Intelligent control system for whole molybdenum wire production process

Abstract

The invention relates to the technical field of molybdenum wire production, in particular to a molybdenum wire production whole process intelligent control system, which comprises a temperature and rate regulation module, a temperature control and stretching rate dynamic regulation model is established based on the physical and chemical characteristics of molybdenum wire production, the model is regulated and optimized through real-time numerical simulation and stability analysis, and the temperature and rate regulation model is obtained; and obtaining a production stability evaluation result. According to the system, key performance indexes in the molybdenum wire production process can be monitored and analyzed in real time through a linear stability analysis method of the production process stability detection sub-module in the temperature and rate adjusting module. Therefore, the system can accurately identify unstable factors possibly occurring in the production process, and predicts the stability under the production condition by calculating the characteristic value of the Jacobian matrix. Thus, the system can quickly adjust the temperature and stretch rate even in the face of differences between batches of raw material or other dynamic changes in the production process.

Description

Technical Field

[0001] The present invention relates to the technical field of molybdenum wire production, and in particular to a whole-process intelligent control system for molybdenum wire production. Background Art

[0002] The field of molybdenum wire production technology is a comprehensive field involving metal processing, material science and automation control technology. Molybdenum wire is a high-performance metal wire material. Due to its excellent strength, corrosion resistance and high temperature resistance, it is widely used in electronics, lighting, aerospace and other fields. At the same time, the production process of molybdenum wire includes multiple steps such as smelting, forging, rolling, wire drawing, etc., and each step requires precise control to ensure the quality of the final product.

[0003] Among them, the intelligent control system for the entire process of molybdenum wire production refers to an integrated technical solution specifically designed to optimize the molybdenum wire production process. Through automation and information technology, it can achieve precise control of the production process, improve quality stability, and effectively manage production costs. It can achieve the effects of improving production efficiency, reducing material waste, ensuring product quality, and accelerating the production cycle. By monitoring production data in real time, the system can also adjust production parameters in a timely manner to prevent abnormalities in the production process, thereby ensuring that the production process of molybdenum wire is more stable and efficient.

[0004] Although the existing system has achieved certain results in molybdenum wire production management, it still has shortcomings in dynamic stability analysis and refined energy consumption monitoring. Specifically, the existing system is difficult to fully cope with the complexity and dynamic changes in the molybdenum wire production process, resulting in a lack of response speed and accuracy in the real-time adjustment and optimization of key production parameters. For example, when the temperature and stretching rate on the molybdenum wire production line need to change rapidly to match the characteristics of different batches of raw materials, the system is difficult to make adjustments in real time, which in turn affects the quality and consistency of the product. In addition, traditional systems have limitations in achieving maximum efficiency in energy use and lack the ability to deeply understand the energy consumption pattern in the molybdenum wire production process. For example, molybdenum wire production equipment may be in an inefficient state, such as running for a long time when the equipment is not fully loaded but running at full power, resulting in energy waste without immediate identification and adjustment, which not only increases production costs but also exacerbates the impact on the environment. Summary of the invention

[0005] This application provides an intelligent control system for the entire process of molybdenum wire production, which solves the problem that although the existing system has achieved certain results in molybdenum wire production management, it still has deficiencies in dynamic stability analysis and refined energy consumption monitoring. Specifically, the existing system is difficult to fully cope with the complexity and dynamic changes in the molybdenum wire production process, resulting in a lack of response speed and accuracy in the real-time adjustment and optimization of key production parameters. For example, when the temperature and stretching rate on the molybdenum wire production line need to change rapidly to match the characteristics of different batches of raw materials, it is difficult for the system to make adjustments in real time, which in turn affects the quality and consistency of the product. In addition, traditional systems have limitations in achieving maximum efficiency in energy use and lack the ability to deeply understand the energy consumption pattern in the molybdenum wire production process. For example, molybdenum wire production equipment may be in an inefficient state, such as when the equipment is not fully loaded but running at full power for a long time, resulting in energy waste without immediate identification and adjustment, which not only increases production costs, but also exacerbates the problem of environmental impact.

[0006] In view of the above problems, the present application provides an intelligent control system for the entire molybdenum wire production process.

[0007] The present application provides a whole-process intelligent control system for molybdenum wire production, wherein the system comprises: The temperature and rate adjustment module establishes a dynamic adjustment model for temperature control and drawing rate based on the physical and chemical characteristics of molybdenum wire production. Through real-time numerical simulation and stability analysis, the model is adjusted and optimized to obtain the production stability evaluation results. The key parameter identification module performs sensitivity analysis on the key parameters of the model based on the production stability evaluation result, screens the parameters according to the influence of the molybdenum wire production stability, and forms a key parameter list; The production energy consumption analysis module collects energy usage data during the molybdenum wire production process, builds a model that reflects the factors and interrelationships of energy consumption in production, analyzes the impact of raw material type and equipment status on energy consumption, and obtains energy consumption analysis results; The energy efficiency optimization module analyzes the energy usage in the molybdenum wire production process through the energy consumption analysis results, and adjusts the production process and equipment parameters according to the analysis results to obtain an energy consumption optimization plan; The production process monitoring module performs real-time monitoring of the molybdenum wire production process based on the key parameter list and the energy consumption optimization plan, reflects the production process status, and generates real-time production monitoring data; The parameter adjustment feedback module dynamically adjusts key parameters in molybdenum wire production based on the real-time production monitoring data to match changes in production conditions and obtain production adjustment feedback data.

