Equipment productivity regulation and control method and system

Abstract

The invention provides an equipment productivity regulation and control method and system. The method comprises the following steps: S1, predicting the current production line productivity through a prediction model based on raw material data and equipment data; s2, judging whether the productivity in a preset time period can meet a preset requirement or not based on the predicted productivity of the current assembly line, and determining a regulation and control strategy according to a judgment result; and S3, the current assembly line is adjusted based on the regulation and control strategy so that the productivity of the current assembly line in the preset time period can meet the preset requirement.

Description

Technical Field

[0001] This invention relates to the field of capacity control technology, specifically to a method and system for controlling equipment capacity. Background Technology

[0002] In modern industrial production, assembly line operations have become the mainstream production mode, with food processing and electronics manufacturing being typical examples. Taking a fish fillet shaping assembly line as an example, a single production line typically deploys various types of equipment, such as raw material processing equipment, AI visual inspection equipment, and robotic shaping equipment. Each type of equipment contains numerous adjustable components, such as the robot's time configuration module and motion speed adjustment components, the AI ​​camera's field of view adjustment components, and similarity threshold control units. Because the various stages of assembly line production are closely interconnected, a change in one stage can affect the entire process. The control of a single piece of equipment or component must not only consider the production efficiency of that stage but also the material supply rhythm of upstream processes and the capacity of downstream processes. Otherwise, it can easily lead to problems such as material accumulation and production interruptions.

[0003] Traditional equipment capacity control methods rely heavily on manual experience, requiring operators to analyze and adjust parameters of each piece of equipment individually. However, this trial-and-error approach has significant drawbacks when faced with a vast number of devices and components on a production line. Firstly, the numerous combinations of equipment and components make it difficult for operators to exhaustively explore all control options, resulting in extremely low efficiency. Secondly, the lack of a systematic control strategy makes it impossible to accurately balance capacity and product quality, failing to meet the dual requirements of production efficiency and product quality for enterprises. Therefore, there is an urgent need for a method that can comprehensively consider the collaborative relationships between multiple devices, components, and upstream and downstream processes to achieve precise and efficient capacity control, thereby improving the intelligence and automation level of assembly line production.

[0004] Patent document CN113009895A (application number: 202110251200.4) discloses a dynamic production control method, system, and computer-readable storage medium. The method includes: firstly, acquiring image data on the production line; then, identifying the image data to obtain first information and second information; next, acquiring product information on the production line; then, determining a unit capacity value as a production line efficiency indicator based on the first information, second information, and product information; if the determined unit capacity value does not exceed a unit capacity threshold, generating a distribution adjustment strategy based on the determined unit capacity value; and finally, adjusting the production line based on the distribution adjustment strategy. Summary of the Invention

[0005] In view of the deficiencies in the prior art, the purpose of this invention is to provide a method and system for regulating equipment capacity.

[0006] A method for regulating equipment capacity according to the present invention includes:

[0007] Step S1: Based on raw material data and equipment data, predict the current production line capacity using a predictive model;

[0008] Step S2: Based on the predicted current production line capacity, determine whether the capacity within the preset time period can meet the preset requirements, and determine the control strategy based on the judgment result;

[0009] Step S3: Adjust the current production line based on the control strategy so that the production capacity of the current production line meets the preset requirements within the preset time period.

[0010] Preferably, step S1 includes:

[0011] Step S1.1: Construct a prediction model based on a long short-term memory network;

[0012] Step S1.2: Construct a dataset based on the collected raw material data, equipment data, and historical production capacity data;

[0013] Step S1.3: Train the prediction model using the constructed dataset to obtain the trained prediction model;

[0014] Step S1.4: Use the trained prediction model to predict the current production line capacity based on the current raw material data and equipment data.

[0015] Preferably, step S2 includes:

[0016] When it is determined that the production capacity within the preset time period cannot meet the preset requirements, the current production line is adjusted based on the preset control strategy to increase the production capacity so that the increased production capacity can meet the preset requirements, and the quality of the target product is reduced.

