Steel rolling equipment optimization system capable of reducing energy consumption

Abstract

The invention discloses a steel rolling equipment optimization system capable of reducing energy consumption, and relates to the technical field of steel rolling, and the optimization system comprises a load monitoring module, a dynamic load balancing module, a load adjusting module and an intelligent control module. Load prediction is performed in combination with an advanced machine learning model, and dynamic load balance adjustment is performed based on the load prediction, so that overload of part of rolling mill stations and light-load idle states of other rolling mill stations can be effectively avoided, the whole rolling equipment always runs in an optimal load state, energy waste is greatly reduced, the energy utilization efficiency is remarkably improved, and the economic benefit is increased. Moreover, the intelligent control module adjusts the frequency and precision of load monitoring according to the production plan and the real-time load condition, and further optimizes the energy management.

Description

Technical Field

[0001] The invention relates to the technical field of steel rolling, and in particular to a steel rolling equipment optimization system for reducing energy consumption. Background Art

[0002] Steel is an indispensable basic material in modern industry, and its rolling process has a vital impact on product quality and production efficiency. With the continuous development of the steel rolling industry, reducing energy consumption and improving resource utilization have become key goals for enterprises to pursue sustainable development. With the increasing market requirements for steel varieties and quality, the steel rolling process has become more and more complicated, involving multiple processes and the coordinated operation of multiple equipment. In this process, the load distribution of each rolling mill is directly related to the energy consumption level and operating efficiency of the entire production line.

[0003] However, traditional rolling equipment optimization systems have many shortcomings in dealing with load fluctuations. On the one hand, due to the lack of effective real-time monitoring methods, it is difficult to accurately grasp the actual load conditions of each rolling mill station; on the other hand, even if load abnormalities are detected, there is a lack of flexible adjustment mechanisms to respond quickly and make adjustments. In addition, traditional optimization systems often adopt fixed working modes and parameter settings, and cannot make dynamic adjustments according to actual conditions, resulting in the inability to effectively redistribute the load even when production conditions change, thereby limiting the improvement of overall production efficiency and energy utilization.

[0004] To sum up, the existing steel rolling optimization system has obvious defects in dynamic load balancing and cannot meet the current high-efficiency and energy-saving production needs. Therefore, the development of an innovative and efficient steel rolling equipment optimization system, especially to achieve breakthroughs in dynamic load balancing, is of great practical significance and urgency for improving the energy utilization efficiency of the steel rolling industry, reducing production costs, improving product quality and enhancing market competitiveness. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the prior art and provide a steel rolling equipment optimization system that reduces energy consumption. It can monitor the load conditions of each rolling mill station in real time and use machine learning models to predict future load changes. It can dynamically adjust the working parameters of each rolling mill station to ensure load balance between the rolling mill stations.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an optimization system for steel rolling equipment to reduce energy consumption, the components of the optimization system include: a load monitoring module, a dynamic load balancing module, a load adjustment module, and an intelligent control module;

[0007] The load monitoring module collects multi-dimensional load data of each rolling mill station in real time, including basic parameters of rolling pressure, motor current, speed, load size and temperature, and also covers roll temperature and equipment vibration frequency to reflect the equipment operation status and load conditions;

[0008] The dynamic load balancing module uses historical data and load data collected by the load monitoring module to predict load changes in the future through a machine learning model;

[0009] The load adjustment module accurately adjusts the working parameters of each rolling mill station based on the output results of the dynamic load balancing module with the help of intelligent optimization algorithm and high-performance speed regulation and control device;

[0010] The intelligent control module is responsible for coordinating and managing the working status of each module, formulating an overall control strategy according to the production plan, equipment status and real-time load conditions, and automatically adjusting the frequency and accuracy of load monitoring, and flexibly configuring the parameter range of load adjustment.

