Enameled wire capacity assisted distribution method and system and storage medium

Abstract

The invention discloses an enameled wire capacity assisted distribution method and system and a storage medium, and relates to the technical field of enameled wire capacity assisted distribution, and the method comprises the steps: collecting real-time production data of each production line through an Internet of Things sensor, and sharing the real-time production data through a block chain platform; through real-time production data, combining historical production data of each production line, and utilizing a deep learning algorithm to predict a production demand; based on the prediction result of the production demand, performing preliminary productivity distribution according to the real-time production data of each production line; through the real-time connection between the intelligent adjustment model based on the deep reinforcement learning algorithm and the block chain platform, the actual operation condition of the production line is continuously monitored, and the capacity distribution is adjusted in real time; by means of the deep reinforcement learning model, continuous monitoring and real-time capacity distribution adjustment are carried out, the production efficiency and the resource utilization rate are effectively improved, and intelligent scheduling and optimization of the production process are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of enameled wire capacity assisted allocation, and in particular to an enameled wire capacity assisted allocation method, system and storage medium. Background Art

[0002] With the continuous advancement of industrial automation, intelligent production management has become one of the keys to improving corporate competitiveness. Especially in the manufacturing industry, the production process of enameled wire requires strict capacity management to ensure stable production efficiency and product quality. However, traditional enameled wire production management methods often rely on manual adjustments and fixed production plans. This method not only has a lag in response, but also easily causes uneven resource allocation and unbalanced production line load, thus affecting overall production efficiency.

[0003] The current capacity allocation assistance method mainly relies on fixed production plans and manual intervention. The response to emergencies such as equipment failure and raw material shortages in the production process is not fast enough. Furthermore, the existing capacity allocation method cannot effectively combine the dynamic load conditions of different production lines in actual operations, which often makes the capacity allocation lack of real-time and flexibility. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an enameled wire capacity assisting allocation method, which solves the problems of production line load balancing and real-time adjustment during enameled wire capacity assisting allocation.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for assisting in allocating enameled wire production capacity, which comprises:

[0008] Use IoT sensors to collect real-time production data from each production line and share it through the blockchain platform;

[0009] Through real-time production data, combined with historical production data of each production line, deep learning algorithms are used to predict production demand;

[0010] Based on the forecast results of production demand, preliminary capacity allocation is carried out according to the real-time production data of each production line;

[0011] Through the real-time connection between the intelligent adjustment model based on deep reinforcement learning algorithm and the blockchain platform, the actual operation of the production line can be continuously monitored and the capacity allocation can be adjusted in real time.

[0012] As a preferred solution of the method for assisting in allocating the capacity of enameled wires of the present invention, the method uses the IoT sensor to collect the real-time production data of each production line. The specific steps are as follows:

[0013] Deploy IoT sensors on each enameled wire production line to collect real-time production data of each production line;

[0014] Real-time production data is transmitted to the blockchain platform via wireless communication protocols.

[0015] As a preferred solution of the method for assisting in allocating the capacity of enameled wires of the present invention, the specific steps of sharing through the blockchain platform are as follows:

[0016] On the blockchain platform, hash processing is performed through a cryptographic hash algorithm, and the production data of each production line is packaged into a block;

[0017] The blockchain platform uses a consensus mechanism to verify the newly added blocks;

[0018] After all participating nodes of the blockchain platform verify the newly added blocks, the validity of the newly added blocks is confirmed;

[0019] The hash value of the newly added block is encrypted and linked to the hash value of the previous block to form a blockchain;

[0020] All participating nodes share real-time production data of all production lines through the blockchain platform.

[0021] As a preferred solution of the enameled wire production capacity assistance allocation method of the present invention, the production demand is predicted by using a deep learning algorithm through real-time production data combined with historical production data of each production line. The specific steps are as follows:

[0022] Based on the blockchain platform, obtain historical and real-time production data of each production line;

[0023] Align the historical and real-time production data of each production line according to the collection timestamp. For production data with missing timestamps, generate corresponding timestamps based on the production line log information and equipment operation records.

