Energy consumption prediction method, device and equipment and readable storage medium

Abstract

The invention discloses an energy consumption prediction method, device and equipment and a readable storage medium, and can be applied to the technical field of artificial intelligence, and the method comprises the steps: obtaining key influence factors for prediction; the key influence factors for prediction comprise target production plan data and target correlation acquisition data corresponding to a to-be-predicted time period; the target correlation acquisition data comprises production field sensor real-time data and external environment data; and in combination with the target production plan data and the target correlation collection data, performing analysis by using a trained energy consumption prediction model, and obtaining energy consumption data of the to-be-predicted time period. In this way, comprehensive energy consumption prediction is carried out in combination with multiple types of data, and the accuracy of energy consumption prediction is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an energy consumption prediction method, device, equipment and readable storage medium. Background Art

[0002] Energy consumption data refers to the amount of each medium (such as water, electricity, and gas) used in a factory over a period of time. By predicting energy consumption in the future and combining the correct methods, energy costs can be reduced, production plans and equipment scheduling can be optimized, and the ability to cope with market fluctuations can be enhanced.

[0003] The existing energy consumption forecasting methods in energy management are too idealistic, often only using historical energy consumption data to forecast future energy consumption, which results in an incomplete forecasting perspective and low accuracy of energy consumption forecasting.

[0004] Therefore, how to improve the accuracy of energy consumption prediction is an issue that technical personnel in this field need to solve urgently. Summary of the invention

[0005] Based on the above problems, the present application provides an energy consumption prediction method, device, equipment and readable storage medium, which improves the accuracy of energy consumption prediction by combining multiple types of data to perform comprehensive prediction of energy consumption.

[0006] In a first aspect, an embodiment of the present application provides an energy consumption prediction method, comprising:

[0007] Acquire key influencing factors for prediction; the key influencing factors for prediction include target production plan data and target correlation collection data corresponding to the time period to be predicted; the target correlation collection data includes real-time data of production site sensors and external environment data;

[0008] The target production plan data and the target correlation collection data are combined and analyzed using a trained energy consumption prediction model to obtain energy consumption data for the time period to be predicted.

[0009] Optionally, the energy consumption prediction model is trained by the following method:

[0010] Acquire historical energy consumption data and key influencing factors for training from a manufacturing operation management system; the key influencing factors for training include historical production plan data and historical correlation collection data corresponding to the historical energy consumption data;

[0011] Based on the historical energy consumption data, historical production plan data and historical correlation collection data, the basic prediction model is trained based on time series analysis to obtain a trained energy consumption prediction model.

[0012] Optionally, the method further includes:

[0013] Based on the manufacturing operation management system, the historical energy consumption data is combined to perform correlation analysis on various types of data and obtain analysis results;

[0014] Based on the analysis results, key influencing factors corresponding to the energy consumption data are determined.

[0015] Optionally, the training of the basic prediction model based on the historical energy consumption data, the historical production plan data and the historical correlation collection data based on time series analysis, and obtaining the trained energy consumption prediction model includes:

[0016] Dividing the historical energy consumption data into a training set and a test set;

[0017] Selecting a first prediction algorithm based on the data characteristics of the training set;

[0018] Based on time series analysis, the basic prediction model is trained using the training set, the key influencing factors corresponding to the training set, and the first prediction algorithm, and prediction training result parameters are obtained;

[0019] Verifying the prediction training result parameters using the test set and the key influencing factors corresponding to the test set;

[0020] If the verification is successful, the model training is completed and a trained energy consumption prediction model is obtained.

[0021] Optionally, the verifying the prediction training result parameters by using the test set and the key influencing factors corresponding to the test set includes:

[0022] Predicting the energy consumption data of the time period corresponding to the training set based on the key influencing factors corresponding to the training set and the predicted training result parameters to obtain a first energy consumption prediction result;

[0023] Comparing the first energy consumption prediction result with the actual energy consumption data corresponding to the training set, and obtaining a comparison result;

[0024] If the comparison result is less than the preset deviation threshold, it means that the verification is passed;

[0025] If the comparison result is greater than or equal to the preset deviation threshold, it means that the verification fails.

