Molybdenum wire production process optimization system based on cloud computing

Abstract

The present invention relates to the technical field of production process optimization, specifically to a molybdenum wire production process optimization system based on cloud computing, the system includes an energy analysis module, an equipment scheduling module, a demand prediction module, a real-time control module, an operation priority module, and a cycle scheduling module. The energy analysis module is based on energy consumption data, uses a cloud computing platform to gather full-process data, analyzes the temperature and time changes during the operation of the molybdenum wire heating furnace, simulates the energy consumption under differentiated heating conditions, and forms an energy consumption distribution map. In the present invention, the demand prediction module uses a linear programming algorithm and combines historical energy data to accurately predict future energy demand, improve energy efficiency, and significantly reduce waste. The operation priority module uses an SJF algorithm to optimize the priority sorting of production tasks, improve the task scheduling process, make the operation efficiency and sequence arrangement more reasonable, and make the production process smoother to reduce production delays.

Description

Technical Field

[0001] The present invention relates to the technical field of production process optimization, and in particular to a molybdenum wire production process optimization system based on cloud computing. Background Art

[0002] The field of production process optimization technology focuses on using big data analysis and artificial intelligence to analyze and improve production processes, thereby improving production efficiency, reducing costs or enhancing quality control, and optimizing resource allocation. Through data-driven insights and intelligent decision support, in-depth analysis and continuous improvement of production links are achieved. This field is becoming increasingly important in modern industry because it involves reducing waste, improving production capacity, and adapting to rapidly changing market demands.

[0003] Among them, the molybdenum wire production process optimization system is a system for improving and optimizing the molybdenum wire production process. Its purpose is to optimize the operating efficiency and product quality of the production line through efficient data processing and resource sharing, and to analyze and process production data in real time in order to promptly discover and solve problems in the production process, improve the flexibility and response speed of the production process, and aim to achieve more efficient, cost-effective and more reliable production results.

[0004] Traditional production systems lack efficient prediction and optimization mechanisms in energy management, which often leads to irrational use of energy, such as excessive consumption or insufficient supply, affecting production efficiency and costs. In terms of task scheduling, job priorities and production efficiency are not fully considered, resulting in irrational arrangement of production tasks, leading to uneven resource allocation and extended production time, which in turn affects the overall production schedule and product quality, resulting in reduced overall production efficiency and quality and increased costs. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings existing in the prior art and to propose a molybdenum wire production process optimization system based on cloud computing.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a molybdenum wire production process optimization system based on cloud computing, the system comprising:

[0007] The energy analysis module is based on energy consumption data and uses the cloud computing platform to gather full-process data, analyze the temperature and time changes during the operation of the molybdenum wire heating furnace, simulate the energy consumption under differentiated heating conditions, and form an energy consumption distribution map;

[0008] The equipment scheduling module adjusts the operating parameters of the molybdenum wire drawing machine based on the energy consumption distribution map, and adjusts the temperature and speed parameters in combination with the production line conditions and historical operation data to obtain the optimal equipment scheduling plan;

[0009] The demand forecasting module applies a linear programming algorithm based on the energy consumption distribution diagram, combines historical energy data, analyzes the energy demand change trend of different production stages, and predicts future energy demand based on the data to form a future energy demand forecast record;

[0010] The real-time control module adjusts the real-time parameters in the production process, including the heating furnace temperature or the stretching speed, based on the future energy demand forecast record, collects real-time production data, compares the forecast record difference, adjusts the production parameters again, and establishes a dynamic energy adjustment strategy;

[0011] The job priority module uses the SJF algorithm to collect task information of the production process, analyze the task duration, and prioritize the tasks according to the optimal job principle to obtain the optimized task execution sequence according to the optimal scheduling plan of the equipment and the characteristics of the molybdenum wire production task;

[0012] The cyclic scheduling module evaluates the task periodicity of the production line based on the optimized task execution sequence, analyzes the process time ratio, balances the operation time of multiple links, and forms a balanced operation schedule.

