Heating furnace forging energy-saving scheduling method based on energy-saving scheduling strategy

By acquiring and preprocessing the energy consumption and load data of heating furnace forging, using integrated and optimization algorithms to generate energy-saving scheduling data, and comparing and adjusting it in real-time operating data, the problem of difficult to optimize the energy-saving scheduling of heating furnace forging in the prior art is solved. It has achieved reduced energy consumption and improved energy use efficiency, ensuring the sustainability and stability of energy-saving effects.

CN118897526AInactive Publication Date: 2024-11-05JIANGSU SOUTH ENERGY SAVING TECHNOLOGY CO LTD

Patent Information

Application Number
CN202410950615.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-16
Publication Date
2024-11-05
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

During the energy-saving scheduling process of existing heating furnaces, it is difficult to optimize the scheduling of forging energy consumption data and load demand data, resulting in high energy consumption and low energy use efficiency, and the inability to effectively predict and schedule load demand, resulting in energy waste and production bottlenecks. In addition, real-time monitoring and dynamic adjustment are difficult, which affects the sustainability and stability of energy-saving effects.

Method used

By acquiring and preprocessing forging energy consumption and load data, using integrated algorithms for prediction, using optimization algorithms to generate energy-saving scheduling data, and deeply analyzing and allocating scheduling data through analysis algorithms, comparing with real-time running data, real-time monitoring and adjustment , to ensure the sustainability and stability of energy-saving effects.

Benefits of technology

Effectively reduce the energy consumption of heating furnaces, improve energy use efficiency, achieve balance and optimization of the production process, avoid energy waste, ensure the sustainability and stability of energy-saving effects, provide scientific energy-saving strategies, reduce production costs, and improve enterprise economic benefits.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118897526A_ABST
    Figure CN118897526A_ABST
Patent Text Reader

Abstract

The invention discloses a heating furnace forging energy-saving scheduling method based on an energy-saving scheduling strategy, and relates to the technical field of energy-saving scheduling, and the heating furnace forging energy-saving scheduling method based on the energy-saving scheduling strategy comprises the following steps: obtaining forging energy consumption characteristic data and forging load characteristic data; predicted energy consumption data and predicted load demand data of the heating furnace are obtained; energy-saving scheduling data of heating furnace forging are generated; energy-saving scheduling data are distributed for forging of the heating furnace; and whether the distributed energy-saving scheduling data conforms to the preset heating furnace forging energy-saving scheduling or not is evaluated. According to the method, the energy consumption of the heating furnace can be effectively reduced, the energy use efficiency is improved, and the balance and optimization of the production process can be realized by predicting and scheduling the forging load demand, so that the deviation and deficiency of an energy-saving scheduling strategy can be found in time, and the efficient utilization of energy can be realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of energy-saving scheduling, and in particular to a heating furnace forging energy-saving scheduling method based on an energy-saving scheduling strategy. Background Art

[0002] With the rapid development of modern manufacturing technology, the research focus in the field of production scheduling has gradually shifted to intelligent manufacturing and green manufacturing. Especially driven by sustainable development planning, energy has become one of the most important resources for manufacturing companies. How to reduce energy loss in the manufacturing process is a manufacturing problem that needs to be solved urgently. The problem of energy-saving scheduling in processing workshops is widely present in actual production workshops. In the processing stage of mixed processing workshops, the energy consumption of heat treatment and other hot processing equipment (such as heating furnaces) is significantly higher than that of cold processing equipment such as machining. However, since the process of heating furnace equipment is difficult to control, energy loss cannot be accurately counted. In terms of energy-saving scheduling of forging production, scheduling methods are mainly concentrated in a single stage of forging production. Most of them are scheduling of heating furnaces, mainly methods such as combined classification of forgings, and a small part is scheduling in the forging stage, such as scheduling methods for reasonable replacement of molds.

[0003] The existing heating furnace forging energy-saving scheduling process is not convenient for optimizing the scheduling of forging energy consumption data and load demand data, and cannot effectively reduce the energy consumption of the heating furnace, which reduces the energy utilization efficiency. It is also not convenient to predict and schedule forging load demand, and it is not convenient to achieve balance and optimization of the production process, resulting in energy waste and production bottlenecks. At the same time, it is not convenient to compare with real-time operation data, and it is not convenient to timely discover deviations and deficiencies in energy-saving scheduling strategies. It is not convenient for real-time monitoring and dynamic adjustment, and cannot ensure the sustainability and stability of energy-saving effects.

[0004] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention proposes a heating furnace forging energy-saving scheduling method based on an energy-saving scheduling strategy, which solves the problems proposed in the above background technology that the existing heating furnace forging energy-saving scheduling process is not convenient for optimizing the scheduling of forging energy consumption data and load demand data, cannot effectively reduce the energy consumption of the heating furnace, reduces the energy utilization efficiency, is not convenient for predicting and scheduling forging load demand, is not convenient for achieving balance and optimization of the production process, causes energy waste and production bottlenecks, and at the same time, is not convenient for comparison with real-time operation data, is not convenient for timely discovering deviations and deficiencies in the energy-saving scheduling strategy, is not convenient for real-time monitoring and dynamic adjustment, and cannot ensure the sustainability and stability of the energy-saving effect.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0007] A heating furnace forging energy-saving scheduling method based on an energy-saving scheduling strategy, the heating furnace forging energy-saving scheduling method based on an energy-saving scheduling strategy comprises the following steps:

[0008] S1. Acquire forging energy consumption data and forging load data of a heating furnace, and pre-process the forging energy consumption data and forging load data to obtain forging energy consumption characteristic data and forging load characteristic data;

[0009] S2. Integrate the obtained forging energy consumption characteristic data and forging load characteristic data using an integration algorithm to obtain predicted energy consumption data and predicted load demand data of the heating furnace;

[0010] S3. Optimize the predicted energy consumption data and the predicted load demand data using an optimization algorithm to generate energy-saving scheduling data for heating furnace forging;

[0011] S4. Based on the analysis algorithm, the generated energy-saving scheduling data of the heating furnace forging is deeply analyzed, and the energy-saving scheduling data is allocated to the heating furnace forging;

[0012] S5. Acquire real-time operation data during the heating furnace forging process, compare the real-time operation data with the allocated energy-saving scheduling data, and evaluate whether the allocated energy-saving scheduling data is consistent with the preset heating furnace forging energy-saving scheduling.

[0013] Further, obtaining the forging energy consumption data and forging load data of the heating furnace, and preprocessing the forging energy consumption data and forging load data to obtain the forging energy consumption characteristic data and forging load characteristic data includes the following steps:

[0014] S11. Deploy data acquisition nodes and use communication protocols to obtain real-time forging energy consumption data and forging load data of the heating furnace;

[0015] S12, obtaining the original forging energy consumption data and forging load data of the heating furnace from the data acquisition node, and converting the original forging energy consumption data and forging load data of the heating furnace from the time domain to the frequency domain through wavelet transform, and screening out the wave field records of each frequency band containing environmental interference;

[0016] S13, tracking the environmental interference waves one by one in the wave field records of each frequency band, and obtaining the interference wave direction at the calculation sample point;

[0017] S14, selecting a number of windows centered on the calculation sample point to perform median filtering, and restoring the environmental interference signal at the calculation sample point;

[0018] S15, recovering the interference signals in the wave field records of each frequency band one by one, and converting the interference wave field back to the time domain by inverse wavelet transform to obtain the entire wave field information of the interference wave;

[0019] S16. Subtract the interference wave field from the original forging energy consumption data and forging load data of the heating furnace to obtain the denoised effective signal wave field, and generate denoised forging energy consumption characteristic data and forging load characteristic data based on the denoised effective signal wave field.