[0026] In a second aspect, an embodiment of the present application provides an energy consumption prediction device, comprising:

[0027] An acquisition module is used to acquire key influencing factors for prediction; the key influencing factors for prediction include target production plan data corresponding to the time period to be predicted and target correlation acquisition data; the target correlation acquisition data includes real-time data of sensors on the production site and external environment data;

[0028] The prediction module is used to combine the target production plan data and the target correlation collection data, use the trained energy consumption prediction model to analyze, and obtain the energy consumption data of the time period to be predicted.

[0029] Optionally, the energy consumption prediction device further includes: a training module;

[0030] The training module is used to obtain historical energy consumption data and key influencing factors for training from the manufacturing operation management system; the key influencing factors for training include historical production plan data and historical correlation collection data corresponding to the historical energy consumption data;

[0031] Based on the historical energy consumption data, historical production plan data and historical correlation collection data, the basic prediction model is trained based on time series analysis to obtain a trained energy consumption prediction model.

[0032] Optionally, the energy consumption prediction device further includes: a determination module;

[0033] The determination module is used to perform correlation analysis on various types of data based on the manufacturing operation management system in combination with the historical energy consumption data, and obtain analysis results;

[0034] Based on the analysis results, key influencing factors corresponding to the energy consumption data are determined.

[0035] In a third aspect, an embodiment of the present application provides an energy consumption prediction device, including:

[0036] Memory for storing computer programs;

[0037] A processor is used to implement the steps of the energy consumption prediction method as described above when executing the computer program.

[0038] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the energy consumption prediction method described above are implemented.

[0039] It can be seen from the above technical solutions that compared with the prior art, the present application has the following advantages:

[0040] This application first obtains the key influencing factors for prediction. Among them, the key influencing factors for prediction include the target production plan data and target correlation collection data corresponding to the time period to be predicted; the target correlation collection data includes real-time data of production site sensors and external environment data. Then, combined with the target production plan data and target correlation collection data, the trained energy consumption prediction model is used for analysis, and the energy consumption data for the time period to be predicted is obtained. In this way, by combining multiple types of data for comprehensive prediction of energy consumption, the accuracy of energy consumption prediction is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flowchart of an energy management service provided in an embodiment of the present application;

[0042] Figure 2 A flowchart of an energy consumption prediction method provided in an embodiment of the present application;

[0043] Figure 3 A schematic diagram of an energy consumption prediction process provided in an embodiment of the present application;

[0044] Figure 4 A schematic diagram of the structure of an energy consumption prediction device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] As mentioned above, the existing energy consumption prediction methods have the problem of low accuracy. Specifically, most of the energy consumption prediction methods based on energy management currently only calculate coefficients through historical energy consumption data to make energy consumption predictions. This prediction method is too idealistic and takes too few factors into consideration, which easily leads to the problem of low prediction accuracy.

[0046] To solve the above problems, an embodiment of the present application provides an energy consumption prediction method, including: first, obtaining key influencing factors for prediction. Among them, the key influencing factors for prediction include target production plan data and target correlation collection data corresponding to the time period to be predicted; the target correlation collection data includes real-time data of production site sensors and external environment data. Then, combined with the target production plan data and the target correlation collection data, the trained energy consumption prediction model is used for analysis to obtain the energy consumption data of the time period to be predicted.

[0047] In this way, the accuracy of energy consumption prediction is improved by combining multiple types of data for comprehensive prediction of energy consumption.

[0048] It should be noted that the energy consumption prediction method, device, equipment and readable storage medium provided in this application can be applied to the field of artificial intelligence technology. The above is only an example and does not limit the application field of the energy consumption prediction method, device, equipment and readable storage medium provided in this application.

[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0050] Figure 1 A flowchart of an energy management service provided in an embodiment of the present application. Figure 1 As shown in the figure, in the internal module, the energy demand department proposes an energy demand plan starting with the operations department, and then the operations department executes the energy demand plan. Then the metering department will sequentially carry out the energy metering process, data review process, energy data balance process, and compile daily and monthly energy consumption statistics (by medium and enterprise statistics) to form energy consumption statistics tables. Among them, the energy data balance process will be carried out only after the data review is passed, and if it fails, it will return to the energy metering process. Finally, the financial department of the external module will carry out the financial settlement and end the entire energy management business process.

