Mine energy consumption monitoring and optimizing system and method based on big data

Abstract

The invention discloses a mine energy consumption monitoring and optimizing system and method based on big data, and belongs to the technical field of energy consumption supervision. The current aging index of corresponding operation equipment is analyzed through historical data, and the future aging index of the corresponding operation equipment is predicted in combination with the current operation data; matching energy consumption influence indexes for various operation data of corresponding operation equipment according to historical data, and predicting comprehensive future energy consumption according to various current operation data, the energy consumption influence indexes and future aging indexes, so as to accurately monitor and screen out equipment with abnormal energy consumption. And according to each energy consumption influence index, the adjustment priority of each type of operation data is obtained, and the energy consumption optimization efficiency and accuracy are improved.

Description

Technical Field

[0001] This invention relates to the field of energy consumption monitoring technology, and in particular to a mine energy consumption monitoring and optimization system and method based on big data. Background Technology

[0002] Mining production involves many stages, such as mining operations, transportation, crushing and grinding, etc. These stages require the use of various equipment to complete them. Therefore, mining production is a typical high-energy-consuming industry. In order to reduce energy costs, it is particularly important to monitor, predict and optimize energy consumption in mining production. However, existing energy consumption monitoring, prediction, and optimization technologies typically rely solely on historical energy consumption data to predict future energy consumption trends, neglecting various operating parameters of equipment and the impact of equipment aging on energy consumption. Furthermore, they are unable to quickly identify the operating parameters that need to be adjusted first, resulting in inaccurate energy consumption monitoring and prediction and insufficient optimization efficiency. Summary of the Invention

[0003] To address the technical problems existing in the prior art, this invention provides a method for monitoring and optimizing mine energy consumption based on big data, comprising the following steps: Acquire the current operating data and historical data of each operating device, wherein the historical data includes historical operating data, historical maintenance data, and historical energy consumption values; By analyzing historical data, the current aging index of the corresponding operating equipment is analyzed, and then combined with the current operating data, the future aging index of the corresponding operating equipment is predicted. Based on historical data, energy consumption impact indices are matched to various operating data of the corresponding operating equipment. Based on various operational data, multiple predicted energy consumption values ​​are obtained through corresponding preset first neural network models. Then, based on the energy consumption impact index analysis, a first future energy consumption value is obtained. Based on the future aging index of the corresponding operating equipment, a second future energy consumption value is obtained through corresponding preset second neural network models. The average of the first future energy consumption value and the second future energy consumption value is used to calculate the comprehensive future energy consumption value of the corresponding operating equipment; if the comprehensive future energy consumption value of the corresponding operating equipment is greater than its preset energy consumption threshold at the same time in the future, it is marked as an abnormal equipment. The energy consumption impact index of various operating data of each abnormal device is obtained, and the adjustment priority of various operating data of the corresponding abnormal device is obtained according to the order of the energy consumption impact index.

[0004] Furthermore, the step of analyzing the current aging index of the corresponding operating equipment through historical data specifically includes: Analyze the deviation (PL) and volatility (BD) of various historical operating data of the corresponding operating equipment; The failure impact index GS of the corresponding operating equipment is analyzed by historical maintenance data, and the performance degradation index XS is analyzed based on PL and BD. Analyze the current aging index LS of the corresponding operating equipment: LS = gsk × GS + xsk × XS; Among them, gsk and xsk are the preset fault weight and preset performance weight, respectively.

[0005] Furthermore, the analysis method for the deviation PL is as follows: ; in, The deviation of the i-th type of historical operating data for the corresponding operating equipment. To obtain the amount of historical running data of the i-th type, Let be the value of the i-th type of historical running data at time t. Let be the preset expected value corresponding to the i-th type of historical running data at time t.

[0006] Furthermore, the analysis method for the volatility BD is as follows: Obtain the corresponding preset expected data segment based on the preset expected value corresponding to the historical operation data; The corresponding historical running data is divided into multiple sub-segments by taking the same and consecutive preset expected values ​​as a sub-segment within a preset expected data segment; Calculate the standard deviation of each segment in the historical running data; The volatility of the corresponding historical data is obtained by averaging the standard deviations of various historical data.

