a wire harness production workshop.

[0064] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the visual management method for a wire harness production workshop.

[0065] Beneficial effects of the present invention:

[0066] During the data acquisition process, this invention collects process data from equipment within a workstation and operator operation image data, fusing these two modalities to achieve human-machine management of the workstation. Through multimodal data analysis, worker performance is quantified, supporting subsequent personnel adjustments and training. Furthermore, the personnel adjustment and operation guidance functions are connected to production management systems (such as MES) to achieve two-way data exchange. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 The figure is a flow chart of the visual management method for a wire harness production workshop according to the present invention. DETAILED DESCRIPTION

[0068] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are for illustrative purposes only, and those skilled in the art will readily appreciate other obvious variations. The basic principles of the present invention defined in the following description may be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the present invention.

[0069] It is understandable that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0070] refer to Figure 1 The technical solution provided by the present invention is: a visual management method for a wire harness production workshop, comprising the following steps:

[0071] Step 1: Obtain the visual display content of the target workshop. This includes the following steps:

[0072] Step 1.1: Obtain the production plan information, workstation information, and staff information of the target workshop to form a basic visualization data set;

[0073] Step 1.2: Obtain the operation image data of each worker at each workstation and the process parameters of the production equipment operated by the corresponding worker to form an analysis data set;

[0074] Step 1.3: Based on the analysis data set, conduct operational process compliance analysis and output analysis results; specifically:

[0075] Synchronize the timestamps of workers’ operation image data and process parameters of production equipment;

[0076] Recognize the operation image data through the pre-trained visual action recognition model and output the action classification result, wherein the action classification result includes correct actions and incorrect actions;

[0077] The visual action recognition model is built based on 3D convolutional neural network and LSTM model, and the loss function is Among them, y i Represents the output of the model based on the i-th frame image, p i represents the motion vector of the i-th frame image, λ represents the smoothing coefficient, and p t represents the action vector at the tth time point in the i-th frame image; p t-1 Represents the action vector at the t-1th time point in the i-th frame image;

[0078] After preprocessing the acquired process parameters of the production equipment, a process parameter vector is constructed. Among them, a i represents the i-th process parameter, and n represents the number of process parameters; the process parameters include one or more of pressure, temperature, displacement, voltage, and current;

[0079] Calculate the Mahalanobis distance of process parameters Where μ represents the standard process parameter matrix; if If the process is abnormal, the process is judged to be abnormal and the process abnormality alarm information is output; otherwise, the process is judged to be normal and the process normal information is output; where D0 is the process alarm threshold;

[0080] Constructing the compliance analysis model H=ω v ·S v +ω p ·S p ; Where H represents the compliance score; S v 、S p Represent the confidence of visual action and the normal probability of process parameters respectively; ω v 、ω p Represent visual weight and process parameter weight respectively, S v ∈(0,1),S p Obtained by mapping the Mahalanobis distance into the (0, 1) interval;

[0081] If H≥H0=0.8, the operator's operation is judged to be compliant and the operation compliance information is output; otherwise, the operation non-compliant information is output; where H0 is the compliance threshold;

[0082] The normal process information, abnormal process alarm information, operation compliance information and operation non-compliance information constitute the compliance result data set.

[0083] Step 1.4: Build a human-machine management matrix based on the basic visualization data set and analysis results; specifically:

[0084] Obtain the staff ID and production equipment ID; construct the staff sequence and production equipment sequence;

[0085] Human-machine management matrix Among them, m nm It represents the comprehensive performance score of the nth worker in the worker sequence on the mth production equipment in the production equipment sequence;

[0086] m nm =α1A m +α2B m +α3C m , where α1, α2, and α3 represent score weights; A m 、B m 、C m They represent the staff's operational compliance rate, production efficiency and equipment efficiency improvement rate respectively.

[0087] Equipment efficiency is calculated based on OEE, which is OEE = availability × performance rate × yield rate, where availability = actual equipment operating time / planned production time, performance rate = (actual output × standard cycle time) / actual operating time, and yield rate = number of compliant products / total production quantity. The industry benchmark for OEE is 85%.

