A computer vision-based automated production line control system and method

Abstract

This invention discloses an automated production line control method based on computer vision, comprising the following steps: S1, collecting data from equipment in the workshop to obtain relevant equipment data; S2, constructing and correcting a mapped equipment model; S3, obtaining the production speed and load rate of each machine and the running speed of each conveyor belt through a simulation calculation module; S4, obtaining the optimal production speed V through iterative optimization using a simulated annealing algorithm. 优 and maximum production speed V 限 S5. Switch between the optimal production speed mode and the maximum production speed mode to obtain the proposed operating speed data; S6. Proceed with production after verification. This invention can accurately calculate and simulate the production speed and load rate of each machine, and regulate the sum of equipment speed and load rate of each process, solving the problem of the inability to balance the load rate within each process in the prior art, and realizing the balance and optimization of the production line.

Description

Technical Field

[0001] This invention relates to the field of automated control and regulation system technology, and more particularly to the field of adaptive control systems, specifically to an automated production line control system and control method based on computer vision. Background Technology

[0002] Automated production lines are a general term encompassing assembly lines, belt conveyor lines, chain conveyor lines, and component insertion lines, etc., primarily operated by automated systems without human intervention. In some automated manufacturing lines, different processes are closely interdependent, such as body welding, painting, and final assembly in automobile manufacturing. To ensure the final vehicle assembly schedule and quality, these processes need to maintain the same output rate.

[0003] In such automated production line control systems, each process involves multiple devices, and each device may have different movement patterns and loads. Computer vision technology can achieve automatic control of the equipment by monitoring and analyzing visual information in real time. Specifically, computer vision systems can acquire real-time status information of the equipment, such as position, speed, and load, through cameras or sensors. Then, by processing and analyzing this information, the system can adjust the movement patterns and speeds of the equipment in real time to achieve coordination and cooperation between different processes.

[0004] However, the matching relationships between different processes can be very complex. Due to factors such as different models, years of use, and maintenance conditions of different machines in the same process, the speed and load of each machine will be different, making it impossible to balance the load rate within each process. Therefore, it is necessary to design appropriate strategies to achieve efficient control of the production line.

[0005] Therefore, it is necessary to develop an automated production line control system with high computational accuracy, high learning efficiency, and high simulation accuracy to solve the above problems. Summary of the Invention

[0006] This invention overcomes the shortcomings of the prior art and provides an automated production line control system and control method based on computer vision.

[0007] To achieve the above objectives, the technical solution adopted by this invention is: an automated production line control method based on computer vision, comprising the following steps:

[0008] S1. Collect data from the equipment in the workshop to obtain relevant equipment data;

[0009] S2. Construct an initial equipment model for each machine in the workshop and correct it to obtain a mapped equipment model;

[0010] S3. Run the mapping equipment model, record the status data of each machine in real time, and obtain the production speed and load rate of each machine and the running speed of each conveyor belt through the simulation calculation module.

[0011] S4. Based on the production speed and load rate of each machine and the running speed of each conveyor belt, the optimal production speed V is obtained through iterative optimization using a simulated annealing algorithm. 优 and maximum production speed V 限 ;

[0012] S5. Under the premise of ensuring that the output per unit time between two adjacent processes is consistent and the load rate is comparable, switch between the optimal production speed mode and the maximum production speed mode according to the workshop conditions and product conditions to obtain the proposed operating speed data.

[0013] S6. After verifying the proposed operating speed data through the simulation deployment terminal, the data is deployed to the actual production line for production.

[0014] In a preferred embodiment of the present invention, in step S1, data collection from equipment within the workshop is performed, specifically including the following steps:

[0015] S11. Input the physical characteristics data of the equipment in advance, and capture the motion range and motion behavior of each device through the dynamic characteristic capture module to generate device motion data;

[0016] S12. Collect corresponding equipment status data and conveyor belt status data of each section of the conveyor belt through several sensors installed in the workshop.