[0017] When it is determined that the production capacity within a preset time period exceeds the preset requirements, the current production line is adjusted based on the preset control strategy to reduce the production capacity so that the reduced production capacity can meet the preset requirements and improve the quality of the target product.

[0018] Preferably, the step of adjusting the current production line based on a preset control strategy to increase production capacity so that the increased capacity can meet preset requirements, while reducing the quality of the target product, includes:

[0019] Expanding the camera's field of view increases the number of products to be identified, thereby increasing the number of workable targets. Based on the increased number of workable targets, the working speed and working range of the robot on the production line are adjusted to improve productivity.

[0020] Lowering the threshold of the camera's optical sensor reduces the image matching accuracy requirements and shortens the single-frame processing time, thereby increasing the number of target products that meet the preset requirements.

[0021] Optimize the robot path, prioritize processing near-end materials, and match it with the increased camera cycle speed;

[0022] The device clock is synchronized at the microsecond level using the IEEE 1588 protocol. Once the camera completes recognition, it immediately triggers the robot's action. The robot's return signal controls the conveyor belt feeding, eliminating upstream and downstream waiting.

[0023] Preferably, the step of adjusting the current production line based on a preset control strategy to reduce capacity while ensuring the reduced capacity meets preset requirements and improves the quality of the target product includes:

[0024] Increase the accuracy of the camera's zoom lens and use an aspect ratio filtering algorithm to exclude target products that do not meet the preset requirements; improve the reference standard for target products and output products with stable quality.

[0025] While ensuring that the robot's working speed is above the basic baseline, control improves the robot's motion accuracy and compensates for the position of the end effector, thereby improving the quality of the target product.

[0026] Control the threshold parameters of adjacent target products to achieve accurate filtering of adjacent target products;

[0027] A physical buffer zone is added to the conveyor belt to temporarily store raw materials when the robot slows down; when the packaging station is ready, the buffered raw materials are processed first, thus achieving adaptive cycle time.

[0028] According to the present invention, a production capacity control system for equipment includes:

[0029] Module M1: Predicts the current production line capacity using a predictive model based on raw material data and equipment data;

[0030] Module M2: Based on the predicted current production line capacity, determine whether the capacity within a preset time period can meet the preset requirements, and determine the control strategy based on the judgment result;

[0031] Module M3: Adjusts the current production line based on the control strategy to ensure that the production capacity of the current production line meets the preset requirements within a preset time period.

[0032] Preferably, the module M1 includes:

[0033] Module M1.1: Constructing a prediction model based on Long Short-Term Memory networks;

[0034] Module M1.2: Constructs a dataset based on the collected raw material data, equipment data, and historical production capacity data;

[0035] Module M1.3: Uses the constructed dataset to train the prediction model and obtains the trained prediction model;

[0036] Module M1.4: Utilizes the trained prediction model to predict the current production line capacity based on current raw material and equipment data.

[0037] Preferably, the module M2 includes:

[0038] When it is determined that the production capacity within the preset time period cannot meet the preset requirements, the current production line is adjusted based on the preset control strategy to increase the production capacity so that the increased production capacity can meet the preset requirements, and the quality of the target product is reduced.

[0039] When it is determined that the production capacity within a preset time period exceeds the preset requirements, the current production line is adjusted based on the preset control strategy to reduce the production capacity so that the reduced production capacity can meet the preset requirements and improve the quality of the target product.

[0040] Preferably, the step of adjusting the current production line based on a preset control strategy to increase production capacity so that the increased capacity can meet preset requirements, while reducing the quality of the target product, includes:

[0041] Expanding the camera's field of view increases the number of products to be identified, thereby increasing the number of workable targets. Based on the increased number of workable targets, the working speed and working range of the robot on the production line are adjusted to improve productivity.

[0042] Lowering the threshold of the camera's optical sensor reduces the image matching accuracy requirements and shortens the single-frame processing time, thereby increasing the number of target products that meet the preset requirements.