[0008] Preferably, the production stability assessment results include key temperature control indicators, rate control indicators, and production process stability analysis; the key parameter list includes temperature setting values ​​that have the greatest impact on production, key stretching speed parameters, and key control factors in the production process; the energy consumption analysis results include key energy consumption types, key energy consumption nodes, and an overall distribution diagram of energy consumption; the energy consumption optimization plan includes energy-saving production process adjustments, efficiency-optimized equipment operation plans, and energy redistribution plans; the real-time production monitoring data includes real-time monitoring records of key production stages, real-time change trends of production parameters, and operating status of key production nodes; the production adjustment feedback data includes optimized production parameter settings, adjustment effect evaluation, and future production optimization plans.

[0009] Preferably, the temperature and rate adjustment module comprises: The temperature control optimization submodule analyzes the temperature fluctuation of the temperature data in the molybdenum wire production process based on the physical and chemical characteristics of the molybdenum wire production, performs real-time temperature adjustment, and generates temperature control indicators; The rate dynamic adjustment submodule analyzes the relationship between the stretching rate and the temperature based on the temperature control index, adjusts the molybdenum wire stretching equipment settings to match the temperature change, and performs real-time optimization of the stretching rate to obtain the rate synchronization adjustment data; The production process stability detection submodule monitors the key performance indicators in the entire molybdenum wire production process based on the rate synchronization adjustment data, identifies production fluctuations, and uses a linear stability analysis method to analyze the stability of the production process by calculating the eigenvalue of the Jacobian matrix to obtain a production stability evaluation result.

[0010] Preferably, the linear stability analysis method is according to the improved formula I:

[0011] Calculate the eigenvalues ​​of the Jacobian matrix, and determine whether the real part vectors of the eigenvalues ​​are all less than zero, analyze the stability of the production process, and obtain the production stability evaluation result; in, Represents the temperature variable during the molybdenum wire production process, represents the stretching rate variable, represents the time delay of temperature control, represents the sensitivity of rate control, Represents the effect of temperature on the hardness of the material, represents the effect of rate on volume change, is the weight coefficient, which is used to adjust the relative importance of each variable and its influencing factors in stability analysis.

[0012] Preferably, the key parameter identification module includes: The production impact analysis submodule analyzes the correlation between parameters and the molybdenum wire production process based on the production stability evaluation results, identifies the parameters that affect the production process by comparing the production effects under various parameter settings, and generates an impact evaluation result; The parameter influence ranking submodule ranks each parameter affecting the molybdenum wire production process according to its influence degree based on the influence evaluation result, identifies key parameters, and forms a parameter importance sequence; The production key factor extraction submodule screens the parameters that have the greatest impact on the quality and efficiency of molybdenum wire production based on the parameter importance sequence, analyzes the parameter action mechanism and adjustment method, and obtains a list of key parameters.

[0013] Preferably, the production energy consumption analysis module includes: The energy consumption collection submodule is based on the molybdenum wire production process, including the electricity and gas energy usage data in the molybdenum wire production stage, and records the time period and intensity of energy consumption to form a production energy consumption record; The energy consumption influencing factor analysis submodule uses the Bayesian network algorithm to analyze the energy consumption patterns of various molybdenum wire production stages based on the production energy consumption records, and identifies key energy consumption driving factors through comparative analysis with reference to the comprehensive influence of various factors such as raw material type and molybdenum wire equipment operation status, thus forming energy consumption key factor data; The energy consumption assessment submodule evaluates the overall energy consumption data of molybdenum wire production based on the key energy consumption factor data, analyzes the total energy consumption, energy efficiency ratio and energy cost, as well as the energy utilization efficiency of each link, and obtains energy consumption analysis results.

[0014] Preferably, the Bayesian network algorithm is based on the improved formula II:

[0015] Calculate the conditional probability of each energy consumption factor in the molybdenum wire production process and generate data on key factors of energy consumption; in, Represents an energy consumption factor in the molybdenum wire production process. represents the observed energy consumption data, Represents the production speed, represents the volume change of molybdenum wire, Represents the production temperature, Given the known energy consumption data , production speed , Molybdenum wire volume change and production temperature Under the condition of The posterior probability of occurrence, It is the energy consumption factor Under the condition of existence, energy consumption data was observed , production speed , Molybdenum wire volume change and production temperature The joint probability of It is an energy consumption factor The prior probability of is the observed energy consumption data , production speed , Molybdenum wire volume change and production temperature The joint probability of .

[0016] Preferably, the energy efficiency optimization module includes: The energy efficiency analysis submodule analyzes the energy usage status of each molybdenum wire production equipment based on the energy consumption analysis results, compares the energy consumption patterns between equipment and production lines, identifies energy efficiency abnormalities, and analyzes deficiencies in energy utilization to obtain energy efficiency diagnosis results; The production process energy-saving optimization submodule formulates energy-saving measures for the designated links of energy use in the molybdenum wire production process based on the energy efficiency diagnosis results, including adjusting the process flow and optimizing energy distribution, and obtaining an energy-saving process optimization plan; The equipment energy efficiency improvement submodule analyzes the energy efficiency data of the equipment in the molybdenum wire production line based on the energy-saving process optimization plan, identifies equipment with abnormal energy efficiency, and formulates an energy consumption optimization plan.

[0017] Preferably, the production process monitoring module includes: The production parameter real-time tracking submodule tracks the temperature and speed of molybdenum wire production in real time based on the key parameter list and energy consumption optimization plan, monitors energy usage, and generates parameter and energy consumption monitoring results; The production process status monitoring submodule analyzes the data change trend based on the parameters and energy consumption monitoring results, with reference to the molybdenum wire production efficiency, product quality and energy consumption performance of the equipment, to form the molybdenum wire production process analysis results; The production abnormality instant alarm submodule is based on the analysis results of the molybdenum wire production process, captures multiple abnormalities in the molybdenum wire production process, including sudden increase in energy consumption or parameter deviation, and generates real-time production monitoring data.

