Circuit board production management system and method

Abstract

The invention discloses a circuit board production management system and method, and relates to the technical field of circuit boards, and the method comprises the following steps: 1, a system receives a new order, analyzes the order through a deep learning model, predicts the production cycle and resource demands of the order, and automatically distributes production resources according to the priority and resource demands of the order; 2, the system predicts material consumption through a recurrent neural network, and automatically adjusts a material supplement plan according to the trend of the material consumption in the production process; 3, the system adopts a multi-objective genetic algorithm and a reinforcement learning model to carry out production scheduling optimization; 4, the system monitors product quality indexes in real time through a sensor and an image recognition technology; 5, based on feedback control module data, the system automatically adjusts resource configuration according to circuit board production real-time data, and the system performs real-time adjustment according to demand changes and equipment faults; and step 6, the system sets a self-learning cycle period, data update deep learning model and optimization algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of circuit boards, and in particular to a circuit board production management system and method. Background Art

[0002] With the continuous development of electronic products, circuit boards, as core electronic components, have become increasingly complex in the production of modern circuit boards in the face of customized needs and fierce market competition. However, with the advancement of information technology, the traditional circuit board production management system has the following shortcomings:

[0003] 1. Traditional production management systems usually rely on manual scheduling and fixed scheduling, and lack a flexible resource scheduling mechanism, which leads to low utilization of equipment and materials, and may cause equipment idleness, material waste, etc., and cannot efficiently match production needs;

[0004] 2. In the face of rapid changes in orders or emergencies, traditional systems often find it difficult to make timely adjustments. For example, when orders change or equipment fails, traditional methods usually take a long time to readjust production plans, resulting in reduced production efficiency;

[0005] 3. Traditional quality control mainly relies on manual inspection and static inspection models, which fail to achieve real-time and accurate quality monitoring. Once quality problems occur in the production process, they are usually discovered only after the product is completed, and the production process cannot be adjusted in time to prevent the spread of defects;

[0006] 4. Traditional production management systems lack the ability to adapt to changes in the production environment (such as equipment failures, raw material supply problems, etc.), and fail to achieve dynamic optimization and adjustment based on data analysis during the production process, resulting in the system being unable to respond effectively to actual conditions;

[0007] 5. Since traditional scheduling methods fail to comprehensively consider various complex constraints in the production process (such as equipment status, personnel arrangements, etc.), scheduling efficiency is low, which easily leads to production bottlenecks, production line shutdowns and other problems;

[0008] 6. Traditional production management systems often find it difficult to track and optimize the entire production process. Especially in large-scale production, it is difficult for managers to accurately grasp the status of each link, resulting in difficulty in maximizing the efficiency and quality of production management.

[0009] Therefore, in response to the above problems, a circuit board production management system is urgently needed to improve data processing efficiency, protect data privacy, and achieve more flexible system integration. Summary of the invention

[0010] The object of the present invention is to provide a circuit board production management system and method to solve the problems raised in the above background technology.

[0011] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0012] A circuit board production management system, including a data acquisition and analysis module, an intelligent scheduling and optimization module, a multi-layer quality monitoring module, a multiple feedback control module, a resource dynamic allocation and adaptive adjustment module and a self-learning and continuous optimization module;

[0013] The data collection and analysis module includes a deep learning model, which collects and analyzes multi-dimensional data on the consumption of circuit board production materials, equipment status, and order progress in real time based on the deep learning model;

[0014] The intelligent scheduling and optimization module: based on the data collection and analysis module, collects relevant circuit board data and comprehensively considers equipment utilization, order priority, and material usage, and automatically generates the optimal schedule through a multi-objective optimization algorithm;

[0015] The multi-layer quality monitoring module includes sensors and data acquisition equipment, through which a multi-layer circuit board production quality monitoring system is formed based on the intelligent scheduling and optimization module to achieve real-time monitoring of the size, electrical performance and surface quality of the circuit board;

[0016] The multiple feedback control module: combined with the circuit board quality monitoring module, realizes adaptive adjustment and abnormal situation processing of the circuit board production process;

[0017] The resource dynamic allocation and adaptive adjustment module is based on the feedback control module data, and the system automatically adjusts the resource configuration according to the real-time data of circuit board production;

[0018] The dynamic resource scheduling cycle and real-time optimization module: based on the real-time data of the resource dynamic allocation and adaptive adjustment module, real-time adjustment of material, equipment and human resource allocation is carried out to achieve efficient production.