[0088] Operation compliance rate = number of correct operations / total number of operations, which can be calculated based on historical operation data; production efficiency = actual number of products produced / planned number of products produced.

[0089] Step 1.5: Generate visualization content using the analysis results of the human-machine management matrix and process compliance analysis. Specifically:

[0090] Generate an operation compliance progress bar based on the current compliance score and compliance threshold, and perform color mapping. That is, when H < H0, the progress bar color is red; otherwise, it is green.

[0091] Generate an operating parameter dashboard based on the process parameter vector and the Mahalanobis distance of the process parameters to display real-time process parameters and alarm status. When a process abnormality is detected, the operating parameter dashboard is highlighted.

[0092] Generate a heat map of the human-machine management matrix based on the staff sequence, equipment sequence, and the human-machine management matrix. Specifically, the staff sequence is arranged according to the staff skill level to form the rows of the heat map of the human-machine management matrix; the equipment sequence is arranged according to the equipment complexity to form the columns of the heat map of the human-machine management matrix.

[0093] Color mapping is performed on each element in the heat map of the human-machine management matrix. Specifically, the color of each element Color(M) = HSL(120°×m ij ,100%,50%); where m ij Indicates the element value of the corresponding position in the human-machine management matrix corresponding to each element of the human-machine management matrix heat map;

[0094] Generate a scatter plot of multimodal data association, specifically:

[0095] The Mahalanobis distance is the X-axis and the visual confidence is the Y-axis;

[0096] Perform cluster analysis on all data points in the multimodal data association scatter plot to identify abnormal areas, namely D 2 >3 and S v <0.6.

[0097] Among them, the production plan information includes production process, production tasks, and production material information; the workstation information includes the workstation ID, the production equipment ID in the workstation, and the process parameter information corresponding to each production equipment ID; the staff information includes the staff ID and the skill level information corresponding to the staff ID.

[0098] Step 2: Build a visualization display strategy for the target workshop, manage visualization display content, display permissions, and display object orientation; the visualization display strategy includes front-end visualization strategy and back-end visualization strategy. Specifically:

[0099] Build a front-end visualization display strategy, including:

[0100] Set the front-end display content whitelist;

[0101] Verify the roles and display permissions of all members in the front-end display content whitelist, that is, calculate the front-end verification value If the verification value Access(c,d) of the member in the whitelist is 1, the whitelist member passes the verification, otherwise it fails the verification; max They respectively represent the member role classification, member display permissions, and switching permission thresholds in the front-end display content whitelist;

[0102] Build backend visualization display strategies, including:

[0103] Set up a whitelist of backend display content;

[0104] Verify the roles and display permissions of all members in the backend display content whitelist, that is, calculate the backend verification value u′ represents the role level of members in the backend display content whitelist;

[0105] If the verification value Access′ of the member in the whitelist is 1, the backend displays the content that the whitelist member has passed the verification, otherwise it enters the frontend visual display strategy.

[0106] Step 3: Push corresponding visual display content to different display-oriented objects; based on the obtained visual display content, the display-oriented objects conduct causal analysis of production problems and personnel and equipment collaboration; the display-oriented objects include members of the front-end display content whitelist and members of the back-end display content whitelist. Specifically, the following steps are included:

[0107] Step 3.1. Push the operation compliance progress bar and operation parameter dashboard to the members in the verified front-end display content whitelist; for example, at the front end, the staff can view the different colors of the compliance progress bar displayed on the display device at the workstation to determine whether their operation is compliant, and view the process parameters of the operating equipment through the operation parameter dashboard.

[0108] Step 3.2: Push the human-machine management matrix heat map, multimodal data association scatter plot, and abnormal area of the multimodal data association scatter plot to the verified backend display content whitelist members;

[0109] Step 3.3: Obtain the process parameter deviation and visual confidence of all data in the abnormal area. Calculate the Pearson correlation coefficient. Among them, D i represents the Mahalanobis distance of the i-th process parameter vector, S v_i represents the visual confidence corresponding to the i-th process parameter vector; represents the average visual confidence; represents the average Mahalanobis distance; N represents the number of process parameter vectors;

[0110] If |γ|>0.7, it is judged that the process is strongly correlated with the operation and personnel optimization is needed;

[0111] Step 3.4: Obtain the workstation ID, production equipment ID, and staff ID corresponding to the data points in the abnormal area, generate personnel replacement suggestion information, and obtain operation guidance video data; the operation guidance video is preset in the local database and can be retrieved by the front-end and back-end.

