Intelligent control method and system for intelligent PCB production line of unmanned workshop

Abstract

The invention discloses an intelligent PCB production line intelligent regulation and control method and system for an unmanned workshop, and particularly relates to the field of intelligent control, and the method comprises the steps: S1, PCB production line information text collection, S2, data standardization processing, S3, PCB production information processing, S4, PCB production line control judgment, and S5, PCB production line control judgment result feedback. According to the method, a mathematical model is constructed through big data analysis and a machine learning algorithm, the real-time health state and the inventory level state of the equipment are accurately quantified, full-period digital management of the PCB production equipment and the inventory level is realized, meanwhile, the production quality of products is predicted in real time through the production quality prediction model, and the product yield and the quality consistency are improved. According to the method, a production progress optimization model is constructed based on discrete event simulation and reinforcement learning algorithms, the relation between PCB production process flow logic and resource competition is accurately simulated, and optimization process sorting, equipment management and inventory management strategies are learned in real time.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and more specifically, to an intelligent control method and system for an intelligent PCB production line in an unmanned workshop. Background Art

[0002] As the PCB manufacturing industry moves towards high-end and unmanned operations, the shortcomings of traditional production line management models are fully exposed. In the field of equipment management, it mostly relies on post-maintenance, lacks preventive maintenance, and has primitive means of monitoring the health status of equipment. Production is often stagnant due to sudden failures, and the maintenance cost is high and the cycle is long, which seriously hinders production continuity and efficiency improvement. In the quality control link, it is mostly based on post-inspection, and it is difficult to trace the root cause of defects. It is impossible to have a real-time and comprehensive insight into the quality fluctuations throughout the production process, resulting in a high risk of defective products flowing out, and the company's reputation and market competitiveness are damaged. The production schedule is usually arranged based on experience, lacking the support of accurate scheduling models, poor process connection, idle equipment and overload coexist, and order delivery is frequently delayed, which is difficult to meet the market's demand for rapid delivery. Inventory management is extensive, the economic order quantity and safety inventory are not set accurately, and the characteristics of raw materials and supply risks are ignored, resulting in inventory backlogs and capital occupation or material shortages and shutdowns, and an imbalance between cost control and production assurance. With the fierce competition in the industry, there is an urgent demand for high precision, short delivery time and low cost of PCB products. The existing technical bottlenecks need to be broken through. The construction of an intelligent control system is imminent to reshape the core competitiveness of unmanned workshops and lead the industry's leap into intelligence. Summary of the invention

[0003] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an intelligent control method and system for an intelligent PCB production line in an unmanned workshop, and solves the problems raised in the above-mentioned background technology through the following scheme.

[0004] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an intelligent control method and system for an intelligent PCB production line in an unmanned workshop, comprising: S1: PCB production line information text collection: including equipment status information collection steps, production parameter information collection steps, environmental information collection steps, material information collection steps and production rhythm information collection steps, which are used to number the production lines and record them as 1, 2, 3...i...n in sequence, and screen PCB feature texts according to different production lines to obtain PCB feature text data;

[0005] S2: Data standardization processing: used to perform outlier deletion, missing value filling and standardization processing analysis on the PCB feature text data to obtain the second PCB feature text;

[0006] S3: PCB production information processing: used to import the second PCB feature text data into the equipment comprehensive performance evaluation model, the production quality prediction model, the production schedule optimization model and the material inventory control model for processing and analysis, and obtain a text output value based on the second PCB feature text;

[0007] S4: PCB production line control judgment: control judgment of PCB production line based on text output value;

[0008] S5: Feedback of PCB production line control judgment results: Feedback of the PCB production line control judgment judgment results and control results to the user information terminal.

[0009] Preferably, the PCB feature text specifically refers to: equipment normal operation time T, equipment failure time T f , the number of products whose processing accuracy meets the standard P, the number of products whose processing accuracy does not meet the standard P f , Equipment theoretical production efficiency E, Equipment actual production efficiency loss E f , product quality Q, equipment status D, raw material quality M, production process N, average service rate μ j , average arrival rate λ j , the sum of the average waiting time and service time W j , annual demand B, fixed cost of each order o, annual holding cost per unit product R, material supply lead time V.