[0007] Furthermore, the analysis method for the fault impact index GS is as follows: Analysis of the impact index YS of each historical fault type of the corresponding operating equipment: ; ; in, This represents the impact index of the i-th historical fault type that occurred in the corresponding operating equipment. This represents the number of occurrences of the i-th historical fault type for the corresponding operating equipment. This represents the overall severity level of the i-th historical fault type corresponding to the operating equipment. To represent the severity level of the i-th historical fault type of the corresponding operating equipment at its last occurrence, pk, ck, and lk are the preset influence weights for the number of occurrences, the preset influence weight for the overall severity, and the preset influence weight for the final severity, respectively. This represents the severity level of the nth occurrence of the i-th historical fault type corresponding to the operating equipment. Analysis of the failure impact index (GS) of the corresponding operating equipment: ; Wherein, GN represents the number of historical fault types that have occurred in the corresponding operating equipment. The preset type influence weight for the i-th historical fault type that occurs in the corresponding operating equipment.

[0008] Furthermore, the analysis method for the performance degradation index XS is as follows: ; Where YN1 represents the number of types of historical operating data for the corresponding operating device. The deviation of the i-th type of historical operating data for the corresponding operating equipment. For the volatility of the i-th type of historical operating data corresponding to the operating equipment, For the preset data influence weight of the i-th type of historical operating data of the corresponding operating equipment, plk and bdk respectively preset deviation influence weight and preset fluctuation influence weight.

[0009] Furthermore, the prediction of the future aging index of the corresponding operating equipment based on current operating data specifically includes: Based on the analysis method of the current aging index, the historical aging degree of the corresponding operating equipment at multiple historical moments and the corresponding second historical operating data are obtained; The historical operation data and the corresponding historical aging index of a historical moment, the historical aging degree of the next adjacent historical moment, and the duration between the next adjacent historical moment are taken as a set of sample data, and then multiple sets of sample data are obtained. After the pre-built deep learning model is pre-trained using the multiple sets of sample data, the current operating data, current aging level, and required future duration of the corresponding operating device are used as inputs to output a predicted value of the future aging index.

[0010] Furthermore, the process of matching energy consumption impact indices to various operating data of corresponding operating equipment based on historical data specifically involves: The standard deviation of the historical energy consumption values ​​of the corresponding operating equipment is calculated as its energy consumption volatility. Calculate the ratio of volatility to energy consumption volatility of various historical operating data for the corresponding operating equipment, and use it as the energy consumption driving index for the corresponding type of operating data; Based on the magnitude of the energy consumption drive index, sort the various operating data of the corresponding operating equipment from smallest to largest, starting with the serial number 1; Calculate the energy consumption impact index of various operating data for the corresponding operating equipment: ; ; This refers to the energy consumption impact index of the i-th type of operating data for the corresponding operating equipment. The weight of the level influence of the i-th type of operating data for the corresponding operating equipment. The pre-set weights for the i-th type of running data are manually assigned. Let i be the sequence number of the i-th type of running data. The sum of the sequence numbers of each operating data of the corresponding operating device is represented by k1 and k2, which are the first preset weight and the second preset weight, respectively.

[0011] Furthermore, the first future energy consumption value obtained based on the energy consumption impact index analysis is specifically as follows: ; This represents the first future energy consumption value of the corresponding operating equipment at time t. This represents the number of current operating data types for the corresponding running device. This represents the predicted energy consumption value corresponding to the i-th type of current operating data of the corresponding operating device at time t in the future.

