Method and system for classifying and estimating power consumption of coal mine enterprise based on multi-source data fusion
Through multi-source data fusion and time series analysis, the power operation categories and time intervals of coal mine enterprises are identified, which solves the problem that the existing technology cannot finely manage coal mine power consumption, and achieves more efficient power resource management and energy conservation and emission reduction.
Patent Information
- Application Number
- CN202411346351.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-26
- Publication Date
- 2025-02-18
AI Technical Summary
The existing technology cannot directly obtain coal mine production power consumption data, resulting in a lack of refined management and prediction capabilities in power consumption management.
By collecting and integrating multi-source data from coal mine enterprises, such as total power consumption data, personnel positioning data and safety monitoring data, time series analysis and classification are carried out, power operation categories and operation time intervals are identified, classification and average power consumption are dynamically adjusted, classification and average power consumption are adjusted Evaluate.
It improves the accuracy and flexibility of power consumption estimates, provides more scientific operation strategies and maintenance plans, optimizes the allocation and use of power resources, and provides effective technical support for energy conservation and emission reduction of coal mine enterprises.
Smart Images
Figure CN119476552A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power management, and in particular to a method and system for classifying and estimating power consumption of a coal mining enterprise by integrating multi-source data. Background Art
[0002] In the daily operation of coal mining enterprises, power consumption management is a key area for cost control and energy efficiency optimization. With the improvement of the automation level of coal mines, the effective management and budget allocation of power resources have become particularly important. Because the data collected from the power grid data center is mostly the total power consumption data of coal mining enterprises, the power consumption data of each industrial link within the enterprise cannot be accurately collected and counted, and the coal mine production power consumption data cannot be directly obtained. Traditional power consumption monitoring mainly relies on statistical analysis of total power consumption. Although this method can provide certain consumption data, it lacks refined management and prediction capabilities. With the rapid development of information technology, especially the application of data mining and machine learning technology, new technical means have been provided for the classification and prediction of power consumption.
[0003] However, existing technologies still have many shortcomings when dealing with complex, multi-source data. First, traditional methods are usually unable to fully utilize data from different sources, resulting in limited accuracy and practicality of prediction results. Second, existing technologies often lack flexibility and adaptability in the selection of classification and prediction algorithms, and cannot dynamically adjust prediction models according to actual operational changes. In addition, the lack of in-depth analysis of power consumption classification makes it difficult for mining companies to implement energy-saving measures for specific operations or time periods. These technical shortcomings not only affect the efficiency of energy management, but also limit the implementation of cost savings and environmental protection measures.
[0004] The present invention proposes a method and system for classifying and estimating the power consumption of coal mining enterprises by integrating multi-source data, which effectively solves the above problems. By integrating multi-source information such as the total power consumption data, personnel location data, and safety monitoring data of coal mining enterprises, the present invention can not only improve the accuracy of power consumption estimation, but also dynamically adjust the classification and average power consumption evaluation according to real-time data. In addition, the present invention provides coal mining enterprises with an effective tool for energy conservation and emission reduction through the subdivision management of power consumption, which helps enterprises to formulate more scientific operation strategies and maintenance plans based on actual power usage. Summary of the invention
[0005] In view of the above-mentioned problems, the present invention is proposed.
[0006] Therefore, the problem to be solved by the present invention is: how to solve the problem that the existing method cannot directly obtain the coal mine production power consumption data.
[0007] To solve the above technical problems, the present invention provides the following technical solutions: a method for classifying and estimating electricity consumption of coal mining enterprises based on multi-source data fusion, comprising: collecting coal mining enterprise data and performing data preprocessing; performing time series analysis on the coal mining enterprise data to identify power operation categories and operation time intervals; estimating the average power consumption of each type of operation based on the identification results; and verifying the accuracy of the estimated average power consumption of each type of operation.
[0008] As an optimal solution of the coal mine enterprise power consumption classification estimation method based on multi-source data fusion described in the present invention, the coal mine enterprise data includes the total power consumption data of the coal mine enterprise, personnel location data, and safety monitoring data; the data preprocessing includes data cleaning and data conversion.
[0009] As a preferred solution of the method for classifying and estimating electricity consumption of coal mining enterprises by fusion of multi-source data described in the present invention, the time series analysis includes segmenting the continuous time series data, extracting key features from the time series data, performing preliminary classification based on the extracted features, classifying the data into different power operation categories, identifying the specific behavior patterns and duration of the operations on the basis of the preliminary classification, determining the final classification results and the specific time intervals of each type of operation, and verifying the classification results.