[0024] Using the sliding window method, the historical and real-time production data of each production line are divided into several time series training samples according to the time window size;

[0025] Divide the time series training samples into training set, validation set and test set;

[0026] Based on LSTM, build a production demand forecasting model;

[0027] The training set is input into the production demand forecasting model for training, the training set is processed through the gate control structure (such as forget gate, input gate, output gate), and the production demand forecast result is output;

[0028] After each training batch, the mean square error is calculated;

[0029] The Adam optimizer is used to adjust the learning rate of the production demand forecasting model;

[0030] After each training batch, the prediction performance of the production demand forecasting model is verified using the validation set;

[0031] When the production demand forecasting model completes the training of all time series training samples in the training set, it inputs the test set;

[0032] The performance of the production demand forecasting model is evaluated by calculating the mean square error and determination coefficient of the test set in the production demand forecasting model.

[0033] By setting different hyperparameter configurations, several production demand forecasting models are trained to obtain different production demand forecasting results;

[0034] By introducing an integrated algorithm, the production demand forecast results of several production demand forecasting models are integrated to obtain the final production demand forecast result.

[0035] As a preferred solution of the enameled wire capacity assisting allocation method of the present invention, wherein: the production demand prediction results of several production demand prediction models are integrated by introducing an integrated algorithm to obtain the final production demand prediction result. The specific steps are as follows:

[0036] Input the time series training samples into several production demand forecasting models with different hyperparameter configurations that have completed training, and record the production demand forecasting results output by different production demand forecasting models;

[0037] According to the mean square error of different production demand forecasting models on the test set (the smaller the mean square error value, the greater the weight), the weight of each production demand forecast result is preset;

[0038] All production demand forecast results are integrated through weighted voting.

[0039] As a preferred solution of the enameled wire capacity assisting allocation method of the present invention, wherein: the prediction result based on production demand is used to perform preliminary capacity allocation according to the real-time production data of each production line, and the specific steps are as follows:

[0040] According to the final production demand forecast result, the enameled wire production demand (for example, the enameled wire production demand in the next day) is obtained;

[0041] Based on the real-time production data of the blockchain platform, the actual production capacity of each production line can be obtained;

[0042] Calculate the capacity difference between the actual capacity and the maximum capacity of each production line. When the actual capacity of the production line is less than the maximum capacity, allocate the capacity according to the capacity difference.

[0043] When the actual capacity of a production line is not less than the maximum capacity, it means that the production line cannot allocate additional capacity.

[0044] As a preferred solution of the method for assisting in allocating the capacity of enameled wires of the present invention, the intelligent adjustment model based on the deep reinforcement learning algorithm is connected to the blockchain platform in real time to continuously monitor the actual operation of the production line and adjust the capacity allocation in real time. The specific steps are as follows:

[0045] Build an intelligent adjustment model based on deep Q network;

[0046] Obtain real-time production data of each production line through the blockchain platform and use it as the state space;

[0047] The capacity of each production line will be dynamically adjusted according to the forecast results of production demand. When the load of the production line is too large or too small, the speed or load of the production line will be adjusted as a decision space;

[0048] According to the matching degree between capacity allocation and production demand forecast results, the reward function is set, and the expression is:

[0049]

[0050] Among them, R is the reward function, P1 is the actual production capacity, P2 is the production demand forecast result, and P3 is the allocated capacity;

[0051] The state space is input into the intelligent adjustment model for simulation training. According to the state space, the intelligent adjustment model makes a series of decisions in the decision space;

[0052] For each decision, calculate the reward function, evaluate the decision effect, and optimize the decision space based on the calculation result of the reward function;

[0053] During the training process, the intelligent adjustment model simulates high-load production line scenarios, equipment failure scenarios, and production bottleneck scenarios, interacts with multiple production scenarios, and further optimizes the decision space;

[0054] According to the changing trend of the reward function, draw a reward value change curve. When the reward value change curve tends to be stable, it is considered that the intelligent adjustment model training is completed;

[0055] Through the completed intelligent adjustment model, decisions are output based on real-time production data from the blockchain platform to adjust the initial capacity allocation.