[0011] Furthermore, the specific steps of the load monitoring module are:

[0012] Sensor deployment: Various types of high-precision sensors are installed at key locations of each rolling mill station, i.e., pressure sensors are installed between the roller bearing seat and the arch, temperature sensors are installed on the surface and inside of the roller, current sensors are installed at the motor inlet end, and vibration sensors are installed on the main structure of the equipment;

[0013] Data collection: These sensors collect multi-dimensional load data in real time, including rolling pressure, motor current, speed, load size, temperature, roll temperature and equipment vibration frequency;

[0014] Data fusion: Use weighted fusion to integrate data from different sensors to form a comprehensive load monitoring view, analyze the relationship between different parameters, and extract load data information.

[0015] Furthermore, the load monitoring module integrates the information of various sensors by assigning different weights to the data from different sensor sources through weighted fusion, that is, assigning a weight value to the data of each sensor, for motor current I, rolling pressure P, and equipment temperature T, assigning a weight w to each sensor I 、w P and w T , the weighted mean Y is: For other sensor data, weighted averaging is used to fuse the data according to their respective weights to obtain comprehensive load data, and the weighted fused comprehensive load data is output for use by subsequent dynamic load balancing modules and load adjustment modules.

[0016] Furthermore, the specific steps of the dynamic load balancing module are:

[0017] Data collection: Obtain historical load data and current load data collected in real time by the load monitoring module, and pre-process the collected data;

[0018] Load prediction: Use machine learning models to train preprocessed data to predict the load change trend in the future and consider multiple factors, namely raw material specifications, rolling process parameters, and production plan changes to optimize the prediction model;

[0019] Balance analysis: Compare the predicted load with the rated load of each rolling mill station to analyze whether there is load imbalance;

[0020] Strategy generation: Based on the analysis results of load imbalance, the corresponding load adjustment strategy is generated to achieve dynamic load balancing, and the generated load adjustment strategy is passed to the load adjustment module to perform load adjustment;

[0021] Feedback monitoring: Monitor real-time load data after load adjustment, evaluate the adjustment effect, and make policy adjustments as needed.

[0022] Furthermore, the dynamic load balancing module is used to predict future load changes through time series analysis in a machine learning algorithm, and the prediction process is as follows:

[0023] Data collection and preprocessing: Collect historical load data and current load data collected in real time by the load monitoring module, that is, the collected time series load data is Y t , t=1,2,…,n, perform stationarity test and processing on the data to meet the model requirements;

[0024] Model construction: Construct an autoregressive integrated moving average ARMA model and use historical data to train the model to learn the law of load data changes over time. The algorithm formula is: c is a constant term, φ i is the autoregressive coefficient, θ j is the moving average coefficient, ∈ t is the white noise error term;

[0025] Parameter estimation and model validation: For the ARMA model, the least squares method is used to estimate the model parameters φ i ,θ j and c, i.e. Perform a residual test on the estimated model to check whether the residual is white noise. If the residual is not white noise, readjust the order and parameters of the model.

[0026] Load forecasting: Use the estimated model to forecast the load for a period of time in the future, and predict the load at the next h moments, that is, Y n+1 ,Y n+2 ,…,Y n+h .

[0027] Furthermore, the specific steps of the load adjustment module are:

[0028] Receiving predicted load data: first, receiving the predicted load data of each rolling mill station in the future period of time output by the dynamic load balancing module, and adjusting the working parameters of each rolling mill station according to the predicted results;

[0029] Analyze the current load status: Combine real-time load monitoring data and forecast data to analyze the current load status of each rolling mill station and determine whether there is overload or underload;

[0030] Formulate load adjustment strategies: According to the analysis results, formulate load adjustment strategies, including but not limited to adjusting the rolling speed, changing the rolling process parameters, reallocating production tasks to different rolling mill stations, and using intelligent optimization algorithms to find the optimal parameter adjustment plan;

[0031] Perform load adjustment: With the help of high-performance speed regulation and control devices, the working parameters of each rolling mill station are accurately adjusted according to the established strategy, including adjusting the motor speed, changing the roll gap, and adjusting the cooling water flow;

[0032] Monitor adjustment effects: During the adjustment process, continuously monitor the load status and production efficiency of each rolling mill station, provide feedback based on the adjustment effect, and optimize the load adjustment strategy to adapt to new production conditions and load changes.