[0051] Figure 2 A flowchart of an energy consumption prediction method provided in an embodiment of the present application. Figure 2 As shown, an energy consumption prediction method provided in an embodiment of the present application may include:

[0052] S201: Acquire key influencing factors for prediction; the key influencing factors for prediction include target production plan data and target correlation collection data corresponding to the time period to be predicted; the target correlation collection data includes real-time data of production site sensors and external environment data.

[0053] In practical applications, unlike only calculating the coefficient through historical energy consumption data and then predicting energy consumption, this application uses a combination of multiple factors that affect energy consumption data to predict future energy consumption data, thereby improving the accuracy of energy consumption prediction. Specifically, taking today as December 31, 2023 as an example, assuming that the energy consumption data for the next month is to be predicted, the energy consumption prediction device needs to first obtain the key influencing factors for prediction. It includes the target production plan data and target correlation acquisition data corresponding to the period to be predicted (January 1-31, 2024). Among them, the target production plan data is the production plan data from January 1 to 31, 2024 that is connected to production, including order quantity, production scheduling, equipment maintenance, and various production line events. It can be understood that under the same factors, the more the production volume is, the more equipment is turned on, and the natural energy consumption will be high, and vice versa. In addition, the target correlation acquisition data includes real-time data of production site sensors and external environment data. Among them, the real-time data of production site sensors includes temperature, pressure, etc. collected by sensors in real time, and the external environment data includes external environment data such as temperature and humidity provided by the weather station.

[0054] S202: combining the target production plan data and the target correlation collection data, using the trained energy consumption prediction model to perform analysis, and obtaining the energy consumption data of the time period to be predicted.

[0055] In practical applications, the prediction accuracy of the trained energy consumption prediction model is above 85%. In an embodiment of the present application, the energy consumption prediction device inputs the target production plan data and the target correlation collection data into the trained energy consumption prediction model, and the energy consumption prediction model performs a comprehensive analysis in combination with the parameter values ​​determined during the training process, thereby obtaining the energy consumption data for the time period to be predicted. It can be understood that the predicted energy consumption data is generally represented by a curve that fluctuates up and down within a certain range on the time axis referred to by the time period to be predicted, and the specific up and down floating values ​​are determined by the above-mentioned parameter values ​​and the target production plan data and the target correlation collection data. The parameter value can be the weight value corresponding to different data affecting the energy consumption.

[0056] In addition, since the methods of training energy consumption prediction models are different, the embodiments of the present application can illustrate a possible training method.

[0057] In one case, the energy consumption prediction model can be trained by the following method:

[0058] Acquire historical energy consumption data and key influencing factors for training from a manufacturing operation management system; the key influencing factors for training include historical production plan data and historical correlation collection data corresponding to the historical energy consumption data;

[0059] Based on the historical energy consumption data, historical production plan data and historical correlation collection data, the basic prediction model is trained based on time series analysis to obtain a trained energy consumption prediction model.

[0060] In practical applications, the energy consumption prediction device can extract historical energy consumption data (energy consumption data for the past three years, combined with the above example, from January 1, 2021 to December 31, 2023) from the numerous data stored in the manufacturing operation management system, as well as key influencing factors for training that can affect the values ​​of these energy consumption data. Among them, the key influencing factors for training include historical production plan data and historical correlation collection data corresponding to the historical energy consumption data. The energy consumption prediction device then trains the basic prediction model based on time series analysis (ARIMA) using historical energy consumption data, historical production plan data, and historical correlation collection data to obtain a trained energy consumption prediction model.

[0061] In addition, since the methods for determining key influencing factors are different, the embodiments of the present application can illustrate a possible determination method.

[0062] In one embodiment, the method further comprises:

[0063] Based on the manufacturing operation management system, the historical energy consumption data is combined to perform correlation analysis on various types of data and obtain analysis results;

[0064] Based on the analysis results, key influencing factors corresponding to the energy consumption data are determined.