[0020] Further, the obtained forging energy consumption characteristic data and forging load characteristic data are integrated by using an integration algorithm to obtain the predicted energy consumption data and predicted load demand data of the heating furnace, including the following steps:

[0021] S21, inputting an initial sample set of forging energy consumption characteristic data and forging load characteristic data;

[0022] S22, classifying all forging energy consumption characteristic data and forging load characteristic data in the initial sample set to obtain a number of sample subsets of forging energy consumption characteristic data and forging load characteristic data;

[0023] S23, performing loop processing on each sample subset to obtain a coefficient matrix;

[0024] S24, rearranging the coefficient matrix, and transforming the initial sample set through the coefficient matrix to generate new forging energy consumption characteristic data and forging load characteristic data samples;

[0025] S25, training the prediction model based on the new forging energy consumption characteristic data and forging load characteristic data samples to obtain sub-models of the predicted energy consumption and predicted load demand of the heating furnace, and returning to step S22, looping a preset number of times to obtain an integrated prediction model;

[0026] S26. Use the integrated prediction model to predict the initial sample set, and use the forging energy consumption characteristic data and the forging load characteristic data to generate the predicted energy consumption data and the predicted load demand data of the heating furnace.

[0027] Further, performing loop processing on each sample subset to obtain a coefficient matrix includes the following steps:

[0028] S231, resampling the sample subsets of forging energy consumption characteristic data and forging load characteristic data by using a stratified sampling method to generate new sample subsets of forging energy consumption characteristic data and forging load characteristic data;

[0029] S232, performing principal component analysis on a sample subset of new forging energy consumption characteristic data and forging load characteristic data to obtain a principal component coefficient vector related to energy consumption and load changes during the heating furnace forging process;

[0030] S233. Repeat steps S231 to S232 to obtain several groups of principal component coefficient vectors, and combine the coefficient vectors into a principal component coefficient matrix.

[0031] Furthermore, the predicted energy consumption data and the predicted load demand data are optimized by using an optimization algorithm, and the energy-saving scheduling data for heating furnace forging is generated, which includes the following steps:

[0032] S31, determining the number of parameters for predicting energy consumption data and predicting load demand data during the heating furnace forging process, and setting the maximum number of iterations and parameter adjustment probability of the optimization process;

[0033] S32, using a heuristic algorithm to generate preliminary energy-saving scheduling data for forging of a number of heating furnaces;

[0034] S33, calculating the fitness value of the preliminary energy-saving scheduling data of each heating furnace forging, and recording the status of the best and second-best energy-saving scheduling data of the heating furnace forging;

[0035] S34, using Levi flight to adjust the state of the energy-saving scheduling data of the heating furnace forging, and repeating step S33;

[0036] S35, retaining the energy-saving scheduling data of the current heating furnace forging or adopting new energy-saving scheduling data of the heating furnace forging according to a specific criterion formula, and repeating step S33;

[0037] S36, mutating the energy-saving scheduling data of the heating furnace forging by a heuristic search algorithm, and repeating step S33;

[0038] S37, loop iterate and execute steps S34 to S36 until a preset iteration termination condition is met;

[0039] S38. After the iteration is completed, the global optimal solution is output as the energy-saving scheduling data for the heating furnace forging.

[0040] Furthermore, the specific criterion formula is:

[0041]

[0042] in, It is represented as the new state of the energy-saving scheduling data of the ath heating furnace forging after c+1 iterations;

[0043] It is represented as the current state of the energy-saving scheduling data of the ath heating furnace forging at the beginning of the cth iteration;

[0044] step a It is represented as the Levy flight step length of the energy-saving scheduling data of the ath heating furnace forging in each iteration;

[0045] b zbest It is represented as the historical best state of the energy-saving scheduling data of the ath heating furnace forging;

[0046] b gbest and b gsecong They are respectively represented as the global historical best state and the global historical second best state in the energy-saving scheduling data of all heating furnace forgings;

[0047] x1, x2, and x3 represent the learning factors of the historical optimal state, the global historical optimal state, and the global historical suboptimal state of the energy-saving scheduling data of the heating furnace forging, respectively.

[0048] Further, based on the analysis algorithm, the generated energy-saving scheduling data of the heating furnace forging is deeply analyzed, and the energy-saving scheduling data of the heating furnace forging is allocated, including the following steps:

[0049] S41, setting a sample set of energy-saving scheduling data for heating furnace forging, and presetting the number of mutation and crossover operations;

[0050] S42, performing a mutation operation on the energy-saving scheduling data sample set of the heating furnace forging, calculating the difference vector between each sample, determining the best energy-saving scheduling data sample in the energy-saving scheduling data sample set of the heating furnace forging, and using the best energy-saving scheduling data sample as a new mutation sample;

[0051] S43, performing a crossover operation on the new variant sample, and determining the best energy-saving scheduling data sample in the energy-saving scheduling data sample set for heating furnace forging;

[0052] S44, using an analysis algorithm to perform a new cluster analysis on the energy-saving scheduling data samples after the mutation crossover, to determine the cluster where each energy-saving scheduling data sample is located and the optimal distance between the samples;

[0053] S45, comparing the mutation crossover result with the objective function, and selecting the energy-saving scheduling data sample with the best objective function value as the energy-saving scheduling data sample in the new heating furnace forging energy-saving scheduling data sample set;

[0054] S46. Determine whether the termination condition is met. If so, end the optimization process, mark the current best energy-saving scheduling data sample set for heating furnace forging as a data set that meets the energy-saving requirements of the forging process, and allocate the best energy-saving scheduling data sample set for heating furnace forging as the energy-saving scheduling data for heating furnace forging.

[0055] Furthermore, using the analysis algorithm to perform a new cluster analysis on the energy-saving scheduling data samples after the mutation crossover, determining the cluster where each energy-saving scheduling data sample is located and the optimal distance between the samples includes the following steps:

[0056] S441, randomly selecting a number of energy-saving scheduling data samples from the heating furnace forging energy-saving scheduling data sample set after mutation crossover as the center points of the initial clustering;

[0057] S442, assigning each unassigned energy-saving scheduling data sample to the cluster center point closest to it to form a preliminary cluster group;

[0058] S443, randomly selecting an energy-saving scheduling data sample of a non-clustering center from the energy-saving scheduling data sample set of heating furnace forging, and recording it as a random energy-saving scheduling data sample;

[0059] S444, calculating the total cost change caused by replacing the current cluster center point with a random energy-saving scheduling data sample, and updating the cluster center set;

[0060] S445. When the cluster center point no longer changes, determine the final clustering of each energy-saving scheduling data sample, and calculate the optimal distance between each energy-saving scheduling data sample.

[0061] Furthermore, obtaining real-time operation data during the heating furnace forging process, comparing the real-time operation data with the allocated energy-saving scheduling data, and evaluating whether the allocated energy-saving scheduling data is consistent with the preset heating furnace forging energy-saving scheduling includes the following steps:

[0062] S51, determining key parameters that affect the real-time operation of the heating furnace forging, and setting an initial search range;

[0063] S52, preset an initial value of the evaluation cycle, and set the number of iterations as the end condition of the evaluation process;

[0064] S53, comparing the real-time operation data of the heating furnace during forging with the allocated energy-saving scheduling data, and updating the key parameters according to a preset comparison method;

[0065] S54. Evaluate the energy-saving efficiency of heating furnace forging after each key parameter comparison by statistical methods;

[0066] S55. Calculate the fitness score of each iteration based on the evaluation result of the heating furnace forging energy saving efficiency;

[0067] S56, comparing the fitness scores of two consecutive iterations, and selecting the key parameter update that has the greatest impact on the operation state of the heating furnace as the current best solution;

[0068] S57, increasing the initial value of the evaluation cycle, and if the preset upper limit of the number of iterations is reached, terminating the evaluation process;

[0069] S58. Analyze the matching degree between the energy-saving scheduling data assigned after the evaluation process and the preset heating furnace forging energy-saving scheduling to determine whether there is a significant impact. If there is a significant impact, make adjustments. If not, use the assigned energy-saving scheduling data as the energy-saving scheduling in the heating furnace forging process.