[0017] In a preferred embodiment of the present invention, the specific steps in S5 to ensure that the output per unit time is consistent between two adjacent processes are as follows:

[0018] S51. Number the equipment and conveyors in the preceding process to obtain N equipment and M conveyors, with the speed of each equipment being V1, V2, ..., V... N The speeds of each conveyor belt are V1, V2, ..., V... M ;

[0019] S52. Number the equipment and conveyor belts in the subsequent processes to obtain X equipment and Y conveyor belts, with the speeds of each equipment being Z1, Z2, ..., Z... X The speeds of each conveyor belt are Z1, Z2, ..., Z... Y ;

[0020] S53. Ensure that the total speed of all equipment and conveyor belts in the preceding process is equal to the total speed of all equipment and conveyor belts in the subsequent process, i.e., (V1 + V2 + ... + VN ) + (V1 + V2 + ... + V M ) = (Z1 + Z2 + ... + Z X ) + (Z1 + Z2 + ... + Z Y This means achieving consistent output per unit time between two adjacent processes.

[0021] In a preferred embodiment of the present invention, in step S5, ensuring that the load rates of two adjacent processes are comparable specifically includes the following steps:

[0022] S54. Obtain the rated load W of each piece of equipment in the preceding process. 定 Given the current load W0 and the number of devices Q, the load rate W for each device is calculated as W = W1 / W. 定 Then the load rate of the preceding process is W 前 =(W1+W2+...+W Q ) / Q;

[0023] S55. Obtain the rated load U of each piece of equipment in the subsequent process. 定 Given the current load U0 and the number of devices P, we can obtain the load rate of each device U = U1 / U 定 Then the load rate of the subsequent process is U 后 =(U1+U2+...+U P ) / P;

[0024] S56. By adjusting the current load W0 of the preceding process and the current load U0 of the following process, W can be achieved. 前 =U 后 .

[0025] In a preferred embodiment of the present invention, step S3 further includes: storing the device-related data and the status data of each machine in real time.

[0026] The present invention also provides an automated production line control system based on computer vision, comprising: a data acquisition module, a virtual model platform, a simulation calculation module, a control and monitoring module, and a simulation and deployment terminal;

[0027] The data acquisition module includes: a parameter input module, a dynamic characteristic capture module, and a characteristic sensing module; it is used to input parameters and dynamically capture the operating status of the device to obtain several device-related data.

[0028] The virtual model platform includes: a data conversion module, a model building module, and a model verification module; used to receive device-related data and build a mapping device model.

[0029] The simulation calculation module includes a simulation module and a calculation optimization module; it is used to simulate the operation of the mapped equipment model and calculate the optimal production speed V in real time. 优 and maximum production speed V 限 ;

[0030] The control and monitoring module includes: a mode switching module, a rate control module, and a load control module; it is used to switch production speed modes according to different needs to adjust the operating speed and load of equipment and conveyor belts, and to monitor the production status of the simulated production line to obtain production status data.

[0031] The simulation and deployment terminal includes a simulation module and a deployment module; it is used to perform simulation verification based on the production status data, and after verification, it is deployed to the actual production line for production.

[0032] In a preferred embodiment of the present invention, the parameter input module is used to pre-input the physical characteristic data of the equipment; the dynamic characteristic capture module is used to capture the motion range and motion behavior of each piece of equipment to generate equipment motion data; and the characteristic sensing module is used to collect corresponding equipment status data and conveyor belt status data of each section of conveyor belt according to the motion mode of different equipment through several sensors installed in the workshop.

[0033] In a preferred embodiment of the present invention, the data conversion module is used to receive the physical characteristic data, the equipment motion data, the equipment status data, and the conveyor belt status data, and convert them into simulated operation data; the model building module is used to construct a virtual workshop scene and generate an initial equipment model in conjunction with the simulated operation data; the model calibration module is used to correct the initial equipment model using a proportional-integral-differential algorithm to obtain the mapped equipment model.

[0034] In a preferred embodiment of the present invention, the simulation module is used to simulate and run the mapped device model in a virtual platform, and calculate the production speed V of each device through an edge computing algorithm. 设 The load rate P corresponding to each device 设 and the operating speed V of each conveyor belt section. 传 The calculation and optimization module is used to iteratively optimize based on the simulated annealing algorithm to finally obtain the optimal production speed V. 优 and maximum production speed V 限 .