[0013] The present invention has improvements in that the energy consumption distribution diagram includes the energy consumption rate of the heating mode, time efficiency comparison, and temperature change pattern; the equipment optimal scheduling plan includes temperature adjustment parameters, speed adjustment settings, and production line energy-saving mode; the future energy demand forecast record includes predicted peak demand time periods, energy consumption trends, and energy demand in key production stages; the dynamic energy adjustment strategy includes real-time energy consumption monitoring, parameter automatic adjustment mechanism, and energy efficiency optimization measures; the optimized task execution sequence includes task priority sorting, production process adjustment, and operation efficiency optimization measures; the balanced operation schedule includes operation time allocation for processes, periodic production arrangements, and efficiency improvement measures.

[0014] The present invention is improved in that the equipment scheduling module comprises:

[0015] The parameter analysis submodule analyzes the key operating parameters of the molybdenum wire drawing machine based on the energy consumption distribution diagram, compares the energy consumption under various parameter settings, refines the influencing factor analysis, and generates key parameter influencing data;

[0016] The historical data integration submodule analyzes the differences between historical and current parameter settings based on the key parameter impact data and the historical operation data of the production line, evaluates the potential and effect of parameter adjustment, and generates historical parameter comparison analysis results;

[0017] The scheduling plan generation submodule reconfigures the temperature and speed parameters of the molybdenum wire drawing machine based on the historical parameter comparison and analysis results, and obtains the optimal equipment scheduling plan in combination with production efficiency and energy conservation.

[0018] The present invention is improved in that the demand forecasting module comprises:

[0019] The first data comparison submodule uses Monte Carlo simulation based on the energy consumption distribution map to directly compare the energy consumption data with the historical energy data, identify the energy usage differences in various production stages, extract key energy consumption features, and generate historical energy usage comparison records;

[0020] The trend analysis submodule identifies and analyzes changes in energy demand in multiple time periods and production stages based on the historical energy usage comparison records, mines the periodic and regular changes in energy usage, and generates energy demand analysis data;

[0021] The demand forecasting submodule applies a linear programming algorithm based on the energy demand analysis data to evaluate the energy demand and pattern in the future production stage, and predicts short-term and long-term energy demand changes in combination with production plans and seasonal factors to form a future energy demand forecast record.

[0022] The present invention is improved in that the linear programming algorithm is according to the formula:

[0023] f(x)=c1x1+c2x2+d1e1+d2e2

[0024] Calculate energy demand cost optimization;

[0025] Among them, x1 is the demand for conventional energy, x2 is the demand for renewable energy, c1 and c2 are the unit costs of the two energy sources respectively, e1 is the production efficiency factor, e2 is the environmental impact factor, d1 and d2 are the corresponding weight coefficients, and f(x) means that as x1 and x2 change, the values ​​of x1 and x2 are captured while satisfying the constraints so that f(x) reaches the optimal value.

[0026] The present invention is improved in that the real-time control module comprises:

[0027] The parameter monitoring submodule continuously monitors the heating furnace temperature and stretching speed parameters based on the future energy demand forecast record, records and analyzes the fluctuation of the parameters in real time, and generates a real-time monitoring data summary;

[0028] The second data comparison submodule compares the differences between the parameter data and the predicted data based on the real-time monitoring data summary, analyzes the causes and trends of the deviations, identifies key adjustment points, and generates parameter difference analysis records;

[0029] The adjustment strategy submodule adjusts the production parameters based on the parameter difference analysis records, optimizes the energy utilization efficiency, and establishes a dynamic energy adjustment strategy for the identified deviation points.

[0030] The present invention is improved in that the job priority module comprises:

[0031] The task information collection submodule collects task information of the production process based on the optimal equipment scheduling plan, including task type, estimated completion time and required resources, and classifies and filters the data to form a task information summary;

[0032] The task duration analysis submodule analyzes the estimated duration of multiple tasks based on the task information summary, evaluates the complexity and required time of the tasks, determines the duration characteristics of the multiple tasks, and generates task duration feature information;

[0033] The priority sorting submodule uses the SJF algorithm based on the task duration feature information to prioritize the tasks according to the task duration and urgency, and optimizes the execution order to obtain an optimized task execution sequence.

