Factory power equipment power supply type selection method and system based on energy consumption analysis

Abstract

The invention discloses a factory power equipment power supply type selection method based on energy consumption analysis. The method comprises the steps that energy consumption characteristic data of various types of equipment are collected in real time and preprocessed; constructing a multi-dimensional energy consumption model of the factory power equipment, and training and optimizing the energy consumption model through a machine learning algorithm; predicting the load demand of the factory power supply system, wherein the prediction result comprises load changes in different time periods; formulating a factory power equipment power supply type selection strategy based on the energy consumption model and the load demand prediction result, and performing energy consumption analysis and evaluation by using analogue simulation; and continuously monitoring the operation state and energy consumption data of the equipment, and dynamically adjusting and optimizing the multi-dimensional energy consumption model and the model selection strategy according to the actual operation data. The invention further discloses a corresponding system. By implementing the method, a scientific basis can be provided for model selection of factory power equipment, and efficient utilization and saving of energy are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of energy management, and particularly to a power supply selection method and system for factory power equipment based on energy consumption analysis. Background Art

[0002] With the rapid development of industrial production, the energy consumption problem of the factory power equipment power supply system has become increasingly prominent. Energy conservation and emission reduction have become one of the key factors for the sustainable development of enterprises. Moreover, the energy consumption problem not only concerns the economic benefits of enterprises, but is also an inevitable requirement for realizing green transformation and fulfilling social responsibilities. Traditional power equipment selection methods often focus on the rated power and basic performance of equipment, rely on empirical rules or basic comparisons, and ignore their energy consumption characteristics in actual operation, lacking systematic energy consumption analysis and optimization strategies, resulting in unreasonable equipment selection, high energy consumption, and low operating efficiency, and there are significant energy waste phenomena in factories. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a power supply selection method and system for factory power equipment based on energy consumption analysis, which provides a scientific basis for the selection of factory power equipment by comprehensively considering factors such as the energy consumption characteristics, load demand, and operating efficiency of equipment, and realizes the efficient utilization and conservation of energy.

[0004] To solve the above technical problem, as one aspect of the present invention, there is provided a power supply selection method for factory power equipment based on energy consumption analysis, which includes the following steps:

[0005] Step S10, using sensors and metering equipment to collect the energy consumption characteristic data of various types of equipment in the factory in real time, and preprocessing the collected data;

[0006] Step S11, based on equipment power load classification, equipment operating parameters, environmental parameters, and production data, constructing a multi-dimensional energy consumption model for factory power equipment, and training and optimizing the energy consumption model through machine learning algorithms;

[0007] Step S12, using the factory historical data and time series analysis algorithms to predict the load demand of the factory power supply system, and the prediction results include the load changes in different time periods;

[0008] Step S13, based on the energy consumption model and the load demand prediction results, comprehensively considering factors such as the energy efficiency ratio, economic cost, and operating stability of equipment, formulating a power supply selection strategy for factory power equipment, and using simulation to conduct energy consumption analysis and evaluation;

[0009] Step S14, applying the determined selection scheme to the actual production of the factory, continuously monitoring the operating status and energy consumption data of the equipment, and dynamically adjusting and optimizing the multi-dimensional energy consumption model and selection strategy according to the actual operating data.

[0010] Preferably, in step S10, it further includes:

[0011] Using sensors and metering devices to collect real-time energy consumption characteristic data of voltage, current, power factor, active power, and reactive power;

[0012] Classifying, labeling, converting, standardizing or normalizing the data.

[0013] Preferably, in the said step S11, it further includes:

[0014] Using a multiple linear regression model and machine learning techniques to construct an energy consumption model;

[0015] Verifying the model through a cross-validation method, and adopting a heuristic search strategy of genetic algorithm and particle swarm optimization to improve the prediction accuracy and generalization ability of the model.

[0016] Preferably, in the said step S12, an improved time series recurrent neural network (RNN) based on LSTM, combined with an attention mechanism, is adopted to further improve the accuracy and speed of load prediction.

[0017] Preferably, in the said step S14, it further includes:

[0018] Making feedback adjustment and optimization on the multi-dimensional energy consumption model according to the actual operation data;

[0019] Adjusting and optimizing the selection strategy plan according to the actual operation conditions and energy consumption performance of the equipment.

