Energy consumption prediction method and system for air compressor
By collecting and preprocessing the energy consumption data of the air compressor, conducting factor classification and energy consumption prediction network training, using factor regression analysis method for data fitting and verification, generating an air compressor energy consumption prediction network, solving the existing technology of air compressor air compressor The problem of inaccurate energy consumption prediction has achieved intelligence and precision in energy consumption prediction.
Patent Information
- Application Number
- CN202411230875.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-04
- Publication Date
- 2024-12-03
AI Technical Summary
The prior art cannot achieve accurate prediction of air compressor energy consumption, and it mainly depends on experience or simple rule setting, so it cannot achieve accurate prediction of energy consumption.
By collecting and preprocessing the energy consumption data of the air compressor, conducting factor classification and energy consumption prediction network training, using factor regression analysis method for data fitting and verification, generating an air compressor energy consumption prediction network, realizing the intelligent energy consumption prediction of energy consumption prediction and precision.
The accuracy and efficiency of energy consumption prediction of air compressors is improved, and accurate energy consumption prediction results are achieved.
Smart Images

Figure CN119067262A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and in particular to an energy consumption prediction method and system for an air compressor. Background Art
[0002] With the development of economy and the increasing shortage of resources, energy conservation and emission reduction of enterprises have become a necessary process of development. Air compressor is the main body of air source device and the air pressure generating device of compressed air. As one of the core equipment in industrial production, its energy consumption has always been a concern. However, the existing air compressor energy consumption control method mainly relies on experience or simple rule setting, which cannot achieve accurate energy consumption prediction. Summary of the invention
[0003] The present application solves the technical problem that the prior art cannot achieve accurate energy consumption prediction by providing an energy consumption prediction method and system for an air compressor, thereby achieving intelligent energy consumption prediction by generating an air compressor energy consumption prediction network, improving the accuracy of energy consumption prediction results and prediction efficiency, and thus achieving the technical effect of accurate energy consumption prediction.
[0004] In view of the above problems, the present invention provides an energy consumption prediction method and system for an air compressor.
[0005] In the first aspect, the present application provides an energy consumption prediction method for an air compressor, the method comprising: collecting and preprocessing to obtain a standard air compressor energy consumption data set; factor classification of the standard air compressor energy consumption data set to obtain an air compressor equipment factor data set, an operating environment factor data set, an operating status factor data set, and an operating energy consumption data set; training energy consumption prediction networks based on the air compressor equipment factor data set, the operating environment factor data set, the operating status factor data set, and the operating energy consumption data set to obtain an air compressor equipment energy consumption prediction network, an operating environment energy consumption prediction network, and an operating status energy consumption prediction network; using factor regression analysis to classify the standard air compressor energy consumption data set to obtain an air compressor equipment energy consumption prediction network, an operating environment energy consumption prediction network, and an operating status energy consumption prediction network; and The air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating status energy consumption prediction network are data fitted to determine the prediction network regression coefficient information; the prediction effect of the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating status energy consumption prediction network are verified to obtain the prediction network effect coefficient information; the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating status energy consumption prediction network are integrated according to the prediction network regression coefficient information and the prediction network effect coefficient information to generate an air compressor energy consumption prediction network, and air compressor energy consumption is predicted based on the air compressor energy consumption prediction network.
[0006] On the other hand, the present application also provides an energy consumption prediction system for an air compressor, the system comprising: an acquisition preprocessing module, used for acquisition preprocessing to obtain a standard air compressor energy consumption data set; a factor classification module, used for factor classification of the standard air compressor energy consumption data set, to obtain an air compressor equipment factor data set, an operating environment factor data set, an operating status factor data set and an operating energy consumption data set; an energy consumption prediction network training module, used for training an energy consumption prediction network based on the air compressor equipment factor data set, the operating environment factor data set, the operating status factor data set and the operating energy consumption data set, to obtain an air compressor equipment energy consumption prediction network, an operating environment energy consumption prediction network and an operating status energy consumption prediction network; a regression coefficient determination module, used for utilizing The factor regression analysis method is used to perform data fitting on the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating status energy consumption prediction network to determine the prediction network regression coefficient information; a prediction effect verification module is used to verify the prediction effect of the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating status energy consumption prediction network to obtain the prediction network effect coefficient information; an air compressor energy consumption prediction module is used to fuse the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating status energy consumption prediction network according to the prediction network regression coefficient information and the prediction network effect coefficient information to generate an air compressor energy consumption prediction network, and perform air compressor energy consumption prediction based on the air compressor energy consumption prediction network.
[0007] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.
[0008] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.