[0018] Preferably, the parameter adjustment feedback module includes: The production data analysis submodule analyzes each type of data collected during the molybdenum wire production process based on the real-time production monitoring data, identifies the fluctuation patterns and trends of key parameters, evaluates the potential impact on production efficiency and product quality, and generates key parameter analysis results; The production parameter refinement and optimization submodule iteratively adjusts and optimizes the key parameters based on the key parameter analysis results, including adjusting the temperature control setting and improving the stretching rate regulation, to form a refined parameter adjustment plan; The optimization adjustment result feedback submodule monitors the performance of the adjusted molybdenum wire production parameters based on the detailed parameter adjustment plan, records the effects of the adjustment measures, and provides immediate feedback on problems in the production process to obtain production adjustment feedback data.

[0019] One or more technical solutions provided in this application have at least the following technical effects or advantages: Through the linear stability analysis method of the production process stability detection submodule in the temperature and rate regulation module, the system can monitor and analyze the key performance indicators of the molybdenum wire production process in real time. The system can accurately identify the unstable factors that may occur in the production process and predict the stability under production conditions by calculating the eigenvalues ​​of the Jacobian matrix. Therefore, even in the face of differences between raw material batches or other dynamic changes in the production process, the system can quickly adjust the temperature and stretching rate to ensure the continuity of the production process and the consistency of product quality. At the same time, through the Bayesian network algorithm of the energy consumption influencing factor analysis submodule in the production energy consumption analysis module, the system can build a complex energy consumption model that reflects the relationship and probability dependence between various parameters in the production process. The system can deeply understand and predict the energy consumption pattern under different production conditions, identify the links with poor energy efficiency, and propose specific energy-saving measures. Therefore, the system can not only optimize energy distribution and reduce energy waste, but also reduce the impact on the environment while maintaining production efficiency, thereby maximizing the energy efficiency of the production process.

[0020] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A module diagram of an intelligent control system for the whole process of molybdenum wire production is proposed for the present invention; Figure 2 The present invention proposes a system framework diagram of an intelligent control system for the entire process of molybdenum wire production; Figure 3 The present invention proposes a specific flow chart of a temperature and rate regulating module in an intelligent control system for the entire process of molybdenum wire production; Figure 4 The present invention proposes a specific flow chart of a key parameter identification module in a molybdenum wire production whole process intelligent control system; Figure 5 The present invention proposes a specific flow chart of a production energy consumption analysis module in a molybdenum wire production whole process intelligent control system; Figure 6 The present invention proposes a specific flow chart of an energy efficiency optimization module in an intelligent control system for the entire molybdenum wire production process; Figure 7 The present invention proposes a specific flow chart of a production process monitoring module in a molybdenum wire production whole process intelligent control system; Figure 8 The present invention proposes a specific flow chart of a parameter adjustment feedback module in an intelligent control system for the entire molybdenum wire production process. DETAILED DESCRIPTION

[0022] The present application provides an intelligent control system for the entire molybdenum wire production process.

[0023] Application Overview The existing technology has the following problems: Although the existing system has achieved certain results in molybdenum wire production management, it still has deficiencies in dynamic stability analysis and refined energy consumption monitoring. Specifically, the existing system is difficult to fully cope with the complexity and dynamic changes in the molybdenum wire production process, resulting in a lack of response speed and accuracy in the real-time adjustment and optimization of key production parameters. For example, when the temperature and stretching rate on the molybdenum wire production line need to change rapidly to match the characteristics of different batches of raw materials, it is difficult for the system to make adjustments in real time, which in turn affects the quality and consistency of the product. In addition, traditional systems have limitations in achieving maximum efficiency in energy use and lack the ability to deeply understand the energy consumption pattern in the molybdenum wire production process. For example, molybdenum wire production equipment may be in an inefficient state, such as running for a long time when the equipment is not fully loaded but running at full power, resulting in energy waste without immediate identification and adjustment, which not only increases production costs, but also exacerbates technical problems such as environmental impact.

[0024] In response to the above technical problems, the overall idea of ​​the technical solution provided by this application is as follows: like Figure 1 As shown, the present application provides a whole-process intelligent control system for molybdenum wire production, wherein the system includes: The temperature and rate adjustment module establishes a dynamic adjustment model for temperature control and drawing rate based on the physical and chemical characteristics of molybdenum wire production. Through real-time numerical simulation and stability analysis, the model is adjusted and optimized to obtain the production stability evaluation results. The key parameter identification module performs sensitivity analysis on the key parameters of the model based on the production stability evaluation results, screens the parameters according to the influence of molybdenum wire production stability, and forms a key parameter list; The production energy consumption analysis module collects energy usage data during the molybdenum wire production process, builds a model that reflects the factors and interrelationships of energy consumption in production, analyzes the impact of raw material type and equipment status on energy consumption, and obtains energy consumption analysis results; The energy efficiency optimization module analyzes the energy usage in the molybdenum wire production process through the energy consumption analysis results, and adjusts the production process and equipment parameters according to the analysis results to obtain an energy consumption optimization plan; The production process monitoring module performs real-time monitoring of the molybdenum wire production process based on the key parameter list and energy consumption optimization plan, reflects the production process status, and generates real-time production monitoring data; The parameter adjustment feedback module dynamically adjusts the key parameters in molybdenum wire production based on real-time production monitoring data to match changes in production conditions and obtain production adjustment feedback data.