[0012] This invention also provides a mine energy consumption monitoring and optimization system based on big data, comprising: The data acquisition module is used to acquire the current operating data and historical data of each operating device. The historical data includes historical operating data, historical maintenance data, and historical energy consumption values. The aging analysis module is used to analyze the current aging index of the corresponding operating equipment through historical data, and then combine the current operating data to predict the future aging index of the corresponding operating equipment. The index matching module is used to match energy consumption impact indices to various operating data of corresponding operating equipment based on historical data; The first prediction module is used to predict multiple predicted energy consumption values ​​based on various types of operating data through corresponding preset first neural network models, and then to obtain the first future energy consumption value based on energy consumption impact index analysis. The second prediction module is used to predict the second future energy consumption value based on the future aging index of the corresponding operating equipment through a corresponding preset second neural network model. The anomaly screening module is used to calculate the comprehensive future energy consumption value of the corresponding operating equipment by averaging the first future energy consumption value and the second future energy consumption value. If the comprehensive future energy consumption value of the corresponding operating equipment is greater than its preset energy consumption threshold at the same time in the future, it is marked as an abnormal device. The priority strategy module is used to obtain the energy consumption impact index of various operating data of each abnormal device, and to obtain the adjustment priority of various operating data of the corresponding abnormal device according to the order of the energy consumption impact index.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention analyzes the current aging index of the corresponding operating equipment using historical data, predicts the future aging index of the corresponding operating equipment using current operating data, matches energy consumption impact indices to various operating data of the corresponding operating equipment based on historical data, and then predicts the comprehensive future energy consumption based on various current operating data, energy consumption impact indices, and future aging indices. This allows for accurate monitoring and screening of equipment with abnormal energy consumption, and the determination of adjustment priorities for various operating data based on each energy consumption impact index, thereby improving the efficiency and accuracy of energy consumption optimization. It also quantifies the degree and stability of equipment operating parameters deviating from preset expected values ​​by analyzing deviation and volatility, effectively reflecting the performance degradation trend. It also analyzes the impact index of each fault type by combining different fault types, their frequency of occurrence, severity, and the severity of the last occurrence. In particular, it introduces the severity of the last occurrence to reflect the recent dynamics of the equipment in the corresponding fault type, and more comprehensively reflects the actual impact of the fault type on energy consumption. Meanwhile, the energy consumption driving index is quantified by the ratio of energy consumption volatility to operational data volatility, accurately identifying the operational parameters that have the greatest impact on energy consumption volatility. The energy consumption driving index is used to sort various operational data to reflect their impact on energy consumption. The final energy consumption impact index is obtained by combining the impact level with manually preset weights, thereby improving the effectiveness of the energy consumption impact index of each operational data and thus enhancing the accuracy of energy consumption optimization at the operational data level. Attached Figure Description

[0014] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart of a big data-based method for monitoring and optimizing mine energy consumption according to the present invention; Figure 2 This is a structural block diagram of a mine energy consumption monitoring and optimization system based on big data according to the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0018] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0019] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" and "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0020] Example 1 See Figure 1 As shown, the present invention provides a method for monitoring and optimizing mine energy consumption based on big data, which specifically includes the following steps: S1. Obtain the current operating data and historical data of each operating device. The historical data includes historical operating data, historical maintenance data, and historical energy consumption values.

[0021] S2. Analyze the current aging index of the corresponding operating equipment through historical data, and then predict the future aging index of the corresponding operating equipment by combining the current operating data.

[0022] S3. Match energy consumption impact indices to various operating data of corresponding operating equipment based on historical data; S4. Based on various current operating data, multiple predicted energy consumption values ​​are obtained through the corresponding preset first neural network model. Then, the first future energy consumption value is obtained by analyzing the energy consumption impact index. Based on the future aging index of the corresponding operating equipment, the second future energy consumption value is predicted through the corresponding preset second neural network model. S5. Calculate the comprehensive future energy consumption value of the corresponding operating equipment by averaging the first future energy consumption value and the second future energy consumption value; if the comprehensive future energy consumption value of the corresponding operating equipment is greater than its preset energy consumption threshold at the same time in the future, it is marked as an abnormal equipment. S6. Obtain the energy consumption impact index of various operating data of each abnormal device, and obtain the adjustment priority of various operating data of the corresponding abnormal device according to the order of the size of the energy consumption impact index.

[0023] In step S1, the current operating data of the running equipment is the operating data used by the equipment in the current work phase. The operating data of the equipment is set according to the preset production plan. Different types of running equipment have their own types of operating data, such as pressure, speed, etc. The corresponding type of operating data of each equipment is obtained according to actual needs.