[0010] As a preferred solution of the method for classifying and estimating power consumption of coal mining enterprises by multi-source data fusion of the present invention, the segmented processing includes using a sliding window to locally analyze the time series, which is expressed as:
[0011] X t ={x t′ ,t≤t′ <t+Δt}
[0012] Among them, X t is the window function, x t′ is the data point at time t′, t is the time point, t′ is the current time point, and Δt is the window size; the preliminary classification includes using a support vector machine to classify the extracted features and find the optimal segmentation hyperplane, which is expressed as:
[0013]
[0014] y i (w·φ(x i )+b)≥1-ξ i ,ξ i ≥0
[0015] Among them, w is the weight vector of the support vector machine, b is the bias term of the support vector machine, C is the regularization parameter of the support vector machine, and y i For data point x i The category label of φ(xi ) is the data point x i The mapping function, ξ i is the slack variable, m is the total number of data points, and i is the i-th data point.
[0016] As a preferred solution of the method for classifying and estimating power consumption of coal mining enterprises by multi-source data fusion of the present invention, the final classification includes using K-means clustering to identify the behavior pattern and time interval of the operation, which is expressed as:
[0017]
[0018] Among them, S is the overall clustering result, j is the jth cluster, k is the total number of clusters, S j is the set of data points in the jth cluster, μ j is the center point of the jth cluster; the final classification result is verified, and the average accuracy is calculated. If the average accuracy exceeds the preset average accuracy threshold, the classification result is qualified. Based on the recognition result, the average power consumption of each type of operation is calculated. If the average accuracy is less than or equal to the preset average accuracy threshold, the classification result is unqualified and the classification and recognition are performed again. According to the final classification, the time series data is divided into different sub-operation categories. For each category of data, the total power consumption in each time period is counted.
[0019] As an optimal solution of the coal mine enterprise power consumption classification estimation method based on multi-source data fusion described in the present invention, wherein: the sub-operation categories include coal mining operations, coal mine excavation operations, coal mine transportation operations, coal mine hoisting operations, drainage operations, gas extraction operations, ventilation, drainage and domestic electricity; the power consumption of mining operations is determined by the power consumption of coal mining operations and coal mine excavation operations; the power consumption of other production support system operations is determined by the power consumption of coal mine transportation operations, coal mine hoisting operations, drainage operations and gas extraction operations; the power consumption of living areas is determined by ventilation, drainage and domestic electricity; the average power consumption of each type of operation includes the average power consumption of mining operations, the average power consumption of other production support system operations and the average power consumption of living areas.
[0020] As a preferred solution of the coal mining enterprise power consumption classification estimation method of multi-source data fusion of the present invention, the average power consumption of each type of operation also includes classifying the time series data into different operation categories according to the classification results, and for each category of data, the total power consumption in the time period is counted, and the total power consumption of each category is divided by the number of time periods of the category to obtain the average power consumption, which is expressed as:
[0021]
[0022] Among them, A lis the average power consumption of the lth type of operation, T is the Tth time period, T l is the total number of time periods for the lth type of work, E lT is the power consumption of the lth type of operation in the Tth time period; calculate the sum of the average power consumption of all categories, and the error rate between the inspection and the total power consumption is expressed as:
[0023]
[0024] Among them, C is the error rate and G is the total power consumption; if the error rate is lower than the set error rate threshold, the average power consumption of each type of operation is accurately estimated; if the error rate is greater than or equal to the set error rate threshold, it is necessary to recheck the data classification and recalculate.
[0025] Another object of the present invention is to provide a system for a method for classifying and estimating electricity consumption of coal mining enterprises based on multi-source data fusion, which can solve the problem of classifying and estimating electricity consumption of coal mining enterprises based on multi-source data fusion by constructing a system for classifying and estimating electricity consumption of coal mining enterprises.
[0026] To solve the above technical problems, the present invention provides the following technical solutions: a coal mine enterprise power consumption classification and estimation system with multi-source data fusion, comprising a data acquisition module, an identification module, an average power consumption estimation module and a verification module; the data acquisition module is used to collect coal mine enterprise data and perform data preprocessing; the identification module is used to perform time series analysis on coal mine enterprise data, and identify power operation categories and operation time intervals; the average power consumption estimation module is used to estimate the average power consumption of each type of operation based on the identification results; the verification module is used to verify the accuracy of the estimated average power consumption of each type of operation.
[0027] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method for classifying and estimating power consumption of coal mining enterprises by fusion of multi-source data as described above are implemented.
[0028] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for classifying and estimating power consumption of coal mining enterprises by fusion of multi-source data as described above.