[0033] Furthermore, the load adjustment module uses linear programming in the intelligent optimization algorithm to formulate the optimal load distribution strategy during the process of formulating the load adjustment strategy. The optimization process is as follows:

[0034] Define the decision variable: x i represents the workload assigned to the i-th mill station, where i = 1, 2, ..., n, and n is the total number of mill stations;

[0035] Determine the objective function: minimize the total energy consumption, i.e. c i represents the energy consumption of the i-th rolling mill station to process unit workload, then the objective function is:

[0036] Establish constraints: Constraints include production capacity constraints, production demand constraints, and equipment load limits. The workload of each rolling mill station cannot exceed its maximum production capacity. The total production demand D is the sum of the workload of all rolling mill stations.

[0037] Analyze the solution and formulate load adjustment strategy: Based on the calculated optimal solution Analyze the optimal workload of each rolling mill station and formulate corresponding load adjustment strategies, i.e. adjust the rolling speed, change the rolling process parameters, and reallocate production tasks;

[0038] Implement load adjustment and monitor the effect: adjust each rolling mill station according to the formulated load adjustment strategy, and monitor the load status and production efficiency after adjustment.

[0039] Furthermore, the specific steps of the intelligent control module are:

[0040] Coordinate and manage various modules: The intelligent control module ensures that the load monitoring module, dynamic load balancing module, load adjustment module and energy management module work together to monitor the working status of each module;

[0041] Production plan matching: According to the requirements of the production plan, the intelligent control module adjusts the working parameters of each module and monitors the equipment status in real time;

[0042] Load situation analysis: Based on the load prediction results provided by the dynamic load balancing module, the intelligent control module analyzes the load situation, decides whether to adjust the load, and adjusts the frequency and accuracy of load monitoring according to the actual situation;

[0043] Load adjustment parameter range: According to production requirements and equipment capabilities, the intelligent control module adjusts the parameter range of the load adjustment module and handles uncertainty and ambiguity through fuzzy logic control.

[0044] Furthermore, the intelligent control module uses the membership function of fuzzy logic control to quantify the degree of uncertainty, and the process is:

[0045] Define input variables and output variables: Input variables are equipment status parameters, i.e. temperature, pressure, speed, production plan parameters, i.e. output requirements, product specifications, load monitoring data, i.e. actual load, load change rate; output variables are control strategy parameters, i.e. frequency adjustment of load monitoring, parameter range change of load adjustment;

[0046] Fuzzification: Convert the exact value of the input variable into the membership degree in the fuzzy set. For example, if the input variable is the equipment temperature T, define the fuzzy set "low temperature", "medium temperature", and "high temperature", and their corresponding membership functions are μ 低温 (T), μ 中温 (T), μ 高温 (T);

[0047] Formulate fuzzy rules: Based on historical data and intelligent control strategies, formulate fuzzy rules, including but not limited to: "When the equipment temperature is high and the load change rate is large, the load monitoring frequency increases";

[0048] Fuzzy reasoning: Reasoning is performed based on the membership of the input variables and fuzzy rules. The membership of the high temperature of the equipment in the rule antecedent is A, the membership of the large load change rate is B, and the membership of the increasing load monitoring frequency in the rule consequence is C. The fuzzy reasoning algorithm is used, that is, F = A × B → C;

[0049] Defuzzification: Convert the result of fuzzy reasoning into an accurate output value, that is, the reasoning result is a fuzzy set F, whose membership function is μ F (x), the exact output value y is:

[0050] Output control decision: The precise value obtained by defuzzification is applied to the actual control decision, that is, adjusting the load monitoring frequency and the parameter range of load adjustment.