[0019] A further improvement of the technical solution of the present invention is that the data collection and analysis module includes an order analysis and task allocation unit and a material loss intelligent prediction and adaptive replenishment unit. The order analysis and task allocation unit: after the system receives an order, it first analyzes the order demand through a deep learning model to predict the production cycle, resource requirements and potential bottlenecks of the order. The deep learning model specifically analyzes as follows:

[0020]

[0021] Where R i It is represented as the resource demand index of order i; P i Expressed as order priority; f(Q i) is a nonlinear function of the order quantity, which is used to characterize the resource impact of large-volume orders; T i Indicates the estimated production time; E i Expressed as equipment efficiency; δ i Represents a possible bottleneck for deep learning model prediction.

[0022] A further improvement of the technical solution of the present invention is that: the order analysis and task allocation unit: the system makes an intelligent prediction of material loss, combines historical loss data and environmental factors, and uses a recursive neural network model to predict the real-time consumption of materials. The loss prediction model is as follows:

[0023] L t =RNN(M t-1 ,X t ,θ)

[0024] Where L t is the predicted material loss at the current time t; M t-1 is the remaining amount of material at the previous moment; X t represents the current environmental conditions (temperature, humidity, material properties, etc.); θ represents the RNN model parameters, and M is set min It is the safety threshold of remaining materials. If the remaining materials are lower than the safety threshold, the system will start the adaptive replenishment mechanism, automatically adjust the replenishment amount and frequency, and issue a replenishment reminder.

[0025] A further improvement of the technical solution of the present invention is that: the intelligent scheduling and optimization module: performs intelligent scheduling based on a combination of a multi-objective genetic algorithm and reinforcement learning, with the specific goal of simultaneously optimizing order completion time, equipment utilization, and material consumption in the production process. The objective function is as follows:

[0026]

[0027]

[0028] Among them C i , S i Respectively represent the completion and start time of order i, W i Expressed as order weight; U j 、T j They are respectively represented as the usage time of device j and the total time of the device; R k Expressed as resource occupancy rate; G(Q k ) represents the material saving benefit.

[0029] The further improvement of the technical solution of the present invention is that the multi-layer quality monitoring module includes: embedded sensors and image recognition technology, which monitor product size, electrical characteristics and surface quality in real time through embedded sensors and image recognition technology. For each quality indicator, the system will set an adaptive dynamic threshold Q th

[0030] Q th =μ+σ·G(Q v )

[0031] Where Q th It is expressed as the adaptive quality threshold; μ is the mean value, σ is the standard deviation; G(Q v ) is expressed as a function of the relationship between production environment and quality deviation.

[0032] A further improvement of the technical solution of the present invention lies in: the multiple feedback control module: the system adopts a feedback control mechanism based on a deep Q network, adjusts production parameters according to real-time monitoring data, and continuously updates the production model to achieve quality stability and adaptive control. Through this feedback mechanism, the system can dynamically adjust the complex production environment and quickly adapt when production conditions change.

[0033] A further improvement of the technical solution of the present invention is that: the resource dynamic allocation and adaptive adjustment module: based on the feedback control module data, the system automatically adjusts the resource configuration according to the real-time data of circuit board production. During the production process, the system makes real-time adjustments according to demand changes and equipment failures.

[0034] A further improvement of the technical solution of the present invention is that the self-learning and continuous optimization module includes a learning cycle unit and an optimization unit. The learning cycle unit system sets a self-learning cycle period, and the system automatically performs the following steps in each cycle:

[0035] S1: Data update and model iteration: Update deep learning models and reinforcement learning strategies based on the latest data;

[0036] S2: Real-time schedule re-optimization: re-optimize the schedule based on the current equipment status, material inventory and order updates;

[0037] S3: Dynamic resource allocation: The system monitors resource status in real time and automatically adjusts resource allocation to respond to sudden orders or equipment failures;

[0038] S4: Feedback control and adaptive parameter adjustment: The system adjusts PID control parameters in real time according to production conditions to make the production process dynamically stable;

[0039] S5: Data storage and trend analysis: The system stores data in a database and analyzes production trends based on historical data for management to monitor at any time.

[0040] A further improvement of the technical solution of the present invention is that: the optimization unit of the self-learning and continuous optimization module: the system gradually optimizes the production process through a multi-dimensional feedback mechanism and realizes adaptive control of the production environment.