[0112] For example, on the back end (management side), the scatter plot shows that an abnormal point in the abnormal area is D 2 =3.5S v =0.5, corresponding to the wire harness crimping station where worker A is located;

[0113] Calculate |γ|=0.73, and determine that the abnormal process parameters are strongly correlated with the personnel operation; generate a "personnel replacement suggestion prompt information" to adjust worker A. In this embodiment, worker B with a higher skill level can be selected to replace worker A. When worker B arrives at the corresponding workstation, the crimping operation instruction video is played through the display device (front end) at the workstation.

[0114] Step 3.5: Construct the visualization interaction rules of the heat map of the human-machine management matrix:

[0115] Manage matrix heatmaps to display the value of each element on hover;

[0116] After clicking on the heat map of the human-machine management matrix, the Hungarian algorithm is activated to optimize the arrangement and obtain the optimized scheduling plan for personnel and equipment coordination;

[0117] Connect with the existing production management system: Generate an optimal allocation table based on the optimized scheduling plan, and convert the optimal allocation table into scheduling instructions that can be executed by MES;

[0118] The MES system obtains scheduling instructions through the API interface, updates the original schedule, and re-matches staff and equipment.

[0119] Among them, the Hungarian algorithm is activated to optimize the arrangement and obtain the optimized scheduling plan, including:

[0120] Find the solution to the following equation:

[0121] where X ij Represents the elements in the allocation matrix X, X ij =1 means that worker i is assigned to production equipment j; X ij =0 means no allocation

[0122] For example: match 4 workers with 4 production equipment in the target workshop.

[0123] The human-machine management matrix at this time Locate the largest element value in each row,

[0124] That is, when worker 1 matches device 1, worker 2 matches device 2, worker 3 matches device 4, and worker 4 matches device 4, the production energy efficiency is the highest, which is 3.4.

[0125] In some embodiments, while visually managing personnel, it is also necessary to supplement the device management optimization strategy, specifically:

[0126] Perform predictive maintenance on equipment by setting a failure rate threshold. If the number of recent failures exceeds the set threshold, equipment maintenance operations are triggered.

[0127] When |γ|<0.7, that is, the process and operation are not strongly correlated, the equipment also needs to be inspected.

[0128] In other embodiments, when OEE is less than 85%, three consecutive process parameter abnormality alarms occur, or the delay time of a special work order exceeds a preset time threshold, the role level of specific members in the front-end display content whitelist of the corresponding workstation (such as team leaders, maintenance engineers, etc.) is increased so that they can view the back-end display content and record the viewed content in the front-end display log.

[0129] The present invention also provides a visual management system for a wire harness production workshop, comprising a processor, and a memory and a communication module connected to the processor. The system is used to execute the visual management method for a wire harness production workshop.

[0130] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the visual management method for a wire harness production workshop.

[0131] In the embodiments disclosed herein, the processes described above with reference to the flowcharts can be implemented as computer software programs. The embodiments disclosed herein include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication component and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), the functions defined in the method of the present invention are performed. It should be noted that the computer-readable medium of the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. The computer-readable storage medium can be, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection having one or more wire segments, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. Furthermore, in the present invention, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, electrical, optical, RF, or any suitable combination thereof.

[0132] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of the systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or portion of code that contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two boxes shown in succession can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, as well as combinations of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified functions or operations, or can be implemented using a combination of dedicated hardware and computer instructions.

[0133] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be subject to any changes or modifications.