[0010] Preferably, Q represents product quality, with a value of 1 representing qualified and 0 representing unqualified;

[0011] D represents the device status. A value of 1 indicates that the device is in good condition, and a value of 0 indicates that the device has a potential fault. The device status can be determined based on the device's operating data, such as whether the device's temperature, vibration and other parameters are within the normal range. If all parameters of the device are normal, the value is 1; if abnormal parameters are detected, indicating that a fault may occur, the value is 0;

[0012] M represents the quality of raw materials, which is a discrete variable with three values: 1 for high quality, 0.5 for qualified, and 0 for poor quality. The quality of raw materials is determined by the quality indicators of raw materials. For example, for copper clad boards in PCB production, if the thickness and flatness of the copper foil meet the standards, it can be judged as high quality with a value of 1; if some indicators meet the requirements, it is judged as qualified with a value of 0.5; if there are obvious defects, it is judged as poor quality with a value of 0;

[0013] N represents the production process parameters, which is a discrete variable. A value of 1 indicates that all production process parameters are within the standard range, and a value of 0 indicates that a production process parameter exceeds the range. The production process parameters include various set parameters in the production process such as temperature, pressure, and processing time. For example, in the etching process of PCB, the temperature of the etching solution needs to be controlled within a certain range. If the actual temperature is within this range, the value is 1; if it exceeds the range, the value is 0.

[0014] Preferably, the equipment comprehensive performance evaluation model is as follows:

[0015] ,in refers to the value of the equipment comprehensive performance evaluation model, T refers to the equipment normal operation time, T f refers to the equipment failure time, P refers to the number of products that meet the equipment processing accuracy standards, and P f Refers to the number of products whose processing accuracy does not meet the standards, E refers to the theoretical production efficiency of the equipment, and E f Refers to the actual production efficiency loss of the equipment.

[0016] Preferably, the production quality prediction model is as follows:

[0017] ,in Refers to the posterior probability that the product quality is qualified. It refers to the joint probability of equipment status, raw material quality and production process parameters when the product quality is 1. Refers to the prior probability that the product quality is qualified. Refers to the joint probability of equipment status, raw material quality and production process parameters.

[0018] Preferably, the production schedule optimization model is as follows:

[0019] = ;

[0020] ;

[0021] ;

[0022] where μ j refers to the average service rate, λ j refers to the average arrival rate, W j Refers to the sum of average waiting time and service time. It refers to the average number of work-in-progress, and j refers to the jth process of the production line.

[0023] Preferably, the material inventory control model is as follows:

[0024] = ;

[0025] 1.645 ;

[0026] B +SS;

[0027] in, Refers to economic order quantity, Refers to safety stock, refers to the reorder point, B refers to the annual demand, o refers to the fixed cost of each order, R refers to the annual holding cost per unit product, and V refers to the material supply lead time. Refers to the standard deviation of annual demand for raw materials.

[0028] Preferably, the method for controlling and judging the PCB production line is as follows:

[0029] Accurately determine the equipment performance level based on the XN value: Set a threshold to accurately distinguish the performance level. When XN≥0.9, the equipment has excellent overall performance, stable operation, high precision and good efficiency; when 0.9>XN≥0.8, the performance is medium, and it is necessary to pay attention to the fluctuation of key indicators and pre-diagnose potential risks; when 0.8>XN, the performance is poor, and in-depth maintenance, optimization and upgrading or replacement of key components are required to ensure smooth production, stable quality and controllable costs;

[0030] Real-time collection of new production data into the production quality prediction model calculation: In the new production task, real-time monitoring to obtain the actual values ​​of D, M, and N, substitute into the production quality prediction model calculation, if If it is greater than 0.5, the product is predicted to be qualified; otherwise, it is predicted to be unqualified.

[0031] based on The value evaluates the backlog of process tasks. If the value is greater than the industry average, it means that the backlog of the j process task of the production line is high and needs to be adjusted. The goal is to minimize the value of the process, use process re-arrangement, equipment increase and decrease, parallel process design, and intelligent scheduling algorithms to optimize the process. The value dropped below the industry average, proving that the optimization was effective, production efficiency was improved, costs were reduced, competitiveness was enhanced, and continuous monitoring of the process Value, when When it is greater than 0.8, it warns of congestion, and measures such as equipment upgrades, optimized production scheduling, process innovation, or adding buffer links are needed to resolve congestion and ensure smooth and balanced production;

[0032] Calculate the economic order quantity to determine the purchase scale. Enterprises can purchase in batches based on this, which can balance the contradiction between frequent ordering and increased costs and inventory backlogs occupying funds, and achieve optimal cost control. Replenishment decisions are triggered based on the reorder point. The inventory monitoring system monitors inventory in real time, and the inventory is reduced to The order process is automatically triggered when the purchase quantity is .