[0070] Furthermore, by means of statistical methods, the energy-saving efficiency of the heating furnace forging after each key parameter comparison is evaluated, including the following steps:

[0071] S541, initializing the verification round number to the first round, and dividing the acquired real-time operation data set in the heating furnace forging process into several subsets. In each round, one subset is selected as a test set, and the union of all the remaining subsets is used as a training set;

[0072] S542. Training the statistical model using the adjusted key parameters on the training set, and testing the predictive performance of the statistical model on the heating furnace forging energy-saving efficiency on the test set;

[0073] S543. Calculate the generalization error of the statistical model based on the actual performance of the key parameters on the test set;

[0074] S544, looping step S541 to step S543 until each subset has been used as a test set;

[0075] S545. Obtain the average value of the generalization errors calculated in all verification rounds as the overall evaluation result of the heating furnace forging energy saving efficiency after each key parameter comparison.

[0076] The beneficial effects of the present invention are:

[0077] 1. The present invention can effectively reduce the energy consumption of the heating furnace and improve the energy utilization efficiency by optimizing the scheduling of forging energy consumption data and load demand data. By predicting and scheduling forging load demand, the balance and optimization of the production process can be achieved to avoid energy waste and production bottlenecks. By comparing real-time operation data, deviations and deficiencies in energy-saving scheduling strategies can be discovered in a timely manner, and real-time monitoring and dynamic adjustment can be achieved to ensure the continuity and stability of energy-saving effects. The energy-saving scheduling data generated through in-depth analysis provides data support for the operation of the heating furnace, which helps decision makers to formulate more scientific and reasonable energy-saving strategies, thereby achieving efficient use of energy, reducing production costs, and optimizing production efficiency.

[0078] 2. The present invention deeply processes the energy consumption and load characteristics through integration algorithm and principal component analysis, and can more accurately predict the energy consumption and load demand of the heating furnace. The integrated prediction model can combine the advantages of multiple sub-models and reduce the risk of overfitting the model to a specific data set, thereby enhancing the generalization ability of the model when facing new data. Based on accurate energy consumption and load predictions, the production plan and energy use of the heating furnace can be arranged more reasonably, avoiding unnecessary energy waste and achieving energy saving: by optimizing energy-saving scheduling, energy consumption is reduced, thereby reducing the operating cost of the heating furnace, improving the economic benefits of the enterprise, and thereby improving the energy-saving efficiency of the heating furnace and the scientific nature of production scheduling.

[0079] 3. The present invention uses an optimization algorithm to find the optimal energy-saving scheduling data to ensure that the heating furnace has the lowest energy consumption during the forging process, thereby improving the overall energy-saving efficiency. The introduction of Levi Flight increases the randomness and exploration ability in the search process, allowing the optimization algorithm to jump out of the local optimal solution, explore a wider solution space, and find a more efficient energy-saving scheduling strategy. By accurately scheduling the operation of the heating furnace and reducing unnecessary energy consumption, the production cost can be significantly reduced and the economic benefits of the enterprise can be improved. By accurately predicting load demand and optimizing energy consumption, the production plan can be arranged more reasonably to ensure the continuity and stability of the production process, avoid energy waste and production delays, and provide strong data support and decision-making suggestions for enterprise management, which can effectively allocate resources and arrange production plans.

[0080] 4. The present invention ensures the optimality of energy-saving scheduling data through meticulous variation and crossover operations, as well as cluster analysis, thereby maximizing the energy efficiency of the heating furnace and reducing energy consumption. Cluster analysis helps managers better understand the relationship between energy consumption and load during the forging process of the heating furnace, thereby making more accurate and scientific decisions in production management. Through accurate energy-saving scheduling data, the production schedule can be arranged more reasonably, avoiding unnecessary energy waste, ensuring the maximization of production efficiency, and thus improving production management efficiency.

[0081] 5. The present invention ensures that the energy depletion of the heating furnace during the forging process is as low as possible through real-time monitoring and analysis, while meeting production needs, thereby improving the overall energy utilization efficiency. By comparing the real-time operation data with the allocated energy-saving scheduling data, the potential energy-saving space in the production process can be revealed, providing a scientific basis for production scheduling, optimizing production processes and energy-saving scheduling strategies. Through real-time monitoring and adjustment, it can ensure that the heating furnace operates in the best state, improve product quality and production efficiency, and through continuous real-time data evaluation and parameter optimization, the energy-saving scheduling strategy of the heating furnace can flexibly adapt to changes in the production process and fluctuations in the external environment, thereby improving the company's ability to respond to uncertain factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] 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 will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0083] Figure 1 It is a flow chart of a heating furnace forging energy-saving scheduling method based on an energy-saving scheduling strategy according to an embodiment of the present invention. DETAILED DESCRIPTION

[0084] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0085] In the description of the present invention, unless otherwise specified, the meaning of "plurality" is two or more. In addition, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0086] According to an embodiment of the present invention, a heating furnace forging energy-saving scheduling method based on an energy-saving scheduling strategy is provided.

[0087] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the heating furnace forging energy-saving scheduling method based on the energy-saving scheduling strategy of an embodiment of the present invention, the heating furnace forging energy-saving scheduling method based on the energy-saving scheduling strategy includes the following steps:

[0088] S1. Acquire forging energy consumption data and forging load data of a heating furnace, and pre-process the forging energy consumption data and forging load data to obtain forging energy consumption characteristic data and forging load characteristic data;

[0089] Specifically, forging energy consumption data include:

[0090] Power consumption: The amount of electrical energy consumed by the heating furnace during the forging process.

[0091] Fuel consumption: If the furnace is heated by fuel, the amount of fuel consumed needs to be recorded, such as natural gas, coal, etc.

[0092] Heat energy consumption: the heat energy consumed by the heating furnace in the process of heating metal materials.

[0093] Cooling water consumption: The amount of water consumed by the heating furnace during the cooling process.

[0094] Forging load data includes:

[0095] Heating temperature: The temperature to which the metal material is heated in the heating furnace.

[0096] Heating time: the time metal materials are heated in a heating furnace.

[0097] Material Type and Weight: The type and weight of the metal material heated in the furnace.

[0098] Forging rate: the forging speed of metal materials, that is, the amount forged per unit time.

[0099] Specifically, the forging energy consumption characteristic data include:

[0100] Energy consumption per unit time: energy consumption per unit time.

[0101] Energy consumption per unit weight: the energy consumed in heating and forging unit weight of material.

[0102] Energy consumption volatility: the degree of fluctuation of energy consumption over time.

[0103] Energy consumption trend: The trend of energy consumption over time.

[0104] Forging load characteristic data include:

[0105] Average heating temperature: the average value of the heating temperature within a certain period of time.

[0106] Temperature fluctuation rate: the degree of fluctuation of heating temperature over time.

[0107] Heating time ratio: the ratio of heating time to total working time.

[0108] Forging Strength: The forging load strength calculated based on material type and weight.

[0109] S2. Integrate the obtained forging energy consumption characteristic data and forging load characteristic data using an integration algorithm to obtain predicted energy consumption data and predicted load demand data of the heating furnace;

[0110] Specifically, the predicted energy consumption data of the heating furnace refers to the prediction of how much energy the heating furnace will consume in the future based on the current production scheduling and historical energy consumption characteristics, including:

[0111] Total energy consumption forecast: The total energy consumption of the heating furnace is expected to be during the next production cycle.