[0041] A further improvement of the technical solution of the present invention is: a circuit board production management method, used to implement a circuit board production management system as described in any one of claims 1 to 9, comprising the following steps:

[0042] Step 1: The system receives new orders and analyzes the demand, quantity, priority, etc. of the orders through deep learning models to predict the production cycle and resource requirements of the orders. Based on the order priority and resource requirements, the system automatically allocates production resources.

[0043] Step 2: At the same time, the system predicts material consumption through recursive neural networks (RNNs) and automatically adjusts the material replenishment plan according to the trend of material loss during the production process. When the remaining material is lower than the set safety threshold, the system automatically issues a replenishment reminder to ensure uninterrupted production;

[0044] Step 3: The system uses a multi-objective genetic algorithm and reinforcement learning model to optimize production scheduling, taking into account factors such as equipment utilization, order priority, and production time, to generate the optimal schedule and dynamically adjust the schedule to ensure that each link is completed efficiently in the shortest time;

[0045] Step 4: The system uses sensors and image recognition technology to monitor product quality indicators (such as size, electrical characteristics, surface quality, etc.) in real time. If it is detected that the product quality does not meet the standards, the system adjusts the production parameters through deep Q network feedback to ensure that the product quality meets the requirements;

[0046] Step 5: The system automatically adjusts resource allocation based on real-time data (such as equipment status, material usage, worker progress, etc.). During the production process, the system makes real-time adjustments based on demand changes and equipment failures to optimize resource usage and avoid production bottlenecks.

[0047] Step 6: The system sets a self-learning cycle and updates the deep learning model and optimization algorithm through real-time data to continuously improve the accuracy and efficiency of production scheduling, resource allocation and quality monitoring. The system gradually optimizes the production process through a multi-dimensional feedback mechanism and achieves adaptive control of the production environment.

[0048] Due to the adoption of the above technical solution, the present invention has the following technical advances compared with the prior art:

[0049] 1. The present invention provides an innovative circuit board production management system and method, which reduces production waiting time, improves equipment utilization, and saves production costs through intelligent optimization algorithms;

[0050] 2. A circuit board production management system and method provided by the present invention ensures that products meet high standards through the use of a multi-dimensional quality monitoring model, and makes real-time adjustments when they are unqualified;

[0051] 3. A circuit board production management system and method provided by the present invention, which automatically allocates materials and human resources based on deep learning prediction and real-time monitoring to reduce production interruptions;

[0052] 4. A circuit board production management system and method provided by the present invention realizes adaptive adjustment of complex conditions in the production process by combining the system with a deep Q network and PID control;

[0053] 5. The present invention provides a circuit board production management system and method. All production data of the system are recorded and analyzed in real time, supporting the management to fully control the production status and improve the efficiency of management decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0055] Figure 1 A flowchart of a circuit board production management system and method according to the present invention; DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0057] Examples, such as Figure 1 , a circuit board production management system, including a data acquisition and analysis module, an intelligent scheduling and optimization module, a multi-layer quality monitoring module, a multiple feedback control module, a resource dynamic allocation and adaptive adjustment module and a self-learning and continuous optimization module;

[0058] Data collection and analysis module: including deep learning models, which collect and analyze multi-dimensional data on circuit board production material consumption, equipment status, and order progress in real time based on deep learning models;

[0059] Intelligent scheduling and optimization module: Based on the data collection and analysis module, the relevant circuit board data is collected and the equipment utilization rate, order priority, and material usage are comprehensively considered, and the optimal schedule is automatically generated through a multi-objective optimization algorithm;

[0060] Multi-layer quality monitoring module: including sensors and data acquisition equipment, through which a multi-layer circuit board production quality monitoring system is formed based on intelligent scheduling and optimization modules, realizing real-time monitoring of the size, electrical performance and surface quality of the circuit board;

[0061] Multiple feedback control module: combined with the circuit board quality monitoring module, it can realize adaptive adjustment and abnormal situation handling of the circuit board production process;

[0062] Dynamic resource allocation and adaptive adjustment module: Based on the data from the feedback control module, the system automatically adjusts resource configuration according to the real-time data of circuit board production;

[0063] Dynamic resource scheduling cycle and real-time optimization module: Based on the real-time data of the resource dynamic allocation and adaptive adjustment module, the allocation of materials, equipment and human resources is adjusted in real time to achieve efficient production.