[0020] Correspondingly, as another aspect of the present invention, there is also provided a factory power equipment power supply selection system based on energy consumption analysis, which is characterized by including:

[0021] A data acquisition and processing module, which is used to use sensors and metering devices to collect real-time energy consumption characteristic data of various types of equipment in the factory, and preprocess the collected data;

[0022] An energy consumption model construction module, which is used to construct a multi-dimensional energy consumption model of the factory power equipment based on equipment power load classification, equipment operation parameters, environmental parameters and production data, and train and optimize the model through machine learning algorithms;

[0023] A load demand prediction module, which is used to use the factory historical data and time series analysis algorithm to predict the load demand of the factory power supply system;

[0024] The selection strategy formulation module is used to formulate the power supply selection strategy for factory power equipment based on the energy consumption model and the load demand prediction results, comprehensively considering factors such as the energy efficiency ratio, economic cost, and operation stability of the equipment, and perform energy consumption analysis and evaluation using simulation;

[0025] The implementation and adjustment module is used to apply the determined selection scheme to the actual production of the factory, continuously monitor the operation status and energy consumption data of the equipment, and dynamically adjust and optimize the multi-dimensional energy consumption model and selection strategy according to the actual operation data.

[0026] Preferably, the data acquisition and processing module further includes:

[0027] The acquisition unit is used to collect energy consumption characteristic data such as voltage, current, power factor, active power, and reactive power in real time;

[0028] The data processing unit is used to classify, label, convert, standardize, or normalize the data.

[0029] Preferably, the energy consumption model construction module further includes:

[0030] The model construction unit constructs an energy consumption model using a multiple linear regression model and machine learning techniques;

[0031] The model optimization unit validates the model through a cross-validation method, and uses heuristic search strategies such as genetic algorithms and particle swarm optimization to improve the prediction accuracy and generalization ability of the model.

[0032] Preferably, the selection strategy formulation module further includes:

[0033] The strategy optimization unit maximizes the overall energy efficiency of factory equipment by optimizing and combining comprehensive factors such as different load classifications, equipment models, operating capacities, production conditions, and environmental conditions;

[0034] The energy consumption evaluation unit uses energy consumption simulation software to evaluate the energy consumption performance of the selection scheme under different working conditions.

[0035] Preferably, the implementation and adjustment module further includes:

[0036] The feedback adjustment unit performs feedback adjustment and optimization on the multi-dimensional energy consumption model according to the actual operation data;

[0037] The strategy optimization and adjustment unit adjusts and optimizes the selection strategy scheme according to the actual operation situation and energy consumption performance of the equipment.

[0038] Implementing the embodiments of the present invention has the following beneficial effects:

[0039] The present invention provides a method and system for power supply selection of factory electrical equipment based on energy consumption analysis. By constructing a multi-dimensional energy consumption model, it can accurately reflect the energy consumption changes of factory electrical equipment under different working conditions. Combining machine learning algorithms to optimize the model improves the accuracy of energy consumption prediction. The selection strategy formulated based on the energy consumption model and load demand prediction results comprehensively considers factors such as the energy efficiency ratio, economic cost, and operation stability of the equipment, realizes the scientific selection of electrical equipment, and effectively reduces the overall energy consumption of the factory.

[0040] Through refined energy consumption analysis and optimization algorithms, the present invention selects electrical equipment with high energy efficiency and reasonable costs, reducing the equipment investment cost. The selection strategy takes into account the operation efficiency and maintenance costs of the equipment, enabling the factory to save a large amount of energy and maintenance costs during long-term operation, and improving economic benefits. Reducing energy consumption directly reduces carbon emissions and environmental pollution. By optimizing equipment selection, the present invention makes the factory more environmentally friendly during the production process. The environmental protection performance of the equipment is considered in the selection strategy, and equipment meeting environmental protection standards is preferentially selected, further enhancing the environmental friendliness of the factory.