[0051] Furthermore, the optimization system also includes an energy management module to monitor, analyze and optimize the energy consumption in the entire rolling process in real time, and obtain the power consumption data of each equipment in the entire rolling process in real time, including but not limited to the power consumption of each rolling mill station, motor, and auxiliary equipment. At the same time, it collects load condition data, i.e., the actual load size, load change rate, and combines the load condition and production progress to calculate the energy consumption index per unit product and adjust the working parameters of each rolling mill station.

[0052] Compared with the prior art, the energy-saving steel rolling equipment optimization system has the following beneficial effects:

[0053] 1. The present invention uses real-time and accurate load monitoring combined with advanced machine learning models to perform load prediction, and based on this, performs dynamic load balancing adjustment, which can effectively avoid overloading of some rolling mills and light-load idle states of other rolling mills, so that the entire rolling equipment always operates under the optimal load state, greatly reducing energy waste and significantly improving energy utilization efficiency. In addition, the intelligent control module adjusts the frequency and accuracy of load monitoring according to the production plan and real-time load conditions, and further optimizes energy management.

[0054] 2. The present invention can ensure that each device always operates in the best state by intelligently adjusting the working parameters of each rolling mill station, avoiding production interruptions and inefficient operation due to load imbalance. The intelligent optimization algorithm and high-performance speed regulation and control device of the load adjustment module can quickly respond to load changes, shorten the adjustment cycle, and improve the overall flexibility and response speed of the production line. The real-time monitoring and feedback mechanism ensures that the system can detect and solve problems in a timely manner, reduce downtime, and thus improve production efficiency.

[0055] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0057] Figure 1 The present invention is an operation flow chart of an optimization system for steel rolling equipment to reduce energy consumption.

[0058] Figure 2 A block diagram of a steel rolling equipment optimization system for reducing energy consumption. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] Embodiment 1

[0061] The present embodiment provides a specific implementation process of a steel rolling equipment optimization system for reducing energy consumption. The system can effectively avoid overload and underload phenomena and reduce energy waste by real-time monitoring of the load status of each rolling mill station and dynamically adjusting the load distribution. It can also intelligently adjust the working parameters of each rolling mill station according to actual needs during the rolling process to achieve reasonable distribution and use of energy consumption, thereby significantly reducing energy consumption overall.

[0062] In the specific implementation, first, various types of high-precision sensors are installed at key locations of each rolling mill station according to the sensor deployment requirements. For example, a pressure sensor is installed between the roll bearing seat and the arch to measure the rolling pressure in real time; temperature sensors are installed on the surface and inside of the roll to monitor the roll temperature; current sensors are installed at the motor input end to obtain motor current data; vibration sensors are installed on the main structure of the equipment to reflect the vibration frequency of the equipment and collect multi-dimensional load data in real time, including rolling pressure P, motor power I, speed R, load size LL, temperature T, roll temperature Tr and equipment vibration frequency V. The load monitoring module integrates these data through weighted fusion and outputs the weighted fused comprehensive load data for use by subsequent modules.

[0063] Then, the dynamic load balancing module uses historical data and real-time collected load data to perform load forecasting through the machine learning ARM model. During the model construction process, the formula is used Conduct training and perform residual test on the estimated model. If the residual is not white noise, readjust the order and parameters of the model. Use the estimated model to predict the load for a period of time in the future, analyze whether there is a load imbalance, and generate a corresponding load adjustment strategy based on the analysis results.