[0035] In a preferred embodiment of the present invention, the mode switching module is used to switch between the optimal production speed mode and the maximum production speed mode according to workshop conditions and product conditions; the rate control module is used to adjust the speed of each piece of equipment and each section of conveyor belt to indirectly control the total speed of all equipment and conveyor belts in the preceding process and the total speed of all equipment and conveyor belts in the subsequent process; the load control module is used to increase or decrease the load on the equipment to control the load rate of each piece of equipment.

[0036] This invention addresses the shortcomings of the prior art and has the following beneficial effects:

[0037] This invention provides an automated production line control system and method based on computer vision. By constructing a virtual model of the equipment and acquiring status data in real time, it can accurately calculate and simulate the production speed and load rate of each machine, thereby providing an accurate basis for subsequent regulation. Furthermore, by regulating the sum of the equipment speed and load rate of each process, it solves the problem of the inability to balance the load rate within each process in the prior art, and can achieve the balance and optimization of the production line, thereby improving production efficiency and quality.

[0038] This invention can accurately capture the movement range and behavior of the equipment by pre-inputting the physical characteristic data of the equipment and the dynamic characteristic capture module. By collecting equipment status data and conveyor belt status data through sensors, the operating status of the equipment and conveyor belt can be monitored in real time, realizing real-time monitoring and adjustment of automated production line control.

[0039] This invention constructs an initial equipment model to build a virtual workshop scene, and can model and simulate the operating status of equipment in the workshop, thereby realistically restoring the workshop's operating conditions. Further correction of the mapped equipment model can improve the model's accuracy, making subsequent simulation calculations and optimization results more reliable and effective.

[0040] This invention obtains the actual operating status of the equipment by running the equipment model and recording status data in real time. At the same time, it can obtain key indicators such as the production speed and load rate of each machine and conveyor belt through simulation calculation. Furthermore, by introducing a simulated annealing algorithm for iterative optimization, the optimal production speed and the maximum production speed can be found. It can be flexibly adjusted under different production conditions to achieve the best production efficiency and quality, thereby maximizing production efficiency and meeting production needs.

[0041] This invention, while ensuring production volume and load rate, can ensure that the production line operates at the highest efficiency under different conditions by switching between different production speed modes according to the conditions of the workshop and the product, and by selecting the optimal production speed mode and the maximum production speed mode, thereby maximizing production efficiency and improving the overall capacity of the production line.

[0042] By maintaining the sum of the rates between processes, this invention can control the output per unit time of two adjacent processes to be consistent. This ensures that the output of each process remains consistent at different production speeds for each piece of equipment in the production line, thus ensuring the balance and smooth operation of the production line, avoiding backlogs or insufficient output during the production process, and improving overall production efficiency and capacity.

[0043] This invention requires that the load rates of two adjacent processes be comparable, that is, the load of each process remains consistent. This can avoid the situation where a bottleneck is caused by an excessively high load on a certain process, ensure the balanced operation of the entire production line, improve production efficiency and quality, and achieve balanced production.

[0044] This invention tightly integrates computer vision with automated production lines, possessing broad application prospects and significant implications. It can collect, analyze, and optimize large amounts of production data. Data analysis reveals bottlenecks and optimization opportunities in the production line, further improving production efficiency and quality. Simultaneously, data analysis and forecasting can optimize production planning and resource allocation, enhancing the overall effectiveness of the production line. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart of an automated production line control method based on computer vision in Embodiment 1 of the present invention;

[0047] Figure 2 This is a schematic diagram of an automated production line control system based on computer vision in Embodiment 1 of the present invention. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Example 1

[0049] This embodiment provides an automated production line control method based on computer vision, such as... Figure 1 The flowchart shown is for an automated production line control method, which includes the following steps:

[0050] S1. Collect data from the equipment in the workshop to obtain relevant equipment data;

[0051] S11. Input the physical characteristics data of the equipment in advance, and capture the motion range and motion behavior of each device through the dynamic characteristic capture module to generate device motion data;

[0052] S12. Collect corresponding equipment status data and conveyor belt status data of each section of the conveyor belt through several sensors installed in the workshop.

[0053] S2. Construct the initial equipment model for each machine in the workshop and correct it to obtain the mapped equipment model.