[0033] Preferably, the user information terminal is a control judgment information output device for receiving the control judgment step of the PCB production line, including a smart phone, a tablet, a computer and other devices that can remotely realize remote communication.

[0034] Preferably, an intelligent control system for an intelligent PCB production line in an unmanned workshop comprises: a system central processing unit module, a system operation database and a user information terminal, a PCB production line information text collection module, a data standardization processing module, a PCB production information processing center, a PCB production line control judgment module and an interactive feedback module;

[0035] The system operation database includes all data texts of an intelligent control system for an intelligent PCB production line in an unmanned workshop, and collects information texts output by each module in real time. The system central processor module is used to centrally control the information text instructions output by each module, and the user information terminal is an information output device for receiving an intelligent control system for an intelligent PCB production line in an unmanned workshop;

[0036] PCB production line information text collection module: including equipment status information collection unit, production parameter information collection unit, environment information collection unit, material information collection unit and production rhythm information collection unit, used to number the production lines and record them as 1, 2, 3...i...n in sequence, filter PCB feature texts according to different production lines, and obtain PCB feature text data;

[0037] Data standardization processing module: used to perform outlier deletion, missing value filling and standardization processing analysis on the PCB feature text data to obtain the second PCB feature text;

[0038] PCB production information processing center: used to import the second PCB feature text data into the equipment comprehensive performance evaluation model, production quality prediction model, production schedule optimization model and material inventory control model for processing and analysis, and obtain a text output value based on the second PCB feature text;

[0039] PCB production line control judgment module: control and judge the PCB production line based on text output values;

[0040] Interactive feedback module: used to feed back the judgment results and control results of the PCB production line control judgment to the user information terminal.

[0041] Technical effects and advantages of the present invention:

[0042] 1. The present invention is based on a production schedule optimization model constructed based on discrete event simulation and reinforcement learning algorithms, which accurately simulates the process logic and resource competition relationship of PCB production processes, takes the shortest order delivery period, the lowest equipment idle rate, and the best production cost as the composite objective function, and learns and optimizes process sequencing, equipment management, and inventory management strategies in real time;

[0043] 2. The present invention constructs a mathematical model through big data analysis and machine learning algorithms, accurately quantifies the real-time health status of the equipment and the inventory level status, and presents them in an intuitive numerical form, thereby realizing full-cycle digital management of PCB production equipment and inventory levels. At the same time, the production quality of the product is predicted in real time through a production quality prediction model, thereby improving product yield and quality consistency. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic diagram of the overall structure of the present invention.

[0045] Figure 2 It is a schematic diagram of the intelligent control structure of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] As attached Figure 1 The intelligent control method of an intelligent PCB production line in an unmanned workshop shown includes:

[0048] S1: PCB production line information text collection: including equipment status information collection steps, production parameter information collection steps, environment information collection steps, material information collection steps and production rhythm information collection steps, which are used to number the production lines and record them as 1, 2, 3...i...n in sequence, and filter PCB feature texts according to different production lines to obtain PCB feature text data;

[0049] The specific PCB key texts in the PCB production line information text mining step in the preferred technical solution of this application are as follows:

[0050] It should be specifically explained in this embodiment that the PCB feature text specifically refers to: the normal operation time of the equipment T, the failure time of the equipment T f, the number of products whose processing accuracy meets the standard P, the number of products whose processing accuracy does not meet the standard P f , Equipment theoretical production efficiency E, Equipment actual production efficiency loss E f , product quality Q, equipment status D, raw material quality M, production process N, average service rate μ j , average arrival rate λ j , the sum of the average waiting time and service time W j , annual demand B, fixed cost of each order o, annual holding cost per unit product R, material supply lead time V;

[0051] It should be specifically explained in this embodiment that Q represents product quality, with a value of 1 representing qualified and 0 representing unqualified;

[0052] D represents the device status. A value of 1 indicates that the device is in good condition, and a value of 0 indicates that the device has a potential fault. The device status can be determined based on the device's operating data, such as whether the device's temperature, vibration and other parameters are within the normal range. If all parameters of the device are normal, the value is 1; if abnormal parameters are detected, indicating that a fault may occur, the value is 0;

[0053] M represents the quality of raw materials, which is a discrete variable with three values: 1 for high quality, 0.5 for qualified, and 0 for poor quality. The quality of raw materials is determined by the quality indicators of raw materials. For example, for copper clad boards in PCB production, if the thickness and flatness of the copper foil meet the standards, it can be judged as high quality with a value of 1; if some indicators meet the requirements, it is judged as qualified with a value of 0.5; if there are obvious defects, it is judged as poor quality with a value of 0;

[0054] N represents the production process parameters, which is a discrete variable. A value of 1 indicates that all production process parameters are within the standard range, and a value of 0 indicates that a production process parameter exceeds the range. The production process parameters include various set parameters in the production process such as temperature, pressure, and processing time. For example, in the etching process of PCB, the temperature of the etching solution needs to be controlled within a certain range. If the actual temperature is within this range, the value is 1; if it exceeds the range, the value is 0.