[0034] The present invention improves that the sjf algorithm is according to the formula:

[0035]

[0036] Calculate the average waiting time of the optimized tasks;

[0037] Among them, T wait′ is the average waiting time, T burst，i is the execution time of the ith task, T arrive，i is the arrival time of the ith task, T priority，i is the urgency score of the i-th task, w1 and w2 are weight coefficients, and n is the total number of tasks.

[0038] Compared with the prior art, the advantages and positive effects of the present invention are:

[0039] In the present invention, the demand forecasting module uses a linear programming algorithm combined with historical energy data to accurately predict future energy demand, improve energy efficiency, and significantly reduce waste. The job priority module uses the SJF algorithm to optimize the priority sorting of production tasks, improve the task scheduling process, make the job efficiency and sequence arrangement more reasonable, make the production process smoother, and reduce production delays. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 The module diagram of the molybdenum wire production process optimization system based on cloud computing is proposed for the present invention;

[0041] Figure 2 The system framework diagram of the molybdenum wire production process optimization system based on cloud computing proposed by the present invention;

[0042] Figure 3The present invention proposes a flow chart of an energy analysis module in a molybdenum wire production process optimization system based on cloud computing;

[0043] Figure 4 The present invention proposes a flow chart of an equipment scheduling module in a molybdenum wire production process optimization system based on cloud computing;

[0044] Figure 5 The present invention proposes a flow chart of a demand forecasting module in a molybdenum wire production process optimization system based on cloud computing;

[0045] Figure 6 The present invention proposes a real-time control module flow chart in a molybdenum wire production process optimization system based on cloud computing;

[0046] Figure 7 The present invention proposes a flow chart of the operation priority module in the molybdenum wire production process optimization system based on cloud computing;

[0047] Figure 8 The present invention proposes a flow chart of a loop scheduling module in a molybdenum wire production process optimization system based on cloud computing. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0049] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0050] Example

[0051] See also Figure 1 The present invention provides a technical solution: a molybdenum wire production process optimization system based on cloud computing includes:

[0052] The energy analysis module is based on energy consumption data and uses the cloud computing platform to gather full-process data, analyze the temperature and time changes during the operation of the molybdenum wire heating furnace, simulate the energy consumption under differentiated heating conditions, and form an energy consumption distribution map;

[0053] The equipment scheduling module adjusts the operating parameters of the molybdenum wire drawing machine based on the energy consumption distribution map, and adjusts the temperature and speed parameters based on the production line conditions and historical operation data to obtain the optimal equipment scheduling plan;

[0054] The demand forecasting module is based on the energy consumption distribution map, applies the linear programming algorithm, combines historical energy data, analyzes the trend of energy demand changes in different production stages, and predicts future energy demand based on the data to form a future energy demand forecast record;

[0055] The real-time control module adjusts the real-time parameters in the production process, including the heating furnace temperature or stretching speed, based on the future energy demand forecast records, collects real-time production data, compares the forecast record differences, adjusts the production parameters again, and establishes a dynamic energy adjustment strategy;

[0056] The job priority module uses the SJF algorithm to collect task information of the production process, analyze task duration, and prioritize tasks according to the optimal job principle to obtain the optimized task execution sequence based on the optimal equipment scheduling plan and molybdenum wire production task characteristics;

[0057] The cycle scheduling module is based on optimizing the task execution sequence, evaluating the task periodicity of the production line, analyzing the process time ratio, balancing the operation time of multiple links, and forming a balanced operation schedule.

[0058] The energy consumption distribution diagram includes the energy consumption rate of the heating mode, time efficiency comparison, and temperature change pattern. The optimal equipment scheduling plan includes temperature adjustment parameters, speed adjustment settings, and production line energy-saving mode. The future energy demand forecast record includes the predicted peak demand period, energy consumption trend, and energy demand in the key production stage. The dynamic energy adjustment strategy includes real-time energy consumption monitoring, parameter automatic adjustment mechanism, and energy efficiency optimization measures. The optimized task execution sequence includes task priority sorting, production process adjustment, and operation efficiency optimization measures. The balanced operation schedule includes the operation time allocation of the process, periodic production arrangement, and efficiency improvement measures.