[0064] Next, the load adjustment module receives the predicted load data of each rolling mill station in the future period output by the dynamic load balancing module, and analyzes the current load status of each rolling mill station in combination with the real-time load monitoring data to determine whether there is overload or underload. Based on the analysis results, a load adjustment strategy is formulated. For example, the optimal load distribution strategy is formulated using linear programming in the intelligent optimization algorithm. The decision variable x is defined. i represents the workload assigned to the i-th mill station, where i = 1, 2, ..., n, n is the total number of mill stations, and determines the objective function Constraints include production capacity constraints, production demand constraints, and equipment load limits. The workload of each rolling mill station cannot exceed its maximum production capacity. The total production demand D is the sum of the workload of all rolling mill stations. According to the calculated optimal solution Analyze the optimal workload of each rolling mill station and formulate corresponding load adjustment strategies, namely, adjust the rolling speed, change the rolling process parameters, and reallocate production tasks. With the help of high-performance speed regulation and control devices, accurately adjust the working parameters of each rolling mill station according to the formulated strategy, including adjusting the motor speed, changing the roll gap, and adjusting the cooling water flow. During the adjustment process, continuously monitor the load status and production efficiency of each rolling mill station, provide feedback based on the adjustment effect, and optimize the load adjustment strategy to adapt to new production conditions and load changes.

[0065] Finally, the intelligent control module ensures that the load monitoring module, dynamic load balancing module, load adjustment module and energy management module work together, monitors the working status of each module, adjusts the working parameters of each module according to the requirements of the production plan, monitors the equipment status in real time, analyzes the load situation based on the load prediction results provided by the dynamic load balancing module, decides whether to adjust the load, and adjusts the frequency and accuracy of load monitoring according to actual conditions. The energy management module monitors energy consumption in real time, collects power consumption data and load situation data, calculates the energy consumption indicators of unit products, and adjusts the working parameters accordingly to further optimize energy use.

[0066] To sum up, this embodiment achieves dynamic load balance, and the system can not only reduce energy consumption but also improve production efficiency. Since the workload of each rolling mill station is more balanced, the operation of the equipment is more stable, which reduces equipment failures and maintenance time caused by overload, and also reduces the waste of production capacity caused by light load. In this way, the overall steel rolling process can run more efficiently, increase the production volume per unit time, and thus improve production efficiency.

[0067] Embodiment 2

[0068] A steel rolling equipment optimization system for reducing energy consumption in this embodiment particularly emphasizes intelligent adjustment of the working parameters of each rolling mill station. The system can ensure that each equipment always operates in the best condition, avoiding production interruptions or inefficient operation due to load imbalance. The intelligent optimization algorithm and high-performance speed regulation and control device of the load adjustment module can quickly respond to load changes, shorten the adjustment cycle, and improve the overall flexibility and response speed of the production line. The real-time monitoring and feedback mechanism ensures that the system can detect and solve problems in a timely manner, reduce fault downtime, and thus improve production efficiency.

[0069] First, the predicted load data of each rolling mill station in the future period of time is received from the dynamic load balancing module. For example, the load of a rolling mill station at a certain time in the future is predicted to be L predicted , combined with real-time load monitoring data L real-time , analyze the current load status of each rolling mill station and determine whether there is overload (L real-time >L predicted ) and light load (L real-time <L predicted ), and formulate a load adjustment strategy based on the analysis results. The formulation of the load adjustment strategy includes but is not limited to adjusting the rolling speed, changing the rolling process parameters, and reallocating production tasks to different rolling mill stations.

[0070] Then, the optimal load distribution strategy is formulated using linear programming in the intelligent optimization algorithm, and the decision variable x is definedi The amount of work assigned to the i-th mill station, where i = 1, 2, ..., n, n is the total number of mill stations, determines the objective function Establish constraints, including capacity constraints Production demand constraints According to the calculated optimal solution Formulate specific adjustment measures, such as adjusting the rolling speed, changing the rolling process parameters, and reallocating production tasks. With the help of high-performance speed regulation and control devices, accurately adjust the working parameters of each rolling mill station. For example, when adjusting the motor speed, calculate the required speed adjustment amount according to the load conditions and make corresponding adjustments. During the adjustment process, continuously monitor the load status and production efficiency of each rolling mill station, and optimize the load adjustment strategy based on real-time feedback data to ensure that it adapts to new production conditions and load changes.