[0029] The beneficial effects of the present invention are as follows: the coal mining enterprise power consumption classification estimation method based on multi-source data fusion provided by the present invention can accurately estimate the average power consumption of various operations, and by verifying and adjusting the accuracy of the estimation results, the efficiency and accuracy of power consumption management are improved. It not only optimizes the allocation and use of power resources, but also provides effective technical support for energy conservation and emission reduction of coal mining enterprises, achieving the dual benefits of cost control and environmental protection. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.
[0031] Figure 1 A flowchart of a method for classifying and estimating electricity consumption of coal mining enterprises by multi-source data fusion provided in the first embodiment of the present invention.
[0032] Figure 2 This is a structural diagram of a coal mining enterprise power consumption classification prediction system based on multi-source data fusion provided in the second embodiment of the present invention. DETAILED DESCRIPTION
[0033] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.
[0034] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0035] Example 1, reference Figure 1 , which is the first embodiment of the present invention, provides a method for classifying and estimating power consumption of coal mining enterprises based on multi-source data fusion, including: collecting coal mining enterprise data and performing data preprocessing; performing time series analysis on the coal mining enterprise data to identify power operation categories and operation time intervals; based on the identification results, estimating the average power consumption of each type of operation; and verifying the accuracy of the estimated average power consumption of each type of operation.
[0036] S1. Collect coal mining enterprise data and perform data preprocessing.
[0037] Because the data collected from the power grid data center are mostly the total power consumption data of coal mining enterprises, the power consumption data of various industrial links within the enterprise cannot be accurately collected and counted, and the coal mine production power consumption data cannot be directly obtained. Therefore, it is necessary to classify, evaluate and calculate the coal mine power consumption data, and separate and evaluate the average power consumption of coal mining operations, the average power consumption of other production support system operations, and the average power consumption of life from the total power consumption. Among them, the power consumption of mining operations mainly includes two parts: coal mining and tunneling operations. The average power consumption of other production support system operations mainly includes coal mine transportation, hoisting, drainage, gas extraction and other operations. The average power consumption of the living area is the power consumption required to maintain normal operation when the coal mine is shut down, mainly including ventilation, drainage, industrial square life electricity, etc.
[0038] Coal mine enterprise data includes total power consumption data, personnel location data, and safety monitoring data; data preprocessing includes data cleaning and data conversion.
[0039] S2. Conduct time series analysis on coal mining enterprise data to identify power operation categories and operation time intervals.
[0040] Time series analysis includes segmenting continuous time series data, extracting key features from the time series data, performing preliminary classification based on the extracted features, classifying the data into different power operation categories, identifying the specific behavior patterns and duration of the operations based on the preliminary classification, determining the final classification results and the specific time intervals for each type of operation, and verifying the classification results.
[0041] Segmented processing uses a sliding window to locally analyze the time series, expressed as:
[0042] X t ={x t′ ,t≤t′ <t+Δt}
[0043] Among them, X t is a window function, which represents the data set within a time period of length Δt starting from time point t, x t′ is the data point at time t′, t is the time point, t′ is the current time point, and Δt is the window size.
[0044] Extract key features, calculate the mean and standard deviation of each window, and apply fast Fourier transform to extract frequency components, expressed as:
[0045]
[0046] Among them, μ t For WindowX t The average value of window X t The standard deviation of kis the Fourier transform result at frequency domain k, N is the number of data points for Fourier transform, and n is the nth data point for Fourier transform.
[0047] The initial classification uses a support vector machine to classify the extracted features and find the optimal segmentation hyperplane, which is expressed as:
[0048]
[0049] y i (w·φ(x i )+b)≥1-ξ i ,ξ i ≥0
[0050] Among them, w is the weight vector of the support vector machine, b is the bias term of the support vector machine, C is the regularization parameter of the support vector machine, and y i For data point x i The category label of φ(x i ) is the data point x i The mapping function, ξ i is a slack variable used to deal with incompletely separable situations, allowing some data points to violate the original complete segmentation condition, m is the total number of data points, and i is the i-th data point. By segmenting the continuous time series data and extracting key features from them for preliminary classification, different power operation categories, their behavior patterns and durations can be more accurately identified.
[0051] The final classification uses K-means clustering to identify the behavior patterns and time intervals of the jobs, expressed as:
[0052]
[0053] Among them, S is the overall clustering result, j is the jth cluster, k is the total number of clusters, S j is the set of data points in the jth cluster, μ j is the center point of the jth cluster.
[0054] Verify the final classification results and calculate the average accuracy. If the average accuracy exceeds the preset average accuracy threshold, the classification result is qualified. Based on the recognition results, calculate the average power consumption of each type of operation. If the average accuracy is less than or equal to the preset average accuracy threshold, the classification result is unqualified and reclassification is performed. Determine the final job category and time interval, and find the optimal classification hyperplane in multi-dimensional data to improve the accuracy of classification.