[0043] Optimize the robot path, prioritize processing near-end materials, and match it with the increased camera cycle speed;

[0044] The device clock is synchronized at the microsecond level using the IEEE 1588 protocol. Once the camera completes recognition, it immediately triggers the robot's action. The robot's return signal controls the conveyor belt feeding, eliminating upstream and downstream waiting.

[0045] Preferably, the step of adjusting the current production line based on a preset control strategy to reduce capacity while ensuring the reduced capacity meets preset requirements and improves the quality of the target product includes:

[0046] Increase the accuracy of the camera's zoom lens and use an aspect ratio filtering algorithm to exclude target products that do not meet the preset requirements; improve the reference standard for target products and output products with stable quality.

[0047] While ensuring that the robot's working speed is above the basic baseline, control improves the robot's motion accuracy and compensates for the position of the end effector, thereby improving the quality of the target product.

[0048] Control the threshold parameters of adjacent target products to achieve accurate filtering of adjacent target products;

[0049] A physical buffer zone is added to the conveyor belt to temporarily store raw materials when the robot slows down; when the packaging station is ready, the buffered raw materials are processed first, thus achieving adaptive cycle time.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] 1. In the process of capacity control, when it is necessary to increase capacity, this invention can rapidly increase the number of products to be identified by expanding the field of view of the camera, providing sufficient processing targets for subsequent processes; at the same time, it lowers the similarity threshold of the target products, relaxes the identification standards for the target products, and further increases the quantity of production capacity. Based on this, the working speed and range of the robot are adjusted, allowing the robot to operate on the target products more efficiently; since this control strategy is based on the prediction and analysis of the overall production line capacity, while increasing the front-end recognition, it improves the operating efficiency and range of the back-end robot, avoiding the backlog of products to be processed due to the increase in the number of front-end products.

[0052] 2. When it is necessary to reduce production capacity and improve product quality, the robot's motion precision is controlled, and the end effector's posture is compensated to ensure the accuracy of the target product. By controlling the threshold parameters of adjacent fish rafts and increasing the similarity threshold, precise filtering and screening of fish rafts can be achieved. These control methods improve product quality while ensuring that the robot's working speed is within a reasonable baseline. They also prevent the upstream material supply rhythm from being affected by excessive speed reduction, thus avoiding material accumulation or downstream waiting. This achieves seamless connection and efficient collaboration between upstream and downstream processes on the production line, greatly improving production efficiency and product quality, and reducing manual control costs and waste of production resources. Attached Figure Description

[0053] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0054] Figure 1 This is a flowchart of the equipment capacity control method.

[0055] Figure 2 This is a flowchart of the equipment collaborative quality inspection method. Detailed Implementation

[0056] The present invention will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present invention, but do not limit the invention in any way. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all fall within the protection scope of the present invention.

[0057] Example 1

[0058] According to the present invention, a method for regulating equipment capacity is provided, such as... Figure 1 As shown, it includes:

[0059] Step S1: Based on raw material data and equipment data, predict the current production line capacity using a predictive model;

[0060] Specifically, step S1 includes:

[0061] Step S1.1: Construct a prediction model based on a long short-term memory network;

[0062] Step S1.2: Construct a dataset based on the collected raw material data, equipment data, and historical production capacity data;

[0063] Step S1.3: Train the prediction model using the constructed dataset to obtain the trained prediction model;

[0064] Step S1.4: Use the trained prediction model to predict the current production line capacity based on the current raw material data and equipment data.

[0065] The raw material data includes the type, quantity, and quality parameters of the raw materials; the quality parameters include the size specifications, shape characteristics, and physical strength of the raw materials.

[0066] The equipment data includes the equipment model, quantity, and operating parameters; the operating parameters include the equipment's working speed, time configuration of each action step, acceleration, working range, historical fault records, and maintenance cycle.

[0067] The collected raw material and equipment data are preprocessed, including standardization and anomaly handling.

[0068] Step S2: Based on the predicted current production line capacity, determine whether the capacity within the preset time period can meet the preset requirements, and determine the control strategy based on the judgment result;

[0069] Specifically, step S2 includes:

[0070] When it is determined that the production capacity within the preset time period cannot meet the preset requirements, the current production line is adjusted based on the preset control strategy to increase the production capacity so that the increased production capacity can meet the preset requirements, and the quality of the target product is reduced.