[0059] See also Figure 2 and Figure 3 ,The energy analysis module includes a data collection submodule, a data analysis submodule, and a simulation generation submodule;

[0060] Based on the energy consumption data, the data collection submodule directly extracts the operation data of the molybdenum wire heating furnace from the cloud computing platform, including temperature records and energy consumption at multiple time points, classifies and processes the data, and generates energy integration data;

[0061] The data analysis submodule compares the temperature changes and energy consumption of the heating furnace based on the energy integration data, subdivides the energy consumption characteristics of the differentiated temperature ranges, and generates heating efficiency analysis records;

[0062] The simulation generation submodule simulates the energy consumption under different heating temperatures and durations based on the heating efficiency analysis records. By comparing and analyzing the results, it calculates the energy consumption distribution under various conditions and generates an energy consumption distribution diagram.

[0063] In the data collection submodule, based on the energy consumption data, the cloud computing platform is used to directly extract the operation data of the molybdenum wire heating furnace. The data is loaded through the read_csv function in the Python Pandas library, and the DataFrame object is used to manage the data and perform data classification processing. Specifically, the groupby method is used to group by time point, and the agg function is applied to aggregate each group. The average temperature and energy consumption are calculated to generate energy integration data.

[0064] In the data analysis submodule, based on the energy integration data, a linear regression algorithm is used. The temperature change and energy consumption data are input through the linregress function in the SciPy library to calculate the slope and intercept, which are used to compare the temperature change and energy consumption of the heating furnace, and to subdivide the energy consumption characteristics of the differentiated temperature ranges. The plot function of the matplotlib library is used to draw a graph showing the relationship between temperature and energy consumption, and to generate a heating efficiency analysis record.

[0065] In the simulation generation submodule, based on the heating efficiency analysis records, the Monte Carlo simulation method is adopted, and random numbers are generated using the random module in the NumPy library to simulate the energy consumption under different heating temperatures and durations. Different temperature intervals are judged through conditional statements, and the energy consumption under different durations is simulated with a loop. The energy consumption distribution under various conditions is calculated, and the scatter function of the matplotlib library is used to generate an energy consumption distribution graph.

[0066] See also Figure 2 and Figure 4 ,The equipment scheduling module includes a parameter analysis submodule, a historical data integration submodule, and a scheduling plan generation submodule;

[0067] The parameter analysis submodule analyzes the key operating parameters of the molybdenum wire drawing machine based on the energy consumption distribution diagram, compares the energy consumption under various parameter settings, refines the analysis of influencing factors, and generates key parameter impact data;

[0068] The historical data integration submodule analyzes the differences between historical and current parameter settings based on key parameter impact data and combines historical production line operation data, evaluates the potential and effect of parameter adjustment, and generates historical parameter comparison analysis results;

[0069] The scheduling scheme generation submodule reconfigures the temperature and speed parameters of the molybdenum wire drawing machine based on the historical parameter comparison and analysis results, and obtains the optimal scheduling scheme for the equipment by combining production efficiency and energy conservation.

[0070] In the parameter analysis submodule, based on the energy consumption distribution diagram, the principal component analysis (PCA) method is adopted. The PCA class in Python's scikit-learn library is used to input the operating parameter data of the molybdenum wire drawing machine, and the fit_transform method is executed to reduce the data dimension. The impact of key operating parameters on energy consumption is analyzed, and the energy consumption under different parameter settings is displayed through the scatter function in the matplotlib library. The influencing factor analysis is refined to generate key parameter impact data.

[0071] In the historical data integration submodule, based on the key parameter influencing data, the time series analysis method is used, and the DataFrame object in Python's Pandas library is used to manage the historical operation data. The rolling method is used for sliding window analysis, and the average difference between the historical parameters and the current parameter settings is calculated. Combined with the historical operation data of the production line, the potential for parameter adjustment is evaluated, and a comparison chart of the historical and current parameter differences is drawn through the plot function of the matplotlib library to generate historical parameter comparison analysis results.