[0055] S2: Data standardization processing: used to perform outlier deletion, missing value filling and standardization processing analysis on the PCB feature text data to obtain the second PCB feature text;

[0056] S3: PCB production information processing: used to import the second PCB feature text data into the equipment comprehensive performance evaluation model, the production quality prediction model, the production schedule optimization model and the material inventory control model for processing and analysis, and obtain a text output value based on the second PCB feature text;

[0057] It should be specifically explained in this embodiment that the text output value includes the value of the equipment comprehensive performance evaluation model, the value of the production quality prediction model, the value of the production schedule optimization model and the value of the material inventory control model;

[0058] It should be specifically explained in this embodiment that the equipment comprehensive performance evaluation model is as follows:

[0059] ,in refers to the value of the equipment comprehensive performance evaluation model, T refers to the equipment normal operation time, T f refers to the equipment failure time, P refers to the number of products that meet the equipment processing accuracy standards, and P f Refers to the number of products whose processing accuracy does not meet the standards, E refers to the theoretical production efficiency of the equipment, and E f Refers to the actual production efficiency loss of the equipment;

[0060] It should be specifically explained in this embodiment that the production quality prediction model is as follows:

[0061] ,in Refers to the posterior probability that the product quality is qualified. It refers to the joint probability of equipment status, raw material quality and production process parameters when the product quality is 1. Refers to the prior probability that the product quality is qualified. Refers to the joint probability of equipment status, raw material quality and production process parameters;

[0062] What needs to be specifically explained in this embodiment is that in the production quality prediction model The value of is obtained by evaluating the new production situation. Assuming that the new production situation , then the production quality prediction model is , so this embodiment does not make specific limitations;

[0063] It should be specifically explained in this embodiment that the production schedule optimization model is as follows:

[0064] = ;

[0065] ;

[0066] ;

[0067] where μ j refers to the average service rate, λ j refers to the average arrival rate, W j Refers to the sum of average waiting time and service time. refers to the average number of work-in-progress, and j refers to the jth process of the production line;

[0068] It should be specifically explained in this embodiment that the material inventory control model is as follows:

[0069] = ;

[0070] 1.645 ;

[0071] B +SS;

[0072] in, Refers to economic order quantity, Refers to safety stock, refers to the reorder point, B refers to the annual demand, o refers to the fixed cost of each order, R refers to the annual holding cost per unit product, and V refers to the material supply lead time. Refers to the standard deviation of annual demand for raw materials;

[0073] S4: PCB production line control judgment: control judgment of PCB production line based on text output value;

[0074] What needs to be specifically explained in this embodiment is that the method for controlling and judging the PCB production line is as follows:

[0075] Accurately determine the equipment performance level based on the XN value: Set a threshold to accurately distinguish the performance level. When XN≥0.9, the equipment has excellent overall performance, stable operation, high precision and good efficiency; when 0.9>XN≥0.8, the performance is medium, and it is necessary to pay attention to the fluctuation of key indicators and pre-diagnose potential risks; when 0.8>XN, the performance is poor, and in-depth maintenance, optimization and upgrading or replacement of key components are required to ensure smooth production, stable quality and controllable costs;

[0076] Real-time collection of new production data into the production quality prediction model calculation: In the new production task, real-time monitoring to obtain the actual values ​​of D, M, and N, substitute into the production quality prediction model calculation, if If it is greater than 0.5, the product is predicted to be qualified; otherwise, it is predicted to be unqualified.