[0025] The production stability assessment results include key temperature control indicators, rate control indicators, and production process stability analysis. The key parameter list includes the temperature setting values ​​that have the greatest impact on production, key stretching speed parameters, and key control factors in the production process. The energy consumption analysis results include key energy consumption types, key energy consumption nodes, and an overall distribution diagram of energy consumption. The energy consumption optimization plan includes energy-saving production process adjustments, efficiency-optimized equipment operation plans, and energy redistribution plans. Real-time production monitoring data includes real-time monitoring records of key production stages, real-time change trends of production parameters, and operating status of key production nodes. Production adjustment feedback data includes optimized production parameter settings, adjustment effect evaluation, and future production optimization plans.

[0026] like Figure 2 and Figure 3 As shown, the temperature and rate regulation module includes: The temperature control optimization submodule analyzes the temperature fluctuation of the temperature data in the molybdenum wire production process based on the physical and chemical characteristics of the molybdenum wire production, and performs real-time temperature adjustment. The specific process of generating temperature control indicators is as follows; The temperature control optimization submodule is based on the physical and chemical characteristics of molybdenum wire production, adopts fuzzy logic control algorithm, uses MATLAB software for algorithm coding, sets the temperature control rule as the temperature membership function, and the input variables include the difference between the real-time temperature and the target temperature. The output variable is the adjustment intensity of the heating or cooling instruction. The optimal temperature adjustment amount is calculated through the fuzzy logic reasoning system to generate the temperature control index.

[0027] The rate dynamic adjustment submodule analyzes the relationship between the stretching rate and temperature based on the temperature control index, adjusts the molybdenum wire stretching equipment settings to match the temperature changes, and optimizes the stretching rate in real time. The specific process of obtaining the rate synchronization adjustment data is as follows; The rate dynamic adjustment submodule is based on the temperature control index and adopts the proportional-integral-differential (PID) controller algorithm. The Simulink environment is used to build the model. The PID controller parameters are set as proportional gain, integral gain and differential gain. The input variable is the difference between the set stretching speed and the actual stretching speed. The output variable is the rate adjustment instruction. By adjusting the parameters of the PID controller to accurately match the dynamic relationship between the stretching speed and temperature changes, the rate synchronization adjustment data is obtained.

[0028] The production process stability detection submodule monitors the key performance indicators of the entire molybdenum wire production process based on the rate synchronization adjustment data, identifies production fluctuations, and uses the linear stability analysis method to analyze the stability of the production process by calculating the eigenvalue of the Jacobian matrix. The specific process of obtaining the production stability evaluation result is as follows; The production process stability detection submodule is based on rate synchronization adjustment data, adopts linear stability analysis method, uses Python language to call NumPy library to calculate the Jacobian matrix, sets the calculation parameters of the Jacobian matrix as the partial derivatives of temperature and stretching rate in the production process, and the input variables are the real-time values ​​of the production parameters. By calculating the eigenvalues ​​of the Jacobian matrix and judging whether the real part vectors of the eigenvalues ​​are all less than zero, the stability of the production process is analyzed to obtain the production stability evaluation results.

[0029] The linear stability analysis method is based on the improved formula I:

[0030] Calculate the eigenvalues ​​of the Jacobian matrix, and determine whether the real part vectors of the eigenvalues ​​are all less than zero, analyze the stability of the production process, and obtain the production stability evaluation result; in, Represents the temperature variable in the molybdenum wire production process, reflecting the temperature conditions of the production environment or material heating process. It stands for the draw rate variable and refers to the speed at which the material is drawn during the molybdenum wire production process. Represents the time delay of temperature control, which is the time difference from when the system adjusts the temperature setting to when the actual temperature is reflected in the production process. Represents the sensitivity of rate control, that is, the response sensitivity to the stretching rate adjustment instruction. Represents the effect of temperature on material hardness, reflecting the degree of influence of temperature change on the hardness properties of molybdenum wire material. It represents the effect of rate on volume change and describes the effect of change in drawing rate on the volume change of material during the production process of molybdenum wire. is the weight coefficient, which is used to adjust the relative importance of each variable and its influencing factors in stability analysis. The weight coefficient is determined by statistical analysis of the impact of temperature changes on product quality in past production data. The weighting coefficients are determined by analyzing historical cases of the impact of time delays in temperature control on production stability. The weight coefficient is determined by evaluating the effect of different stretching rates on the dimensional accuracy of the product. The weight coefficient is determined by regression analysis of the relationship between the stretching rate adjustment instruction response time and production efficiency. The weight coefficient is determined by analyzing experimental data on the effect of temperature change on material hardness. The weight coefficient is determined by experimentally measuring the data of the change in material hardness under different temperature conditions. The weight coefficient is determined by analyzing the effect of changes in stretching rate on the volume stability of the final product in historical production data. The weight coefficient is determined by quantitatively studying the effect of rate control accuracy on the volume change of the material during the stretching process.

[0031] The execution process is as follows: Collect real-time data during the molybdenum wire production process, including temperature (x) and drawing rate (y), as well as the time delay associated with them ( ), the sensitivity of rate control ( ), the effect of temperature on material hardness ( ), the effect of rate on volume change ( ).

[0032] By statistically analyzing historical production data, the weight coefficients are determined. It includes regression analysis, correlation analysis and optimization algorithm solution to ensure that the weight coefficient can accurately reflect the relative importance of each parameter in the stability of molybdenum wire production.