[0055] According to the final classification, the time series data is divided into different sub-job categories, and for each category of data, the total power consumption in each time period is counted.
[0056] Sub-operation categories include coal mining operations, coal tunneling operations, coal transportation operations, coal hoisting operations, drainage operations, gas extraction operations, ventilation, drainage and domestic electricity.
[0057] The power consumption of mining operations is determined by the power consumption of coal mining operations and coal mine tunneling operations.
[0058] The power consumption of other production support systems is determined by the power consumption of coal mine transportation operations, coal mine hoisting operations, drainage operations, and gas extraction operations.
[0059] The power consumption of the living area is determined through ventilation, drainage and domestic electricity consumption.
[0060] The average power consumption of various operations includes the average power consumption of mining operations, the average power consumption of other production support system operations and the average power consumption of living areas.
[0061] S3. Based on the recognition results, estimate the average power consumption of each type of operation.
[0062] According to the classification results, the time series data is divided into different job categories. For each category of data, the total power consumption in the time period is counted. The total power consumption of each category is divided by the number of time periods of the category to obtain the average power consumption, which is expressed as:
[0063]
[0064] Among them, A l is the average power consumption of the lth type of operation, T is the Tth time period, T l is the total number of time periods for the lth type of work, E lT is the power consumption of the lth type of operation in the Tth time period.
[0065] S4. Verify the accuracy of the estimated average power consumption of each type of operation.
[0066] Calculate the sum of the average power consumption of all categories and check the error rate with the total power consumption as:
[0067]
[0068] Among them, C is the error rate and G is the total power consumption.
[0069] If the error rate is lower than the set error rate threshold, the average power consumption of each type of operation is estimated accurately. If the error rate is greater than or equal to the set error rate threshold, it is necessary to recheck the data classification and recalculate.
[0070] Example 2, reference Figure 2, which is the second embodiment of the present invention, is different from the previous embodiment in that it provides a coal mine enterprise power consumption classification prediction system with multi-source data fusion, including: a data acquisition module 100, an identification module 200, an average power consumption prediction module 300 and a verification module 400.
[0071] The data collection module 100 is used to collect coal mining enterprise data and perform data preprocessing.
[0072] The identification module 200 is used to perform time series analysis on coal mining enterprise data and identify power operation categories and operation time intervals.
[0073] The average power consumption estimation module 300 is used to estimate the average power consumption of various operations based on the recognition result.
[0074] The verification module 400 is used to verify the accuracy of the estimated average power consumption of various types of operations.
[0075] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.
[0076] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.
[0077] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.
[0078] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0079] Embodiment 3 is the third embodiment of the present invention. It is different from the first two embodiments in that it is used to verify the technical effects adopted in the present invention so as to verify the real effects of the method.
[0080] The power consumption data of the same mining enterprise are simulated simultaneously using the method of the present invention and the traditional method.
[0081] Traditional methods mainly rely on statistical analysis of the total power consumption of coal mining enterprises. Usually, the analysis is done through data from a single source, such as the total power consumption data provided by the power grid data center. There is a lack of segmentation and classification of different operating categories, so there are deficiencies in refined management and energy efficiency optimization. It is impossible to dynamically adjust the classification and average power consumption assessment, and it is impossible to improve the accuracy and flexibility of the prediction through multi-source data.
[0082] This embodiment uses the traditional method and the method of the present invention to perform detection simultaneously, and the detection comparison results are shown in the following Table 1:
[0083] Table 1 Comparison table between traditional method and method of the present invention
[0084]
[0085] The present invention significantly reduces the average error rate of power consumption estimation by integrating multi-source data and applying machine learning algorithms, which shows that the present invention is significantly superior to traditional methods in terms of accuracy. The present invention is also significantly higher than traditional methods in terms of classification accuracy, especially in the classification of power consumption of specific operation categories. Through segmented management, the present invention identifies more potential energy-saving opportunities and provides a basis for coal mining enterprises to formulate more scientific operation strategies.
[0086] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A classification estimation method for power consumption of coal mining enterprises based on multi-source data fusion, characterized by: include, Collect coal mining enterprise data and perform data preprocessing; Conduct time series analysis on coal mining enterprise data to identify power operation categories and operation time intervals; Based on the recognition results, the average power consumption of each type of operation is estimated; Verify the accuracy of the estimated average power consumption for each type of operation.
2. The method for classifying and estimating power consumption of coal mining enterprises by multi-source data fusion according to claim 1, characterized in that: The coal mine enterprise data includes total power consumption data, personnel location data, and safety monitoring data of the coal mine enterprise; The data preprocessing includes data cleaning and data conversion.