[0064] Specifically, the data collection and analysis module includes an order analysis and task allocation unit and a material loss intelligent prediction and adaptive replenishment unit. The order analysis and task allocation unit: After the system receives an order, it first analyzes the order demand through a deep learning model to predict the order's production cycle, resource requirements, and potential bottlenecks. The deep learning model specifically analyzes the following:

[0065]

[0066] Where R i It is represented as the resource demand index of order i; P i Expressed as order priority; f(Q i ) is a nonlinear function of the order quantity, which is used to characterize the resource impact of large-volume orders; T i Indicates the estimated production time; E i Expressed as equipment efficiency; δ i Represents a possible bottleneck for deep learning model prediction.

[0067] Through deep learning to predict resource demand, the system calculates the resource demand index R of the order. i Sorting, allocating resources first based on the orders with high priority, and dynamically adjusting the priority using fuzzy logic algorithm.

[0068] Specifically, the order analysis and task allocation unit: The system makes intelligent predictions on material loss, combines historical loss data and environmental factors, and uses a recursive neural network model to predict the real-time consumption of materials. The loss prediction model is as follows:

[0069] L t =RNN(M t-1 ,X t ,θ)

[0070] Where L t is the predicted material loss at the current time t; M t-1 is the remaining amount of material at the previous moment; X t represents the current environmental conditions (temperature, humidity, material properties, etc.); θ represents the RNN model parameters, and M is set min It is the safety threshold of remaining materials. If the remaining materials are lower than the safety threshold, the system will start the adaptive replenishment mechanism, automatically adjust the replenishment amount and frequency, and issue a replenishment reminder.

[0071] The system adopts a dual strategy: ensuring uninterrupted production through quantitative replenishment and dynamic inventory optimization.

[0072] Specifically, the intelligent scheduling and optimization module: intelligent scheduling is performed based on a combination of multi-objective genetic algorithm and reinforcement learning. The specific goal is to simultaneously optimize order completion time, equipment utilization, and material consumption in the production process. The objective function is as follows:

[0073]

[0074]

[0075] Among them C i , S i Respectively represent the completion and start time of order i, W i Expressed as order weight; U j , T j They are respectively represented as the usage time of device j and the total time of the device; R k Expressed as resource occupancy rate; G(Q k ) represents the material saving benefit.

[0076] Through the reinforcement learning model, the system dynamically updates scheduling parameters driven by real-time data, ensuring that the system always approaches the optimal solution in a dynamic environment.

[0077] Specifically, the multi-layer quality monitoring module includes: embedded sensors and image recognition technology, which monitor product size, electrical characteristics and surface quality in real time. For each quality indicator, the system will set an adaptive dynamic threshold Q th

[0078] Q th =μ+σ·G(Q v )

[0079] Where Q th It is expressed as the adaptive quality threshold; μ is the mean value, σ is the standard deviation; G(Q v ) is expressed as a function of the relationship between production environment and quality deviation.

[0080] Specifically, multiple feedback control modules: the system adopts a feedback control mechanism based on a deep Q network, adjusts production parameters according to real-time monitoring data, and continuously updates the production model to achieve quality stability and adaptive control. Through this feedback mechanism, the system can dynamically adjust to complex production environments and quickly adapt when production conditions change.

[0081] The system adopts a feedback control mechanism based on the deep Q network (DQN) to adjust production parameters according to real-time detection data and continuously update the production model to achieve quality stability and adaptive control. Through this feedback mechanism, the system can dynamically adjust to complex production environments and quickly adapt when production conditions change.

[0082] Specifically, the resource dynamic allocation and adaptive adjustment module: based on the feedback control module data, the system automatically adjusts the resource configuration according to the real-time data of circuit board production. During the production process, the system makes real-time adjustments based on demand changes and equipment failures.

[0083] Specifically, the self-learning and continuous optimization module includes a learning cycle unit and an optimization unit. The learning cycle unit system sets a self-learning cycle, and the system automatically performs the following steps in each cycle:

[0084] S1: Data update and model iteration: Update deep learning models and reinforcement learning strategies based on the latest data;

[0085] S2: Real-time schedule re-optimization: re-optimize the schedule based on the current equipment status, material inventory and order updates;

[0086] S3: Dynamic resource allocation: The system monitors resource status in real time and automatically adjusts resource allocation to respond to sudden orders or equipment failures;

[0087] S4: Feedback control and adaptive parameter adjustment: The system adjusts PID control parameters in real time according to production conditions to make the production process dynamically stable;

[0088] S5: Data storage and trend analysis: The system stores data in a database and analyzes production trends based on historical data for management to monitor at any time.