[0033] Use Python language to call NumPy library to calculate the partial derivatives of temperature and stretching rate based on real-time monitoring data and . Including the partial derivative calculation of the mathematical expression of the production process model.

[0034] Substitute the collected real-time data parameters, the calculated partial derivative values, and the determined weight coefficients into Formula I, and use NumPy's linear algebra to calculate the improved Jacobian matrix , and analyze whether the real parts of the eigenvalues ​​are all less than zero.

[0035] Based on the analysis results of the eigenvalues, the stability of the molybdenum wire production process is evaluated. If the real part of all eigenvalues ​​is less than zero, the production process is considered to be stable under the current parameter settings.

[0036] like Figure 2 and Figure 4 As shown, the key parameter identification module includes: The production impact analysis submodule analyzes the correlation between parameters and the molybdenum wire production process based on the production stability assessment results. By comparing the production effects under various parameter settings, the parameters that affect the production process are identified. The specific process of generating the impact assessment results is as follows; The production impact analysis submodule is based on the production stability assessment results, adopts data mining algorithms, uses Python language combined with the pandas library for data processing, and sets the specific command items used in the data mining process as data frame screening and grouping operations. The parameters include various indicators of the production process and their corresponding stability assessment values. The operation content is to compare and analyze the production effects under different parameter settings. The relationship between parameters and production effects is classified through cluster analysis methods to generate impact assessment results.

[0037] The parameter influence ranking submodule ranks each parameter affecting the molybdenum wire production process according to its influence degree based on the influence evaluation results, identifies key parameters, and forms the specific process of parameter importance sequence as follows; The parameter influence sorting submodule adopts a sorting algorithm based on the influence assessment results. It uses Python language combined with the NumPy library to perform array operations. The specific command item used in the sorting algorithm is set to an array sorting function. The parameters include the parameter influence score generated in the previous step. The operation content is to sort all parameters in descending order according to the influence score. The priority serialization of the parameters is realized through the array indexing function to form a parameter importance sequence.

[0038] The production key factor extraction submodule screens the parameters that have the greatest impact on the quality and efficiency of molybdenum wire production based on the parameter importance sequence, analyzes the parameter action mechanism and adjustment method, and obtains the specific process of the key parameter list as follows; The production key factor extraction submodule is based on the parameter importance sequence and adopts the decision tree algorithm. The decision tree model is constructed using Python language combined with the scikit-learn library. The specific command item used in the decision tree construction process is set to the fit method. The parameters include the parameter importance sequence and the historical data of molybdenum wire production quality and efficiency. The operation content is to study and analyze the factors affecting the quality and efficiency in the molybdenum wire production process according to the parameter importance sequence, and to obtain a list of key parameters by screening the parameters that have the greatest impact on production quality and efficiency by constructing decision rules.

[0039] like Figure 2 and Figure 5 As shown, the production energy consumption analysis module includes: The energy consumption collection submodule is based on the molybdenum wire production process, including the electricity and gas energy usage data in the molybdenum wire production stage, and records the time period and intensity of energy consumption. The specific process of forming the production energy consumption record is as follows; The energy consumption collection submodule records energy consumption based on real-time monitoring data during the molybdenum wire production process and uses an SQL database for data storage. It records electricity and gas usage data, including timestamp, energy type, consumption, and production stage identifier, as parameters by executing SQL insert commands. The operation content is to create an energy consumption record table in the database, record each energy usage data in real time, and form a production energy consumption record.

[0040] The energy consumption influencing factor analysis submodule is based on the production energy consumption records and uses the Bayesian network algorithm to analyze the energy consumption patterns of various molybdenum wire production stages. It refers to the comprehensive influence of various factors such as raw material type and molybdenum wire equipment operation status, and identifies the key energy consumption driving factors through comparative analysis. The specific process of forming the data of key energy consumption factors is as follows; The energy consumption influencing factor analysis submodule is based on the production energy consumption records, adopts the Bayesian network algorithm, and uses Python language combined with the PyMC3 library to realize the construction and inference of the Bayesian model. By defining network nodes to represent various elements of energy consumption, including raw material type, molybdenum wire equipment operating status, etc., as input variables, setting the prior probability distribution, and performing probabilistic inference on the energy consumption data in the production process, the operation content is to train the network using the MCMC method, so as to identify and quantify the main factors affecting energy consumption and form data on key factors of energy consumption.

[0041] The Bayesian network algorithm follows the improved formula II:

[0042] Calculate the conditional probability of each energy consumption factor in the molybdenum wire production process and generate data on key factors of energy consumption; in, Represents an energy consumption factor in the molybdenum wire production process, such as the type of energy used or the operating status of the equipment. Represents observed energy consumption data, such as electricity and gas consumption recorded during a specific production phase. Represents the production speed, that is, the rate at which the material passes through the equipment during the molybdenum wire manufacturing process, an important factor affecting energy consumption. Represents the volume change of molybdenum wire, reflecting the change of material volume or shape caused by factors such as temperature change and drawing speed during the production process, which may affect the distribution and total amount of energy consumption. It stands for production temperature, which refers to the temperature reached during the heating or cooling process of molybdenum wire production, and has a direct impact on energy consumption. Given the known energy consumption data , production speed , Molybdenum wire volume change and production temperature Under the condition of The posterior probability of occurrence indicates the possibility of a certain energy consumption factor occurring under certain conditions. In specific energy consumption factors Under the condition of existence, energy consumption data was observed , production speed , Molybdenum wire volume change and production temperature The joint probability reflects the probability of the conditions occurring simultaneously when a certain energy consumption factor is known. It is an energy consumption factor The prior probability of energy consumption factor is Probability of occurrence. is the observed energy consumption data , production speed , Molybdenum wire volume change and production temperature The joint probability of , which represents the overall probability of the conditions occurring simultaneously.