[0072] In the scheduling plan generation submodule, based on the historical parameter comparison and analysis results, an optimization algorithm is adopted, and the optimize module in Python's SciPy library is used to input the temperature and speed parameters of the molybdenum wire drawing machine. The minimize method is executed to find the minimum energy consumption configuration, considering production efficiency and energy savings. The optimal range of temperature and speed parameters is determined through conditional judgment, and the molybdenum wire drawing machine parameters are reconfigured to generate the optimal scheduling plan for the equipment.

[0073] See also Figure 2 and Figure 5 , the demand forecasting module includes a first data comparison submodule, a trend analysis submodule, and a demand forecasting submodule;

[0074] The first data comparison submodule uses Monte Carlo simulation based on the energy consumption distribution map to directly compare energy consumption data with historical energy data, identify energy usage differences in various production stages, extract key energy consumption features, and generate historical energy usage comparison records;

[0075] The trend analysis submodule identifies and analyzes changes in energy demand over multiple time periods and production stages based on historical energy usage comparison records, mines periodic and regular changes in energy usage, and generates energy demand analysis data;

[0076] The demand forecasting submodule is based on energy demand analysis data and applies linear programming algorithms to evaluate the energy demand and pattern in future production stages. It combines production plans and seasonal factors to predict short-term and long-term energy demand changes and form a future energy demand forecast record.

[0077] In the first data comparison submodule, based on the energy consumption distribution map, the Monte Carlo simulation method is adopted, and random numbers are generated using the random module in Python's NumPy library to simulate the energy consumption in different production stages. The historical energy data is compared, and the differences in energy usage in different stages are identified through conditional judgment. The plot function in the matplotlib library is used to draw the energy consumption feature map, extract key energy consumption features, and generate historical energy usage comparison records.

[0078] In the trend analysis submodule, based on the historical energy usage comparison records, the time series analysis method is applied, the DataFrame object in Python's Pandas library is used to manage the data, the rolling method is used for sliding window analysis, the energy demand changes in the time period and production stage are calculated, and the energy demand change trend chart is drawn through the plot function of the matplotlib library. The periodic and regular changes in energy use are explored to generate energy demand analysis data.

[0079] In the demand forecasting submodule, based on the energy demand analysis data, a linear programming algorithm is adopted, and the optimize module in Python's SciPy library is used to execute the linprog method to evaluate the energy demand and pattern in the future production stage. By passing in the coefficient matrix and constraints, combined with the production plan and seasonal factors, the short-term and long-term energy demand changes are calculated to form a future energy demand forecast record.

[0080] Linear programming algorithm, according to the formula:

[0081] f(x)=c1x1+c2x2+d1e1+d2e2

[0082] Calculate energy demand cost optimization;

[0083] Among them, x1 is the demand for conventional energy, x2 is the demand for renewable energy, c1 and c2 are the unit costs of the two energy sources respectively, e1 is the production efficiency factor, e2 is the environmental impact factor, d1 and d2 are the corresponding weight coefficients, and f(x) means that as x1 and x2 change, the values ​​of x1 and x2 are captured while satisfying the constraints so that f(x) reaches the optimal value.

[0084] Execution process:

[0085] First, determine the demand for conventional energy and renewable energy x1 and x2, and calculate the basic energy cost based on their respective unit costs c1 and c2. Then introduce the production efficiency factor e1 and the environmental impact factor e2 to consider the efficiency and environmental cost in the production process. The factors are obtained through the analysis of historical data, among which d1 and d2 are weight coefficients determined by data regression analysis, reflecting the importance of production efficiency and environmental factors in the total cost. Considering production and environmental factors will help to formulate more effective energy strategies.