[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages: The standard air compressor energy consumption data set is acquired through collection preprocessing, and then the data set is classified into factors. The classified factor data sets are trained with energy consumption prediction networks to obtain air compressor equipment energy consumption prediction networks, operating environment energy consumption prediction networks, and operating status energy consumption prediction networks. The factor regression analysis method is used to fit the data of each energy consumption prediction network, determine the prediction network regression coefficient information, and verify the prediction effect of each energy consumption prediction network to obtain the prediction network effect coefficient information. The air compressor equipment energy consumption prediction network, operating environment energy consumption prediction network, and operating status energy consumption prediction network are integrated according to the prediction network regression coefficient information and the prediction network effect coefficient information to generate an air compressor energy consumption prediction network, and the air compressor energy consumption prediction network is used to predict the air compressor energy consumption. The technical solution is used to achieve intelligent energy consumption prediction by generating an air compressor energy consumption prediction network, improve the accuracy of energy consumption prediction results and prediction efficiency, and thus achieve the technical effect of precise energy consumption prediction.
[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] Figure 1 A schematic diagram of a flow chart of an energy consumption prediction method for an air compressor in this application; Figure 2 A schematic diagram of a process for obtaining a standard air compressor energy consumption data set in an air compressor energy consumption prediction method of the present application; Figure 3 This is a schematic diagram of the structure of an energy consumption prediction system for an air compressor in the present application; Figure 4 This is a schematic diagram of the structure of an exemplary electronic device of the present application.
[0012] Explanation of the accompanying drawings: acquisition preprocessing module 11, factor classification module 12, energy consumption prediction network training module 13, regression coefficient determination module 14, prediction effect verification module 15, air compressor energy consumption prediction module 16, bus 1110, processor 1120, transceiver 1130, bus interface 1140, memory 1150, operating system 1151, application 1152 and user interface 1160. DETAILED DESCRIPTION
[0013] In the description of this application, those skilled in the art should know that this application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, this application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, this application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.
[0014] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.
[0015] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.
[0016] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.
[0017] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.
[0018] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.
[0019] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.
[0020] The present application is described below in conjunction with the drawings in the present application.
[0021] Embodiment 1 like Figure 1 As shown, the present application provides a method for predicting energy consumption of an air compressor, the method comprising: Step S1: collect and preprocess to obtain a standard air compressor energy consumption data set; like Figure 2 As shown, further, the step of obtaining the standard air compressor energy consumption data set in this application also includes: The data set of air compressor energy consumption source is acquired through data mining technology; Obtaining data anomaly identification indicators, wherein the data anomaly identification indicators include numerical consistency, missing degree, and over-limit threshold; Based on the data anomaly identification index, anomaly identification is performed on the air compressor energy consumption source data set to obtain an abnormal energy consumption index data set; According to the data anomaly identification indicator, mapping determines the data preprocessing rules; The abnormal energy consumption index data set is standardized and preprocessed based on the data preprocessing rules to obtain the standard air compressor energy consumption data set.
[0022] Furthermore, the step of performing standardized preprocessing on the abnormal energy consumption index data set based on the data preprocessing rule also includes: Classifying the abnormal energy consumption index data set to obtain a numerically opposed data set, a missing energy consumption data set, and an over-limit threshold data set; Based on the data preprocessing rules, the numerical opposition data set is normalized and compared to obtain a consistent energy consumption data set; Tracing and filling the missing energy consumption data set to obtain a complete energy consumption data set; The over-limit threshold data set is normalized and cleaned according to a preset data format.
[0023] Specifically, with the development of the economy and the increasing shortage of resources, energy conservation and emission reduction of enterprises have become a necessary process of development. The air compressor is the main body of the air source device and is a compressed air pressure generating device. As one of the core equipment in industrial production, its energy consumption has always been a concern. In order to realize the intelligent air compressor energy consumption prediction, the historical data related to the air compressor energy consumption is first collected through data mining technology to obtain the air compressor energy consumption source data set, which includes the historical operation energy consumption data of various types of air compressors. Formulate the acquisition of data anomaly identification indicators, which are used to evaluate and identify abnormal energy consumption data, including numerical consistency, that is, whether the values before and after the data are consistent; missing degree, that is, the degree of data missing; over-limit threshold, that is, whether the data exceeds the normal limit range, too large or too small. Based on the data anomaly identification index, the air compressor energy consumption source data set is anomaly identified, and the data anomaly standard is set according to the air compressor operation experience. The data information that meets the data anomaly standard after the abnormal identification index is evaluated is integrated to obtain the abnormal energy consumption index data set. According to the data anomaly identification index, a data preprocessing rule is mapped and determined. The data preprocessing rule is determined according to the data anomaly identification index and serves as a basis for the abnormal data preprocessing method.