[0112] Energy consumption by time period: Energy consumption forecast for different time periods (such as day and night or different production stages).

[0113] Energy consumption per unit of product: Predict the energy required to heat and forge per unit weight or per unit of product.

[0114] Peak energy consumption: The maximum peak energy consumption expected during the production process.

[0115] Energy consumption trend: The expected growth or decrease trend of energy consumption in the next cycle.

[0116] Specifically, the load demand forecast refers to the forecast of the material demand, production rate and energy intensity of the heating furnace in the future, including:

[0117] Throughput Forecasting: Predict the total amount of material that the furnace will need to process within a specific period of time.

[0118] Material type distribution: predict the proportion and quantity of different types of materials in future production.

[0119] Production rate forecasting: Predict production rates over different time periods, and changes in production rhythm that may affect energy consumption.

[0120] Heating temperature requirements: Estimate the average heating temperature or temperature range required by the furnace during production based on the predicted material type and volume.

[0121] Load Fluctuations: Predict changes and fluctuations in load demand during production.

[0122] S3. Optimize the predicted energy consumption data and the predicted load demand data using an optimization algorithm to generate energy-saving scheduling data for heating furnace forging;

[0123] Specifically, the energy-saving scheduling data for heating furnace forging refers to the specific scheduling plan formulated to achieve efficient energy utilization and maximize production efficiency after processing the predicted energy consumption data and load demand data through the optimization algorithm, including:

[0124] Production Scheduling: Determine when forging operations should be performed to maximize the use of off-peak electricity prices or low-cost energy while ensuring production tasks are completed on time.

[0125] Energy usage plan: A detailed plan of when, where and how energy is used based on predicted energy consumption and load demand. For example, adjusting energy supply intensity, optimizing the start and stop time of heating furnaces, etc.

[0126] Temperature control strategy: Based on material type and production demand forecast, the heating furnace temperature control strategy is formulated to reduce energy consumption while ensuring product quality.

[0127] Load distribution strategy: In order to optimize energy consumption and improve production efficiency, time and resources are allocated to heating operations of different production batches or different materials.

[0128] Energy consumption optimization measures: including but not limited to improving energy conversion efficiency, reducing energy loss, utilizing waste heat recovery and other energy-saving technologies.

[0129] Emergency scheduling strategy: When unexpected situations occur in energy consumption or production, how to quickly adjust production plans and energy usage to minimize losses and impacts.

[0130] S4. Based on the analysis algorithm, the generated energy-saving scheduling data of the heating furnace forging is deeply analyzed, and the energy-saving scheduling data is allocated to the heating furnace forging;

[0131] Specifically, allocating energy-saving scheduling data refers to applying the heating furnace forging energy-saving scheduling data obtained based on the analysis algorithm to the actual production process, that is, allocating these scheduling data to specific heating furnace operations and production plans to achieve energy-saving goals.

[0132] Specifically, the allocation methods include:

[0133] Prioritization: Prioritize different production tasks and operations based on production needs and energy consumption targets to ensure that important production activities are executed first while maximizing energy efficiency.

[0134] Adjust production plan: According to energy-saving scheduling data, adjust production plan and operation sequence to reduce energy consumption peaks and avoid energy waste. For example, arrange high-energy consumption production activities during periods of low electricity prices.

[0135] Allocate energy resources: According to the dispatch data, reasonably allocate energy resources to ensure that the energy supply and demand of the heating furnace in different time periods match and avoid excessive energy consumption.

[0136] Implement temperature control strategies: Based on scheduling data, adjust the temperature control of the heating furnace to reduce energy consumption while ensuring product quality.

[0137] Monitoring and adjustment: During the implementation of the energy-saving scheduling plan, the operating status and energy consumption of the heating furnace shall be continuously monitored, and the scheduling plan shall be adjusted in a timely manner according to the actual situation to ensure the maximum energy-saving effect.

[0138] S5. Acquire real-time operation data during the heating furnace forging process, compare the real-time operation data with the allocated energy-saving scheduling data, and evaluate whether the allocated energy-saving scheduling data is consistent with the preset heating furnace forging energy-saving scheduling.

[0139] Specifically, real-time operation data includes:

[0140] Heating furnace temperature: includes the real-time temperature inside the heating furnace and how the temperature changes over time.

[0141] Energy consumption data: Real-time record of the energy consumption of the heating furnace during operation, including electricity consumption, fuel consumption, etc.

[0142] Production Rate: The rate at which a furnace processes material, including the amount of material processed per hour.

[0143] Material Type and Quantity: The type of material being processed in the furnace and its quantity.

[0144] Heating time: The actual time the material is heated in the heating furnace.

[0145] Cooling data: If the heating furnace includes a cooling process, the relevant cooling parameters, such as cooling time and cooling medium usage.

[0146] Operating status: the heating furnace's on status, shut down status and their changes.

[0147] Environmental conditions: external environmental conditions that affect the operating efficiency of the heating furnace, such as outdoor temperature, humidity, etc.

[0148] Preferably, obtaining the forging energy consumption data and forging load data of the heating furnace, and preprocessing the forging energy consumption data and forging load data to obtain the forging energy consumption characteristic data and forging load characteristic data comprises the following steps:

[0149] S11. Deploy data acquisition nodes and use communication protocols to obtain real-time forging energy consumption data and forging load data of the heating furnace;

[0150] Specifically, multiple data collection nodes are deployed at key operating locations of the heating furnace to collect real-time forging energy consumption data and forging load data of the heating furnace in that area. These nodes can communicate with the central data management system using various communication protocols (such as LoRaWAN, NB-IoT, Wi-Fi, etc.) to transmit the collected data in real time.

[0151] S12, obtaining the original forging energy consumption data and forging load data of the heating furnace from the data acquisition node, and converting the original forging energy consumption data and forging load data of the heating furnace from the time domain to the frequency domain through wavelet transform, and screening out the wave field records of each frequency band containing environmental interference;

[0152] Specifically, wavelet transform is a mathematical transformation method used to decompose a signal or function into components at different scales or resolutions. It is an extension of Fourier transform and is particularly suitable for analyzing non-stationary signals with different time scale characteristics. The core idea of ​​wavelet transform is to use a set of basis functions to perform multi-scale time-frequency analysis on data. This set of basis functions is obtained by scaling (scaling) and translating a fixed mother wavelet function.

[0153] Specifically, the original environment and performance data obtained from the data collection node usually contains various environmental interferences. Using wavelet transform technology, these data can be converted from the time domain to the frequency domain, which helps to more clearly identify and separate environmental interference signals in different frequency bands.

[0154] S13, tracking the environmental interference waves one by one in the wave field records of each frequency band, and obtaining the interference wave direction at the calculation sample point;

[0155] Specifically, in the frequency domain, the bands containing environmental interference are tracked one by one, and the directions of these interference waves at the sample points are calculated. The key is to accurately identify the environmental interference waves and obtain their direction information, laying the foundation for the next step of interference elimination.

[0156] S14, selecting a number of windows centered on the calculation sample point to perform median filtering, and restoring the environmental interference signal at the calculation sample point;

[0157] Specifically, several windows centered on the calculation sample points are selected for median filtering. Median filtering is an effective nonlinear filtering technology that can effectively remove noise interference in wave field records while retaining the edge information of the signal.

[0158] S15, recovering the interference signals in the wave field records of each frequency band one by one, and converting the interference wave field back to the time domain by inverse wavelet transform to obtain the entire wave field information of the interference wave;

[0159] Specifically, the interference signals in the wave field records of each frequency band are restored, and then these interference wave fields are converted back to the time domain through inverse wavelet transform, so that the time domain waveform of the interference wave field can be reconstructed.