3. The method for classifying and estimating power consumption of coal mining enterprises by multi-source data fusion according to claim 2, characterized in that: The time series analysis includes segmenting the continuous time series data, extracting key features from the time series data, performing preliminary classification based on the extracted features, classifying the data into different power operation categories, identifying the specific behavior patterns and duration of the operations based on the preliminary classification, determining the final classification results and the specific time intervals of each type of operation, and verifying the classification results.
4. The method for classifying and estimating power consumption of coal mining enterprises by multi-source data fusion according to claim 3 is characterized by: The segmentation process involves locally analyzing the time series using a sliding window, expressed as, X t ={x t′ ,t≤t′<t+Δt} Among them, X t is the window function, x t′ is the data point at time t′, t is the time point, t′ is the current time point, and Δt is the window size; The preliminary classification includes using a support vector machine to classify the extracted features and find the optimal segmentation hyperplane, which is expressed as: y i (w·φ(x i )+b)≥1-ξ i ,x i ≥0 Among them, w is the weight vector of the support vector machine, b is the bias term of the support vector machine, C is the regularization parameter of the support vector machine, and y i For data point x i The category label of φ(x i ) is the data point x i The mapping function, ξ i is the slack variable, m is the total number of data points, and i is the i-th data point.
5. The method for classifying and estimating power consumption of coal mining enterprises by multi-source data fusion according to claim 4 is characterized in that: The final classification includes using K-means clustering to identify the behavior patterns and time intervals of the jobs, expressed as, Among them, S is the overall clustering result, j is the jth cluster, k is the total number of clusters, S j is the set of data points in the jth cluster, μ j is the center point of the jth cluster; The final classification result is verified and the average accuracy is calculated. If the average accuracy exceeds the preset average accuracy threshold, the classification result is qualified. Based on the recognition result, the average power consumption of each type of operation is calculated. If the average accuracy is less than or equal to the preset average accuracy threshold, the classification result is unqualified and the classification recognition is performed again. According to the final classification, the time series data is divided into different sub-job categories. For each category of data, the total power consumption in each time period is counted.
6. The method for classifying and estimating power consumption of coal mining enterprises by multi-source data fusion according to claim 5, characterized in that: The sub-operation categories include coal mining operations, coal excavation operations, coal transportation operations, coal hoisting operations, drainage operations, gas extraction operations, ventilation, drainage and domestic electricity; The power consumption of mining and excavation operations is determined by the power consumption of coal mining operations and coal excavation operations; Determine the power consumption of other production support systems through the power consumption of coal mine transportation, coal mine hoisting, drainage, and gas extraction operations; Determine the power consumption of the living area through ventilation, drainage and domestic electricity consumption; The average power consumption of various types of operations includes the average power consumption of mining operations, the average power consumption of other production support system operations and the average power consumption of living areas.
7. The method for classifying and estimating power consumption of coal mining enterprises by multi-source data fusion according to claim 6, characterized in that: The average power consumption of each type of operation also includes classifying the time series data into different operation categories according to the classification results, and for each category of data, the total power consumption in the time period is counted, and the total power consumption of each category is divided by the number of time periods of the category to obtain the average power consumption, which is expressed as: Among them, A l is the average power consumption of the lth type of operation, T is the Tth time period, T l is the total number of time periods for the lth type of work, E lT is the power consumption of the lth type of operation in the Tth time period; Calculate the sum of the average power consumption of all categories and check the error rate with the total power consumption as, Among them, C is the error rate, G is the total power consumption; If the error rate is lower than the set error rate threshold, the average power consumption of each type of operation is estimated accurately. If the error rate is greater than or equal to the set error rate threshold, it is necessary to recheck the data classification and recalculate.
8. A system for classifying and estimating the power consumption of coal mining enterprises using the multi-source data fusion method as claimed in any one of claims 1 to 7, characterized in that: It comprises a data collection module (100), an identification module (200), an average power consumption estimation module (300) and a verification module (400); The data collection module (100) is used to collect coal mining enterprise data and perform data preprocessing; The identification module (200) is used to perform time series analysis on coal mining enterprise data to identify power operation categories and operation time intervals; The average power consumption estimation module (300) is used to estimate the average power consumption of various operations based on the identification results; The verification module (400) is used to verify the accuracy of the estimated average power consumption of various types of operations.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for classifying and estimating power consumption of coal mining enterprises by multi-source data fusion according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for classifying and estimating power consumption of coal mining enterprises by multi-source data fusion according to any one of claims 1 to 7 are implemented.