[0056] After the capacity allocation is adjusted, continue to monitor the real-time production data of the production line and make real-time adjustments to the capacity allocation based on the real-time situation;

[0057] Regularly evaluate the effectiveness of capacity allocation and retrain the intelligent adjustment model based on the evaluation results.

[0058] In a second aspect, the present invention provides an enameled wire capacity assistance allocation system, including a data sharing module, a demand forecasting module, a capacity allocation module and a real-time adjustment module.

[0059] The data sharing module is used to collect real-time production data of each production line using IoT sensors and share it through the blockchain platform;

[0060] The demand forecasting module is used to forecast production demand by using real-time production data combined with historical production data of each production line and using a deep learning algorithm;

[0061] The capacity allocation module is used to perform preliminary capacity allocation based on the real-time production data of each production line based on the forecast results of production demand;

[0062] The real-time adjustment module is used to continuously monitor the actual operation of the production line and adjust the capacity allocation in real time through real-time connection between the intelligent adjustment model based on the deep reinforcement learning algorithm and the blockchain platform.

[0063] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method for assisting in allocating the capacity of enameled wire as described in the first aspect of the present invention is implemented.

[0064] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the method for assisting in allocating the capacity of enameled wire as described in the first aspect of the present invention is implemented.

[0065] The beneficial effects of the present invention are as follows: the present invention collects production line data in real time through Internet of Things sensors, and uses the blockchain platform to ensure the secure sharing and non-tamperability of data, thereby improving the transparency and reliability of the production process. By combining historical data with real-time data, a deep learning algorithm is used to predict production demand, thereby improving the accuracy of demand forecasting and reducing production plan errors. Based on these prediction results, the system can dynamically adjust production capacity allocation, optimize the load between production lines, avoid resource waste and production bottlenecks, and enhance the stability and accuracy of the prediction by integrating the results of multiple prediction models. With the help of a deep reinforcement learning model, the production capacity allocation is continuously monitored and adjusted in real time, effectively improving production efficiency and resource utilization, and realizing intelligent scheduling and optimization of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0067] Figure 1 This is a flow chart of the method for assisting in allocating enameled wire production capacity in Example 1.

[0068] Figure 2 This is a module diagram of the enameled wire capacity assistance allocation system in Example 1. DETAILED DESCRIPTION

[0069] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0070] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0071] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0072] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides an enameled wire capacity assisting allocation method, comprising the following steps:

[0073] S1. Use IoT sensors to collect real-time production data from each production line and share it through the blockchain platform.

[0074] IoT sensors are deployed on each enameled wire production line to collect real-time production data of each production line, including equipment operation status (such as temperature, pressure, speed, etc.), production task progress (such as process completion time, production volume, etc.), raw material consumption, equipment failure and maintenance records;

[0075] Transmit real-time production data to the blockchain platform through low-latency, high-bandwidth wireless communication protocols (such as 5G and Wi-Fi 6);

[0076] On the blockchain platform, hashing is performed using a cryptographic hashing algorithm (such as SHA-256), and the production data of each production line is packaged into a block;

[0077] Among them, each block contains a block header and a block body;

[0078] The block header contains information such as timestamp, hash value of the previous block, hash value of the current block, etc. to ensure the order and integrity of the data;

[0079] The block contains detailed data of the production line, such as equipment status, production progress, quality inspection, fault information, etc.