[0086] See also Figure 2 and Figure 6 , the real-time control module includes a parameter monitoring submodule, a second data comparison submodule, and an adjustment strategy submodule;

[0087] The parameter monitoring submodule continuously monitors the heating furnace temperature and stretching speed parameters based on the future energy demand forecast records, records and analyzes the parameter fluctuations in real time, and generates a real-time monitoring data summary;

[0088] The second data comparison submodule compares the differences between parameter data and predicted data based on the real-time monitoring data summary, analyzes the causes and trends of deviations, identifies key adjustment points, and generates parameter difference analysis records;

[0089] The adjustment strategy submodule adjusts production parameters based on the parameter difference analysis records, optimizes energy efficiency, and establishes a dynamic energy adjustment strategy based on the identified deviation points.

[0090] In the parameter monitoring submodule, based on the future energy demand forecast records, real-time data monitoring technology is adopted. The std function in Python's NumPy library is used to calculate the standard deviation of the heating furnace temperature and stretching speed parameters. The parameter fluctuation is monitored by the standard deviation. The plot function in the matplotlib library is used to draw the parameter fluctuation graph in real time, analyze the parameter fluctuation, and generate a real-time monitoring data summary.

[0091] In the second data comparison submodule, based on the real-time monitoring data summary, the difference analysis method is adopted. The merge function in Python's Pandas library is used to merge the real-time data and the predicted data. The subtract method is used to calculate the difference between the parameter data and the predicted data. The cause and trend of the difference are identified through conditional statements, and the key adjustment points are identified. The scatter function in the matplotlib library is used to display the parameter differences and generate parameter difference analysis records.

[0092] In the adjustment strategy submodule, based on the parameter difference analysis records, the decision tree algorithm is applied, the DecisionTreeClassifier class in Python's scikit-learn library is used, the identified deviation point data is input, and the fit method is executed to build a decision tree model. The production parameters are adjusted according to the decision tree results, and the where function in Python's NumPy library is used to optimize the energy utilization efficiency and establish a dynamic energy adjustment strategy.

[0093] See also Figure 2 and Figure 7 ,The job priority module includes the task information collection submodule, the task duration analysis submodule, and the priority sorting submodule;

[0094] The task information collection submodule collects task information of the production process based on the optimal equipment scheduling plan, including task type, estimated completion time and required resources, and classifies and filters the data to form a task information summary;

[0095] The task duration analysis submodule analyzes the estimated duration of multiple tasks based on task information summary, evaluates the complexity and time required for tasks, determines the duration characteristics of multiple tasks, and generates task duration feature information;

[0096] The priority sorting submodule uses the SJF algorithm based on the task duration feature information to prioritize tasks according to task duration and urgency, and optimizes the execution order to obtain the optimized task execution sequence.

[0097] In the task information collection submodule, based on the optimal equipment scheduling plan, database query technology is used to execute the SELECT command through the SQL language to retrieve the task type, estimated completion time and required resource information from the production management database, use the JOIN operation to connect related data tables, execute the WHERE clause to filter data, and apply the ORDER BY clause to sort the result set to form a task information summary.

[0098] In the task duration analysis submodule, based on the task information summary, statistical analysis methods are adopted, and the DataFrame object in Python's Pandas library is used to manage the data. The describe method is executed to calculate the estimated duration statistics of each task, including the mean and standard deviation. The distribution diagram of the task duration is drawn through the hist function, the task complexity and the required time are evaluated, the duration characteristics of multiple tasks are determined, and the task duration feature information is generated.

[0099] In the priority sorting submodule, based on the task duration feature information, the shortest job first (SJF) algorithm is adopted, and the Python sorted function is used to sort the tasks by task duration and urgency. The execution order is optimized through list derivation and conditional statements to obtain the optimized task execution sequence.

[0100] SJF algorithm, according to the formula:

[0101]

[0102] Calculate the average waiting time of the optimized tasks;

[0103] Among them, T wait′ is the average waiting time, T burst，i is the execution time of the ith task, T arrive，i is the arrival time of the ith task, T priority,i is the urgency score of the i-th task, w1 and w2 are weight coefficients, and n is the total number of tasks.