[0041] The implementation of the present invention helps to improve the energy efficiency level of factory production, enabling the factory to utilize energy more efficiently during the production process and reducing energy waste. By continuously monitoring the operation status and energy consumption data of the equipment, and dynamically adjusting and optimizing the multi-dimensional energy consumption model and selection strategy, the present invention promotes the factory's development towards the direction of green, low-carbon, and high-efficiency, and helps to achieve the vision of "carbon neutrality". BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, obtaining other drawings without creative efforts still belongs to the scope of the present invention;

[0043] Figure 1 It is a schematic diagram of the main process of an embodiment of a method for power supply selection of factory electrical equipment based on energy consumption analysis provided by the present invention;

[0044] Figure 2 It is a more detailed schematic diagram of the process of the method involved in the present invention;

[0045] Figure 3 It is a schematic diagram of the structure of an embodiment of a system for power supply selection of factory electrical equipment based on energy consumption analysis provided by the present invention;

[0046] Figure 4 For Figure 3Schematic diagram of the structure of the data acquisition and processing module in

[0047] Figure 5 is Figure 3 Schematic diagram of the structure of the energy consumption model construction module in

[0048] Figure 6 is Figure 3 Schematic diagram of the structure of the selection strategy formulation module in

[0049] Figure 7 is Figure 3 Schematic diagram of the structure of the implementation and adjustment module in Detailed implementation manner

[0050] To make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings.

[0051] As Figure 1 shown, a main process schematic diagram of an embodiment of a method for selecting power supply for factory electrical equipment based on energy consumption analysis provided by the present invention is shown. In combination with Figure 2 shown, in this embodiment, the method at least includes the following steps:

[0052] Step S10, using sensors and metering devices to collect the energy consumption characteristic data of various types of equipment in the factory in real time, and preprocessing the collected data;

[0053] In this step, it is necessary to sort out the types of electrical loads of factory equipment and collect the historical load data of factory equipment at different times. For example, the daily load data of a certain factory in the past year, including the maximum load, average load, load factor, etc. every day.

[0054] And collect the types of factory power supply equipment, and based on the load type and production requirements, summarize and classify the factory equipment data, covering production equipment, auxiliary equipment, factory facilities, etc. in the factory. For example, transformers, switchgear, cables, etc., which are the basis of the factory power supply.

[0055] And collect the historical energy consumption data (such as active power, reactive power), operating parameters (such as voltage, current, power factor, etc.), environmental parameters (such as temperature, humidity, etc.) of the target equipment type, as well as the production data and environmental data of the equipment. These data can be collected in real time by using sensors and metering devices.

[0056] At the same time, clean and preprocess the collected data, including data classification and annotation, data conversion, data standardization or normalization, etc., extract data features, improve data quality, and ensure the accuracy of subsequent modeling.

[0057] Among them, data cleaning: such as removing duplicate data, filling in missing data, correcting incorrect data, etc. Data transformation: such as converting data of string type into data of numerical type for mathematical operations. Data standardization or normalization: such as converting data with different dimensions into data with the same dimension for comparison and analysis. Data feature extraction: such as extracting features such as the load rate and peak-valley difference of the equipment, which can reflect the energy consumption characteristics of the equipment.

[0058] Step S11, based on the equipment power consumption load classification, equipment operation parameters, environmental parameters, and production data, construct a multi-dimensional energy consumption model for factory power equipment, and train and optimize the energy consumption model through machine learning algorithms;

[0059] In a specific example, in this step, it is necessary to perform an energy consumption characteristic analysis on the preprocessed data, including:

[0060] Conduct trend analysis: Use autoregressive moving average model (ARMA) technology to analyze the change trend of equipment energy consumption over time, and identify laws such as seasonality and periodicity. For example, the energy consumption of the air conditioning equipment in a certain factory is higher in summer and lower in winter.

[0061] Conduct correlation analysis: Use the (Pearson) correlation coefficient algorithm to analyze the correlation between equipment energy consumption and operation parameters, environmental parameters, and production data, and determine the key factors affecting energy consumption. For example, the energy consumption of a certain motor is positively correlated with its load rate.

[0062] Conduct load characteristic indicators: Analyze the load characteristics of the equipment, including indicators such as load rate and peak-valley difference, and obtain the equipment working conditions, operation characteristics, and energy consumption distribution of the factory. For example, the load rate of a certain factory's production line is higher during peak periods and lower during off-peak periods.

[0063] Then construct a multi-dimensional energy consumption model:

[0064] First, based on the results of the energy consumption characteristic analysis and the preprocessed data, use modeling techniques such as multiple linear regression models and machine learning to construct a multi-dimensional energy consumption model. Among them, the formula for the multiple linear regression algorithm: f(x) = kTx + b, where x is the input vector, including multiple features (independent variables); f(x) is the output or response of the model (the predicted target variable); kT is the feature weight; b is the intercept or bias of the model.