[0080] The blockchain platform uses a consensus mechanism to verify the newly added blocks;

[0081] Specifically, each participating node in the blockchain platform checks whether the block data is legal, including checking whether the hash value of the block matches and whether the data is complete;

[0082] Use the Practical Byzantine Fault Tolerance (PBFT) algorithm to verify newly added blocks;

[0083] After all participating nodes of the blockchain platform (raw material nodes, production nodes, finished product nodes, etc.) verify the newly added blocks, the validity of the newly added blocks is confirmed;

[0084] The hash value of the newly added block is encrypted and linked to the hash value of the previous block to form a blockchain. The creation of each new block depends on the hash value of the previous block. This structure makes any tampering of the data of a block invalidate the entire chain.

[0085] All participating nodes share real-time production data of all production lines through the blockchain platform.

[0086] S2. Use real-time production data combined with historical production data of each production line to predict production demand using deep learning algorithms.

[0087] Based on the blockchain platform, obtain historical and real-time production data of each production line;

[0088] Align the historical and real-time production data of each production line according to the collection timestamp. For production data with missing timestamps, generate corresponding timestamps based on the production line log information and equipment operation records.

[0089] Using the sliding window method, the historical and real-time production data of each production line are divided into several time series training samples according to the time window size;

[0090] Specifically, when the timestamp of the input data is recorded on a daily basis and the demand is predicted for the next day, each input sequence contains the data of the past 7 days, which is used as the input of the LSTM model to predict the demand for the 8th day;

[0091] For complex production environments, the window size (e.g., 7 days) and prediction step size (e.g., 1 day) can be adjusted according to specific production needs;

[0092] The time series training samples are randomly divided into training set, validation set and test set;

[0093] Based on LSTM (Long Short-Term Memory Network), a production demand forecasting model is built;

[0094] The training set is input into the production demand forecasting model for training, the training set is processed through the gate control structure (such as forget gate, input gate, output gate), and the production demand forecast result is output;

[0095] After each training batch, the mean square error is calculated to measure the error between the generated demand forecast and the actual production demand;

[0096] In order to accelerate training and ensure convergence, the Adam optimizer is used to adjust the learning rate of the production demand forecasting model;

[0097] After each training batch, the prediction performance (such as loss value, determination coefficient, etc.) of the production demand forecasting model is verified using the validation set;

[0098] When the production demand forecasting model completes the training of all time series training samples in the training set, it inputs the test set;

[0099] The performance of the production demand forecasting model is evaluated by calculating the mean square error and determination coefficient of the test set in the production demand forecasting model.

[0100] Furthermore, by setting different hyperparameter configurations (such as the number of LSTM layers, learning rate, batch size, etc.), several production demand forecasting models are trained to obtain different production demand forecasting results;

[0101] It should be noted that the predicted value of all production demand should not be greater than the sum of the remaining capacity of all production lines. If it is greater than the sum of the remaining capacity of all production lines, it means that the production demand prediction result is wrong and the corresponding production demand prediction model should be retrained.

[0102] By introducing an integrated algorithm to fuse the production demand forecast results of several production demand forecast models, the final production demand forecast result is obtained;

[0103] Input the time series training samples into several production demand forecasting models with different hyperparameter configurations that have completed training, and record the production demand forecasting results output by different production demand forecasting models;

[0104] According to the mean square error of different production demand forecasting models on the test set (the smaller the mean square error value, the greater the weight), the weight of each production demand forecast result is preset, and the expression is as follows:

[0105]

[0106] Among them, ω i is the weight of the prediction result of the i-th production demand forecasting model, MSE i The mean square error of the i-th production demand forecasting model, n is the number of production demand forecasting models, and i is the index of the number of production demand forecasting models;

[0107] All production demand forecast results are integrated by weighted voting, and the expression is as follows:

[0108]

[0109] Among them, Y is the final production demand forecast result, y i is the prediction result of the i-th production demand prediction model;

[0110] It should be noted that when the prediction results of a single LSTM model may be affected by noise or specific data patterns, integrating the prediction results of multiple models can effectively reduce errors and improve the accuracy and stability of production demand forecasts.