[0054] S3. Run the mapping equipment model, record the status data of each machine in real time, and obtain the production speed and load rate of each machine and the running speed of each conveyor belt through the simulation calculation module; store the relevant equipment data and the status data of each machine in real time.

[0055] S4. Based on the production speed and load rate of each machine and the running speed of each conveyor belt, the optimal production speed V is obtained through iterative optimization using a simulated annealing algorithm. 优 and maximum production speed V 限 .

[0056] S5. Under the premise of ensuring that the output per unit time between two adjacent processes is consistent and the load rate is comparable, switch between the optimal production speed mode and the maximum production speed mode according to the workshop conditions and product conditions to obtain the proposed operating speed data.

[0057] S51. Number the equipment and conveyors in the preceding process to obtain N equipment and M conveyors, with the speed of each equipment being V1, V2, ..., V... N The speeds of each conveyor belt are V1, V2, ..., V... M ;

[0058] S52. Number the equipment and conveyor belts in the subsequent processes to obtain X equipment and Y conveyor belts, with the speeds of each equipment being Z1, Z2, ..., Z... X The speeds of each conveyor belt are Z1, Z2, ..., Z... Y ;

[0059] S53. Ensure that the total speed of all equipment and conveyor belts in the preceding process is equal to the total speed of all equipment and conveyor belts in the subsequent process, i.e., (V1 + V2 + ... + V N ) + (V1 + V2 + ... + VM ) = (Z1 + Z2 + ... + Z X ) + (Z1 + Z2 + ... + Z Y This means achieving consistent output per unit time between two adjacent processes;

[0060] S54. Obtain the rated load W of each piece of equipment in the preceding process. 定 Given the current load W0 and the number of devices Q, the load rate W for each device is calculated as W = W1 / W. 定 Then the load rate of the preceding process is W 前 =(W1+W2+...+W Q ) / Q;

[0061] S55. Obtain the rated load U of each piece of equipment in the subsequent process. 定 Given the current load U0 and the number of devices P, we can obtain the load rate of each device U = U1 / U 定 Then the load rate of the subsequent process is U 后 =(U1+U2+...+U P ) / P;

[0062] S56. By adjusting the current load W0 of the preceding process and the current load U0 of the following process, W can be achieved. 前 =U 后 .

[0063] S6. After verifying the proposed operating speed data through the simulation deployment terminal, the data is deployed to the actual production line for production.

[0064] This embodiment, by constructing a virtual model of the equipment and acquiring status data in real time, can accurately calculate and simulate the production speed and load rate of each machine, thereby providing an accurate basis for subsequent regulation; and by regulating the sum of the equipment speed and load rate of each process, it solves the problem of the inability to balance the load rate within each process in the prior art, and can achieve the balance and optimization of the production line, thereby improving production efficiency and quality.

[0065] This embodiment also provides an automated production line control system based on computer vision, such as... Figure 2 The diagram shows the structure of an automated production line control system, which includes: a data acquisition module, a virtual model platform, a simulation calculation module, a control and monitoring module, and a simulation and deployment terminal.

[0066] The data acquisition module includes: a parameter input module, a dynamic characteristic capture module, and a characteristic sensing module; it is used to input parameters and dynamically capture the operating status of the device to obtain various device-related data.

[0067] The parameter input module is used to pre-input the physical characteristic data of the equipment; the dynamic characteristic capture module is used to capture the motion range and motion behavior of each piece of equipment to generate equipment motion data; the characteristic sensing module is used to collect corresponding equipment status data and conveyor belt status data of each section of the conveyor belt according to the motion mode of different equipment through several sensors installed in the workshop.

[0068] This embodiment can accurately capture the movement range and behavior of the equipment by pre-inputting the physical characteristic data of the equipment and the dynamic characteristic capture module. By collecting equipment status data and conveyor belt status data through sensors, the operating status of the equipment and conveyor belt can be monitored in real time, realizing real-time monitoring and adjustment of automated production line control.

[0069] The virtual model platform includes a data conversion module, a model building module, and a model calibration module; it is used to receive device-related data and build a mapping device model.