[0065] In actual applications, there are many types of data stored in the manufacturing operation management system, such as machines, sensors, operators and other information. Based on correlation analysis, the actual relevant data can be screened out from many types of data. Among them, by analyzing the relationship between production volume and energy consumption, the relationship between equipment operation status and energy consumption, and the relationship between external environment and energy consumption, the factors affecting energy consumption data can be obtained, that is, the key influencing factors can be production volume (production plan), equipment operation time, external environment data, and real-time monitoring data (real-time data of sensors at the production site). Among them, the equipment operation time is related to the production plan and can be collectively referred to as production plan data. It can be understood that different states such as equipment operation, stop, and maintenance will have an impact on energy consumption; the instantaneous high water in the real-time monitoring data means high cycle energy consumption of water, and the pressure of compressed air, natural gas, etc. will affect the energy consumption of gas; the high and low temperature in the external environment data will affect the use of air conditioning, etc., which will in turn affect energy consumption. Under the same factors in the production plan data, the more production and the more equipment are turned on, the higher the energy consumption will be. Conversely, in order to make accurate predictions, it is necessary to combine the production plan data. An accurate production plan also needs to consider order volume, equipment maintenance, production line events, etc.

[0066] In addition, since the methods of training energy consumption prediction models are different, the embodiments of the present application can illustrate a possible training method.

[0067] In one case, the training of the basic prediction model based on the historical energy consumption data, the historical production plan data and the historical correlation collection data based on time series analysis to obtain the trained energy consumption prediction model includes:

[0068] Dividing the historical energy consumption data into a training set and a test set;

[0069] Selecting a first prediction algorithm based on the data characteristics of the training set;

[0070] Based on time series analysis, the basic prediction model is trained using the training set, the key influencing factors corresponding to the training set, and the first prediction algorithm, and prediction training result parameters are obtained;

[0071] Verifying the prediction training result parameters using the test set and the key influencing factors corresponding to the test set;

[0072] If the verification is successful, the model training is completed and a trained energy consumption prediction model is obtained.

[0073] In practical applications, continue to combine the above, take today as December 31, 2023 as an example, assume that you want to predict the energy consumption data for the next month, and you need to train the energy consumption prediction model first. Then you can obtain the historical energy consumption data from January 1, 2021 to December 31, 2023 from the manufacturing operation management system, as well as the key influencing factors corresponding to this period. Then these historical energy consumption data and the corresponding key influencing factors are divided into a training set and a test set. The division method can be divided by time period or in other ways. The division principle can be that the data in the training set is more than the data in the test set. The data characteristic refers to the law of the historical energy consumption data obtained, which is generally a curve that fluctuates up and down within a certain range. The embodiment of the present application can select a prediction algorithm (first prediction algorithm) according to the data characteristics of the historical energy consumption data in the training set, and then train the model based on time series analysis (such as ARIMA or machine learning model LSTM) using the historical energy consumption data in the test set, the key influencing factors corresponding to the test set, and the selected algorithm to obtain the prediction training result parameters. This parameter can be used to indicate the weights corresponding to each factor in the key influencing factors. Finally, the prediction training result parameters obtained through training are verified through the historical energy consumption data in the test set and the key influencing factors corresponding to the test set. If the verification passes, the model training is completed and the trained energy consumption prediction model is obtained for subsequent energy consumption prediction.

[0074] In addition, since the methods for verifying whether the energy consumption prediction model is trained are different, the embodiment of the present application can illustrate a possible verification method.

[0075] In one case, the verifying the prediction training result parameters by using the test set and the key influencing factors corresponding to the test set includes:

[0076] Predicting the energy consumption data of the time period corresponding to the training set based on the key influencing factors corresponding to the training set and the predicted training result parameters to obtain a first energy consumption prediction result;

[0077] Comparing the first energy consumption prediction result with the actual energy consumption data corresponding to the training set, and obtaining a comparison result;

[0078] If the comparison result is less than the preset deviation threshold, it means that the verification is passed;

[0079] If the comparison result is greater than or equal to the preset deviation threshold, it means that the verification fails.

[0080] In practical applications, combined with the prediction training result parameters obtained from the above training, the key influencing factors corresponding to the test set can be input into the above trained model to predict the energy consumption of the corresponding time period of the training set, and obtain the actual prediction result (the first energy consumption prediction result). It can be understood that the first energy consumption prediction result is a curve that fluctuates up and down within a certain range with a time span of the entire test set. The first energy consumption prediction result is then compared with the actual energy consumption data of the test set that is actually recorded in the manufacturing operation management system. If the prediction accuracy is required to be above 85%, the preset deviation threshold can be set to 15%. When the comparison result is less than 15%, it indicates that the verification is passed; when the comparison result is greater than or equal to 15%, it indicates that the verification has failed.