[0089] Specifically, the optimization unit of the self-learning and continuous optimization module: the system gradually optimizes the production process through a multi-dimensional feedback mechanism and realizes adaptive control of the production environment.

[0090] The system sets a self-learning cycle, updates the deep learning model and optimization algorithm through real-time data, and continuously improves the accuracy and efficiency of production scheduling, resource allocation and quality monitoring. Through this series of steps, the system can efficiently manage the production process, optimize resource allocation, improve production efficiency, reduce losses, and ensure the stability of product quality.

[0091] Specifically, a circuit board production management method is used to implement a circuit board production management system according to any one of claims 1 to 9, comprising the following steps:

[0092] Step 1: The system receives new orders and analyzes the demand, quantity, priority, etc. of the orders through deep learning models to predict the production cycle and resource requirements of the orders. Based on the order priority and resource requirements, the system automatically allocates production resources.

[0093] Step 2: At the same time, the system predicts material consumption through recursive neural networks (RNNs) and automatically adjusts the material replenishment plan according to the trend of material loss during the production process. When the remaining material is lower than the set safety threshold, the system automatically issues a replenishment reminder to ensure uninterrupted production;

[0094] Step 3: The system uses a multi-objective genetic algorithm and reinforcement learning model to optimize production scheduling, taking into account factors such as equipment utilization, order priority, and production time, to generate the optimal schedule and dynamically adjust the schedule to ensure that each link is completed efficiently in the shortest time;

[0095] Step 4: The system uses sensors and image recognition technology to monitor product quality indicators (such as size, electrical characteristics, surface quality, etc.) in real time. If it is detected that the product quality does not meet the standards, the system adjusts the production parameters through deep Q network feedback to ensure that the product quality meets the requirements;

[0096] Step 5: The system automatically adjusts resource allocation based on real-time data (such as equipment status, material usage, worker progress, etc.). During the production process, the system makes real-time adjustments based on demand changes and equipment failures to optimize resource usage and avoid production bottlenecks.

[0097] Step 6: The system sets a self-learning cycle and updates the deep learning model and optimization algorithm through real-time data to continuously improve the accuracy and efficiency of production scheduling, resource allocation and quality monitoring. The system gradually optimizes the production process through a multi-dimensional feedback mechanism and achieves adaptive control of the production environment.

[0098] How it works: The system receives new orders and uses a deep learning model to:

[0099]

[0100] Where R i It is represented as the resource demand index of order i; P i Expressed as order priority; f(Q i ) is a nonlinear function of the order quantity, which is used to characterize the resource impact of large-volume orders; T i Indicates the estimated production time; E i Expressed as equipment efficiency; δ i It is expressed as the possible bottleneck predicted by the deep learning model, analyzing the demand, quantity, priority, etc. of the order, predicting the production cycle and resource requirements of the order. According to the priority and resource requirements of the order, the system automatically allocates production resources; at the same time, the system predicts the material consumption through the recursive neural network (RNN), that is, the recursive neural network model predicts the real-time consumption of the material. The loss prediction model is as follows:

[0101] L t =RNN(M t-1 ,X t ,θ)

[0102] Where L t is the predicted material loss at the current time t; M t-1 is the remaining amount of material at the previous moment; X t represents the current environmental conditions (temperature, humidity, material properties, etc.); θ represents the RNN model parameters, and M is set min is the safety threshold of the remaining material. If the remaining material is lower than the safety threshold, the system will start the adaptive replenishment mechanism, automatically adjust the material replenishment amount and frequency, and issue a replenishment reminder to ensure that production is not interrupted. The system uses a multi-objective genetic algorithm and reinforcement learning model to optimize production scheduling, taking into account factors such as equipment utilization, order priority, and production time, to generate the optimal schedule, dynamically adjust the schedule, and ensure that each link is completed efficiently in the shortest time. The objective function is as follows:

[0103]

[0104]

[0105] Among them C i , Si Respectively represent the completion and start time of order i, W i Expressed as order weight;