[0043] The execution process is as follows: Based on the requirements and characteristics of the molybdenum wire production process, a Bayesian network is defined, which includes the energy consumption factor (such as equipment operating status), and influencing factor nodes (Energy consumption data), (production speed), (Molybdenum wire volume change) and (Production temperature).

[0044] Collect relevant real-time monitoring data during the molybdenum wire production process, including energy consumption data , production speed , Molybdenum wire volume change , and production temperature , as the input of the Bayesian network.

[0045] Estimating prior probabilities , using historical data to estimate each energy consumption factor The probability of occurrence when there is no other external information. This can be done through statistical analysis methods such as frequency counting or Bayesian parameter estimation.

[0046] Calculating joint probability According to the structure of Bayesian network, the specific energy consumption factor is calculated When present, observed energy consumption data , production speed , Molybdenum wire volume change and production temperature The probability of co-occurrence. Each conditional probability table needs to be populated, including the use of statistical models and machine learning algorithms.

[0047] Calculating marginal probabilities , calculated without considering energy consumption factors In the case of , production speed , Molybdenum wire volume change and production temperature The joint probability of all possible energy consumption factors The joint probability summation is realized.

[0048] Apply Bayes' theorem to calculate the posterior probability , Substitute the prior probability, joint probability and marginal probability calculated above into Formula II and calculate , production speed , Molybdenum wire volume change and production temperature Under the condition of The posterior probability of occurrence.

[0049] According to the calculation results, which energy consumption factors are analyzed? With high posterior probability, they are considered as key energy consumption drivers in the molybdenum wire production process. The factors can then be used as the basis for energy consumption optimization and management decisions.

[0050] The energy consumption assessment submodule evaluates the overall energy consumption data of molybdenum wire production based on the key factors of energy consumption, analyzes the total energy consumption, energy efficiency ratio and energy cost, as well as the energy utilization efficiency of each link, and obtains the specific process of energy consumption analysis results as follows; The energy consumption assessment submodule conducts a comprehensive assessment of the overall energy consumption data of molybdenum wire production based on the data of key energy consumption factors. It uses Excel for data analysis and constructs a pivot table to input key factors such as total energy consumption, energy efficiency ratio and energy cost as well as the energy utilization efficiency of each production link as parameters. The operation content is to summarize and calculate each parameter in order to analyze the contribution of each factor to the total energy consumption and obtain the energy consumption analysis results.

[0051] like Figure 2 and Figure 6 As shown, the energy efficiency optimization module includes: The energy efficiency analysis submodule analyzes the energy usage status of each molybdenum wire production equipment based on the energy consumption analysis results, compares the energy consumption patterns between equipment and production lines, identifies energy efficiency abnormalities, and analyzes the deficiencies in energy utilization. The specific process for obtaining energy efficiency diagnosis results is as follows; The energy efficiency analysis submodule analyzes the energy usage status based on the energy consumption analysis results, and uses the energy management system software to summarize and analyze the data. By executing data query and processing commands, the energy consumption data, including the electricity and gas usage of each device and the time period information, are input as parameters. The operation content is to summarize the energy consumption pattern of each molybdenum wire production equipment and production line, compare the energy consumption differences between equipment and production lines through data visualization tools, identify energy efficiency abnormalities, and obtain energy efficiency diagnosis results.

[0052] The production process energy-saving optimization submodule formulates energy-saving measures for the designated links of energy use in the molybdenum wire production process based on the energy efficiency diagnosis results, including adjusting the process flow and optimizing energy distribution. The specific process of the energy-saving process optimization plan is as follows; The production process energy-saving optimization submodule formulates energy-saving measures based on the energy efficiency diagnosis results, and uses process simulation software to simulate the energy consumption of the production process. By setting simulation parameters, including original process parameters and adjusted process parameters, the operation content is to simulate and analyze the energy usage of specific links in the current molybdenum wire production process. By simulating the impact of different process parameters on energy consumption, the adjustment plan with the greatest energy-saving potential is identified to obtain an energy-saving process optimization plan.

[0053] The equipment energy efficiency improvement submodule analyzes the energy efficiency data of the equipment in the molybdenum wire production line based on the energy-saving process optimization plan, identifies equipment with abnormal energy efficiency, and formulates the specific process of energy consumption optimization plan as follows; The equipment energy efficiency improvement submodule conducts energy efficiency data analysis based on the energy-saving process optimization plan, uses the maintenance management system to monitor equipment energy efficiency, and tracks the equipment identifier and energy consumption index as parameters by setting monitoring commands. The operation content is to collect and analyze the energy efficiency data of each equipment in the molybdenum wire production line, identify the equipment with low energy efficiency by comparing and analyzing the equipment energy efficiency indicators, and obtain the energy consumption optimization plan based on the energy efficiency data and the production process optimization plan.