[0104] Execution process:

[0105] First, assign weights to the execution time and urgency of each task, and calculate the weighted execution time and weighted urgency score of each task. Then subtract the weighted value from the arrival time of each task, sum up all adjusted time differences, and finally divide it by the total number of tasks to get the average waiting time. The weights w1 and w2 are usually determined by analyzing historical data. Linear regression or other statistical methods can be used to minimize the total waiting time, thereby optimizing task processing efficiency.

[0106] See also Figure 2 and Figure 8 ,The cycle scheduling module includes the task execution analysis submodule, the process time evaluation submodule, and the ,job time balancing submodule;

[0107] The task execution analysis submodule optimizes the task execution sequence, analyzes the execution order and time interval of multiple tasks, identifies the continuity and periodicity between tasks, performs process simulation, and generates execution process analysis data;

[0108] The process time evaluation submodule evaluates the time proportion of multiple processes based on the execution process analysis data, analyzes the imbalance of time usage on the production line, identifies potential bottlenecks in time allocation, and generates time allocation analysis records;

[0109] The operation time balancing submodule reallocates the operation time of multiple links based on the time allocation analysis records, adjusts the operation execution cycle, and achieves time balance and production efficiency to form a balanced operation schedule.

[0110] In the task execution analysis submodule, based on optimizing the task execution sequence, process simulation technology is adopted, and discrete event simulation is performed using Python's SimPy library. The simulation environment is created through the env object, and the simulation process of the task execution order and time interval is defined. The yield statement and timeout event are used to simulate the waiting time between tasks, identify the continuity and periodicity between tasks, and use the plot function in the matplotlib library to draw the execution flow chart to generate execution process analysis data.

[0111] In the process time evaluation submodule, based on the execution process analysis data, the working time analysis method is applied, the DataFrame object in Python's Pandas library is used to manage the data, the groupby method is executed to classify and count the time of different processes, the sum function is used to calculate the total time of each process, and the bar function is used to draw the process time ratio chart, analyze the imbalance of time usage on the production line, identify potential bottlenecks in time allocation, and generate time allocation analysis records.

[0112] In the job time balancing submodule, based on the time allocation analysis records, the linear programming method is applied, the optimize module in Python's SciPy library is used, the linprog method is executed to reallocate the working hours, the coefficients and constraints of the job time in different links are input, the job execution cycle is adjusted, and the optimal allocation of job time is determined through conditional judgment. The scatter function in the matplotlib library is used to display the adjusted job time distribution to form a balanced job schedule.

[0113] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. The molybdenum wire production process optimization system based on cloud computing is characterized by: The system comprises: The energy analysis module is based on energy consumption data and uses the cloud computing platform to gather full-process data, analyze the temperature and time changes during the operation of the molybdenum wire heating furnace, simulate the energy consumption under differentiated heating conditions, and form an energy consumption distribution map; The equipment scheduling module adjusts the operating parameters of the molybdenum wire drawing machine based on the energy consumption distribution map, and adjusts the temperature and speed parameters in combination with the production line conditions and historical operation data to obtain the optimal equipment scheduling plan; The demand forecasting module applies a linear programming algorithm based on the energy consumption distribution diagram, combines historical energy data, analyzes the energy demand change trend of different production stages, and predicts future energy demand based on the data to form a future energy demand forecast record; The real-time control module adjusts the real-time parameters in the production process, including the heating furnace temperature or the stretching speed, based on the future energy demand forecast record, collects real-time production data, compares the forecast record difference, adjusts the production parameters again, and establishes a dynamic energy adjustment strategy; The job priority module uses the SJF algorithm to collect task information of the production process, analyze the task duration, and prioritize the tasks according to the optimal job principle to obtain the optimized task execution sequence according to the optimal scheduling plan of the equipment and the characteristics of the molybdenum wire production task; The cycle scheduling module evaluates the task periodicity of the production line based on the optimized task execution sequence, analyzes the process time ratio, balances the operation time of multiple links, and forms a balanced operation schedule; The demand forecasting module comprises: The first data comparison submodule uses Monte Carlo simulation based on the energy consumption distribution map to directly compare the energy consumption data with the historical energy data, identify the energy usage differences in various production stages, extract key energy consumption features, and generate historical energy usage comparison records; The trend analysis submodule identifies and analyzes changes in energy demand in multiple time periods and production stages based on the historical energy usage comparison records, mines the periodic and regular changes in energy usage, and generates energy demand analysis data; The demand forecasting submodule uses a linear programming algorithm based on the energy demand analysis data to evaluate the energy demand and pattern in the future production stage, and combines production plans and seasonal factors to predict short-term and long-term energy demand changes to form a future energy demand forecast record; The linear programming algorithm is according to the formula: ； Calculate energy demand cost optimization; in, is the conventional energy demand, is the demand for renewable energy, and are the unit costs of the two energies, is the production efficiency factor, is the environmental impact factor, and is the corresponding weight coefficient, Indicates that with and The change of, while satisfying the constraints, captures and value, so that reach the optimal value.