[0071] When it is determined that the production capacity within a preset time period exceeds the preset requirements, the current production line is adjusted based on the preset control strategy to reduce the production capacity so that the reduced production capacity can meet the preset requirements and improve the quality of the target product.

[0072] The step of adjusting the current production line based on a preset control strategy to increase production capacity so that the increased capacity can meet preset requirements, while reducing the quality of the target product, includes:

[0073] Expanding the camera's field of view increases the number of products to be identified, thereby increasing the number of workable targets. Based on the increased number of workable targets, the working speed and working range of the robot on the production line are adjusted to improve productivity. The working speed of the robot on the production line includes the robot's movement speed, movement acceleration, and downward clamping speed. With the expansion of the robot's working range, the corresponding robot working speed also increases, thus increasing productivity.

[0074] Lowering the threshold of the camera's optical sensor reduces the image matching accuracy requirements and shortens the single-frame processing time, thereby increasing the number of target products that meet the preset requirements.

[0075] Optimize the robot path, prioritize processing near-end materials, and match it with the increased camera cycle speed;

[0076] The device clock is synchronized at the microsecond level using the IEEE 1588 protocol. Once the camera completes recognition, it immediately triggers the robot's action. The robot's return signal controls the conveyor belt feeding, eliminating upstream and downstream waiting.

[0077] In this embodiment, taking fish fillets as an example, the area pressed down by the end clamp is fixed. When this value is relaxed, the end may press down on part of the fish fillets, but the number of fish fillets to be filtered will decrease, thus increasing the production capacity.

[0078] Adjust the shaping priority based on the fish raft arrival situation and staffing ratio on the day to achieve the expected production capacity:

[0079] When the quality of incoming materials is generally in line with requirements, but the factory has insufficient manpower, the distance and centerline weights are adjusted to allow the robot to prioritize the shaping of fish fillets in positions that are difficult for humans to reach. This human-robot collaboration improves the working rhythm of both humans and robots.

[0080] When the staffing ratio is sufficient, by adjusting the similarity weight to be higher, the robot will prioritize the removal of targets that the AI ​​considers to be fish rafts and that are closer to the robot, thereby increasing the removal cycle and thus increasing production capacity. At this time, the requirement for similarity in AI recognition has been reduced, and the number of removals performed by the robot will naturally increase.

[0081] The step of adjusting the current production line based on a preset control strategy to reduce capacity while ensuring the reduced capacity meets preset requirements and improves the quality of the target product includes:

[0082] Increase the accuracy of the camera's zoom lens, for example, by adjusting the similarity threshold from 0.9 to 0.95; and use an aspect ratio filtering algorithm to exclude abnormal raw materials that do not meet the preset requirements; improve the reference standard of the target product and output products with stable quality.

[0083] While ensuring the robot's working speed is above the basic baseline, the control improves the robot's motion accuracy and compensates for the position of the end effector, thereby improving the quality of the target product. In this embodiment, the accuracy of the robot's force control sensor (±0.1N) and the servo reducer (speed -25%) are adjusted.

[0084] Control the threshold parameters of adjacent target products to achieve accurate filtering of adjacent target products;

[0085] Physical buffer zones are added to the conveyor belt to temporarily store raw materials when the robot slows down; when the packaging station is ready, the buffered raw materials are processed first, achieving adaptive cycle time. Through an elastic buffer mechanism, 3-5 physical buffer zones for raw materials are added to the conveyor belt. When the robot slows down, the buffer zones temporarily store raw materials to prevent accumulation.

[0086] In this embodiment, taking fish fillets as an example, the force of the robot's shaping (pressing and clamping) is adjusted to ensure that each fish fillet is clamped and pressed in place, which better meets the standards for fish fillets and improves the shaping quality of fish fillets.