Claims

1. A visual management method for a wire harness production workshop, characterized in that: The method comprises: Obtain visual display content of the target workshop; Build visualization display strategies for target workshops, manage visualization display content, display permissions, and display object orientation; Push corresponding visual display content to different display-oriented objects; based on the obtained visual display content, the display-oriented objects conduct causal analysis of production problems and coordination of personnel and equipment; The visualization display strategy includes a front-end visualization strategy and a back-end visualization strategy.

2. The visual management method for a wire harness production workshop according to claim 1, characterized in that: The obtaining of the visual display content of the target workshop includes: Obtain the production plan information, workstation information, and staff information of the target workshop to form a basic visualization data set; Obtain the operation image data of each worker at each workstation and the process parameters of the production equipment operated by the corresponding worker to form an analysis data set; Based on the analysis data set, conduct operational process compliance analysis and output analysis results; Build a human-machine management matrix based on basic visualization data sets and analysis results; Generate visualization content using the analysis results of the human-machine management matrix and process compliance analysis; The production plan information includes production process, production tasks, and production material information; the workstation information includes the workstation ID, the production equipment ID in the workstation, and the process parameter information corresponding to each production equipment ID; the staff information includes the staff ID and the skill level information corresponding to the staff ID.

3. The visual management method for a wire harness production workshop according to claim 2, characterized in that: The aforementioned operation process compliance analysis is performed based on the analysis data set and the analysis results are output, including: Synchronize the timestamps of workers’ operation image data and process parameters of production equipment; Recognize the operation image data through the pre-trained visual action recognition model and output the action classification result, wherein the action classification result includes correct actions and incorrect actions; The visual action recognition model is built based on 3D convolutional neural network and LSTM model, and the loss function is Among them, y i Represents the output of the model based on the i-th frame image, p i represents the motion vector of the i-th frame image, λ represents the smoothing coefficient, and p t represents the action vector at the tth time point in the i-th frame image; p t-1 Represents the action vector at the t-1th time point in the i-th frame image; After preprocessing the acquired process parameters of the production equipment, a process parameter vector is constructed. Among them, a i represents the i-th process parameter, and n represents the number of process parameters; the process parameters include one or more of pressure, temperature, displacement, voltage, and current; Calculate the Mahalanobis distance of process parameters Where μ represents the standard process parameter matrix; if If the process is abnormal, the process is judged to be abnormal and the process abnormality alarm information is output; otherwise, the process is judged to be normal and the process normal information is output; where D0 is the process alarm threshold; Constructing the compliance analysis model H=ω v ·S v +ω p ·S p ; Where H represents the compliance score; S v 、S p Represent the confidence of visual action and the normal probability of process parameters respectively; ω v 、ω p Represent visual weight and process parameter weight respectively, S v ∈(0,1),S p Obtained by mapping the Mahalanobis distance into the (0, 1) interval; If H≥H0=0.8, the operator's operation is judged to be compliant and the operation compliance information is output; otherwise, the operation non-compliant information is output; where H0 is the compliance threshold; The normal process information, abnormal process alarm information, operation compliance information and operation non-compliance information constitute the compliance result data set.

4. The visual management method for a wire harness production workshop according to claim 3, characterized in that: The construction of a human-machine management matrix based on basic visualization data sets and analysis results includes: Obtain the staff ID and production equipment ID; construct the staff sequence and production equipment sequence; Human-machine management matrix Among them, m nm It represents the comprehensive performance score of the nth worker in the worker sequence on the mth production equipment in the production equipment sequence; m nm =α1A m +α2B m +α3C m , where α1, α2, and α3 represent score weights; A m 、B m 、C m They represent the staff's operational compliance rate, production efficiency and equipment efficiency improvement rate respectively.