[0054] like Figure 2 and Figure 7 As shown, the production process monitoring module includes: The production parameter real-time tracking submodule tracks the temperature and speed of molybdenum wire production in real time based on the key parameter list and energy consumption optimization plan, and monitors energy usage. The specific process of generating parameter and energy consumption monitoring results is as follows; The production parameter real-time tracking submodule tracks the temperature and rate of molybdenum wire production in real time based on the key parameter list and energy consumption optimization plan. It uses the industrial Internet of Things platform to collect data, configures the sensor data collection frequency and upload threshold as parameters, and creates a device instance on the IIoT platform. It subscribes to the real-time data stream for each key production parameter, uses the data stream processing engine to analyze the real-time changes of temperature and rate data, monitors energy usage, and generates parameter and energy consumption monitoring results; The production process status monitoring submodule is based on the parameter and energy consumption monitoring results, refers to the molybdenum wire production efficiency, product quality and energy consumption performance of the equipment, analyzes the data change trend, and forms the specific process of the molybdenum wire production process analysis results; The production process status monitoring submodule performs data change trend analysis based on parameter and energy consumption monitoring results, and uses data analysis software to perform time series analysis. By setting the analysis model parameters, including the sliding window size and anomaly detection threshold, the operation content is to import the monitoring result data, and apply the time series analysis algorithm to perform trend analysis on the molybdenum wire production efficiency, product quality and energy consumption performance of the equipment. By identifying the patterns and trends of data changes, the analysis results of the molybdenum wire production process are formed.

[0055] The production abnormality instant alarm submodule is based on the analysis results of the molybdenum wire production process, capturing multiple abnormalities in the molybdenum wire production process, including sudden increase in energy consumption or parameter deviation, and generating real-time production monitoring data. The specific process is as follows; The production anomaly instant alarm submodule performs anomaly detection and alarm generation based on the analysis results of the molybdenum wire production process, and uses a complex event processing engine for real-time data monitoring. By defining anomaly detection rules, including conditions and thresholds for sudden increases in energy consumption or parameter deviations, the operation content is to configure event rules in the CEP engine and analyze the real-time data stream in the molybdenum wire production process. When an event matching the anomaly detection rule is detected, the alarm mechanism is immediately triggered to generate real-time production monitoring data.

[0056] like Figure 2 and Figure 8 As shown, the parameter adjustment feedback module includes: The production data analysis submodule analyzes each type of data collected during the molybdenum wire production process based on real-time production monitoring data, identifies the fluctuation patterns and trends of key parameters, and evaluates the potential impact on production efficiency and product quality. The specific process of generating key parameter analysis results is as follows; The production data analysis submodule performs data fluctuation pattern and trend analysis based on real-time production monitoring data. It uses time series analysis methods to process time series data through Python language combined with pandas and NumPy libraries. The specific command items used in the time series analysis process are set to rolling window calculation and autoregressive model fitting. The parameters include time window size and model order. The operation content is to convert real-time monitoring data into time series format, apply the rolling window method to calculate the moving average and standard deviation of each parameter, analyze the fluctuation pattern and trend of the parameters through the autoregressive model, and generate key parameter analysis results.

[0057] The production parameter refinement and optimization submodule iteratively adjusts and optimizes key parameters based on the key parameter analysis results, including adjusting the temperature control settings and improving the stretching rate regulation. The specific process of forming a refined parameter adjustment plan is as follows; The production parameter refinement and optimization submodule performs iterative parameter adjustment and optimization based on the key parameter analysis results. It uses the simulated annealing algorithm and implements the algorithm logic in Python. The specific command items used in the simulated annealing algorithm are set as temperature drop functions and state update rules. The parameters include initial temperature, cooling rate, and stop conditions. The operation content is to define a state representing the current parameter setting, apply the temperature drop function to gradually reduce the system "temperature", explore the parameter setting space through the state update rules at each "temperature", and find parameter configurations that can optimize production efficiency and product quality to form a detailed parameter adjustment plan.

[0058] The optimization adjustment result feedback submodule monitors the adjusted molybdenum wire production parameter performance based on the detailed parameter adjustment plan, records the effect of the adjustment measures, and immediately feedbacks the problems in the production process. The specific process of obtaining the production adjustment feedback data is as follows; The optimization adjustment result feedback submodule is based on the detailed parameter adjustment plan, monitors the performance of the adjusted molybdenum wire production parameters, uses the real-time data feedback system to record the adjustment effect, and inputs the adjusted production parameters and production effect data as parameters by configuring the data acquisition and analysis module. The operation content is to create a data listener in the system, monitor the adjusted production parameters in real time, compare the production data before and after the adjustment, identify the actual effect of the adjustment measures through data comparison and analysis, and obtain production adjustment feedback data.

[0059] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary illustrations of the present application as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include these modifications and variations.

Claims

1. A whole-process intelligent control system for molybdenum wire production, characterized in that: The system comprises: The temperature and rate adjustment module establishes a dynamic adjustment model for temperature control and stretching rate based on the physical and chemical characteristics of molybdenum wire production. Through real-time numerical simulation and stability analysis, the model is adjusted and optimized to obtain the production stability evaluation results. The key parameter identification module performs sensitivity analysis on the key parameters of the model based on the production stability evaluation result, screens the parameters according to the influence of the molybdenum wire production stability, and forms a key parameter list; The production energy consumption analysis module collects energy usage data in the molybdenum wire production process, builds a model that reflects the factors and interrelationships of energy consumption in production, analyzes the impact of raw material type and equipment status on energy consumption, and obtains energy consumption analysis results; The energy efficiency optimization module analyzes the energy usage in the molybdenum wire production process through the energy consumption analysis results, and adjusts the production process and equipment parameters according to the analysis results to obtain an energy consumption optimization plan; The production process monitoring module performs real-time monitoring of the molybdenum wire production process based on the key parameter list and the energy consumption optimization scheme, reflects the production process status, and generates real-time production monitoring data; The parameter adjustment feedback module dynamically adjusts key parameters in molybdenum wire production based on the real-time production monitoring data to match changes in production conditions and obtain production adjustment feedback data.