[0106] U j , T j They are respectively represented as the usage time of device j and the total time of the device; R k Expressed as resource occupancy rate; G(Q k ) is expressed as material saving benefits; the system monitors the quality indicators of products (such as size, electrical characteristics, surface quality, etc.) in real time through sensors and image recognition technology. If it is detected that the product quality does not meet the standards, the system adjusts the production parameters through deep Q network feedback to ensure that the product quality meets the requirements. That is, the system will set an adaptive dynamic threshold Q th

[0107] Q th =μ+σ·G(Q v )

[0108] Where Q th It is expressed as the adaptive quality threshold; μ is the mean value, σ is the standard deviation; G(Q v ) is expressed as a function of the relationship between the production environment and the quality deviation. The system adopts a feedback control mechanism based on a deep Q network, adjusts production parameters according to real-time monitoring data, and continuously updates the production model to achieve quality stability and adaptive control. Through this feedback mechanism, the system can dynamically adjust the complex production environment and quickly adapt when production conditions change. The system automatically adjusts resource allocation according to real-time data (such as equipment status, material usage, worker progress, etc.). During the production process, the system makes real-time adjustments based on demand changes and equipment failures to optimize resource usage and avoid production bottlenecks. The system sets a self-learning cycle, updates deep learning models and optimization algorithms through real-time data, and continuously improves the accuracy and efficiency of production scheduling, resource allocation, and quality monitoring. The system gradually optimizes the production process through a multi-dimensional feedback mechanism and achieves adaptive control of the production environment.

[0109] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A circuit board production management system, characterized by: It includes data collection and analysis module, intelligent scheduling and optimization module, multi-layer quality monitoring module, multiple feedback control module, dynamic resource allocation and adaptive adjustment module and self-learning and continuous optimization module; The data collection and analysis module includes a deep learning model, which collects and analyzes multi-dimensional data on the consumption of circuit board production materials, equipment status, and order progress in real time based on the deep learning model; The intelligent scheduling and optimization module: based on the data collection and analysis module, collects relevant circuit board data and comprehensively considers equipment utilization, order priority, and material usage, and automatically generates the optimal schedule through a multi-objective optimization algorithm; The multi-layer quality monitoring module includes sensors and data acquisition equipment, through which a multi-layer circuit board production quality monitoring system is formed based on the intelligent scheduling and optimization module to achieve real-time monitoring of the size, electrical performance and surface quality of the circuit board; The multiple feedback control module: combined with the circuit board quality monitoring module, realizes adaptive adjustment and abnormal situation processing of the circuit board production process; The resource dynamic allocation and adaptive adjustment module is based on the feedback control module data, and the system automatically adjusts the resource configuration according to the real-time data of circuit board production; The dynamic resource scheduling cycle and real-time optimization module: based on the real-time data of the resource dynamic allocation and adaptive adjustment module, real-time adjustment of material, equipment and human resource allocation is carried out to achieve efficient production.

2. A circuit board production management system according to claim 1, characterized in that: The data collection and analysis module includes an order analysis and task allocation unit and a material loss intelligent prediction and adaptive replenishment unit. The order analysis and task allocation unit: after the system receives an order, it first analyzes the order demand through a deep learning model to predict the production cycle, resource requirements and potential bottlenecks of the order. The deep learning model specifically analyzes as follows: Where R i It is represented as the resource demand index of order i; P i Expressed as order priority; f(Q i ) is a nonlinear function of the order quantity, used to characterize the resource impact of large-volume orders; T i Indicates the estimated production time; E i Expressed as equipment efficiency; δ i Represents a possible bottleneck for deep learning model prediction.

3. A circuit board production management system according to claim 2, characterized in that: The order analysis and task allocation unit: The system makes intelligent predictions on material loss, combines historical loss data and environmental factors, and uses a recursive neural network model to predict the real-time consumption of materials. The loss prediction model is as follows: L t =RNN(M t-1 ,X t ,θ) Where L t is the predicted material loss at the current time t; M t-1 is the remaining amount of material at the previous moment; X t Represents the current environmental conditions (temperature, humidity, material properties, etc.); θ represents the RNN model parameter, and M is set min It is the safety threshold of remaining materials. If the remaining materials are lower than the safety threshold, the system will start the adaptive replenishment mechanism, automatically adjust the replenishment amount and frequency, and issue a replenishment reminder.