[0024] Based on the data preprocessing rules, the abnormal energy consumption index data set is subjected to standardized preprocessing, specifically, the abnormal energy consumption index data set is first classified, that is, the abnormal data is integrated according to the data anomaly identification index, and the numerical opposition data set, the missing energy consumption data set, and the over-limit threshold data set are obtained respectively. Based on the data preprocessing rules, the abnormal data is preprocessed. For the numerical opposition data set, the numerical opposition data set is normalized, the data unit is unified, and the data dimensionless processing is realized. Then, the normalized data is compared and verified to realize data consistency correction, so as to obtain a consistent energy consumption data set. For the missing energy consumption data set, the missing energy consumption data set is traced and filled, that is, the source of the missing data is traced, so as to fill the missing data according to the data source, and obtain a complete energy consumption data set. For the over-limit threshold data set, since the abnormal data may exceed the limit due to different bases, the data base format is set, and the over-limit threshold data set is normalized and cleaned according to the preset data base format, wherein the preset data base format is the preset data display base. For example, the data is displayed in a normalized format according to a preset decimal format, and the data that still exceeds the limit after normalization is cleaned. By performing targeted preprocessing on each abnormal indicator data, a standard air compressor energy consumption data set after data preprocessing and integration is obtained. Data preprocessing standardization is achieved to ensure data availability, thereby improving data processing efficiency.
[0025] Step S2: classifying the standard air compressor energy consumption data set by factors to obtain an air compressor equipment factor data set, an operating environment factor data set, an operating state factor data set, and an operating energy consumption data set; Specifically, the standard air compressor energy consumption data set is classified by factors, that is, data factor classification indicators are set, including air compressor equipment factors, such as air compressor model, specification, lubrication method, etc.; operating environment factors, such as ambient temperature, humidity, air pressure, etc.; operating state factors, such as intake and exhaust pressure, exhaust gas volume, operating time, etc. Then the standard air compressor energy consumption data set is classified according to the set data factor classification indicators, and the data of the same factor type are integrated into one category to obtain the corresponding air compressor equipment factor data set, operating environment factor data set, operating state factor data set, and operating energy consumption data set corresponding to each factor data set, providing a data basis for subsequent energy consumption prediction network training.
[0026] Step S3: Based on the air compressor equipment factor data set, the operating environment factor data set, the operating state factor data set and the operating energy consumption data set, respectively, energy consumption prediction network training is performed to obtain an air compressor equipment energy consumption prediction network, an operating environment energy consumption prediction network and an operating state energy consumption prediction network; Furthermore, the step of obtaining the piston machine operation detection data stream in this application also includes: Extracting related indicators from the air compressor equipment factor data set, the operating environment factor data set, the operating status factor data set and the operating energy consumption data set respectively, to obtain an air compressor equipment factor indicator set, an operating environment factor indicator set and an operating status factor indicator set; Based on the air compressor equipment factor index set, the operating environment factor index set and the operating status factor index set, principal component analysis is performed respectively to obtain a dimensionality reduction associated index set, wherein the dimensionality reduction associated index set includes a dimensionality reduction air compressor equipment factor index set, a dimensionality reduction operating environment factor index set and a dimensionality reduction operating status factor index set; The air compressor equipment factor data set, the operating environment factor data set, the operating status factor data set and the operating energy consumption data set are classified and integrated according to the dimension reduction association index set, and energy consumption prediction network training is performed based on the integrated data sets.
[0027] Specifically, the energy consumption prediction network training is performed based on the air compressor equipment factor data set, the operating environment factor data set, the operating state factor data set and the operating energy consumption data set. In order to improve the model training efficiency, the associated indicators of the air compressor equipment factor data set, the operating environment factor data set, the operating state factor data set and the operating energy consumption data set are firstly extracted, that is, the indicator types of all relevant sources in the factor data set are extracted and integrated to obtain the corresponding air compressor equipment factor indicator set, operating environment factor indicator set and operating state factor indicator set. Then, principal component analysis is performed based on the air compressor equipment factor indicator set, operating environment factor indicator set and operating status factor indicator set, and the process steps include removing the mean, calculating the covariance matrix, calculating the eigenvalues and eigenvectors, retaining the most important first k features, finding the eigenvectors corresponding to the k eigenvalues, and multiplying the standardized data set by the k eigenvectors, and then extracting the main related indicator features, transforming multiple factor indicators into a few comprehensive indicators, so as to obtain a reduced dimensionality related indicator set, which is factor indicator information with strong correlation, including a reduced dimensionality air compressor equipment factor indicator set, a reduced dimensionality operating environment factor indicator set and a reduced dimensionality operating status factor indicator set.
[0028] According to the dimensionality reduction associated index set, the air compressor equipment factor data set, the operating environment factor data set, the operating state factor data set and the operating energy consumption data set are classified and integrated, that is, the data in the factor data set is classified according to the dimensionality reduction associated index, and the data of the same associated index type is integrated into one category to obtain each factor data set after the associated index is integrated. And based on the integrated data set, the energy consumption prediction network is trained respectively to obtain the energy consumption prediction network set trained with the associated index data in the air compressor equipment factors, the energy consumption prediction network set trained with the associated index data in the operating environment factors, and the energy consumption prediction network set trained with the associated index data in the operating state factors. Then, the energy consumption prediction network sets obtained by the training of each associated index are fused according to the factor type to obtain the corresponding air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network and the operating state energy consumption prediction network. The dimensionality reduction of the index is realized, the correlation of the factor index training is enhanced, the calculation efficiency is improved, and the training accuracy of the energy consumption prediction network is improved.