5. The visual management method for a wire harness production workshop according to claim 4, characterized in that: The visualization content generated by the analysis results of the human-machine management matrix and process compliance analysis includes: Generate an operation compliance progress bar based on the current compliance score and compliance threshold, and perform color mapping. That is, when H < H0, the progress bar color is red; otherwise, it is green. Generate an operating parameter dashboard based on the process parameter vector and the Mahalanobis distance of the process parameters to display real-time process parameters and alarm status. When a process abnormality is detected, the operating parameter dashboard is highlighted. Generate a heat map of the human-machine management matrix based on the staff sequence, equipment sequence, and the human-machine management matrix. Specifically, the staff sequence is arranged according to the staff skill level to form the rows of the heat map of the human-machine management matrix; the equipment sequence is arranged according to the equipment complexity to form the columns of the heat map of the human-machine management matrix. Color mapping is performed on each element in the heat map of the human-machine management matrix. Specifically, the color of each element Color(M) = HSL(120°×m ij ,100%,50%); where m ij Indicates the element value of the corresponding position in the human-machine management matrix corresponding to each element of the human-machine management matrix heat map; Generate a scatter plot of multimodal data association, specifically: The Mahalanobis distance is the X-axis and the visual confidence is the Y-axis; Perform cluster analysis on all data points in the multimodal data association scatter plot to identify abnormal areas, namely D 2 >3 and S v <0.

6.

6. The visual management method for a wire harness production workshop according to claim 5, characterized in that: The construction of the visualization display strategy of the target workshop, management of visualization display content, display authority and display object orientation includes: Build a front-end visualization display strategy, including: Set the front-end display content whitelist; Verify the roles and display permissions of all members in the front-end display content whitelist, that is, calculate the front-end verification value If the verification value Access(c,d) of the member in the whitelist is 1, the whitelist member passes the verification, otherwise it fails the verification; max They respectively represent the member role classification, member display permissions, and switching permission thresholds in the front-end display content whitelist; Build backend visualization display strategies, including: Set up a whitelist of backend display content; Verify the roles and display permissions of all members in the backend display content whitelist, that is, calculate the backend verification value u′ represents the role level of members in the backend display content whitelist; If the verification value Access′ of the member in the whitelist is 1, the backend displays the content that the whitelist member has passed the verification, otherwise it enters the frontend visual display strategy.

7. The visual management method for a wire harness production workshop according to claim 6, characterized in that: The corresponding visual display content is pushed for different display objects, including: Push the operation compliance progress bar and operation parameter dashboard to members on the verified front-end display content whitelist; Push the human-machine management matrix heat map, multimodal data association scatter plot, and abnormal areas of the multimodal data association scatter plot to verified backend display content whitelist members; The display-oriented objects include members of a front-end display content whitelist and members of a back-end display content whitelist.

8. The visual management method for a wire harness production workshop according to claim 7, characterized in that: The object-oriented display performs causal analysis of production problems and coordination of personnel and equipment based on the obtained visual display content, including: Obtain process parameter deviations and visual confidence levels for all data within the abnormal area; Calculate Pearson correlation coefficient Among them, D i represents the Mahalanobis distance of the i-th process parameter vector, S v_i represents the visual confidence corresponding to the i-th process parameter vector; represents the average visual confidence; represents the average Mahalanobis distance; N represents the number of process parameter vectors; If |γ|>0.7, it is judged that the process is strongly correlated with the operation and personnel optimization is needed; Obtain the workstation ID, production equipment ID, and staff member ID corresponding to the data points in the abnormal area, generate staff replacement suggestion information, and obtain operation guidance video data; Constructing the human-machine management matrix heat map visualization interaction rules: Manage matrix heatmaps to display the value of each element on hover; After clicking on the heat map of the human-machine management matrix, the Hungarian algorithm is activated to optimize the arrangement and obtain the optimized scheduling plan for personnel and equipment coordination; Generate an optimal allocation table based on the optimized scheduling plan and convert the optimal allocation table into scheduling instructions executable by MES; The MES system obtains scheduling instructions through the API interface, updates the original schedule, and re-matches staff and equipment; The Hungarian algorithm is started to optimize the arrangement and obtain the optimized scheduling plan, including: Find the solution to the following equation: where X ij Represents the elements in the allocation matrix X, X ij =1 means that worker i is assigned to production equipment j; X ij =0 means no allocation.

9. A visual management system for a wiring harness production workshop, characterized in that: The system is used to execute the visual management method for a wire harness production workshop as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the visual management method for a wire harness production workshop according to any one of claims 1 to 8.

Images