[0081] Figure 3 A schematic diagram of an energy consumption prediction process provided in an embodiment of the present application. Figure 3As shown, the manufacturing operation management system is capable of data collection and processing, including historical energy consumption data, real-time monitoring data, external environment data, and production plan data. Before the prediction begins, the energy consumption prediction device needs to perform feature selection from the manufacturing operation management system, extract historical energy consumption data for training and key influencing factors for training, select an algorithm for training, and optimize the model. In addition, the trained model needs to be verified. If it meets the requirements, it is trained to obtain a trained energy consumption prediction model. At this point, if you want to predict energy consumption data for a period of time in the future, you can use the trained energy consumption prediction model to obtain historical energy consumption data and related key influencing factors (real-time monitoring data, external environment data, and production plan data) from the manufacturing operation management system for prediction, and then obtain the prediction result.

[0082] In summary, the present application first obtains the key influencing factors for prediction. Among them, the key influencing factors for prediction include the target production plan data and target correlation collection data corresponding to the time period to be predicted; the target correlation collection data includes real-time data of production site sensors and external environment data. Then, combined with the target production plan data and the target correlation collection data, the trained energy consumption prediction model is used for analysis, and the energy consumption data for the time period to be predicted is obtained. In this way, by combining multiple types of data for comprehensive prediction of energy consumption, the accuracy of energy consumption prediction is improved.

[0083] Figure 4 A schematic diagram of the structure of an energy consumption prediction device provided in an embodiment of the present application. Figure 4 As shown, the energy consumption prediction device 400 provided in the embodiment of the present application includes:

[0084] The acquisition module 401 is used to acquire key influencing factors for prediction; the key influencing factors for prediction include target production plan data and target correlation acquisition data corresponding to the time period to be predicted; the target correlation acquisition data includes real-time data of sensors on the production site and external environment data;

[0085] The prediction module 402 is used to combine the target production plan data and the target correlation collection data, use the trained energy consumption prediction model to perform analysis, and obtain the energy consumption data of the time period to be predicted.

[0086] As an implementation method, regarding how to train the energy consumption prediction model, the energy consumption prediction device 400 further includes: a training module;

[0087] A training module, used to obtain historical energy consumption data and key influencing factors for training from a manufacturing operation management system; the key influencing factors for training include historical production plan data and historical correlation collection data corresponding to the historical energy consumption data;

[0088] Based on the historical energy consumption data, historical production plan data and historical correlation collection data, the basic prediction model is trained based on time series analysis to obtain a trained energy consumption prediction model.

[0089] As an implementation method, with respect to how to determine the key influencing factors, the energy consumption prediction device 400 further includes: a determination module;

[0090] A determination module, used to perform correlation analysis on various types of data based on the manufacturing operation management system and in combination with the historical energy consumption data, and obtain analysis results;

[0091] Determine the key influencing factors corresponding to the energy consumption data based on the analysis results

[0092] As an implementation method, regarding how to obtain a trained energy consumption prediction model, the above training module is specifically used for:

[0093] Dividing the historical energy consumption data into a training set and a test set;

[0094] Selecting a first prediction algorithm based on the data characteristics of the training set;

[0095] Based on time series analysis, the basic prediction model is trained using the training set, the key influencing factors corresponding to the training set, and the first prediction algorithm, and prediction training result parameters are obtained;

[0096] Verifying the prediction training result parameters using the test set and the key influencing factors corresponding to the test set;

[0097] If the verification is successful, the model training is completed and a trained energy consumption prediction model is obtained.

[0098] As an implementation method, regarding how to verify whether the energy consumption prediction model has been trained, the above training module is specifically used to:

[0099] Predicting the energy consumption data of the time period corresponding to the training set based on the key influencing factors corresponding to the training set and the predicted training result parameters to obtain a first energy consumption prediction result;

[0100] Comparing the first energy consumption prediction result with the actual energy consumption data corresponding to the training set, and obtaining a comparison result;

[0101] If the comparison result is less than the preset deviation threshold, it means that the verification is passed;

[0102] If the comparison result is greater than or equal to the preset deviation threshold, it means that the verification fails.

[0103] In summary, the present application first obtains the key influencing factors for prediction. Among them, the key influencing factors for prediction include the target production plan data and target correlation collection data corresponding to the time period to be predicted; the target correlation collection data includes real-time data of production site sensors and external environment data. Then, combined with the target production plan data and the target correlation collection data, the trained energy consumption prediction model is used for analysis, and the energy consumption data for the time period to be predicted is obtained. In this way, by combining multiple types of data for comprehensive prediction of energy consumption, the accuracy of energy consumption prediction is improved.