[0070] The data conversion module receives physical characteristic data, equipment motion data, equipment status data, and conveyor belt status data, and converts them into simulated operation data; the model building module constructs a virtual workshop scene and generates an initial equipment model in conjunction with the simulated operation data; the model calibration module corrects the initial equipment model using proportional-integral-differential algorithms to obtain a mapped equipment model.

[0071] This embodiment can construct a virtual workshop scene and model and simulate the operating status of equipment in the workshop, thereby realistically restoring the workshop's operating conditions. Further correction of the mapped equipment model can improve the model's accuracy, making subsequent simulation calculations and optimization results more reliable and effective.

[0072] The simulation calculation module includes a simulation module and a calculation optimization module; it is used to simulate the operation of the mapped equipment model and calculate the optimal production speed V in real time. 优 and maximum production speed V 限 .

[0073] The simulation module is used to simulate and run the mapped equipment model in a virtual platform, and calculates the production speed V of each piece of equipment through edge computing algorithms. 设 The load rate P corresponding to each device 设 and the operating speed V of each conveyor belt section. 传 The computational optimization module is used to iteratively optimize based on the simulated annealing algorithm, ultimately obtaining the optimal production speed V. 优 and maximum production speed V 限 .

[0074] This embodiment obtains the actual operating status of the equipment and, through simulation calculations, obtains key indicators such as the production speed and load rate of each machine and conveyor belt. Furthermore, by introducing a simulated annealing algorithm for iterative optimization, the optimal production speed and maximum production speed can be found. These can be flexibly adjusted under different production conditions to achieve the best production efficiency and quality, thereby maximizing production efficiency and meeting production needs.

[0075] The control and monitoring module includes a mode switching module, a speed control module, and a load control module; it is used to switch production speed modes according to different needs to adjust the operating speed and load of equipment and conveyor belts, and to monitor the production status of the simulated production line to obtain production status data.

[0076] The mode switching module is used to switch between the optimal production speed mode and the maximum production speed mode according to workshop conditions and product conditions; the rate control module is used to adjust the speed of each piece of equipment and each section of conveyor belt to indirectly control the total speed of all equipment and conveyor belts in the preceding process and the total speed of all equipment and conveyor belts in the subsequent process; the load control module is used to increase or decrease the load on the equipment to control the load rate of each piece of equipment.

[0077] This embodiment, while ensuring production volume and load rate, selects the optimal production speed mode and the maximum production speed mode by switching between different production speed modes according to the conditions of the workshop and products. This ensures that the production line can operate at the highest efficiency under different conditions, thereby maximizing production efficiency and improving the overall capacity of the production line.

[0078] It should be noted that workshop conditions include: the quantity and type of equipment, workshop resource supply, and process flow; product conditions include: product quality requirements, product demand, and production cost control.

[0079] The simulation and deployment terminal includes a simulation module and a deployment module; it is used to perform simulation verification based on production status data, and after verification, it is deployed to the actual production line for production.

[0080] This embodiment proposes a control method that maintains the sum of the rates between processes to ensure that the output per unit time between two adjacent processes is consistent. This method can ensure that the output of each process remains consistent at different production speeds for each piece of equipment in the production line.

[0081] Meanwhile, this embodiment requires that the load rates of two adjacent processes be similar, that is, the load of each process remains consistent, which can avoid the situation where a certain process is overloaded and causes a bottleneck.

[0082] This control method ensures the balance and smooth operation of the production line, avoids backlogs or insufficient output during the production process, and guarantees the balanced operation of the entire production line, improving production efficiency and quality, and achieving balanced production. Example 2

[0083] This embodiment, based on Embodiment 1, specifically explains several device-related data:

[0084] Physical characteristics data include: the size, shape, movement mode, and rated load capacity of the equipment.

[0085] Equipment motion data includes: equipment position, direction of movement, speed, acceleration, and path of movement.

[0086] Equipment status data includes: equipment on / off status, equipment operating mode, equipment energy consumption data, and equipment output data.

[0087] The conveyor belt status data for each section includes the length, initial speed, and current operating speed of each section.