[0087] By raising the similarity threshold of fish fillets, substandard fish fillet raw materials are precisely filtered out, and some non-standard or abnormally shaped fish fillets are completely filtered out. The work is only carried out on raw materials that are close to the standard fish fillets, thereby improving the quality of work.

[0088] Filtering out fish fillets that are too large or too small, AI identifies that such fish fillets cannot be reshaped to meet the standard fish fillet style.

[0089] During the AI ​​recognition of fish fillets, basic information such as the area, length, width, and color of standard fish fillets is collected. The fish fillet shaping reference template is continuously optimized and used as a reference for whether the fish fillet needs to be shaped, thereby improving the quality of the template and making subsequent shaping more closely resemble the standard shaped template.

[0090] Step S3: Adjust the current production line based on the control strategy so that the production capacity of the current production line meets the preset requirements within the preset time period.

[0091] The present invention also provides an equipment capacity control system, which can be implemented by executing the process steps of the equipment capacity control method. That is, those skilled in the art can understand the equipment capacity control method as a preferred embodiment of the equipment capacity control system.

[0092] Example 2

[0093] Example 2 is a preferred example of Example 1.

[0094] According to the present invention, a collaborative quality inspection method for equipment is provided, such as... Figure 2 As shown, this includes: when multiple devices are working on the production line, vision-based inspection is performed simultaneously with product evaluation; specifically, it includes the following steps:

[0095] Step 1: Obtain product image information from the production line and preprocess the obtained product image information to obtain preprocessed product image information;

[0096] Specifically, step 1 includes:

[0097] Step 1.1: Acquire product images on the production line using a camera through high-frequency shooting;

[0098] Step 1.2: Perform image enhancement, geometric correction and normalization processing on the acquired product image information from the production line to obtain the processed product image.

[0099] Step 2: Identify the product type based on the preprocessed product image information and obtain the corresponding quality inspection parameters; perform quality inspection on the products on the production line based on the quality inspection parameters to distinguish between qualified and unqualified products and calculate the pass rate;

[0100] Specifically, step 2 includes:

[0101] Step 2.1: The preprocessed product images are used for product type recognition based on a convolutional neural network;

[0102] Step 2.2: Based on the identified product type, obtain the corresponding product quality inspection parameters from the standard database. The quality inspection parameters include: color, length, width, height, and texture feature information.

[0103] Step 2.3: After preprocessing, the product image is separated from the background using image segmentation technology. The separated product is then converted from the RGB color space to the HSV color space. The converted image is scanned pixel by pixel, and the HSV value of each pixel is counted to obtain the product's color distribution information. The obtained product color distribution information is compared with the color standard in the quality inspection parameters to calculate the color distribution similarity. When the color distribution similarity is less than the first threshold, the current product is considered to be unqualified.

[0104] Step 2.4: Based on the preprocessed product image, extract the product's edge contour using Canny edge detection, calculate the product's circumscribed matrix based on the edge contour, and obtain the product's length and width on the image plane; then, combine the product's position information on the production line and the camera's installation parameters, calculate the product's actual height using the triangulation principle; compare the obtained product's length, width, and height with the standard length, width, and height parameters in the quality inspection parameters, and calculate the errors in length, width, and height respectively; when any one or more errors in length, width, and height exceed the second threshold, the current product is considered a non-conforming product;

[0105] Step 2.5: Use the Local Binary Pattern (LBP) algorithm to extract the texture feature information of the product. Compare the extracted texture feature information with the texture feature information in the quality inspection parameters to calculate the similarity of the texture features. When the similarity of the texture features is less than the third threshold, the current product is considered to be a non-conforming product.

[0106] This embodiment utilizes technologies such as convolutional neural networks, image segmentation, and Canny edge detection to perform quantitative analysis of products based on multi-dimensional parameters such as color, size, and texture. This avoids the problems of false detection and missed detection caused by visual fatigue and inconsistent subjective standards in manual quality inspection, ensuring that quality inspection rules are constant and effectively improving the accuracy and consistency of product quality inspection.