[0065] Then, the model is verified through methods such as cross-validation. The optimization algorithm comprehensively considers multiple objectives such as device performance, energy consumption, cost, and reliability. The dataset is divided into K subsets. Each time, K - 1 subsets are used as the training set, and the remaining one subset is used as the test set. K times of training and testing are carried out, and finally the average value of the K test results is calculated as the performance index of the model. At the same time, heuristic search strategies such as genetic algorithms and particle swarm optimization are adopted to improve the prediction accuracy and generalization ability of the model.

[0066] Step S12: Use the factory historical data and time series analysis algorithm to predict the load demand of the factory power supply system. The prediction results include the load changes in different time periods.

[0067] In this step, through the analysis of the historical load data of factory equipment at different time periods using the time series recurrent neural network (RNN) algorithm, the load demand is predicted for the load changes in different time periods (such as daily, weekly, monthly, and yearly). In a specific example, the attention mechanism can be combined to further improve the accuracy and speed of load prediction.

[0068] Specifically, the RNN algorithm can be used to predict the load demand of factory equipment. For example, use the RNN algorithm to predict the daily load demand of a certain factory in the next year. The RNN is trained through the training dataset to obtain a prediction model, and then this model is used to predict the future load demand. The load demand prediction result can be, for example, to obtain the daily load demand prediction curve for the next year, which can reflect the change trend and law of the factory load demand.

[0069] Step S13: Based on the energy consumption model and the load demand prediction results, comprehensively consider the energy efficiency ratio, economic cost, and operation stability factors of the equipment, formulate a power supply selection strategy for factory electrical equipment, and use simulation to conduct energy consumption analysis and evaluation.

[0070] Specifically, in this step, based on the multi-dimensional energy consumption model and load demand analysis, combined with production data and environmental information, a power equipment selection plan is generated. The plan includes detailed information such as the model, quantity, and configuration of the equipment. For example, for a production line with a large load demand, select a transformer and motor with a high energy efficiency ratio and large capacity.

[0071] Analyze the selection plan through an energy consumption simulation software to evaluate its energy consumption performance under different working conditions. During the evaluation process, consider factors such as the actual operating efficiency of the equipment and load changes to ensure the accuracy and reliability of the evaluation results.

[0072] According to the optimal indicators such as energy consumption, cost, and reliability of the selection plan, form the final equipment selection strategy plan.

[0073] Step S14: Apply the determined selection solution to the actual production of the factory, continuously monitor the operating status and energy consumption data of the equipment, and dynamically adjust and optimize the multi-dimensional energy consumption model and selection strategy according to the actual operating data.

[0074] In a specific example, in the step S14, it further includes:

[0075] Feedback-adjust and optimize the multi-dimensional energy consumption model according to the actual operating data;

[0076] Adjust and optimize the selection strategy solution according to the actual operating conditions and energy consumption performance of the equipment. Specifically, the multi-dimensional energy consumption model can be feedback-adjusted and optimized according to the actual operating data to improve the prediction accuracy and applicability of the model. At the same time, adjust and optimize the selection strategy solution according to the actual operating conditions and energy consumption performance of the equipment to ensure that the solution can continuously meet the needs of the factory and reduce the energy consumption cost. For example, a certain factory finds in actual operation that the energy consumption of a certain motor is high and the operation is unstable, so it decides to replace it with a motor model with a higher energy efficiency ratio and more stable operation.

[0077] As Figure 3 shown, it shows a structural schematic diagram of an embodiment of a factory power equipment power supply selection system based on energy consumption analysis provided by the present invention. Combined with Figures 4 to 7 shown, in this embodiment, the system 1 at least includes:

[0078] A data acquisition and processing module 10, configured to use sensors and metering devices to collect the energy consumption characteristic data of various types of equipment in the factory in real time, and preprocess the collected data;

[0079] An energy consumption model construction module 11, configured to construct a multi-dimensional energy consumption model of the factory power equipment based on equipment power load classification, equipment operating parameters, environmental parameters, and production data, and train and optimize the model through machine learning algorithms;

[0080] A load demand prediction module 12, configured to use the factory historical data and time series analysis algorithm to predict the load demand of the factory power supply system;

[0081] A selection strategy formulation module 13, configured to formulate a factory power equipment power supply selection strategy based on the energy consumption model and the load demand prediction result, comprehensively consider factors such as the energy efficiency ratio, economic cost, and operating stability of the equipment, and perform energy consumption analysis and evaluation using simulation;

[0082] An implementation and adjustment module 14, configured to apply the determined selection solution to the actual production of the factory, continuously monitor the operating status and energy consumption data of the equipment, and dynamically adjust and optimize the multi-dimensional energy consumption model and selection strategy according to the actual operating data.