[0088] This embodiment collects physical characteristic data, equipment motion data, equipment status data, and conveyor belt status data of each section of the conveyor belt. By using multiple data sources, it enhances the specific details of the equipment, reconstructs the complete operating trajectory of the equipment, and ensures the accuracy of the model. Example 3

[0089] Based on Example 1, this embodiment proposes another computer vision-based automated pipeline control method:

[0090] S1. Model Building: Construct a deep learning model and collect data from the equipment in the workshop;

[0091] S2. Model Training: Data is collected from the equipment in the workshop to obtain a number of equipment-related data. The data is then input into a deep learning model to continuously optimize the model, simulate the state and performance of the equipment and the relationship between the equipment, and obtain a high-precision optimized model.

[0092] S3. Equipment Monitoring: Real-time monitoring of the operating status and performance data of equipment in the workshop. When a problem is detected in equipment used in a certain process, it triggers the need for equipment speed adjustment.

[0093] S4. Control Parameter Output: Input the current status and performance data of the equipment in the workshop into the high-precision optimization model, and obtain the control parameters through the simulation calculation module, including the production speed and load rate of each machine and the running speed of each conveyor belt.

[0094] S5. Equipment speed control: Based on the obtained control parameters, adjust its production speed or load rate to control the equipment speed in the entire control system.

[0095] S6. Switching Mode: Based on workshop and product conditions, and on the premise of ensuring consistent output per unit time and comparable load rates between adjacent processes, switch between the optimal production speed mode and the maximum production speed mode as needed.

[0096] S7. Verification and Deployment: Verify the adjusted equipment speed data through simulation and deployment terminals to ensure it meets expectations. If the verification is successful, deploy the adjusted equipment speed data to the actual production line for production.

[0097] The difference between this embodiment and Embodiment 1 is that a deep learning model is first established, which can quickly analyze equipment status and performance data and output corresponding control parameters to achieve real-time equipment speed regulation; the model is continuously trained with the latest data to improve its accuracy and predictive ability, thereby outputting equipment control parameters more accurately.

[0098] Furthermore, by utilizing deep learning algorithms, the speed of equipment in the entire control system can be automatically adjusted, reducing the need for manual intervention and operation; and by optimizing the equipment speed control parameters, the efficiency and capacity of the production line can be maximized, achieving higher production speeds and output.

[0099] Based on the preferred embodiments of the present invention described above, those skilled in the art can make various changes and modifications without departing from the inventive concept. The technical scope of this invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A computer vision-based automated production line control method, characterized in that, Includes the following steps: S1. Collect data from the equipment in the workshop to obtain relevant equipment data; S2. Construct an initial equipment model for each machine in the workshop and correct it to obtain a mapped equipment model; S3. Run the mapping equipment model, record the status data of each machine in real time, and obtain the production speed and load rate of each machine and the running speed of each conveyor belt through the simulation calculation module. S4. Based on the production speed and load rate of each machine and the running speed of each conveyor belt, the optimal production speed V is obtained through iterative optimization using a simulated annealing algorithm. 优 and maximum production speed V 限 ; S5. Under the premise of ensuring that the output per unit time between two adjacent processes is consistent and the load rate is comparable, switch between the optimal production speed mode and the maximum production speed mode according to the workshop conditions and product conditions to obtain the proposed operating speed data. S6. After verifying the proposed operating speed data through the simulation deployment terminal, the data is deployed to the actual production line for production. Specifically, in step S5, the steps to ensure consistent output per unit time between two adjacent processes are as follows: S51. Number the equipment and conveyors in the preceding process to obtain N equipment and M conveyors, with the speed of each equipment being V1, V2, ..., V... N The speeds of each conveyor belt are V1, V2, ..., V... M ; S52. Number the equipment and conveyor belts in the subsequent processes to obtain X equipment and Y conveyor belts, with the speeds of each equipment being Z1, Z2, ..., Z... X The speeds of each conveyor belt are Z1, Z2, ..., Z... Y ; S53. Ensure that the total speed of all equipment and conveyor belts in the preceding process is equal to the total speed of all equipment and conveyor belts in the subsequent process, i.e., (V1 + V2 + ... + V N ) + (V1 + V2 + ... + V M ) = (Z1 + Z2 + ... + Z X ) + (Z1 + Z2 + ... + Z Y This means achieving consistent output per unit time between two adjacent processes; To ensure that the load rates of two adjacent processes are comparable, the following steps are included: S54. Obtain the rated load W of each piece of equipment in the preceding process. 定 Given the current load W0 and the number of devices Q, the load rate W for each device is calculated as W = W1 / W. 定 Then the load rate of the preceding process is W 前 =(W1+W2+ ...+W Q ) / Q; S55. Obtain the rated load U of each piece of equipment in the subsequent process. 定 Given the current load U0 and the number of devices P, we can obtain the load rate of each device U = U1 / U 定 Then the load rate of the subsequent process is U 后 =(U1+U2+ ...+U P ) / P; S56. By adjusting the current load W0 of the preceding process and the current load U0 of the following process, W can be achieved. 前 =U 后 .