[0107] Step 3: Count the number of qualified products to obtain the current production line capacity;

[0108] Step 4: Analyze equipment working efficiency based on the preprocessed product image information;

[0109] Acquire pre-processed product images under the current device, and classify the current products according to the acquired pre-processed product images under the current device, including: processable products, unprocessable products, and processed products;

[0110] When the current product is classified as a processable product, the efficiency of the current equipment is analyzed through the downstream equipment of the production line.

[0111] The process of analyzing the working efficiency of the current equipment through downstream equipment in the production line includes:

[0112] The system acquires pre-processed product images from downstream equipment on the production line and classifies the current products based on these images, including processable products, unprocessable products, and processed products.

[0113] When the number / percentage of processable products decreases, the number / percentage of processed products increases, and the number / percentage of unprocessable products remains stable, the current equipment is working effectively; when the number / percentage of processable products remains unchanged or increases, the current equipment's efficiency decreases.

[0114] More specifically, in this embodiment, taking a food processing production line as an example, firstly, we analyze the situation of the raw materials themselves;

[0115] Raw materials are recorded as they pass through the equipment's field of view, and the vision system identifies and categorizes them into three types: processable, unprocessable, and processed. Unprocessable materials are further subdivided based on the reasons for their unprocessability. Common reasons include: being too close to the source, sticking together, stacking, or being too large / too small. These are inherent properties of the raw materials that make them unprocessable. If this type of material constitutes a high percentage, the final production capacity will be affected. This impact cannot be resolved by adjusting the equipment's own parameters; therefore, an alarm on the control panel is used to alert on-site personnel for intervention, thereby improving the quality of the raw materials.

[0116] Then, analyze the condition of the raw materials after processing:

[0117] After the equipment processes raw materials visually marked as processable, downstream equipment on the production line will conduct quality inspections on that equipment. The overall logic of the quality inspection analysis is as follows:

[0118] After visual recognition, the types of raw materials within the field of view are classified and compared with upstream equipment. The overall trend should show a decreasing trend, meaning the quantity / percentage of processable raw materials decreases, the quantity / percentage of processed raw materials increases, and the quantity of unprocessable raw materials remains stable. If this data trend is observed, it indicates that the upstream production line equipment is working effectively and the raw material processing is efficient.

[0119] If the overall trend of the quantity / proportion of raw materials that can be processed remains unchanged or increases, it means that the working efficiency of the front-end equipment is decreasing. At this time, the cloud platform needs to adjust the rules and work configuration.

[0120] This embodiment analyzes the equipment's working efficiency based on product image information, which can promptly identify problems in the equipment's operation, making it easier for enterprises to optimize equipment operating parameters or adjust production processes in a targeted manner, thereby improving equipment utilization and overall production efficiency.

[0121] Step 5: When any one or more of the pass rate, work efficiency, and current production line capacity are lower than the preset value, an early warning will be triggered, and the current production line will be adjusted according to the preset requirements.

[0122] Specifically, step 5 includes: uploading quality inspection analysis data to the cloud in real time, during which equipment data from the same workshop and production line will be recorded and summarized, and the cloud platform will manage and maintain equipment position information, etc.; and analyzing the equipment quality inspection data.

[0123] In this embodiment, when the current production line capacity is lower than the preset value, the factory is prompted via the display screen to adjust the raw materials; the poor quality of the raw materials is caused by human error and cannot be controlled by the equipment.

[0124] When the pass rate is lower than the preset value, the robot's working angle is adjusted to make the pass rate meet the preset requirements; if the shape of the raw material is still abnormal after processing, the quality inspector adjusts the angle of the robotic arm's movement according to the abnormal location and the direction of shape deviation.

[0125] When the equipment's working efficiency is lower than the preset value, that is, the processed targets within a unit of time do not reach the qualified level, first check the speed status of the production line to rule out the possibility that the fish raft flow is reduced due to the slow speed. At this time, the speed can be increased; check the recognition data of vision and strategy.

[0126] When the equipment's operating efficiency is lower than the preset value, check if it is due to insufficient raw materials. If there are insufficient raw materials, prompt the factory to adjust the raw material supply.