[0029] Step S4: using factor regression analysis to perform data fitting on the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating state energy consumption prediction network to determine the prediction network regression coefficient information; Furthermore, the step of determining the prediction network regression coefficient information also includes: Obtain a multivariate indicator linear regression model; The energy consumption prediction network of the air compressor equipment, the energy consumption prediction network of the operating environment, and the energy consumption prediction network of the operating state are fitted with data through the multivariate index linear regression model to obtain the regression coefficient information of the initial prediction network; The initial prediction network regression coefficient information is fitted and evaluated until a preset fitting determination coefficient is reached to determine the prediction network regression coefficient information.
[0030] Specifically, in order to improve the accuracy of air compressor energy consumption prediction, the factor regression analysis method is used to perform data fitting on the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating status energy consumption prediction network. First, a multivariate indicator linear regression model is obtained. The multivariate indicator linear regression model is a multivariate linear regression function, which predicts or estimates the dependent variable energy consumption prediction by the optimal combination of multiple independent variable network models. The multivariate indicator linear regression model is used to perform data fitting on the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating status energy consumption prediction network. The initial prediction network regression coefficient information is obtained through data fitting regression. The initial prediction network regression coefficient information is the regression weighted calculation coefficient of each energy consumption prediction network.
[0031] In order to ensure the accuracy of the regression coefficient, the regression coefficient information of the initial prediction network is fitted and evaluated, that is, the data verification of its fitting effect is carried out, and the determination coefficient is used as the regression model evaluation index to measure the degree of fit of the regression coefficient to the data. The calculation formula of the determination coefficient is: R²= 1-SSres / SStot, where SSres is the residual sum of squares, which indicates the degree of difference between the actual observed value and the predicted value, and SStot is the total sum of squares, which is the sum of squares between the actual observed value and the average value, indicating the degree of difference between all actual observed values and the average value. The larger the R², the better the model fits the data, and the more accurate the regression coefficient of the model is, until the preset fitting determination coefficient is reached. The preset fitting determination coefficient is the regression coefficient fitting accuracy standard. When the preset fitting regression effect is reached, the prediction network regression coefficient information of each energy consumption prediction network is determined. The regression coefficient of the sub-energy consumption prediction network model can be interpreted as the degree of response to a specific independent variable, and in the fusion model, these regression coefficients can be combined to produce a more comprehensive model. Improve the fitting accuracy of the model regression coefficient, thereby ensuring the fusion accuracy of the energy consumption prediction network.
[0032] Step S5: verifying the prediction effect of the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating state energy consumption prediction network to obtain prediction network effect coefficient information; Specifically, the prediction effect of the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating status energy consumption prediction network is verified, that is, the output data of each energy consumption prediction network is compared with the actual data through a data verification set, and its prediction accuracy is calculated, and its prediction accuracy is used as the prediction network effect coefficient information. The larger the coefficient, the greater the output accuracy of the energy consumption prediction network and the better the prediction effect.
[0033] Step S6: According to the prediction network regression coefficient information and the prediction network effect coefficient information, the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating state energy consumption prediction network are integrated to generate an air compressor energy consumption prediction network, and air compressor energy consumption prediction is performed based on the air compressor energy consumption prediction network.
[0034] Furthermore, the generation of the air compressor energy consumption prediction network, the application steps also include: Construct the coefficient integration function: ; in, Identify model fusion parameters, Characterizes the prediction network regression coefficient, Characterize the predicted network effect coefficient, is an increasing function; Calculate the prediction network regression coefficient information and the prediction network effect coefficient information based on the coefficient fusion function, and output network fusion parameter information; Based on the network fusion parameter information, the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating status energy consumption prediction network are fused to generate the air compressor energy consumption prediction network.
[0035] Specifically, the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating state energy consumption prediction network are fused according to the prediction network regression coefficient information and the prediction network effect coefficient information, specifically, firstly constructing a coefficient fusion function: ,in, Identify model fusion parameters, Characterizes the prediction network regression coefficient, Characterize the predicted network effect coefficient, Based on the coefficient fusion function, the prediction network regression coefficient information and the prediction network effect coefficient information are calculated, and the network fusion parameter information corresponding to each energy consumption prediction network is output.
[0036] The coefficient fusion function is an increasing function, indicating that the larger the regression coefficient of the energy consumption prediction network and the larger the model effect coefficient, the larger the calculated network fusion parameter, and the greater its voting power in the final fusion energy consumption prediction network. Based on the network fusion parameter information, the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating status energy consumption prediction network are fused to generate an air compressor energy consumption prediction network with more accurate and comprehensive prediction effects, and air compressor energy consumption prediction is performed based on the air compressor energy consumption prediction network. Intelligent and efficient energy consumption prediction is realized, the accuracy and efficiency of air compressor energy consumption prediction are improved, and precise energy consumption prediction is achieved.