4. A circuit board production management system according to claim 1, characterized in that: The intelligent scheduling and optimization module: intelligent scheduling is performed based on a combination of multi-objective genetic algorithm and reinforcement learning. The specific goal is to optimize the order completion time, equipment utilization and material consumption in the production process at the same time. The objective function is as follows: Among them C i , S i Respectively represent the completion and start time of order i, W i Expressed as order weight; U j , T j They are respectively represented as the usage time of device j and the total time of the device; R k Expressed as resource occupancy rate; G(Q k ) represents the material saving benefit.

5. A circuit board production management system according to claim 1, characterized in that: The multi-layer quality monitoring module includes: embedded sensors and image recognition technology, which monitor product size, electrical characteristics and surface quality in real time. For each quality indicator, the system will set an adaptive dynamic threshold Q th Q th =μ+σ·G(Q v ) Where Q th It is expressed as the adaptive quality threshold; μ is the mean value, σ is the standard deviation; G(Q v ) is expressed as a function of the relationship between production environment and quality deviation.

6. A circuit board production management system according to claim 1, characterized in that: The multiple feedback control module: The system adopts a feedback control mechanism based on a deep Q network to adjust production parameters according to real-time detection data and continuously update the production model to achieve quality stability and adaptive control. Through this feedback mechanism, the system can dynamically adjust to complex production environments and quickly adapt when production conditions change.

7. A circuit board production management system according to claim 1, characterized in that: The resource dynamic allocation and adaptive adjustment module: based on the feedback control module data, the system automatically adjusts the resource configuration according to the real-time data of circuit board production. During the production process, the system makes real-time adjustments according to demand changes and equipment failures.

8. A circuit board production management system according to claim 1, characterized in that: The self-learning and continuous optimization module includes a learning cycle unit and an optimization unit. The learning cycle unit system sets a self-learning cycle period, and the system automatically performs the following steps in each cycle: S1: Data update and model iteration: Update deep learning models and reinforcement learning strategies based on the latest data; S2: Real-time schedule re-optimization: re-optimize the schedule based on the current equipment status, material inventory and order updates; S3: Dynamic resource allocation: The system monitors resource status in real time and automatically adjusts resource allocation to respond to sudden orders or equipment failures; S4: Feedback control and adaptive parameter adjustment: The system adjusts PID control parameters in real time according to production conditions to make the production process dynamically stable; S5: Data storage and trend analysis: The system stores data in a database and analyzes production trends based on historical data for management to monitor at any time.

9. A circuit board production management system according to claim 1, characterized in that: The optimization unit of the self-learning and continuous optimization module: the system gradually optimizes the production process through a multi-dimensional feedback mechanism and realizes adaptive control of the production environment.

10. A circuit board production management method, used to implement a circuit board production management system according to any one of claims 1 to 9, comprising the following steps: Step 1: The system receives new orders and analyzes the demand, quantity, priority, etc. of the orders through deep learning models to predict the production cycle and resource requirements of the orders. Based on the order priority and resource requirements, the system automatically allocates production resources. Step 2: At the same time, the system predicts material consumption through recursive neural networks (RNNs) and automatically adjusts the material replenishment plan according to the trend of material loss during the production process. When the remaining material is lower than the set safety threshold, the system automatically issues a replenishment reminder to ensure uninterrupted production; Step 3: The system uses a multi-objective genetic algorithm and reinforcement learning model to optimize production scheduling, taking into account factors such as equipment utilization, order priority, and production time, to generate the optimal schedule and dynamically adjust the schedule to ensure that each link is completed efficiently in the shortest time; Step 4: The system uses sensors and image recognition technology to monitor product quality indicators in real time. If it detects that the product quality does not meet the standards, the system adjusts the production parameters through deep Q network feedback to ensure that the product quality meets the requirements; Step 5: Based on the data from the feedback control module, the system automatically adjusts resource allocation according to the real-time data of circuit board production. During the production process, the system makes real-time adjustments based on demand changes and equipment failures to optimize resource usage and avoid production bottlenecks. Step 6: The system sets a self-learning cycle and updates the deep learning model and optimization algorithm through real-time data to continuously improve the accuracy and efficiency of production scheduling, resource allocation and quality monitoring. The system gradually optimizes the production process through a multi-dimensional feedback mechanism and achieves adaptive control of the production environment.

Images