2. The automated production line control method based on computer vision according to claim 1, characterized in that: In step S1, data collection is performed on the equipment within the workshop, specifically including the following steps: S11. Input the physical characteristics data of the equipment in advance, and capture the motion range and motion behavior of each device through the dynamic characteristic capture module to generate device motion data; S12. Collect corresponding equipment status data and conveyor belt status data of each section of the conveyor belt through several sensors installed in the workshop.

3. The automated production line control method based on computer vision according to claim 1, characterized in that: S3 further includes: storing the device-related data and the status data of each machine in real time.

4. A computer vision-based automated production line control system, used to implement the computer vision-based automated production line control method as described in any one of claims 1-3, comprising: The data acquisition module, virtual model platform, simulation calculation module, control and monitoring module, and simulation deployment terminal are characterized in that: The data acquisition module includes: a parameter input module, a dynamic characteristic capture module, and a characteristic sensing module; it is used to input parameters and dynamically capture the operating status of the device to obtain several device-related data. The virtual model platform includes: a data conversion module, a model building module, and a model verification module; used to receive device-related data and build a mapping device model. The simulation calculation module includes a simulation module and a calculation optimization module; it is used to simulate the operation of the mapped equipment model and calculate the optimal production speed Voptimal and the maximum production speed Vlimit in real time. The control and monitoring module includes: a mode switching module, a rate control module, and a load control module; it is used to switch production speed modes according to different needs to adjust the operating speed and load of equipment and conveyor belts, and to monitor the production status of the simulated production line to obtain production status data. The simulation and deployment terminal includes a simulation module and a deployment module; it is used to perform simulation verification based on the production status data, and after verification, it is deployed to the actual production line for production.

5. The automated production line control system based on computer vision according to claim 4, characterized in that: The parameter input module is used to pre-input the physical characteristic data of the equipment; the dynamic characteristic capture module is used to capture the motion range and motion behavior of each piece of equipment to generate equipment motion data; the characteristic sensing module is used to collect corresponding equipment status data and conveyor belt status data of each section of the conveyor belt according to the motion mode of different equipment through several sensors installed in the workshop.

6. The automated production line control system based on computer vision according to claim 5, characterized in that: The data conversion module is used to receive the physical characteristic data, the equipment motion data, the equipment status data, and the conveyor belt status data, and convert them into simulated operation data; the model building module is used to construct a virtual workshop scene and generate an initial equipment model in conjunction with the simulated operation data; the model calibration module is used to correct the initial equipment model using a proportional-integral-differential algorithm to obtain the mapped equipment model.

7. The automated production line control system based on computer vision according to claim 4, characterized in that: The simulation module is used to simulate the mapping device model in a virtual platform and calculate the production speed V of each device using an edge computing algorithm. 设 The load rate P corresponding to each device 设 and the operating speed V of each conveyor belt section. 传 The calculation and optimization module is used to iteratively optimize based on the simulated annealing algorithm to finally obtain the optimal production speed V. 优 and maximum production speed V 限 .

8. The automated production line control system based on computer vision according to claim 4, characterized in that: The mode switching module is used to switch between the optimal production speed mode and the maximum production speed mode according to workshop conditions and product conditions; the rate control module is used to adjust the speed of each piece of equipment and each section of conveyor belt to indirectly control the total speed of all equipment and conveyor belts in the preceding process and the total speed of all equipment and conveyor belts in the subsequent process; the load control module is used to increase or decrease the load on the equipment to control the load rate of each piece of equipment.

Images