[0037] Furthermore, the application steps also include: Perform air compressor energy consumption prediction based on the air compressor energy consumption prediction network, and output air compressor energy consumption prediction information; Acquire air compressor application scenario information, extract parameters from the air compressor application scenario information, and obtain application scenario element information; Perform a transport energy consumption analysis on the application scenario element information to determine a transport energy consumption influencing factor, and perform additional optimization and correction on the air compressor energy consumption prediction information based on the transport energy consumption influencing factor.
[0038] Specifically, the air compressor energy consumption is predicted in real time based on the air compressor energy consumption prediction network, and the air compressor energy consumption prediction information is output. At the same time, in the actual application of the air compressor, transportation energy consumption will also be generated, that is, the energy consumed by the compressed air during the transportation process, mainly including the energy consumption of components such as pipelines, accessories and pressure regulators. In order to increase the comprehensiveness of the energy consumption prediction, the application scenario information of the target air compressor is obtained. Air compressors are widely used in many fields such as electronics, automobiles, and energy. Then, the air compressor application scenario information is parameter extracted to obtain application scenario element information. The application scenario element information is the parameters such as the transportation equipment and transportation environment of the air compressor application scenario. The actual transportation energy consumption of the air compressor varies with different application scenarios, and the transportation energy consumption analysis is performed on the application scenario element information. The application scenario elements can be intelligently analyzed through the transportation energy consumption empirical model to determine the transportation energy consumption influencing factor. The transportation energy consumption influencing factor is used to indicate the actual consumption of the air compressor transportation energy consumption generated by the application scenario. Based on the transmission energy consumption influencing factor, the air compressor energy consumption prediction information is additionally optimized and corrected, and the air compressor transmission energy consumption is combined with calculation to improve the comprehensiveness and accuracy of the actual energy consumption prediction of the air compressor, ensure the practical applicability of the prediction result, and thus realize accurate energy consumption prediction.
[0039] In summary, the energy consumption prediction method and system for an air compressor provided by the present application have the following technical effects: The standard air compressor energy consumption data set is acquired through collection preprocessing, and then the data set is classified into factors. The classified factor data sets are trained with energy consumption prediction networks to obtain air compressor equipment energy consumption prediction networks, operating environment energy consumption prediction networks, and operating status energy consumption prediction networks. The factor regression analysis method is used to fit the data of each energy consumption prediction network, determine the prediction network regression coefficient information, and verify the prediction effect of each energy consumption prediction network to obtain the prediction network effect coefficient information. The air compressor equipment energy consumption prediction network, operating environment energy consumption prediction network, and operating status energy consumption prediction network are integrated according to the prediction network regression coefficient information and the prediction network effect coefficient information to generate an air compressor energy consumption prediction network, and the air compressor energy consumption prediction network is used to predict the air compressor energy consumption. The technical solution is used to achieve intelligent energy consumption prediction by generating an air compressor energy consumption prediction network, improve the accuracy of energy consumption prediction results and prediction efficiency, and thus achieve the technical effect of precise energy consumption prediction.
[0040] Embodiment 2 Based on the same inventive concept as the energy consumption prediction method of an air compressor in the aforementioned embodiment, the present invention also provides an energy consumption prediction system for an air compressor, such as Figure 3 As shown, the system comprises: The collection and preprocessing module 11 is used for collection and preprocessing to obtain a standard air compressor energy consumption data set; A factor classification module 12 is used to classify the standard air compressor energy consumption data set into factors to obtain an air compressor equipment factor data set, an operating environment factor data set, an operating state factor data set, and an operating energy consumption data set; The energy consumption prediction network training module 13 is used to perform energy consumption prediction network training based on the air compressor equipment factor data set, the operating environment factor data set, the operating state factor data set and the operating energy consumption data set, respectively, to obtain the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network and the operating state energy consumption prediction network; The regression coefficient determination module 14 is used to perform data fitting on the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating state energy consumption prediction network using a factor regression analysis method to determine the prediction network regression coefficient information; The prediction effect verification module 15 is used to verify the prediction effect of the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating state energy consumption prediction network, and obtain the prediction network effect coefficient information; The air compressor energy consumption prediction module 16 is used to fuse the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating status energy consumption prediction network according to the prediction network regression coefficient information and the prediction network effect coefficient information to generate an air compressor energy consumption prediction network, and perform air compressor energy consumption prediction based on the air compressor energy consumption prediction network.
[0041] Furthermore, the system also includes: A data mining acquisition unit, used for collecting and acquiring a data set of energy consumption sources of an air compressor through data mining technology; An abnormality identification index acquisition unit is used to acquire data abnormality identification indicators, wherein the data abnormality identification indicators include numerical consistency, missing degree, and over-limit threshold; A data anomaly identification unit, used to identify anomalies of the air compressor energy consumption source data set based on the data anomaly identification index, and obtain an abnormal energy consumption index data set; A preprocessing rule determination unit, used to map and determine data preprocessing rules according to the data anomaly identification indicator; A standardization preprocessing unit is used to perform standardization preprocessing on the abnormal energy consumption index data set based on the data preprocessing rule to obtain the standard air compressor energy consumption data set.