[0071] Finally, the intelligent control module comprehensively coordinates and manages the working status of each module, monitors the operation of the load monitoring module, dynamic load balancing module, load adjustment module and energy management module in real time, ensures that they work together efficiently, and intelligently adjusts the working parameters of each module according to the requirements of the production plan. According to the product specifications and output requirements specified in the production plan, the required load distribution and equipment operating parameters are calculated, and the settings of each module are adjusted accordingly. Based on the load prediction results provided by the dynamic load balancing module, the load situation is deeply analyzed, and fuzzy logic control is used to deal with uncertainty and ambiguity. The input variables are defined as equipment state parameters, namely temperature T, pressure P, speed N, and production plan parameters, namely Q. req 、Product Specifications spec , load monitoring data, that is, the actual load L actual , load change rate R lood The output variable is the parameter of the control strategy, that is, the frequency adjustment value f of load monitoring adjust , load adjustment parameter range change ΔP range , convert the exact value of the input variable into the membership degree in the fuzzy set. For example, if the input variable is the equipment temperature T, define the fuzzy set "low temperature", "medium temperature", and "high temperature", and their corresponding membership functions are μ 低温 (T), μ 中温 (T), μ 高温(T), formulate fuzzy rules based on historical data and intelligent control strategies, for example: "When the equipment temperature is high and the load change rate is large, the load monitoring frequency increases", and perform reasoning based on the membership of the input variables and fuzzy rules. For example, the membership of the equipment temperature being high in the rule antecedent is A, the membership of the load change rate being large is B, and the membership of the load monitoring frequency increasing in the rule consequence is C. Use the fuzzy reasoning algorithm, i.e., R(A,B)→C, to convert the result of fuzzy reasoning into an accurate output value. The reasoning result is a fuzzy set F, whose membership function is μ F (x), the exact output value is The precise value obtained by defuzzification is applied to the actual control decision, that is, adjusting the load monitoring frequency and the parameter range of load adjustment.

[0072] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A steel rolling equipment optimization system for reducing energy consumption, characterized in that: The components of the optimization system include: load monitoring module, dynamic load balancing module, load adjustment module, and intelligent control module; The load monitoring module collects multi-dimensional load data of each rolling mill station in real time, including basic parameters of rolling pressure, motor current, speed, load size and temperature, and also covers roll temperature and equipment vibration frequency to reflect the equipment operation status and load conditions; The dynamic load balancing module uses historical data and load data collected by the load monitoring module to predict load changes in the future through a machine learning model; The load adjustment module accurately adjusts the working parameters of each rolling mill station based on the output results of the dynamic load balancing module with the help of intelligent optimization algorithm and high-performance speed regulation and control device; The intelligent control module is responsible for coordinating and managing the working status of each module, formulating an overall control strategy according to the production plan, equipment status and real-time load conditions, and automatically adjusting the frequency and accuracy of load monitoring, and flexibly configuring the parameter range of load adjustment.

2. The steel rolling equipment optimization system for reducing energy consumption according to claim 1, characterized in that: The specific steps of the load monitoring module are: Sensor deployment: Various types of high-precision sensors are installed at key locations of each rolling mill station, i.e., pressure sensors are installed between the roller bearing seat and the arch, temperature sensors are installed on the surface and inside of the roller, current sensors are installed at the motor inlet end, and vibration sensors are installed on the main structure of the equipment; Data collection: These sensors collect multi-dimensional load data in real time, including rolling pressure, motor current, speed, load size, temperature, roll temperature and equipment vibration frequency; Data fusion: Use weighted fusion to integrate data from different sensors to form a comprehensive load monitoring view, analyze the relationship between different parameters, and extract load data information.