2. The cloud computing-based molybdenum wire production process optimization system according to claim 1, characterized in that: The energy consumption distribution diagram includes the energy consumption rate of the heating mode, time efficiency comparison, and temperature change pattern; the equipment optimal scheduling plan includes temperature adjustment parameters, speed adjustment settings, and production line energy-saving mode; the future energy demand forecast record includes predicted peak demand time periods, energy consumption trends, and energy demand in key production stages; the dynamic energy adjustment strategy includes real-time energy consumption monitoring, parameter automatic adjustment mechanism, and energy efficiency optimization measures; the optimized task execution sequence includes task priority sorting, production process adjustment, and operation efficiency optimization measures; the balanced operation schedule includes operation time allocation for processes, periodic production arrangements, and efficiency improvement measures.

3. The cloud computing-based molybdenum wire production process optimization system according to claim 1 is characterized in that: The device scheduling module includes: The parameter analysis submodule analyzes the key operating parameters of the molybdenum wire drawing machine based on the energy consumption distribution diagram, compares the energy consumption under various parameter settings, refines the influencing factor analysis, and generates key parameter influencing data; The historical data integration submodule analyzes the differences between historical and current parameter settings based on the key parameter impact data and the historical operation data of the production line, evaluates the potential and effect of parameter adjustment, and generates historical parameter comparison analysis results; The scheduling plan generation submodule reconfigures the temperature and speed parameters of the molybdenum wire drawing machine based on the historical parameter comparison and analysis results, and obtains the optimal equipment scheduling plan in combination with production efficiency and energy conservation.

4. The cloud computing-based molybdenum wire production process optimization system according to claim 1, characterized in that: The real-time control module comprises: The parameter monitoring submodule continuously monitors the heating furnace temperature and stretching speed parameters based on the future energy demand forecast record, records and analyzes the fluctuation of the parameters in real time, and generates a real-time monitoring data summary; The second data comparison submodule compares the differences between the parameter data and the predicted data based on the real-time monitoring data summary, analyzes the causes and trends of the deviations, identifies key adjustment points, and generates parameter difference analysis records; The adjustment strategy submodule adjusts the production parameters based on the parameter difference analysis records, optimizes the energy utilization efficiency, and establishes a dynamic energy adjustment strategy for the identified deviation points.

5. The cloud computing-based molybdenum wire production process optimization system according to claim 1, characterized in that: The job priority module includes: The task information collection submodule collects task information of the production process based on the optimal equipment scheduling plan, including task type, estimated completion time and required resources, and classifies and filters the data to form a task information summary; The task duration analysis submodule analyzes the estimated duration of multiple tasks based on the task information summary, evaluates the complexity and required time of the tasks, determines the duration characteristics of the multiple tasks, and generates task duration feature information; The priority sorting submodule uses the SJF algorithm based on the task duration feature information to prioritize the tasks according to the task duration and urgency, and optimizes the execution order to obtain an optimized task execution sequence.

6. The cloud computing-based molybdenum wire production process optimization system according to claim 5, characterized in that: The sjf algorithm is based on the formula: ； Calculate the average waiting time of the optimized tasks; in, is the average waiting time, is the execution time of the ith task, is the arrival time of the ith task, Score the urgency of the i-th task, and is the weight coefficient, The total number of tasks.

Images