[0042] Furthermore, the system also includes: An abnormal data set classification unit is used to classify the abnormal energy consumption index data set to obtain a numerical opposition data set, a missing energy consumption data set, and an over-limit threshold data set; A comparison and verification unit, used for normalizing and comparing the numerical opposition data set based on the data preprocessing rule to obtain a consistent energy consumption data set; A traceability filling unit, used to perform traceability filling on the missing energy consumption data set to obtain a complete energy consumption data set; The out-of-bounds data processing unit is used to perform normalization processing and data cleaning on the out-of-bounds threshold data set according to a preset data format.
[0043] Furthermore, the system also includes: A correlation index extraction unit is used to extract correlation indexes from the air compressor equipment factor data set, the operating environment factor data set, the operating state factor data set and the operating energy consumption data set, respectively, to obtain an air compressor equipment factor index set, an operating environment factor index set and an operating state factor index set; A principal component analysis unit, configured to perform principal component analysis based on the air compressor equipment factor index set, the operating environment factor index set, and the operating status factor index set, respectively, to obtain a dimensionality reduction associated index set, wherein the dimensionality reduction associated index set includes a dimensionality reduction air compressor equipment factor index set, a dimensionality reduction operating environment factor index set, and a dimensionality reduction operating status factor index set; The data set classification and integration unit is used to classify and integrate the air compressor equipment factor data set, the operating environment factor data set, the operating status factor data set and the operating energy consumption data set according to the dimension reduction association index set, and perform energy consumption prediction network training based on the integrated data sets.
[0044] Furthermore, the system also includes: A linear regression model obtaining unit is used to obtain a multivariate indicator linear regression model; A data fitting unit is used to perform data fitting on the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating state energy consumption prediction network through the multivariate index linear regression model to obtain initial prediction network regression coefficient information; The regression fitting evaluation unit is used to perform fitting evaluation on the initial prediction network regression coefficient information until a preset fitting determination coefficient is reached to determine the prediction network regression coefficient information.
[0045] Furthermore, the system also includes: The fusion function construction unit is used to construct the coefficient fusion function: ; in, Identify model fusion parameters, Characterizes the prediction network regression coefficient, Characterize the predicted network effect coefficient, is an increasing function; A fusion parameter output unit, used to calculate the prediction network regression coefficient information and the prediction network effect coefficient information based on the coefficient fusion function, and output network fusion parameter information; The prediction network fusion unit is used to fuse the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating status energy consumption prediction network based on the network fusion parameter information to generate the air compressor energy consumption prediction network.
[0046] Furthermore, the system also includes: An air compressor energy consumption prediction unit, used to predict the air compressor energy consumption based on the air compressor energy consumption prediction network and output air compressor energy consumption prediction information; A scene parameter extraction unit, used to obtain the air compressor application scene information, perform parameter extraction on the air compressor application scene information, and obtain application scene element information; An additional optimization and correction unit is used to perform a transportation energy consumption analysis on the application scenario element information, determine a transportation energy consumption influencing factor, and perform additional optimization and correction on the air compressor energy consumption prediction information based on the transportation energy consumption influencing factor.
[0047] The foregoing Figure 1The various variations and specific examples of the energy consumption prediction method for an air compressor in Example 1 are also applicable to the energy consumption prediction system for an air compressor in this embodiment. Through the above detailed description of the energy consumption prediction method for an air compressor, technical personnel in this field can clearly know the implementation method of the energy consumption prediction system for an air compressor in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.
[0048] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and run on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method embodiment for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0049] Exemplary Electronic Devices For details, see Figure 4 As shown, the present application also provides an electronic device, which includes a bus 1110 , a processor 1120 , a transceiver 1130 , a bus interface 1140 , a memory 1150 and a user interface 1160 .
[0050] In the present application, the electronic device further includes: a computer program stored in the memory 1150 and executable on the processor 1120, and when the computer program is executed by the processor 1120, each process of the above-mentioned method embodiment for controlling output data is implemented.
[0051] The transceiver 1130 is configured to receive and send data under the control of the processor 1120 .
[0052] In the present application, a bus architecture (represented by bus 1110 ) may include any number of interconnected buses and bridges. Bus 1110 connects various circuits including one or more processors represented by processor 1120 and a memory represented by memory 1150 .
[0053] Bus 1110 represents one or more of any of several types of bus structures, including a memory bus and memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. Such architectures include, by way of example and not limitation, an Industry Standard Architecture bus, a Micro Channel Architecture bus, an expansion bus, a Video Electronics Standards Association, a Peripheral Component Interconnect bus.