3. The steel rolling equipment optimization system for reducing energy consumption according to claim 2, characterized in that: The load monitoring module integrates the information of various sensors by assigning different weights to the data from different sensor sources through weighted fusion, that is, assigning a weight value to the data of each sensor. For the motor current I, rolling pressure P, and equipment temperature T, a weight w is assigned to each sensor. I 、w P and w T , the weighted mean Y is: For other sensor data, weighted averaging is used to fuse the data according to their respective weights to obtain comprehensive load data, and the weighted fused comprehensive load data is output for use by subsequent dynamic load balancing modules and load adjustment modules.

4. The steel rolling equipment optimization system for reducing energy consumption according to claim 1, characterized in that: The specific steps of the dynamic load balancing module are: Data collection: Obtain historical load data and current load data collected in real time by the load monitoring module, and pre-process the collected data; Load prediction: Use machine learning models to train preprocessed data to predict the load change trend in the future and consider multiple factors, namely raw material specifications, rolling process parameters, and production plan changes to optimize the prediction model; Balance analysis: Compare the predicted load with the rated load of each rolling mill station to analyze whether there is load imbalance; Strategy generation: Based on the analysis results of load imbalance, the corresponding load adjustment strategy is generated to achieve dynamic load balancing, and the generated load adjustment strategy is passed to the load adjustment module to perform load adjustment; Feedback monitoring: Monitor real-time load data after load adjustment, evaluate the adjustment effect, and make policy adjustments as needed.

5. The steel rolling equipment optimization system for reducing energy consumption according to claim 4, characterized in that: The dynamic load balancing module is used to predict future load changes through time series analysis in the machine learning algorithm. The prediction process is as follows: Data collection and preprocessing: Collect historical load data and current load data collected in real time by the load monitoring module, that is, the collected time series load data is Y t , t=1,2,…,n, perform stationarity test and processing on the data to meet the model requirements; Model construction: Construct an autoregressive integrated moving average ARMA model and use historical data to train the model to learn the law of load data changes over time. The algorithm formula is: c is a constant term, φ i is the autoregressive coefficient, θ j is the moving average coefficient, ∈ t is the white noise error term; Parameter estimation and model validation: For the ARMA model, the least squares method is used to estimate the model parameters φ i ,θ j and c, i.e. Perform a residual test on the estimated model to check whether the residual is white noise. If the residual is not white noise, readjust the order and parameters of the model. Load forecasting: Use the estimated model to forecast the load for a period of time in the future, and predict the load at the next h moments, that is, Y n+1 ,Y n+2 ,…,Y n+h .

6. The steel rolling equipment optimization system for reducing energy consumption according to claim 1, characterized in that: The specific steps of the load adjustment module are: Receiving predicted load data: first, receiving the predicted load data of each rolling mill station in the future period of time output by the dynamic load balancing module, and adjusting the working parameters of each rolling mill station according to the predicted results; Analyze the current load status: Combine real-time load monitoring data and forecast data to analyze the current load status of each rolling mill station and determine whether there is overload or underload; Formulate load adjustment strategies: According to the analysis results, formulate load adjustment strategies, including but not limited to adjusting the rolling speed, changing the rolling process parameters, reallocating production tasks to different rolling mill stations, and using intelligent optimization algorithms to find the optimal parameter adjustment plan; Perform load adjustment: With the help of high-performance speed regulation and control devices, the working parameters of each rolling mill station are accurately adjusted according to the established strategy, including adjusting the motor speed, changing the roll gap, and adjusting the cooling water flow; Monitor adjustment effects: During the adjustment process, continuously monitor the load status and production efficiency of each rolling mill station, provide feedback based on the adjustment effect, and optimize the load adjustment strategy to adapt to new production conditions and load changes.