[0111] S3. Based on the forecast results of production demand, preliminary capacity allocation is carried out according to the real-time production data of each production line.

[0112] According to the final production demand forecast result, the enameled wire production demand (for example, the enameled wire production demand in the next day) is obtained;

[0113] Based on the real-time production data of the blockchain platform, the actual capacity of each production line is obtained (maximum capacity of each production line, equipment performance, production line health status, maintenance cycle);

[0114] Calculate the capacity difference between the actual capacity and the maximum capacity of each production line. When the actual capacity of the production line is less than the maximum capacity, allocate the capacity according to the capacity difference.

[0115] When the actual capacity of the production line is not less than the maximum capacity, it means that the production line cannot allocate additional capacity.

[0116] S4. Through the real-time connection between the intelligent adjustment model based on deep reinforcement learning algorithm and the blockchain platform, the actual operation status of the production line is continuously monitored and the capacity allocation is adjusted in real time.

[0117] Building an intelligent adjustment model based on the Deep Q Network (DQN);

[0118] Obtain real-time production data of each production line through the blockchain platform and use it as the state space;

[0119] The capacity of each production line will be dynamically adjusted according to the forecast results of production demand. When the load of the production line is too large or too small, the speed or load of the production line will be adjusted as a decision space;

[0120] According to the matching degree between capacity allocation and production demand forecast results, the reward function is set, and the expression is:

[0121]

[0122] Among them, R is the reward function, P1 is the actual production capacity, P2 is the production demand forecast result, and P3 is the allocated capacity;

[0123] The state space is input into the intelligent adjustment model for simulation training. According to the state space, the intelligent adjustment model makes a series of decisions in the decision space;

[0124] For each decision, calculate the reward function, evaluate the decision effect, and optimize the decision space based on the calculation result of the reward function;

[0125] During the training process, the intelligent adjustment model simulates high-load production line scenarios, equipment failure scenarios, and production bottleneck scenarios, interacts with multiple production scenarios, and further optimizes the decision space;

[0126] According to the changing trend of the reward function, draw a reward value change curve. When the reward value change curve tends to be stable, that is, the up and down amplitude does not exceed 2%, the intelligent adjustment model training is considered to be completed;

[0127] Through the completed intelligent adjustment model, decisions are output based on real-time production data from the blockchain platform to adjust the initial capacity allocation.

[0128] Specifically, for example, if the load of production line A is too high and production line B has spare capacity, part of the production demand of production line A will be transferred to production line B according to the decision of the model;

[0129] When production demand is high, the system adjusts capacity allocation based on the priorities of different production lines (such as the urgency of production tasks);

[0130] When the load of multiple production lines is close to saturation, the system dynamically adjusts the capacity allocation to ensure the overall load balance;

[0131] After the capacity allocation is adjusted, continue to monitor the real-time production data of the production line and make real-time adjustments to the capacity allocation based on the real-time situation;

[0132] In order to ensure the long-term stability and adaptability of the model, the effectiveness of capacity allocation is evaluated regularly, and the intelligent adjustment model is retrained based on the evaluation results.

[0133] This embodiment also provides an enameled wire capacity assistance allocation system, including: a data sharing module, a demand forecasting module, a capacity allocation module and a real-time adjustment module. The data sharing module is used to use Internet of Things sensors to collect real-time production data of each production line and share it through a blockchain platform; the demand forecasting module is used to use real-time production data in combination with historical production data of each production line to predict production demand using a deep learning algorithm; the capacity allocation module is used to make preliminary capacity allocation based on the real-time production data of each production line based on the predicted results of production demand; the real-time adjustment module is used to continuously monitor the actual operation of the production line and adjust the capacity allocation in real time through real-time connection between an intelligent adjustment model based on a deep reinforcement learning algorithm and the blockchain platform.