[0054] The processor 1120 may be an integrated circuit chip having signal processing capabilities. In the implementation process, each step of the above method embodiment may be completed by an integrated logic circuit of hardware in the processor or instructions in the form of software. The above processors include: a general-purpose processor, a central processing unit, a network processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array, a complex programmable logic device, a programmable logic array, a microcontroller unit or other programmable logic device, a discrete gate, a transistor logic device, and a discrete hardware component. The various methods, steps, and logic block diagrams disclosed in this application may be implemented or executed. For example, the processor may be a single-core processor or a multi-core processor, and the processor may be integrated into a single chip or located on multiple different chips.
[0055] Processor 1120 may be a microprocessor or any conventional processor. The method steps disclosed in the present application may be directly executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a readable storage medium known in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, a register, etc. The readable storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
[0056] The bus 1110 may also connect various other circuits such as peripheral devices, voltage regulators or power management circuits, and the bus interface 1140 provides an interface between the bus 1110 and the transceiver 1130, which are well known in the art. Therefore, this application will not further describe them.
[0057] The transceiver 1130 may be one element or multiple elements, such as multiple receivers and transmitters, and provides a unit for communicating with various other devices on a transmission medium. For example, the transceiver 1130 receives external data from other devices, and the transceiver 1130 is used to send data processed by the processor 1120 to other devices. Depending on the nature of the computer device, a user interface 1160 may also be provided, such as a touch screen, a physical keyboard, a display, a mouse, a speaker, a microphone, a trackball, a joystick, or a stylus.
[0058] It should be understood that in the present application, the memory 1150 may further include a memory remotely arranged relative to the processor 1120, and these remotely arranged memories may be connected to the server through a network. One or more parts of the above network may be a self-organizing network, an intranet, an extranet, a virtual private network, a local area network, a wireless local area network, a wide area network, a wireless wide area network, a metropolitan area network, the Internet, a public switched telephone network, a plain old telephone service network, a cellular telephone network, a wireless network, a wireless fidelity network, and a combination of two or more of the above networks. For example, the cellular telephone network and the wireless network may be a global mobile communication device, a code division multiple access device, a global microwave interconnection access device, a general packet radio service device, a wideband code division multiple access device, a long term evolution device, a LTE frequency division duplex device, a LTE time division duplex device, an advanced long term evolution device, a universal mobile communication device, an enhanced mobile broadband device, a massive machine type communication device, an ultra-reliable low latency communication device, and the like.
[0059] It should be understood that the memory 1150 in the present application may be a volatile memory or a non-volatile memory, or may include both a volatile memory and a non-volatile memory. Among them, the non-volatile memory includes: a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, or a flash memory.
[0060] Volatile memory includes random access memory, which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory, dynamic random access memory, synchronous dynamic random access memory, double data rate synchronous dynamic random access memory, enhanced synchronous dynamic random access memory, synchronously linked dynamic random access memory, and direct memory bus random access memory. The memory 1150 of the electronic device described in the present application includes, but is not limited to, the above and any other suitable types of memory.
[0061] In the present application, the memory 1150 stores the following elements of the operating system 1151 and the application program 1152: executable modules, data structures, or subsets thereof, or extended sets thereof.
[0062] Specifically, the operating system 1151 includes various device programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application 1152 includes various application programs, such as a media player and a browser, which are used to implement various application services. The program implementing the method of the present application may be included in the application 1152. The application 1152 includes applets, objects, components, logic, data structures, and other computer device executable instructions that perform specific tasks or implement specific abstract data types.
[0063] In addition, the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned method embodiment for controlling output data are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0064] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A method for predicting energy consumption of an air compressor. It is characterized in that The method comprises: Collect and preprocess to obtain the standard air compressor energy consumption data set; Classifying the standard air compressor energy consumption data set by factors to obtain an air compressor equipment factor data set, an operating environment factor data set, an operating state factor data set, and an operating energy consumption data set; Based on the air compressor equipment factor data set, the operating environment factor data set, the operating state factor data set and the operating energy consumption data set, respectively, energy consumption prediction network training is performed to obtain an air compressor equipment energy consumption prediction network, an operating environment energy consumption prediction network, and an operating state energy consumption prediction network; Using factor regression analysis method to perform data fitting on the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating state energy consumption prediction network to determine the prediction network regression coefficient information; Verify the prediction effect of the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating state energy consumption prediction network to obtain prediction network effect coefficient information; The air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating status energy consumption prediction network are integrated according to the prediction network regression coefficient information and the prediction network effect coefficient information to generate an air compressor energy consumption prediction network, and air compressor energy consumption prediction is performed based on the air compressor energy consumption prediction network.
2. The method according to claim 1, It is characterized in that The step of obtaining a standard air compressor energy consumption data set includes: The data set of air compressor energy consumption source is acquired through data mining technology; Obtaining data anomaly identification indicators, wherein the data anomaly identification indicators include numerical consistency, missing degree, and over-limit threshold; Based on the data anomaly identification index, anomaly identification is performed on the air compressor energy consumption source data set to obtain an abnormal energy consumption index data set; According to the data anomaly identification indicator, mapping determines the data preprocessing rules; The abnormal energy consumption index data set is standardized and preprocessed based on the data preprocessing rules to obtain the standard air compressor energy consumption data set.