[0160] S16. Subtract the interference wave field from the original forging energy consumption data and forging load data of the heating furnace to obtain the denoised effective signal wave field, and generate denoised forging energy consumption characteristic data and forging load characteristic data based on the denoised effective signal wave field.

[0161] Preferably, integrating the obtained forging energy consumption characteristic data and forging load characteristic data by using an integration algorithm to obtain the predicted energy consumption data and predicted load demand data of the heating furnace comprises the following steps:

[0162] S21, inputting an initial sample set of forging energy consumption characteristic data and forging load characteristic data;

[0163] S22, classifying all forging energy consumption characteristic data and forging load characteristic data in the initial sample set to obtain a number of sample subsets of forging energy consumption characteristic data and forging load characteristic data;

[0164] S23, performing a loop process (i.e., principal component analysis) on each sample subset to obtain a coefficient matrix (i.e., a principal component coefficient matrix);

[0165] S24, rearranging the coefficient matrix, and transforming the initial sample set through the coefficient matrix to generate new forging energy consumption characteristic data and forging load characteristic data samples;

[0166] S25, training the prediction model based on the new forging energy consumption characteristic data and forging load characteristic data samples to obtain sub-models of the predicted energy consumption and predicted load demand of the heating furnace, and returning to step S22, looping a preset number of times to obtain an integrated prediction model;

[0167] S26. Use the integrated prediction model to predict the initial sample set, and use the forging energy consumption characteristic data and the forging load characteristic data to generate the predicted energy consumption data and the predicted load demand data of the heating furnace.

[0168] Specifically, the integration algorithm is a heterogeneous multi-classifier integration algorithm. First, the rotation forest is used to transform and divide the original sample set to obtain a new sample set. Then, a support vector machine with high classification accuracy or a kernel matching pursuit with fast classification speed is selected as the basic integrated individual classifier through a specific proportion, and the new sample set is classified to obtain its prediction label. Finally, the prediction labels under the two models are combined. By combining two different classifier models, the algorithm achieves the complementarity of accuracy and speed, and improves the generalization error of the integrated system after the mixed integration of the two.

[0169] Preferably, performing a loop process on each sample subset to obtain a coefficient matrix comprises the following steps:

[0170] S231, resampling the sample subsets of forging energy consumption characteristic data and forging load characteristic data by using a stratified sampling method to generate new sample subsets of forging energy consumption characteristic data and forging load characteristic data;

[0171] Specifically, the stratified sampling method is used to resample the sample subsets of the forging energy consumption characteristic data and the forging load characteristic data. When extracting samples, the data is divided into different layers or subsets, and each layer represents a specific subgroup in the data. The purpose of this method is to ensure that the sample is more representative statistically, because it can be guaranteed that the data from each important subgroup in the data set are included in the sample.

[0172] S232, performing principal component analysis on a sample subset of new forging energy consumption characteristic data and forging load characteristic data to obtain a principal component coefficient vector related to energy consumption and load changes during the heating furnace forging process;

[0173] S233. Repeat steps S231 to S232 to obtain several groups of principal component coefficient vectors, and combine the coefficient vectors into a principal component coefficient matrix.

[0174] Preferably, the predicted energy consumption data and the predicted load demand data are optimized by using an optimization algorithm, and the generation of energy-saving scheduling data for heating furnace forging includes the following steps:

[0175] S31, determining the number of parameters (i.e., the number of cuckoo nests) for predicting energy consumption data and load demand data during the heating furnace forging process, and setting the maximum number of iterations and parameter adjustment probability (i.e., mutation probability) of the optimization process;

[0176] S32, using a heuristic algorithm (i.e., Tent mapping) to generate preliminary energy-saving scheduling data for forging of several heating furnaces;

[0177] Specifically, the index configuration scheme for generating a database table using Tent mapping includes:

[0178] Understanding the Tent Mapping Principle: The Tent Mapping is a simple one-dimensional mapping used to generate sequences with chaotic properties. It generates a series of values ​​in an iterative manner that exhibit irregular and unpredictable behavior under certain conditions.

[0179] Determine the goal of index configuration: Clearly define the goal of using tent mapping to generate preliminary welding gun motion trajectories. For example, it may be to optimize query efficiency, balance read and write performance, or reduce the cost of index maintenance.

[0180] Generate index configuration plan: Use the data or pattern generated by Tent mapping to guide the creation of indexes. For example, determine the type and parameters of the index based on the distribution characteristics of the data. In this step, you need to consider the actual usage scenarios and performance requirements of the database.

[0181] S33, calculating the fitness value of the preliminary energy-saving scheduling data (i.e., the bird's nest) of each heating furnace forging, and recording the status of the best and second-best energy-saving scheduling data of the heating furnace forging;

[0182] S34, using Levi flight to adjust the state of the energy-saving scheduling data of the heating furnace forging, and repeating step S33;

[0183] Specifically, Levy flight is a mathematical random walk method. In the cuckoo search algorithm, Levy flight is used to update the location of the bird's nest (i.e., energy-saving scheduling data).

[0184] S35, retaining the energy-saving scheduling data of the current heating furnace forging or adopting new energy-saving scheduling data of the heating furnace forging according to a specific criterion formula, and repeating step S33;

[0185] Specifically, the specific criterion formula is the nest position update formula. Since the cuckoo algorithm uses random migration and greedy strategies in each iteration, only the global optimal individual is always kept as the leader in the population, which easily leads to a decrease in the algorithm's regional exploration ability for other excellent solutions. In order to enhance the vitality and efficiency of the search, the present invention draws on the idea of ​​particle swarm algorithm and adds social learning and self-learning parts.

[0186] S36, mutating the energy-saving scheduling data of the heating furnace forging by a heuristic search algorithm (i.e., the gray wolf algorithm), and repeating step S33;

[0187] Specifically, the present invention draws on the hunting mechanism of α, β, and δ wolves in the gray wolf algorithm, that is, the leader wolf calls on the group to get close to its surroundings as quickly as possible to achieve the purpose of rapid population convergence. The optimal solution in the gray wolf group is α, the second optimal solution is β, the third optimal solution is δ, and other solutions are called ω. In each search process, α, β, and δ wolves are used as leader wolves to surround the prey, wherein the prey is marked as the location of the head wolf. In the present invention, the global historical optimal solution, the global historical suboptimal solution, and the individual historical optimal solution after each cuckoo algorithm optimization are used as α, β, and δ wolves, respectively, and other solutions in the population are mutated according to the gray wolf algorithm.

[0188] S37, loop iterate and execute steps S34 to S36 until a preset iteration termination condition is met;

[0189] S38. After the iteration is completed, the global optimal solution is output as the energy-saving scheduling data for the heating furnace forging.

[0190] Specifically, the optimization algorithm is a hybrid cuckoo optimization algorithm, which is an optimization algorithm developed on the basis of the original cuckoo search algorithm. The cuckoo search algorithm is a global optimization algorithm based on the cuckoo parasitic strategy, and in the hybrid cuckoo optimization algorithm, other types of optimization algorithms are integrated, such as genetic algorithm, ant colony optimization algorithm, particle swarm optimization algorithm, gray wolf algorithm, etc., to enhance the search ability and speed of the cuckoo search algorithm.

[0191] Preferably, the specific criterion formula is:

[0192]

[0193] in, It is represented as the new state of the energy-saving scheduling data of the ath heating furnace forging after c+1 iterations;

[0194] It is represented as the current state of the energy-saving scheduling data of the ath heating furnace forging at the beginning of the cth iteration;

[0195] step a It is represented as the Levy flight step length (i.e., the trajectory of Levy flight) of the energy-saving scheduling data of the ath heating furnace forging in each iteration;

[0196] b zbest It is represented as the historical best state of the energy-saving scheduling data of the ath heating furnace forging (which can enhance the self-learning ability of position update);

[0197] bgbest and b gsecong They are respectively represented as the global historical best state and the global historical sub-optimal state in the energy-saving scheduling data of all heating furnace forgings (which can enhance the social learning ability of position updating);

[0198] x1, x2, and x3 represent the learning factors of the historical optimal state, the global historical optimal state, and the global historical suboptimal state of the energy-saving scheduling data of the heating furnace forging, respectively.