2. The whole process intelligent control system of molybdenum wire production according to claim 1 is characterized in that: The production stability assessment results include key temperature control indicators, rate control indicators, and production process stability analysis; the key parameter list includes temperature setting values ​​that have the greatest impact on production, key stretching speed parameters, and key control factors in the production process; the energy consumption analysis results include key energy consumption types, key energy consumption nodes, and an overall distribution diagram of energy consumption; the energy consumption optimization plan includes energy-saving production process adjustments, efficiency-optimized equipment operation plans, and energy redistribution plans; the real-time production monitoring data includes real-time monitoring records of key production stages, real-time change trends of production parameters, and operating status of key production nodes; the production adjustment feedback data includes optimized production parameter settings, adjustment effect evaluation, and future production optimization plans.

3. The whole process intelligent control system of molybdenum wire production according to claim 1 is characterized in that: The temperature and rate adjustment module comprises: The temperature control optimization submodule analyzes the temperature fluctuation of the temperature data in the molybdenum wire production process based on the physical and chemical characteristics of the molybdenum wire production, performs real-time temperature adjustment, and generates temperature control indicators; The rate dynamic adjustment submodule analyzes the relationship between the stretching rate and the temperature based on the temperature control index, adjusts the molybdenum wire stretching equipment settings to match the temperature change, and performs real-time optimization of the stretching rate to obtain the rate synchronization adjustment data; The production process stability detection submodule monitors the key performance indicators in the entire molybdenum wire production process based on the rate synchronization adjustment data, identifies production fluctuations, and uses a linear stability analysis method to analyze the stability of the production process by calculating the eigenvalue of the Jacobian matrix to obtain a production stability evaluation result.

4. The whole process intelligent control system of molybdenum wire production according to claim 3 is characterized in that: The linear stability analysis method is based on the improved formula I: ； Calculate the eigenvalues ​​of the Jacobian matrix, and determine whether the real part vectors of the eigenvalues ​​are all less than zero, analyze the stability of the production process, and obtain the production stability evaluation result; in, Represents the temperature variable during the molybdenum wire production process, represents the stretching rate variable, represents the time delay of temperature control, represents the sensitivity of rate control, Represents the effect of temperature on the hardness of the material, represents the effect of rate on volume change, is the weight coefficient, which is used to adjust the relative importance of each variable and its influencing factors in stability analysis.

5. The whole process intelligent control system of molybdenum wire production according to claim 1 is characterized in that: The key parameter identification module includes: The production impact analysis submodule analyzes the correlation between parameters and the molybdenum wire production process based on the production stability evaluation results, identifies the parameters that affect the production process by comparing the production effects under various parameter settings, and generates an impact evaluation result; The parameter influence ranking submodule ranks each parameter affecting the molybdenum wire production process according to its influence degree based on the influence evaluation result, identifies key parameters, and forms a parameter importance sequence; The production key factor extraction submodule screens the parameters that have the greatest impact on the quality and efficiency of molybdenum wire production based on the parameter importance sequence, analyzes the parameter action mechanism and adjustment method, and obtains a list of key parameters.

6. The whole process intelligent control system of molybdenum wire production according to claim 1 is characterized in that: The production energy consumption analysis module includes: The energy consumption collection submodule is based on the molybdenum wire production process, including the electricity and gas energy usage data in the molybdenum wire production stage, and records the time period and intensity of energy consumption to form a production energy consumption record; The energy consumption influencing factor analysis submodule uses the Bayesian network algorithm to analyze the energy consumption patterns of various molybdenum wire production stages based on the production energy consumption records, and identifies key energy consumption driving factors through comparative analysis with reference to the comprehensive influence of various factors such as raw material type and molybdenum wire equipment operation status, thus forming energy consumption key factor data; The energy consumption assessment submodule evaluates the overall energy consumption data of molybdenum wire production based on the key energy consumption factor data, analyzes the total energy consumption, energy efficiency ratio and energy cost, as well as the energy utilization efficiency of each link, and obtains energy consumption analysis results.

7. The whole process intelligent control system of molybdenum wire production according to claim 6 is characterized in that: The Bayesian network algorithm is based on the improved formula II: ； Calculate the conditional probability of each energy consumption factor in the molybdenum wire production process and generate data on key factors of energy consumption; in, Represents an energy consumption factor in the molybdenum wire production process. represents the observed energy consumption data, Represents the production speed, represents the volume change of molybdenum wire, Represents the production temperature, Given the known energy consumption data , production speed , Molybdenum wire volume change and production temperature Under the condition of The posterior probability of occurrence, It is the energy consumption factor Under the condition of existence, energy consumption data was observed , production speed , Molybdenum wire volume change and production temperature The joint probability of It is an energy consumption factor The prior probability of is the observed energy consumption data , production speed , Molybdenum wire volume change and production temperature The joint probability of .

8. The whole process intelligent control system of molybdenum wire production according to claim 1 is characterized in that: The production process monitoring module includes: The production parameter real-time tracking submodule tracks the temperature and speed of molybdenum wire production in real time based on the key parameter list and energy consumption optimization plan, monitors energy usage, and generates parameter and energy consumption monitoring results; The production process status monitoring submodule analyzes the data change trend based on the parameters and energy consumption monitoring results, with reference to the molybdenum wire production efficiency, product quality and energy consumption performance of the equipment, to form the molybdenum wire production process analysis results; The production abnormality instant alarm submodule is based on the analysis results of the molybdenum wire production process, captures multiple abnormalities in the molybdenum wire production process, including sudden increase in energy consumption or parameter deviation, and generates real-time production monitoring data.

Images