3. The method according to claim 2, It is characterized in that The performing standardized preprocessing on the abnormal energy consumption index data set based on the data preprocessing rule includes: Classifying the abnormal energy consumption index data set to obtain a numerically opposed data set, a missing energy consumption data set, and an over-limit threshold data set; Based on the data preprocessing rules, the numerical opposition data set is normalized and compared to obtain a consistent energy consumption data set; Tracing and filling the missing energy consumption data set to obtain a complete energy consumption data set; The over-limit threshold data set is normalized and cleaned according to a preset data format.
4. The method according to claim 1, It is characterized in that The method comprises: Extracting related indicators from the air compressor equipment factor data set, the operating environment factor data set, the operating status factor data set and the operating energy consumption data set respectively, to obtain an air compressor equipment factor indicator set, an operating environment factor indicator set and an operating status factor indicator set; Based on the air compressor equipment factor index set, the operating environment factor index set and the operating status factor index set, principal component analysis is performed respectively to obtain a dimensionality reduction associated index set, wherein the dimensionality reduction associated index set includes a dimensionality reduction air compressor equipment factor index set, a dimensionality reduction operating environment factor index set and a dimensionality reduction operating status factor index set; The air compressor equipment factor data set, the operating environment factor data set, the operating status factor data set and the operating energy consumption data set are classified and integrated according to the dimension reduction association index set, and energy consumption prediction network training is performed based on the integrated data sets.
5. The method according to claim 1, It is characterized in that The step of determining the prediction network regression coefficient information includes: Obtain a multivariate indicator linear regression model; The energy consumption prediction network of the air compressor equipment, the energy consumption prediction network of the operating environment, and the energy consumption prediction network of the operating state are fitted with data through the multivariate index linear regression model to obtain the regression coefficient information of the initial prediction network; The initial prediction network regression coefficient information is fitted and evaluated until a preset fitting determination coefficient is reached to determine the prediction network regression coefficient information.
6. The method according to claim 1, It is characterized in that The generating of the air compressor energy consumption prediction network comprises: Construct the coefficient integration function: ; in, Identify model fusion parameters, Characterizes the prediction network regression coefficient, Characterize the predicted network effect coefficient, is an increasing function; Calculate the prediction network regression coefficient information and the prediction network effect coefficient information based on the coefficient fusion function, and output network fusion parameter information; Based on the network fusion parameter information, the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating status energy consumption prediction network are fused to generate the air compressor energy consumption prediction network.
7. The method according to claim 1, It is characterized in that The method comprises: Perform air compressor energy consumption prediction based on the air compressor energy consumption prediction network, and output air compressor energy consumption prediction information; Acquire air compressor application scenario information, extract parameters from the air compressor application scenario information, and obtain application scenario element information; Perform a transport energy consumption analysis on the application scenario element information to determine a transport energy consumption influencing factor, and perform additional optimization and correction on the air compressor energy consumption prediction information based on the transport energy consumption influencing factor.
8. An energy consumption prediction system for air compressors. It is characterized in that The system comprises: The collection and preprocessing module is used for collection and preprocessing to obtain the standard air compressor energy consumption data set; A factor classification module is used to classify the standard air compressor energy consumption data set into factors to obtain an air compressor equipment factor data set, an operating environment factor data set, an operating state factor data set, and an operating energy consumption data set; An energy consumption prediction network training module is used to perform energy consumption prediction network training based on the air compressor equipment factor data set, the operating environment factor data set, the operating state factor data set and the operating energy consumption data set, respectively, to obtain an air compressor equipment energy consumption prediction network, an operating environment energy consumption prediction network, and an operating state energy consumption prediction network; A regression coefficient determination module is used to perform data fitting on the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating state energy consumption prediction network using a factor regression analysis method to determine the prediction network regression coefficient information; A prediction effect verification module is used to verify the prediction effect of the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating state energy consumption prediction network, and obtain prediction network effect coefficient information; The air compressor energy consumption prediction module is used to fuse the air compressor equipment energy consumption prediction network, the operating environment energy consumption prediction network, and the operating status energy consumption prediction network according to the prediction network regression coefficient information and the prediction network effect coefficient information, generate an air compressor energy consumption prediction network, and perform air compressor energy consumption prediction based on the air compressor energy consumption prediction network.
9. An electronic device comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus. It is characterized in that When the computer program is executed by the processor, the steps of the energy consumption prediction method for an air compressor as described in any one of claims 1-7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps in the energy consumption prediction method for an air compressor as described in any one of claims 1-7 are implemented.
Citation Information
Cited By
Air compressor modeling method, system and equipment based on data fitting driving and medium
CN119939804A