[0127] When the equipment's efficiency falls below the preset value, check if the strategy calculation time is too long, meaning the computation consumes the overall processing time. In this case, it's necessary to reduce the computational load, aiming for the fastest possible output, even at the cost of reduced accuracy. For example, typically, n targets are analyzed simultaneously, with n possibilities calculated for each target, ultimately selecting the path with the lowest error and fastest speed. Excessive computational load slows down the equipment's processing speed, requiring a reduction in the number of computation threads to improve computational speed.

[0128] When the equipment's working efficiency is lower than the preset value, check the working time of the actuator. If the working time exceeds the qualified level, it means that the robot's execution speed is too slow. At this time, it is necessary to adjust the equipment's speed, acceleration, and jerk values, and at the same time increase the cylinder's action speed, such as the speed of pressing, grasping, and clamping, so that the speed of fine movement can also be accelerated.

[0129] In this embodiment, when any one or more of the pass rate, work efficiency, and production line capacity fall below the preset value, an early warning is triggered and adjustments are made in a timely manner. This enables a rapid response to abnormal situations in the production process, preventing problems from escalating and reducing production losses. At the same time, automatic adjustments ensure that the production line operates efficiently and stably, improving the flexibility and competitiveness of enterprise production.

[0130] The present invention also provides a collaborative equipment quality inspection system, which can be implemented by executing the process steps of the collaborative equipment quality inspection method. That is, those skilled in the art can understand the collaborative equipment quality inspection method as a preferred embodiment of the collaborative equipment quality inspection system.

[0131] Those skilled in the art will understand that, in addition to implementing the system, apparatus, and their modules provided by this invention in purely computer-readable program code, the same program can be implemented in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system, apparatus, and their modules provided by this invention can be considered a hardware component, and the modules included therein for implementing various programs can also be considered structures within the hardware component; alternatively, modules for implementing various functions can be considered both software programs implementing the method and structures within the hardware component.

[0132] Specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. Unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined with each other.

Claims

1. A method for regulating equipment production capacity, characterized in that, include: Step S1: Based on raw material data and equipment data, predict the current production line capacity using a predictive model; Step S2: Based on the predicted current production line capacity, determine whether the capacity within the preset time period can meet the preset requirements, and determine the control strategy based on the judgment result; Step S3: Adjust the current production line based on the control strategy so that the production capacity of the current production line meets the preset requirements within the preset time period.

2. The equipment capacity control method according to claim 1, characterized in that, Step S1 includes: Step S1.1: Construct a prediction model based on a long short-term memory network; Step S1.2: Construct a dataset based on the collected raw material data, equipment data, and historical production capacity data; Step S1.3: Train the prediction model using the constructed dataset to obtain the trained prediction model; Step S1.4: Use the trained prediction model to predict the current production line capacity based on the current raw material data and equipment data.

3. The equipment capacity control method according to claim 1, characterized in that, Step S2 includes: When it is determined that the production capacity within the preset time period cannot meet the preset requirements, the current production line is adjusted based on the preset control strategy to increase the production capacity so that the increased production capacity can meet the preset requirements, and the quality of the target product is reduced. When it is determined that the production capacity within a preset time period exceeds the preset requirements, the current production line is adjusted based on the preset control strategy to reduce the production capacity so that the reduced production capacity can meet the preset requirements and improve the quality of the target product.

4. The equipment capacity control method according to claim 3, characterized in that, The adjustment of the current production line based on a preset control strategy to increase production capacity so that the increased capacity can meet preset requirements, while reducing the quality of the target product, includes: Expanding the camera's field of view increases the number of products to be identified, thereby increasing the number of workable targets. Based on the increased number of workable targets, the working speed and working range of the robot on the production line are adjusted to improve productivity. Lowering the threshold of the camera's optical sensor reduces the image matching accuracy requirements and shortens the single-frame processing time, thereby increasing the number of target products that meet the preset requirements. Optimize the robot path, prioritize processing near-end materials, and match it with the increased camera cycle speed; The device clock is synchronized at the microsecond level using the IEEE 1588 protocol. Once the camera completes recognition, it immediately triggers the robot's action. The robot's return signal controls the conveyor belt feeding, eliminating upstream and downstream waiting.