[0083] Specifically, as Figure 4 shown, in one example, the data acquisition and processing module 10 further includes:

[0084] An acquisition unit 100 for real-time acquisition of voltage, current, power factor, active power, and reactive power energy consumption characteristic data;

[0085] A data processing unit 101 for classifying, labeling, converting, standardizing, or normalizing the data.

[0086] Specifically, as Figure 5 shown, in one example, the energy consumption model construction module 11 further includes:

[0087] A model construction unit 110 that constructs an energy consumption model using a multiple linear regression model and machine learning techniques;

[0088] A model optimization unit 111 that validates the model through a cross-validation method and uses heuristic search strategies such as genetic algorithms and particle swarm optimization to improve the prediction accuracy and generalization ability of the model.

[0089] Specifically, as Figure 6 shown, in one example, the selection strategy formulation module 13 further includes:

[0090] A strategy optimization unit 130 that maximizes the overall energy efficiency of factory equipment by optimizing and combining comprehensive factors such as different load classifications, equipment models, operating capacities, production conditions, and environmental conditions;

[0091] An energy consumption evaluation unit 131 that evaluates the energy consumption performance of the selection scheme under different operating conditions using energy consumption simulation software.

[0092] Specifically, as Figure 7 shown, in one example, the implementation and adjustment module 14 further includes:

[0093] A feedback adjustment unit 140 that performs feedback adjustment and optimization on the multi-dimensional energy consumption model based on actual operation data;

[0094] A strategy optimization and adjustment unit 141 that adjusts and optimizes the selection strategy scheme according to the actual operation conditions and energy consumption performance of the equipment.

[0095] For more details, reference can be made to and combined with the foregoing description of Figures 1 to 2 and will not be elaborated here.

[0096] Implementing the embodiments of the present invention has the following beneficial effects:

[0097] The present invention provides a method and system for power supply selection of factory electrical equipment based on energy consumption analysis. By constructing a multi-dimensional energy consumption model, it can accurately reflect the energy consumption changes of factory electrical equipment under different working conditions. Combining machine learning algorithms to optimize the model improves the accuracy of energy consumption prediction. The selection strategy formulated based on the energy consumption model and the load demand prediction results comprehensively considers factors such as the energy efficiency ratio, economic cost, and operation stability of the equipment, realizes the scientific selection of electrical equipment, and effectively reduces the overall energy consumption of the factory.

[0098] Through refined energy consumption analysis and optimization algorithms, the present invention selects electrical equipment with high energy efficiency and reasonable costs, reducing the equipment investment cost. The selection strategy takes into account the operation efficiency and maintenance costs of the equipment, enabling the factory to save a large amount of energy and maintenance costs during long-term operation and improving economic benefits. Reducing energy consumption directly reduces carbon emissions and environmental pollution. By optimizing equipment selection, the present invention makes the factory more environmentally friendly during the production process. The environmental protection performance of the equipment is considered in the selection strategy, and equipment meeting environmental protection standards is preferentially selected, further enhancing the environmental friendliness of the factory.

[0099] The implementation of the present invention helps to improve the energy efficiency level of factory production, enabling the factory to utilize energy more efficiently during the production process and reducing energy waste. By continuously monitoring the operation status and energy consumption data of the equipment and dynamically adjusting and optimizing the multi-dimensional energy consumption model and selection strategy, the present invention promotes the factory's development towards the direction of green, low-carbon, and high-efficiency, and helps to achieve the "carbon neutrality" vision.

[0100] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a unit for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0101] The above-disclosed is only a preferred embodiment of the present invention, and of course, it cannot be used to limit the scope of rights of the present invention. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope covered by the present invention.