[0077] based on The value evaluates the backlog of process tasks. If the value is greater than the industry average, it means that the backlog of the j process task of the production line is high and needs to be adjusted. The goal is to minimize the value of the process, use process re-arrangement, equipment increase and decrease, parallel process design, and intelligent scheduling algorithms to optimize the process. The value dropped below the industry average, proving that the optimization was effective, production efficiency was improved, costs were reduced, competitiveness was enhanced, and continuous monitoring of the process Value, when When it is greater than 0.8, it warns of congestion, and measures such as equipment upgrades, optimized production scheduling, process innovation, or adding buffer links are needed to resolve congestion and ensure smooth and balanced production;

[0078] Calculate the economic order quantity to determine the purchase scale. Enterprises can purchase in batches based on this, which can balance the contradiction between frequent ordering and increased costs and inventory backlogs occupying funds, and achieve optimal cost control. Replenishment decisions are triggered based on the reorder point. The inventory monitoring system monitors inventory in real time, and the inventory is reduced to The order process is automatically triggered when the purchase quantity is ;

[0079] S5: Feedback of PCB production line control judgment result: Feedback of the judgment result and control result of the PCB production line control judgment to the user information terminal;

[0080] It should be specifically explained in this embodiment that the user information terminal is a control judgment information output device that receives the control judgment step of the PCB production line, including a smart phone, a tablet, a computer and other devices that can remotely realize remote communication;

[0081] As attached Figure 2 The intelligent control system of an intelligent PCB production line in an unmanned workshop shown includes: a system central processor module, a system operation database and a user information terminal, a PCB production line information text collection module, a data standardization processing module, a PCB production information processing center, a PCB production line control judgment module and an interactive feedback module;

[0082] The system operation database includes all data texts of an intelligent control system for an intelligent PCB production line in an unmanned workshop, and collects information texts output by each module in real time. The system central processor module is used to centrally control the information text instructions output by each module, and the user information terminal is an information output device for receiving an intelligent control system for an intelligent PCB production line in an unmanned workshop;

[0083] PCB production line information text collection module: including equipment status information collection unit, production parameter information collection unit, environment information collection unit, material information collection unit and production rhythm information collection unit, used to number the production lines and record them as 1, 2, 3...i...n in sequence, filter PCB feature texts according to different production lines, and obtain PCB feature text data;

[0084] Data standardization processing module: used to perform outlier deletion, missing value filling and standardization processing analysis on the PCB feature text data to obtain the second PCB feature text;

[0085] PCB production information processing center: used to import the second PCB feature text data into the equipment comprehensive performance evaluation model, production quality prediction model, production schedule optimization model and material inventory control model for processing and analysis, and obtain a text output value based on the second PCB feature text;

[0086] PCB production line control judgment module: control and judge the PCB production line based on text output values;

[0087] Interactive feedback module: used to feed back the judgment results and control results of the PCB production line control judgment to the user information terminal.

[0088] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0089] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent control method for an intelligent PCB production line in an unmanned workshop, characterized in that: include: S1: PCB production line information text collection: including equipment status information collection steps, production parameter information collection steps, environment information collection steps, material information collection steps and production rhythm information collection steps, which are used to number the production lines and record them as 1, 2, 3...i...n in sequence, and filter PCB feature texts according to different production lines to obtain PCB feature text data; S2: Data standardization processing: used to perform outlier deletion, missing value filling and standardization processing analysis on the PCB feature text data to obtain the second PCB feature text; S3: PCB production information processing: used to import the second PCB feature text data into the equipment comprehensive performance evaluation model, the production quality prediction model, the production schedule optimization model and the material inventory control model for processing and analysis, and obtain a text output value based on the second PCB feature text; S4: PCB production line control judgment: control judgment of PCB production line based on text output value; S5: Feedback of PCB production line control judgment results: Feedback of the PCB production line control judgment judgment results and control results to the user information terminal.

2. According to claim 1, the intelligent control method for an intelligent PCB production line in an unmanned workshop is characterized in that: The PCB feature text specifically refers to: equipment normal operation time T, equipment failure time T f , the number of products whose processing accuracy meets the standard P, the number of products whose processing accuracy does not meet the standard P f , Equipment theoretical production efficiency E, Equipment actual production efficiency loss E f , product quality Q, equipment status D, raw material quality M, production process N, average service rate μ j , average arrival rate λ j , the sum of the average waiting time and service time W j , annual demand B, fixed cost of each order o, annual holding cost per unit product R, material supply lead time V.

3. According to claim 1, the intelligent control method for an intelligent PCB production line in an unmanned workshop is characterized in that: The equipment comprehensive performance evaluation model is as follows: ,in refers to the value of the equipment comprehensive performance evaluation model, T refers to the equipment normal operation time, T f refers to the equipment failure time, P refers to the number of products that meet the equipment processing accuracy standards, P f Refers to the number of products whose processing accuracy does not meet the standards, E refers to the theoretical production efficiency of the equipment, and E f Refers to the actual production efficiency loss of the equipment.