[0199] Specifically, x1, x2, and x3 are all random numbers in the interval [0, 1].

[0200] Specifically, x1 is the learning factor for the individual best historical solution, which represents the self-learning ability of the particle; x2 and x3 are the learning factors for the global best historical solution and the global second-best historical solution, respectively, which represent the social learning ability of the particle.

[0201] Preferably, based on the analysis algorithm, the generated energy-saving scheduling data for heating furnace forging is deeply analyzed, and the energy-saving scheduling data for heating furnace forging is allocated, including the following steps:

[0202] S41, setting a sample set of energy-saving scheduling data for heating furnace forging, and presetting the number of mutation and crossover operations;

[0203] S42, performing a mutation operation on the energy-saving scheduling data sample set of the heating furnace forging, calculating the difference vector between each sample, determining the best energy-saving scheduling data sample in the energy-saving scheduling data sample set of the heating furnace forging, and using the best energy-saving scheduling data sample as a new mutation sample;

[0204] Specifically, the mutation operation is the processing of the mutation operation in the differential evolution algorithm (DE).

[0205] S43, performing a crossover operation on the new variant sample, and determining the best energy-saving scheduling data sample in the energy-saving scheduling data sample set for heating furnace forging;

[0206] Specifically, the crossover operation is the processing of the crossover operation in the differential evolution algorithm (DE).

[0207] S44, using an analysis algorithm to perform a new cluster analysis on the energy-saving scheduling data samples after the mutation crossover, to determine the cluster where each energy-saving scheduling data sample is located and the optimal distance between the samples;

[0208] S45, comparing the mutation crossover result with the objective function, and selecting the energy-saving scheduling data sample with the best objective function value as the energy-saving scheduling data sample in the new heating furnace forging energy-saving scheduling data sample set;

[0209] S46. Determine whether the termination condition is met. If so, end the optimization process, mark the current best energy-saving scheduling data sample set for heating furnace forging as a data set that meets the energy-saving requirements of the forging process, and allocate the best energy-saving scheduling data sample set for heating furnace forging as the energy-saving scheduling data for heating furnace forging.

[0210] Specifically, the analysis algorithm is a K-medoids clustering algorithm based on differential evolution. The idea of ​​the K-medoids clustering algorithm based on differential evolution is: first, a group of a certain size is randomly selected from the population, and the size of the group is set to a fixed value. At the same time, the maximum size limit of the population is set. Then, the differential evolution algorithm (DE) is used to perform mutation and crossover operations on this population to determine the optimal mutant individuals and experimental individuals in the population, thereby avoiding the population from falling into the local optimum and enhancing the algorithm's local search ability in the cluster space area. Next, according to the K-medoids clustering algorithm, a new clustering analysis is performed on these optimized experimental individuals to determine the cluster to which each individual belongs and the optimal distance between them. In this way, the individual with the lowest objective function value can be found and used as a member of the new population, and the optimal solution is finally output. Finally, the global search ability of the differential evolution algorithm (DE) and the local search efficiency of the K-medoids clustering algorithm in a specific spatial area are combined to achieve more efficient clustering analysis and feature extraction.

[0211] Specifically, the differential evolution algorithm (DE) is an algorithm based on population evolution. It has the characteristics of memorizing individual optimal solutions and sharing information within the population. That is, it solves the optimization problem through cooperation and competition among individuals in the population. Its essence is a greedy genetic algorithm based on real number coding with the idea of ​​preserving excellence.

[0212] Preferably, using an analysis algorithm to perform a new cluster analysis on the energy-saving scheduling data samples after the mutation crossover, and determining the cluster where each energy-saving scheduling data sample is located and the optimal distance between the samples includes the following steps:

[0213] S441, randomly selecting a number of energy-saving scheduling data samples from the heating furnace forging energy-saving scheduling data sample set after mutation crossover as the center points of the initial clustering;

[0214] S442, assigning each unassigned energy-saving scheduling data sample to the cluster center point closest to it to form a preliminary cluster group;

[0215] S443, randomly selecting an energy-saving scheduling data sample of a non-clustering center from the energy-saving scheduling data sample set of heating furnace forging, and recording it as a random energy-saving scheduling data sample;

[0216] S444, calculating the total cost change caused by replacing the current cluster center point with a random energy-saving scheduling data sample, and updating the cluster center set;

[0217] S445. When the cluster center point no longer changes, determine the final clustering of each energy-saving scheduling data sample, and calculate the optimal distance between each energy-saving scheduling data sample.

[0218] Preferably, obtaining real-time operation data during the heating furnace forging process, comparing the real-time operation data with the allocated energy-saving scheduling data, and evaluating whether the allocated energy-saving scheduling data is consistent with the preset heating furnace forging energy-saving scheduling includes the following steps:

[0219] S51, determining key parameters that affect the real-time operation of the heating furnace forging, and setting an initial search range;

[0220] Specifically, the key parameters that affect the real-time operation of the heating furnace forging include:

[0221] Heating temperature: It is one of the key parameters of heating furnace performance and affects the heating efficiency and quality of materials.

[0222] Heating rate: determines how quickly the material reaches the required temperature, affecting overall production efficiency.

[0223] Fuel consumption rate: directly related to the energy efficiency and operating cost of the heating furnace.

[0224] Electricity consumption: The electricity consumption of the heating furnace operation is also an important parameter for evaluating energy consumption.

[0225] Cooling Rate: For some forging processes, the cooling rate can affect the microstructure and properties of the final product.

[0226] Material type and weight: Different materials and weights require different amounts of energy and time during the heating and forging process.

[0227] Environmental conditions: such as temperature, humidity, etc., may affect the efficiency and energy consumption of the heating furnace.

[0228] Production rhythm: that is, the time arrangement in the production process, which has an important impact on the efficiency and energy consumption of the entire process.

[0229] S52, preset an initial value of the evaluation cycle (i.e., preset an initial value of the time counter), and set the number of iterations as the end condition of the evaluation process;

[0230] Specifically, a time counter is a counting variable used to track the iteration process in an algorithm or program. In optimization and computational tasks, a time counter is used to monitor the number of iterations that an algorithm has executed and decide when to stop the iteration process.

[0231] Specifically, the termination conditions include that the time recorded by the time counter reaches a preset maximum value and the number of iterations of the optimization algorithm reaches a preset maximum number.

[0232] S53, comparing the real-time operation data of the heating furnace during forging with the allocated energy-saving scheduling data, and updating the key parameters according to a preset comparison method;

[0233] S54. Evaluate the energy-saving efficiency of heating furnace forging after each key parameter comparison by statistical methods (i.e., k-fold cross validation);

[0234] Specifically, k-fold cross validation is a machine learning model evaluation method, which refers to dividing the collected key factor parameter data set of towel sample hair removal into k subsets, one of which is used as a validation set, and the remaining k-1 subsets are used as training sets.

[0235] S55. Calculate the fitness score of each iteration based on the evaluation result of the heating furnace forging energy saving efficiency;

[0236] S56, comparing the fitness scores of two consecutive iterations, and selecting the key parameter update that has the greatest impact on the operation state of the heating furnace as the current best solution;

[0237] S57, increasing the initial value of the evaluation cycle, and if the preset upper limit of the number of iterations is reached, terminating the evaluation process;

[0238] S58. Analyze the matching degree between the energy-saving scheduling data assigned after the evaluation process and the preset heating furnace forging energy-saving scheduling to determine whether there is a significant impact. If there is a significant impact, make adjustments. If not, use the assigned energy-saving scheduling data as the energy-saving scheduling in the heating furnace forging process.