[0104] In addition, the present application also provides an energy consumption prediction device, including:

[0105] Memory for storing computer programs;

[0106] A processor is used to implement the steps of the energy consumption prediction method as described in any one of the above items when executing the computer program.

[0107] In addition, the present application also provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the energy consumption prediction method as described in any one of the above items are implemented.

[0108] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting energy consumption, characterized in that: The method comprises: Acquire key influencing factors for prediction; the key influencing factors for prediction include target production plan data and target correlation collection data corresponding to the time period to be predicted; the target correlation collection data includes real-time data of production site sensors and external environment data; The target production plan data and the target correlation collection data are combined and analyzed using a trained energy consumption prediction model to obtain energy consumption data for the time period to be predicted.

2. The method according to claim 1, characterized in that The energy consumption prediction model is trained by the following method: Acquire historical energy consumption data and key influencing factors for training from a manufacturing operation management system; the key influencing factors for training include historical production plan data and historical correlation collection data corresponding to the historical energy consumption data; Based on the historical energy consumption data, historical production plan data and historical correlation collection data, the basic prediction model is trained based on time series analysis to obtain a trained energy consumption prediction model.

3. The method according to claim 2, characterized in that The method further comprises: Based on the manufacturing operation management system, the historical energy consumption data is combined to perform correlation analysis on various types of data and obtain analysis results; Based on the analysis results, key influencing factors corresponding to the energy consumption data are determined.

4. The method according to claim 2, characterized in that: The training of the basic prediction model based on the historical energy consumption data, the historical production plan data and the historical correlation collection data based on time series analysis, and obtaining the trained energy consumption prediction model includes: Dividing the historical energy consumption data into a training set and a test set; Selecting a first prediction algorithm based on the data characteristics of the training set; Based on time series analysis, the basic prediction model is trained using the training set, the key influencing factors corresponding to the training set, and the first prediction algorithm, and prediction training result parameters are obtained; Verifying the prediction training result parameters using the test set and the key influencing factors corresponding to the test set; If the verification is successful, the model training is completed and a trained energy consumption prediction model is obtained.

5. The method according to claim 4, characterized in that The verifying the prediction training result parameters by using the test set and the key influencing factors corresponding to the test set includes: Predicting the energy consumption data of the time period corresponding to the training set based on the key influencing factors corresponding to the training set and the predicted training result parameters to obtain a first energy consumption prediction result; Comparing the first energy consumption prediction result with the actual energy consumption data corresponding to the training set, and obtaining a comparison result; If the comparison result is less than the preset deviation threshold, it means that the verification is passed; If the comparison result is greater than or equal to the deviation threshold, it means that the verification fails.

6. An energy consumption prediction device, characterized in that: include: An acquisition module is used to obtain key influencing factors for prediction; The key influencing factors for prediction include target production plan data and target correlation acquisition data corresponding to the time period to be predicted; The target-related collected data includes real-time data from production site sensors and external environment data; The prediction module is used to combine the target production plan data and the target correlation collection data, use the trained energy consumption prediction model to analyze, and obtain the energy consumption data of the time period to be predicted.

7. The device according to claim 6, characterized in that The energy consumption prediction device further includes: a training module; The training module is used to obtain historical energy consumption data and key influencing factors for training from the manufacturing operation management system; the key influencing factors for training include historical production plan data and historical correlation collection data corresponding to the historical energy consumption data; Based on the historical energy consumption data, historical production plan data and historical correlation collection data, the basic prediction model is trained based on time series analysis to obtain a trained energy consumption prediction model.

8. The device according to claim 7, characterized in that The energy consumption prediction device further includes: a determination module; The determination module is used to perform correlation analysis on various types of data based on the manufacturing operation management system in combination with the historical energy consumption data, and obtain analysis results; Based on the analysis results, key influencing factors corresponding to the energy consumption data are determined.

9. An energy consumption prediction device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the energy consumption prediction method as claimed in any one of claims 1 to 5 when executing the computer program.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the energy consumption prediction method according to any one of claims 1 to 5 are implemented.

Images