[0134] This embodiment also provides a computer device, which is applicable to the enameled wire capacity assistance allocation method, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the enameled wire capacity assistance allocation method proposed in the above embodiment.

[0135] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0136] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for assisting in allocating the production capacity of enameled wire proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0137] In summary, the present invention improves the transparency and reliability of the production process by: using IoT sensors to collect production line data in real time, and using the blockchain platform to ensure the secure sharing and non-tamperability of data, and by combining historical data with real-time data and using a deep learning algorithm to predict production demand, thereby improving the accuracy of demand forecasting and reducing production plan errors. Based on these prediction results, the system can dynamically adjust production capacity allocation, optimize the load between production lines, avoid resource waste and production bottlenecks, and enhance the stability and accuracy of the prediction by integrating the results of multiple prediction models. With the help of a deep reinforcement learning model, the capacity allocation is continuously monitored and adjusted in real time, which effectively improves production efficiency and resource utilization, and realizes intelligent scheduling and optimization of the production process.

[0138] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for assisting in allocating enameled wire production capacity, characterized in that: include, Use IoT sensors to collect real-time production data from each production line and share it through the blockchain platform; Through real-time production data, combined with historical production data of each production line, deep learning algorithms are used to predict production demand; Based on the forecast results of production demand, preliminary capacity allocation is carried out according to the real-time production data of each production line; Through the real-time connection between the intelligent adjustment model based on deep reinforcement learning algorithm and the blockchain platform, the actual operation of the production line can be continuously monitored and the capacity allocation can be adjusted in real time.

2. The method for assisting in allocating enameled wire production capacity according to claim 1, characterized in that: The IoT sensors are used to collect real-time production data of each production line. The specific steps are as follows: Deploy IoT sensors on each enameled wire production line to collect real-time production data of each production line; Real-time production data is transmitted to the blockchain platform via wireless communication protocols.

3. The method for assisting in allocating enameled wire production capacity according to claim 2, characterized in that: The specific steps for sharing through the blockchain platform are as follows: On the blockchain platform, hash processing is performed through a cryptographic hash algorithm, and the production data of each production line is packaged into a block; The blockchain platform uses a consensus mechanism to verify the newly added blocks; After all participating nodes of the blockchain platform verify the newly added blocks, the validity of the newly added blocks is confirmed; The hash value of the newly added block is encrypted and linked to the hash value of the previous block to form a blockchain; All participating nodes share real-time production data of all production lines through the blockchain platform.

4. The method for assisting in allocating enameled wire production capacity according to claim 3, characterized in that: The real-time production data is combined with the historical production data of each production line to use the deep learning algorithm to predict production demand. The specific steps are as follows: Based on the blockchain platform, obtain historical and real-time production data of each production line; Align the historical and real-time production data of each production line according to the collection timestamp. For production data with missing timestamps, generate corresponding timestamps based on the production line log information and equipment operation records. Using the sliding window method, the historical and real-time production data of each production line are divided into several time series training samples according to the time window size; Divide the time series training samples into training set, validation set and test set; Based on LSTM, build a production demand forecasting model; The training set is input into the production demand forecasting model for training, the training set is processed through the gate control structure (such as forget gate, input gate, output gate), and the production demand forecast result is output; After each training batch, the mean square error is calculated; The Adam optimizer is used to adjust the learning rate of the production demand forecasting model; After each training batch, the prediction performance of the production demand forecasting model is verified using the validation set; When the production demand forecasting model completes the training of all time series training samples in the training set, it inputs the test set; The performance of the production demand forecasting model is evaluated by calculating the mean square error and determination coefficient of the test set in the production demand forecasting model. By setting different hyperparameter configurations, several production demand forecasting models are trained to obtain different production demand forecasting results; By introducing an integrated algorithm, the production demand forecast results of several production demand forecasting models are integrated to obtain the final production demand forecast result.