[0239] Specifically, the present invention compares the real-time operation data with the allocated energy-saving scheduling data by using an evaluation algorithm to evaluate whether the allocated energy-saving scheduling data is consistent with the preset heating furnace forging energy-saving scheduling.

[0240] Specifically, the evaluation algorithm is an SVM parameter selection method based on an improved bird flock optimization algorithm, which is a strategy for applying nature-inspired algorithms to machine learning parameter optimization. In this method, an improved bird flock optimization algorithm is used to select or optimize SVM parameters to improve the performance of the model.

[0241] Specifically, SVM is a supervised learning algorithm based on the principle of structural risk minimization. It uses expected risk minimization as the evaluation criterion and aims to obtain a decision function with high generalization ability through finite sample training, that is, to find an optimal hyperplane to completely separate the samples under the condition of linear separability.

[0242] Specifically, the improved bird flock optimization algorithm refers to an improvement and variant of the traditional particle swarm optimization algorithm (Particle Swarm Optimization, PSO). The particle swarm optimization algorithm is an optimization technology based on swarm intelligence, which simulates the social behavior of bird flocks or fish schools to solve optimization problems.

[0243] Specifically, the improved bird flock optimization algorithm includes the following improvements:

[0244] Improvements in speed and position update rules: In standard PSO, the movement of particles is based on their best historical position and the best position of the entire group. Improved algorithms may use different rules to adjust the speed and position of particles to improve convergence speed and avoid falling into local optimality.

[0245] Parameter adjustment and control: Improved algorithms may include dynamic adjustment mechanisms for PSO parameters such as inertia weight, individual best and group best learning factors to balance exploration (global search) and exploitation (local search) during the search process.

[0246] Customization to adapt to specific problems: For specific types of problems (such as nonlinear problems, multi-objective problems, etc.), the improved bird flock optimization algorithm may be specially designed to solve these problems more effectively.

[0247] Preferably, evaluating the heating furnace forging energy saving efficiency after each key parameter comparison by statistical methods includes the following steps:

[0248] S541, initializing the verification round number to the first round, and dividing the acquired real-time operation data set in the heating furnace forging process into several subsets. In each round, one subset is selected as a test set, and the union of all the remaining subsets is used as a training set;

[0249] S542, using the adjusted key parameters on the training set to train a statistical model (i.e., a SVM model), and testing the predictive performance of the statistical model on the heating furnace forging energy-saving efficiency on the test set;

[0250] S543. Calculate the generalization error of the statistical model based on the actual performance of the key parameters on the test set;

[0251] Specifically, generalization error is an important indicator for evaluating the generalization ability of machine learning models. It reflects the prediction error of the model on new data that has not been seen.

[0252] Specifically, calculating the generalization error of the statistical model (ie, the SVM model) refers to calculating the prediction error of the statistical model (ie, the SVM model) on the test set.

[0253] S544, looping step S541 to step S543 until each subset has been used as a test set;

[0254] S545. Obtain the average value of the generalization errors calculated in all verification rounds as the overall evaluation result of the heating furnace forging energy saving efficiency after each key parameter comparison.

[0255] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A heating furnace forging energy-saving scheduling method based on energy-saving scheduling strategy, characterized in that: The heating furnace forging energy-saving scheduling method based on the energy-saving scheduling strategy comprises the following steps: S1. Acquire forging energy consumption data and forging load data of a heating furnace, and pre-process the forging energy consumption data and forging load data to obtain forging energy consumption characteristic data and forging load characteristic data; S2. Integrate the obtained forging energy consumption characteristic data and forging load characteristic data using an integration algorithm to obtain predicted energy consumption data and predicted load demand data of the heating furnace; S3. Optimize the predicted energy consumption data and the predicted load demand data using an optimization algorithm to generate energy-saving scheduling data for heating furnace forging; S4. Based on the analysis algorithm, the generated energy-saving scheduling data of the heating furnace forging is deeply analyzed, and the energy-saving scheduling data is allocated to the heating furnace forging; S5. Acquire real-time operation data during the heating furnace forging process, compare the real-time operation data with the allocated energy-saving scheduling data, and evaluate whether the allocated energy-saving scheduling data is consistent with the preset heating furnace forging energy-saving scheduling.

2. According to the energy-saving scheduling method of heating furnace forging based on energy-saving scheduling strategy in claim 1, it is characterized in that: The step of obtaining the forging energy consumption data and forging load data of the heating furnace, and preprocessing the forging energy consumption data and forging load data to obtain the forging energy consumption characteristic data and forging load characteristic data comprises the following steps: S11. Deploy data acquisition nodes and use communication protocols to obtain real-time forging energy consumption data and forging load data of the heating furnace; S12, obtaining the original forging energy consumption data and forging load data of the heating furnace from the data acquisition node, and converting the original forging energy consumption data and forging load data of the heating furnace from the time domain to the frequency domain through wavelet transform, and screening out the wave field records of each frequency band containing environmental interference; S13, tracking the environmental interference waves one by one in the wave field records of each frequency band, and obtaining the interference wave direction at the calculation sample point; S14, selecting a number of windows centered on the calculation sample point to perform median filtering, and restoring the environmental interference signal at the calculation sample point; S15, recovering the interference signals in the wave field records of each frequency band one by one, and converting the interference wave field back to the time domain by inverse wavelet transform to obtain the entire wave field information of the interference wave; S16. Subtract the interference wave field from the original forging energy consumption data and forging load data of the heating furnace to obtain the denoised effective signal wave field, and generate denoised forging energy consumption characteristic data and forging load characteristic data based on the denoised effective signal wave field.

3. The method for energy-saving scheduling of heating furnace forging based on energy-saving scheduling strategy according to claim 1 is characterized in that: The method of integrating the obtained forging energy consumption characteristic data and forging load characteristic data by using an integration algorithm to obtain the predicted energy consumption data and predicted load demand data of the heating furnace comprises the following steps: S21, inputting an initial sample set of forging energy consumption characteristic data and forging load characteristic data; S22, classifying all forging energy consumption characteristic data and forging load characteristic data in the initial sample set to obtain a number of sample subsets of forging energy consumption characteristic data and forging load characteristic data; S23, performing loop processing on each sample subset to obtain a coefficient matrix; S24, rearranging the coefficient matrix, and transforming the initial sample set through the coefficient matrix to generate new forging energy consumption characteristic data and forging load characteristic data samples; S25, training the prediction model based on the new forging energy consumption characteristic data and forging load characteristic data samples to obtain sub-models of the predicted energy consumption and predicted load demand of the heating furnace, and returning to step S22, looping a preset number of times to obtain an integrated prediction model; S26. Use the integrated prediction model to predict the initial sample set, and use the forging energy consumption characteristic data and the forging load characteristic data to generate the predicted energy consumption data and the predicted load demand data of the heating furnace.

4. The method for energy-saving scheduling of heating furnace forging based on energy-saving scheduling strategy according to claim 3 is characterized in that: The loop processing is performed on each sample subset to obtain a coefficient matrix, which comprises the following steps: S231, resampling the sample subsets of forging energy consumption characteristic data and forging load characteristic data by using a stratified sampling method to generate new sample subsets of forging energy consumption characteristic data and forging load characteristic data; S232, performing principal component analysis on a sample subset of new forging energy consumption characteristic data and forging load characteristic data to obtain a principal component coefficient vector related to energy consumption and load changes during the heating furnace forging process; S233. Repeat steps S231 to S232 to obtain several groups of principal component coefficient vectors, and combine the coefficient vectors into a principal component coefficient matrix.