4. According to claim 1, the intelligent control method for an intelligent PCB production line in an unmanned workshop is characterized in that: The production quality prediction model is as follows: ,in Refers to the posterior probability that the product quality is qualified. It refers to the joint probability of equipment status, raw material quality and production process parameters when the product quality is 1. Refers to the prior probability that the product quality is qualified. Refers to the joint probability of equipment status, raw material quality and production process parameters.

5. According to claim 1, the intelligent control method for an intelligent PCB production line in an unmanned workshop is characterized in that: The production schedule optimization model is as follows: = ； ； ； where μ j refers to the average service rate, λ j refers to the average arrival rate, W j Refers to the sum of average waiting time and service time. It refers to the average number of work-in-progress, and j refers to the jth process of the production line.

6. According to claim 1, the intelligent control method for an intelligent PCB production line in an unmanned workshop is characterized in that: The material inventory control model is as follows: = ； 1.645 ； B +SS; in, Refers to economic order quantity, Refers to safety stock, refers to the reorder point, B refers to the annual demand, o refers to the fixed cost of each order, R refers to the annual holding cost per unit product, and V refers to the material supply lead time. Refers to the standard deviation of annual demand for raw materials.

7. According to claim 1, the intelligent control method for an intelligent PCB production line in an unmanned workshop is characterized in that: The specific methods for controlling and judging the PCB production line are as follows: Accurately determine the equipment performance level based on the XN value: Set a threshold to accurately distinguish the performance level. When XN≥0.9, the equipment has excellent overall performance, stable operation, high accuracy and good efficiency; when 0.9>XN≥0.8, the performance is medium, and it is necessary to pay attention to the fluctuation of key indicators and pre-diagnose potential risks; when 0.8>XN, the performance is poor; Real-time collection of new production data into the production quality prediction model calculation: In the new production task, real-time monitoring to obtain the actual values ​​of D, M, N, substitute into the production quality prediction model calculation, if If it is greater than 0.5, the product is predicted to be qualified; otherwise, it is predicted to be unqualified. The value evaluates the backlog of process tasks. If the value is greater than the industry average, it means that the backlog of the j process task of the production line is high and needs to be adjusted. The goal is to minimize the value of the process, use process re-arrangement, equipment increase and decrease, parallel process design, and intelligent scheduling algorithms to optimize the process. The value dropped below the industry average, proving that the optimization was effective, production efficiency was improved, costs were reduced, competitiveness was enhanced, and continuous monitoring of the process Value, when When it is greater than 0.8, it warns of congestion; Calculate the economic order quantity to determine the purchase scale. Enterprises can purchase in batches based on this, which can balance the contradiction between frequent ordering and increased costs and inventory backlogs occupying funds, and achieve optimal cost control. Replenishment decisions are triggered based on the reorder point. The inventory monitoring system monitors inventory in real time, and the inventory is reduced to The order process is automatically triggered when the purchase quantity is .

8. An intelligent control system for an intelligent PCB production line in an unmanned workshop, characterized in that: include: System central processor module, system operation database and user information terminal, PCB production line information text collection module, data standardization processing module, PCB production information processing center, PCB production line control judgment module and interactive feedback module; The system operation database includes all data texts of an intelligent control system for an intelligent PCB production line in an unmanned workshop, and collects information texts output by each module in real time. The system central processor module is used to centrally control the information text instructions output by each module, and the user information terminal is an information output device for receiving an intelligent control system for an intelligent PCB production line in an unmanned workshop; PCB production line information text collection module: including equipment status information collection unit, production parameter information collection unit, environment information collection unit, material information collection unit and production rhythm information collection unit, used to number the production lines and record them as 1, 2, 3...i...n in sequence, filter PCB feature texts according to different production lines, and obtain PCB feature text data; Data standardization processing module: used to perform outlier deletion, missing value filling and standardization processing analysis on the PCB feature text data to obtain the second PCB feature text; PCB production information processing center: used to import the second PCB feature text data into the equipment comprehensive performance evaluation model, production quality prediction model, production schedule optimization model and material inventory control model for processing and analysis, and obtain a text output value based on the second PCB feature text; PCB production line control judgment module: control and judge the PCB production line based on text output values; Interactive feedback module: used to feed back the judgment results and control results of the PCB production line control judgment to the user information terminal.

Images