Claims

1. A method for selecting power supply for factory power equipment based on energy consumption analysis, characterized in that: The following steps are involved: Step S10, collecting energy consumption characteristic data of various types of equipment in the factory in real time, and preprocessing the collected data; Step S11, based on equipment power load classification, equipment operating parameters, environmental parameters and production data, a multi-dimensional energy consumption model of factory power equipment is constructed, and the energy consumption model is trained and optimized through a machine learning algorithm; Step S12, using the factory historical data and time series analysis algorithm to predict the load demand of the factory power supply system, the prediction result includes the load changes in different time periods; Step S13, based on the energy consumption model and load demand forecast results, comprehensively considering the energy efficiency ratio, economic cost and operation stability factors of the equipment, formulate a power supply selection strategy for the factory power equipment, and use simulation to perform energy consumption analysis and evaluation; Step S14, applying the determined selection scheme to the actual production of the factory, continuously monitoring the operating status and energy consumption data of the equipment, and dynamically adjusting and optimizing the multi-dimensional energy consumption model and selection strategy according to the actual operating data.

2. The method according to claim 1, characterized in that In step S10, further comprising: Use sensors and metering equipment to collect energy consumption characteristic data of voltage, current, power factor, active power, and reactive power in real time; Classify, label, transform, standardize or normalize the data.

3. The method according to claim 2, characterized in that In the step S11, it further includes: The energy consumption model was constructed using multiple linear regression model and machine learning techniques; The model was verified by cross-validation method, and the heuristic search strategy of genetic algorithm and particle swarm optimization was used to improve the prediction accuracy and generalization ability of the model.

4. The method according to claim 3, characterized in that In step S12, an improved time series recurrent neural network (RNN) based on LSTM is used in combination with an attention mechanism to further improve the accuracy and speed of load forecasting.

5. The method according to claim 4, characterized in that In the step S14, it further includes: Feedback adjustment and optimization of multi-dimensional energy consumption models based on actual operation data; Adjust and optimize the selection strategy according to the actual operation status and energy consumption performance of the equipment.

6. A factory power equipment power supply selection system based on energy consumption analysis, characterized in that: include: The data acquisition and processing module is used to collect energy consumption characteristic data of various types of equipment in the factory in real time using sensors and metering equipment, and pre-process the collected data; Energy consumption model building module, which is used to build a multi-dimensional energy consumption model of factory power equipment based on equipment power load classification, equipment operating parameters, environmental parameters and production data, and train and optimize the model through machine learning algorithms; Load demand forecasting module, used to forecast the load demand of the factory power supply system by using the factory historical data and time series analysis algorithm; The selection strategy formulation module is used to formulate the power supply selection strategy for the factory power equipment based on the energy consumption model and load demand forecast results, comprehensively consider the energy efficiency ratio, economic cost and operation stability factors of the equipment, and use simulation to analyze and evaluate energy consumption; The implementation adjustment module is used to apply the determined selection scheme to the actual production of the factory, continuously monitor the operating status and energy consumption data of the equipment, and dynamically adjust and optimize the multi-dimensional energy consumption model and selection strategy according to the actual operating data.

7. The system according to claim 6, characterized in that The data acquisition and processing module further comprises: The acquisition unit is used to collect energy consumption characteristic data such as voltage, current, power factor, active power, reactive power, etc. in real time using sensors and metering equipment; The data processing unit is used to classify, label, convert, standardize or normalize the data.

8. The system according to claim 7, characterized in that The energy consumption model building module further includes: Model building unit, which uses multiple linear regression model and machine learning technology to build energy consumption model; The model optimization unit verifies the model through the cross-validation method and adopts heuristic search strategies such as genetic algorithm and particle swarm optimization to improve the prediction accuracy and generalization ability of the model.

9. The system according to claim 8, characterized in that The selection strategy formulation module further includes: The strategy optimization unit maximizes the overall energy efficiency of factory equipment by optimizing the combination of different load classifications, equipment models, operating capacity, production conditions, environmental conditions and other comprehensive factors; The energy consumption evaluation unit uses energy consumption simulation software to evaluate the energy consumption performance of the selected solution under different working conditions.

10. The system according to claim 9, characterized in that The implementation adjustment module further includes: Feedback adjustment unit, which performs feedback adjustment and optimization on the multi-dimensional energy consumption model based on actual operation data; The strategy optimization and adjustment unit adjusts and optimizes the selection strategy according to the actual operation status and energy consumption performance of the equipment.

Images