5. The method for assisting in allocating enameled wire production capacity according to claim 4, characterized in that: The production demand forecast results of several production demand forecast models are integrated by introducing an integrated algorithm to obtain the final production demand forecast result. The specific steps are as follows: Input the time series training samples into several production demand forecasting models with different hyperparameter configurations that have completed training, and record the production demand forecasting results output by different production demand forecasting models; According to the mean square error of different production demand forecasting models on the test set (the smaller the mean square error value, the greater the weight), the weight of each production demand forecast result is preset; All production demand forecast results are integrated through weighted voting.

6. The method for assisting in allocating enameled wire production capacity according to claim 5, characterized in that: Based on the forecast results of production demand, preliminary capacity allocation is carried out according to the real-time production data of each production line. The specific steps are as follows: According to the final production demand forecast result, the enameled wire production demand (for example, the enameled wire production demand in the next day) is obtained; Based on the real-time production data of the blockchain platform, the actual production capacity of each production line can be obtained; Calculate the capacity difference between the actual capacity and the maximum capacity of each production line. When the actual capacity of the production line is less than the maximum capacity, allocate the capacity according to the capacity difference. When the actual capacity of a production line is not less than the maximum capacity, it means that the production line cannot allocate additional capacity.

7. The method for assisting in allocating enameled wire production capacity according to claim 6, characterized in that: The intelligent adjustment model based on deep reinforcement learning algorithm is connected to the blockchain platform in real time to continuously monitor the actual operation of the production line and adjust the capacity allocation in real time. The specific steps are as follows: Build an intelligent adjustment model based on deep Q network; Obtain real-time production data of each production line through the blockchain platform and use it as the state space; The capacity of each production line will be dynamically adjusted according to the forecast results of production demand. When the load of the production line is too large or too small, the speed or load of the production line will be adjusted as a decision space; According to the matching degree between capacity allocation and production demand forecast results, the reward function is set, and the expression is: Among them, R is the reward function, P1 is the actual production capacity, P2 is the production demand forecast result, and P3 is the allocated capacity; The state space is input into the intelligent adjustment model for simulation training. According to the state space, the intelligent adjustment model makes a series of decisions in the decision space; For each decision, calculate the reward function, evaluate the decision effect, and optimize the decision space based on the calculation result of the reward function; During the training process, the intelligent adjustment model simulates high-load production line scenarios, equipment failure scenarios, and production bottleneck scenarios, interacts with multiple production scenarios, and further optimizes the decision space; According to the changing trend of the reward function, draw a reward value change curve. When the reward value change curve tends to be stable, it is considered that the intelligent adjustment model training is completed; Through the completed intelligent adjustment model, decisions are output based on real-time production data from the blockchain platform to adjust the initial capacity allocation. After the capacity allocation is adjusted, continue to monitor the real-time production data of the production line and make real-time adjustments to the capacity allocation based on the real-time situation; Regularly evaluate the effectiveness of capacity allocation and retrain the intelligent adjustment model based on the evaluation results.

8. An enameled wire production capacity assisting allocation system, based on the enameled wire production capacity assisting allocation method according to any one of claims 1 to 7, characterized in that: Including data sharing module, demand forecasting module, capacity allocation module and real-time adjustment module The data sharing module is used to collect real-time production data of each production line using IoT sensors and share it through the blockchain platform; The demand forecasting module is used to forecast production demand by using real-time production data combined with historical production data of each production line and using a deep learning algorithm; The capacity allocation module is used to perform preliminary capacity allocation based on the prediction results of production demand and the real-time production data of each production line; The real-time adjustment module is used to continuously monitor the actual operation of the production line and adjust the capacity allocation in real time through real-time connection between the intelligent adjustment model based on the deep reinforcement learning algorithm and the blockchain platform.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for assisting in allocating the production capacity of enameled wire according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for assisting in allocating the production capacity of enameled wire according to any one of claims 1 to 7 are implemented.

Images