7. The steel rolling equipment optimization system for reducing energy consumption according to claim 6, characterized in that: The load adjustment module uses linear programming in the intelligent optimization algorithm to formulate the optimal load distribution strategy during the process of formulating the load adjustment strategy. The optimization process is as follows: Define the decision variable: x i represents the workload assigned to the i-th rolling mill station, where i = 1, 2, ..., n, and n is the total number of rolling mill stations; Determine the objective function: minimize the total energy consumption, i.e. c i represents the energy consumption of the i-th rolling mill station to process unit workload, then the objective function is: Establish constraints: Constraints include production capacity constraints, production demand constraints, and equipment load limits. The workload of each rolling mill station cannot exceed its maximum production capacity. The total production demand D is the sum of the workload of all rolling mill stations. Analyze the solution and formulate load adjustment strategy: Based on the calculated optimal solution Analyze the optimal workload of each rolling mill station and formulate corresponding load adjustment strategies, i.e. adjust the rolling speed, change the rolling process parameters, and reallocate production tasks; Implement load adjustment and monitor the effect: adjust each rolling mill station according to the formulated load adjustment strategy, and monitor the load status and production efficiency after adjustment.

8. The steel rolling equipment optimization system for reducing energy consumption according to claim 1, characterized in that: The specific steps of the intelligent control module are: Coordinate and manage various modules: The intelligent control module ensures that the load monitoring module, dynamic load balancing module, load adjustment module and energy management module work together to monitor the working status of each module; Production plan matching: According to the requirements of the production plan, the intelligent control module adjusts the working parameters of each module and monitors the equipment status in real time; Load situation analysis: Based on the load prediction results provided by the dynamic load balancing module, the intelligent control module analyzes the load situation, decides whether to adjust the load, and adjusts the frequency and accuracy of load monitoring according to the actual situation; Load adjustment parameter range: According to production requirements and equipment capabilities, the intelligent control module adjusts the parameter range of the load adjustment module and handles uncertainty and ambiguity through fuzzy logic control.

9. The steel rolling equipment optimization system for reducing energy consumption according to claim 8, characterized in that: The intelligent control module uses the membership function of fuzzy logic control to quantify the degree of uncertainty, and the process is: Define input variables and output variables: Input variables are equipment status parameters, namely temperature T, pressure P, speed N, and production plan parameters, namely Q req 、Product Specifications spec , load monitoring data, that is, the actual load L actual , load change rate R lood , the output variables are the parameters of the control strategy, i.e., the frequency adjustment of load monitoring and the parameter range change of load adjustment; Fuzzification: Convert the exact value of the input variable into the membership degree in the fuzzy set. For example, if the input variable is the equipment temperature T, define the fuzzy sets "low temperature", "medium temperature", and "high temperature", and their corresponding membership functions are μ 低温 (T), μ 中温 (T), μ 高温 (T); Formulate fuzzy rules: According to historical data and intelligent control strategies, formulate fuzzy rules, including but not limited to: "When the equipment temperature is high and the load change rate is large, the load monitoring frequency increases"; Fuzzy reasoning: Reasoning is performed based on the membership of the input variables and fuzzy rules. The membership of the high temperature of the equipment in the rule antecedent is A, the membership of the large load change rate is B, and the membership of the increasing load monitoring frequency in the rule consequence is C. The fuzzy reasoning algorithm is used, that is, F = A × B → C; Defuzzification: Convert the result of fuzzy reasoning into an accurate output value, that is, the reasoning result is a fuzzy set F, whose membership function is μ F (x), the exact output value y is: Output control decision: The precise value obtained by defuzzification is applied to the actual control decision, that is, adjusting the load monitoring frequency and the parameter range of load adjustment.

10. The steel rolling equipment optimization system for reducing energy consumption according to claim 1, characterized in that: The optimization system also includes an energy management module to monitor, analyze and optimize the energy consumption in the entire rolling process in real time, and obtain the power consumption data of each equipment in the entire rolling process in real time, including but not limited to the power consumption of each rolling mill station, motor, and auxiliary equipment. At the same time, it collects load condition data, that is, the actual load size, load change rate, and combines the load condition and production progress to calculate the energy consumption index per unit product and adjust the working parameters of each rolling mill station.

Images