5. The equipment capacity control method according to claim 3, characterized in that, The adjustment of the current production line based on a preset control strategy to reduce capacity while ensuring the reduced capacity meets preset requirements and improves the quality of the target product includes: Increase the accuracy of the camera's zoom lens and use an aspect ratio filtering algorithm to exclude target products that do not meet the preset requirements; improve the reference standard for target products and output products with stable quality. While ensuring that the robot's working speed is above the basic baseline, control improves the robot's motion accuracy and compensates for the position of the end effector, thereby improving the quality of the target product. Control the threshold parameters of adjacent target products to achieve accurate filtering of adjacent target products; A physical buffer zone is added to the conveyor belt to temporarily store raw materials when the robot slows down; when the packaging station is ready, the buffered raw materials are processed first, thus achieving adaptive cycle time.

6. A device capacity control system, characterized in that, include: Module M1: Predicts the current production line capacity using a predictive model based on raw material data and equipment data; Module M2: Based on the predicted current production line capacity, determine whether the capacity within a preset time period can meet the preset requirements, and determine the control strategy based on the judgment result; Module M3: Adjusts the current production line based on the control strategy to ensure that the production capacity of the current production line meets the preset requirements within a preset time period.

7. The equipment capacity control system according to claim 6, characterized in that, The module M1 includes: Module M1.1: Constructing a prediction model based on Long Short-Term Memory networks; Module M1.2: Constructs a dataset based on the collected raw material data, equipment data, and historical production capacity data; Module M1.3: Uses the constructed dataset to train the prediction model and obtains the trained prediction model; Module M1.4: Utilizes the trained prediction model to predict the current production line capacity based on current raw material and equipment data.

8. The equipment capacity control system according to claim 6, characterized in that, The module M2 includes: When it is determined that the production capacity within the preset time period cannot meet the preset requirements, the current production line is adjusted based on the preset control strategy to increase the production capacity so that the increased production capacity can meet the preset requirements, and the quality of the target product is reduced. When it is determined that the production capacity within a preset time period exceeds the preset requirements, the current production line is adjusted based on the preset control strategy to reduce the production capacity so that the reduced production capacity can meet the preset requirements and improve the quality of the target product.

9. The equipment capacity control system according to claim 8, characterized in that, The adjustment of the current production line based on a preset control strategy to increase production capacity so that the increased capacity can meet preset requirements, while reducing the quality of the target product, includes: Expanding the camera's field of view increases the number of products to be identified, thereby increasing the number of workable targets. Based on the increased number of workable targets, the working speed and working range of the robot on the production line are adjusted to improve productivity. Lowering the threshold of the camera's optical sensor reduces the image matching accuracy requirements and shortens the single-frame processing time, thereby increasing the number of target products that meet the preset requirements. Optimize the robot path, prioritize processing near-end materials, and match it with the increased camera cycle speed; The device clock is synchronized at the microsecond level using the IEEE 1588 protocol. Once the camera completes recognition, it immediately triggers the robot's action. The robot's return signal controls the conveyor belt feeding, eliminating upstream and downstream waiting.

10. The equipment capacity control system according to claim 8, characterized in that, The adjustment of the current production line based on a preset control strategy to reduce capacity while ensuring the reduced capacity meets preset requirements and improves the quality of the target product includes: Increase the accuracy of the camera's zoom lens and use an aspect ratio filtering algorithm to exclude target products that do not meet the preset requirements; improve the reference standard for target products and output products with stable quality. While ensuring that the robot's working speed is above the basic baseline, control improves the robot's motion accuracy and compensates for the position of the end effector, thereby improving the quality of the target product. Control the threshold parameters of adjacent target products to achieve accurate filtering of adjacent target products; A physical buffer zone is added to the conveyor belt to temporarily store raw materials when the robot slows down; when the packaging station is ready, the buffered raw materials are processed first, thus achieving adaptive cycle time.

Images