5. The method for energy-saving scheduling of heating furnace forging based on energy-saving scheduling strategy according to claim 1 is characterized in that: The method of optimizing the predicted energy consumption data and the predicted load demand data by using an optimization algorithm to generate energy-saving scheduling data for heating furnace forging includes the following steps: S31, determining the number of parameters for predicting energy consumption data and predicting load demand data during the heating furnace forging process, and setting the maximum number of iterations and parameter adjustment probability of the optimization process; S32, using a heuristic algorithm to generate preliminary energy-saving scheduling data for forging of a number of heating furnaces; S33, calculating the fitness value of the preliminary energy-saving scheduling data of each heating furnace forging, and recording the status of the best and second-best energy-saving scheduling data of the heating furnace forging; S34, using Levi flight to adjust the state of the energy-saving scheduling data of the heating furnace forging, and repeating step S33; S35, retaining the energy-saving scheduling data of the current heating furnace forging or adopting new energy-saving scheduling data of the heating furnace forging according to a specific criterion formula, and repeating step S33; S36, mutating the energy-saving scheduling data of the heating furnace forging by a heuristic search algorithm, and repeating step S33; S37, loop iterate and execute steps S34 to S36 until a preset iteration termination condition is met; S38. After the iteration is completed, the global optimal solution is output as the energy-saving scheduling data for the heating furnace forging.

6. The method for energy-saving scheduling of heating furnace forging based on energy-saving scheduling strategy according to claim 5 is characterized in that: The specific criterion formula is: in, It is represented as the new state of the energy-saving scheduling data of the ath heating furnace forging after c+1 iterations; It is represented as the current state of the energy-saving scheduling data of the ath heating furnace forging at the beginning of the cth iteration; step a It is represented as the Levy flight step length of the energy-saving scheduling data of the ath heating furnace forging in each iteration; b zbest It is represented as the historical best state of the energy-saving scheduling data of the ath heating furnace forging; b gest and b gsecong They are respectively represented as the global historical best state and the global historical second best state in the energy-saving scheduling data of all heating furnace forgings; x1, x2, and x3 represent the learning factors of the historical optimal state, the global historical optimal state, and the global historical suboptimal state of the energy-saving scheduling data of the heating furnace forging, respectively.

7. The method for energy-saving scheduling of heating furnace forging based on energy-saving scheduling strategy according to claim 1 is characterized in that: The method of deeply analyzing the generated energy-saving scheduling data of heating furnace forging based on the analysis algorithm and allocating the energy-saving scheduling data to the heating furnace forging includes the following steps: S41, setting a sample set of energy-saving scheduling data for heating furnace forging, and presetting the number of mutation and crossover operations; S42, performing a mutation operation on the energy-saving scheduling data sample set of the heating furnace forging, calculating the difference vector between each sample, determining the best energy-saving scheduling data sample in the energy-saving scheduling data sample set of the heating furnace forging, and using the best energy-saving scheduling data sample as a new mutation sample; S43, performing a crossover operation on the new variant sample, and determining the best energy-saving scheduling data sample in the energy-saving scheduling data sample set for heating furnace forging; S44, using an analysis algorithm to perform a new cluster analysis on the energy-saving scheduling data samples after the mutation crossover, to determine the cluster where each energy-saving scheduling data sample is located and the optimal distance between the samples; S45, comparing the mutation crossover result with the objective function, and selecting the energy-saving scheduling data sample with the best objective function value as the energy-saving scheduling data sample in the new heating furnace forging energy-saving scheduling data sample set; S46. Determine whether the termination condition is met. If so, end the optimization process, mark the current best energy-saving scheduling data sample set for heating furnace forging as a data set that meets the energy-saving requirements of the forging process, and allocate the best energy-saving scheduling data sample set for heating furnace forging as the energy-saving scheduling data for heating furnace forging.

8. The method for energy-saving scheduling of heating furnace forging based on energy-saving scheduling strategy according to claim 7 is characterized in that: The method of using the analysis algorithm to perform a new cluster analysis on the energy-saving scheduling data samples after the mutation crossover to determine the cluster where each energy-saving scheduling data sample is located and the optimal distance between the samples includes the following steps: S441, randomly selecting a number of energy-saving scheduling data samples from the heating furnace forging energy-saving scheduling data sample set after mutation crossover as the center points of the initial clustering; S442, assigning each unassigned energy-saving scheduling data sample to the cluster center point closest to it to form a preliminary cluster group; S443, randomly selecting an energy-saving scheduling data sample of a non-clustering center from the energy-saving scheduling data sample set of heating furnace forging, and recording it as a random energy-saving scheduling data sample; S444, calculating the total cost change caused by replacing the current cluster center point with a random energy-saving scheduling data sample, and updating the cluster center set; S445. When the cluster center point no longer changes, determine the final clustering of each energy-saving scheduling data sample, and calculate the optimal distance between each energy-saving scheduling data sample.

9. The method for energy-saving scheduling of heating furnace forging based on energy-saving scheduling strategy according to claim 1 is characterized in that: The step of obtaining the real-time operation data during the heating furnace forging process, comparing the real-time operation data with the allocated energy-saving scheduling data, and evaluating whether the allocated energy-saving scheduling data is consistent with the preset heating furnace forging energy-saving scheduling includes the following steps: S51, determining key parameters that affect the real-time operation of the heating furnace forging, and setting an initial search range; S52, preset an initial value of the evaluation cycle, and set the number of iterations as the end condition of the evaluation process; S53, comparing the real-time operation data of the heating furnace during forging with the allocated energy-saving scheduling data, and updating the key parameters according to a preset comparison method; S54. Evaluate the energy-saving efficiency of heating furnace forging after each key parameter comparison by statistical methods; S55. Calculate the fitness score of each iteration based on the evaluation result of the heating furnace forging energy saving efficiency; S56, comparing the fitness scores of two consecutive iterations, and selecting the key parameter update that has the greatest impact on the operation state of the heating furnace as the current best solution; S57, increasing the initial value of the evaluation cycle, and if the preset upper limit of the number of iterations is reached, terminating the evaluation process; S58. Analyze the matching degree between the energy-saving scheduling data assigned after the evaluation process and the preset heating furnace forging energy-saving scheduling to determine whether there is a significant impact. If there is a significant impact, make adjustments. If not, use the assigned energy-saving scheduling data as the energy-saving scheduling in the heating furnace forging process.

10. The method for energy-saving scheduling of heating furnace forging based on energy-saving scheduling strategy according to claim 9 is characterized in that: The method of evaluating the heating furnace forging energy saving efficiency after each key parameter comparison by statistical method includes the following steps: S541, initializing the verification round number to the first round, and dividing the acquired real-time operation data set in the heating furnace forging process into several subsets. In each round, one subset is selected as a test set, and the union of all the remaining subsets is used as a training set; S542. Training the statistical model using the adjusted key parameters on the training set, and testing the predictive performance of the statistical model on the heating furnace forging energy-saving efficiency on the test set; S543. Calculate the generalization error of the statistical model based on the actual performance of the key parameters on the test set; S544, looping step S541 to step S543 until each subset has been used as a test set; S545. Obtain the average value of the generalization errors calculated in all verification rounds as the overall evaluation result of the heating furnace forging energy saving efficiency after each key parameter comparison.

Citation Information

Patent Citations

  • Distributed forging flow shop energy-saving scheduling method considering concentrated heat treatment

    CN112859761A

  • Rigging forging process parameter monitoring and early warning method and device based on artificial intelligence

    CN117892251A

Cited By

  • Flue gas circulation type kiln energy-saving method and system

    CN120120867A

  • A flue gas circulation type kiln energy-saving method and system

    CN120120867B