[0024] The historical maintenance data is extracted from the equipment's maintenance records or maintenance logs, including but not limited to maintenance time, fault type, and specific maintenance content.

[0025] In step S1, all acquired data undergoes data preprocessing, including but not limited to missing value handling and outlier detection. Missing value handling identifies missing values ​​in the data and can be completed using linear interpolation or mean imputation. Data segments with long-term, continuous missing values ​​are marked as unusable and removed. Outlier detection uses existing statistical methods or box plots to identify outliers in the data, and then smooths or removes them.

[0026] In step S2, the step of analyzing the current aging index of the corresponding operating equipment through historical data specifically includes: Sa21, Analyze the deviation PL and volatility BD of various historical operating data of the corresponding operating equipment; Sa22, analyze the fault impact index GS of the corresponding operating equipment through historical maintenance data, and analyze the performance degradation index XS based on PL and BD; Sa23, Analyze the current aging index LS of the corresponding operating equipment: LS = gsk × GS + xsk × XS; Among them, gsk and xsk are the preset fault weight and preset performance weight, respectively.

[0027] The higher the current aging index, the more severe the current aging of the corresponding operating equipment.

[0028] The degree of deviation of equipment operating parameters from the preset expected value (deviation PL) and stability (volatility BD) are quantified to effectively reflect the performance degradation trend; by distinguishing the impact weight of failure and performance degradation, the rationality of aging assessment is improved.

[0029] In step Sa21, the analysis method for the deviation PL is specifically as follows: ; in, The deviation of the i-th type of historical operating data for the corresponding operating equipment. To obtain the amount of historical running data of the i-th type, Let be the value of the i-th type of historical running data at time t. Let be the preset expected value corresponding to the i-th type of historical running data at time t.

[0030] In step Sa21, the analysis method for the volatility BD is specifically as follows: S211. Obtain the corresponding preset expected data segment based on the preset expected value corresponding to the historical operation data; S212. Divide the corresponding historical running data into multiple sub-segments by taking the same and consecutive preset expected values ​​as a sub-segment in a preset expected data segment; S213. Calculate the standard deviation of each segment in the historical running data; S214. Calculate the mean of the standard deviations of various historical operating data to obtain the volatility of the corresponding historical operating data.

[0031] By dividing the data into segments, calculating the standard deviation of each segment, and then performing a mean calculation, the volatility of the corresponding historical operating data is represented. This avoids the impact of changes in actual parameter settings, thereby improving the effectiveness and accuracy of the volatility of the corresponding historical operating data.

[0032] To clearly illustrate the above volatility analysis method, the following examples will explain each step: Based on the preset expected value corresponding to the historical operating data, obtain the corresponding preset expected data segment. For example, if the historical operating data a of device A is obtained and arranged in chronological order as 2, 2, 3, 4, 6, 6, 1, 3, 2, the preset expected data segment corresponding to this historical operating data is the same chronological arrangement of the preset expected value corresponding to the time of each data point of the historical operating data. Assume that the preset expected data segment corresponding to historical operating data a is 2, 2, 2, 5, 5, 5, 2, 2, 2. The corresponding historical running data is divided into multiple sub-segments by taking the same and consecutive preset expected values ​​as a sub-segment within a preset expected data segment. For example, the preset expected data segment mentioned above is divided into three sub-segments: [2, 2, 2], [5, 5, 5], and [2, 2, 2]. The corresponding historical running data a is divided into three sub-segments: [2, 2, 3], [4, 6, 6], and [1, 3, 2]. It should be noted that the values ​​in the above examples are for illustrative purposes only and do not represent the actual data values.

[0033] In step Sa22, the analysis method of the fault impact index GS is as follows: S221. Analyze the impact index YS of each historical fault type of the corresponding operating equipment: ; ; in, This represents the impact index of the i-th historical fault type that occurred in the corresponding operating equipment. This represents the number of occurrences of the i-th historical fault type for the corresponding operating equipment. This represents the overall severity level of the i-th historical fault type corresponding to the operating equipment. To represent the severity level of the i-th historical fault type of the corresponding operating equipment at its last occurrence, pk, ck, and lk are the preset influence weights for the number of occurrences, the preset influence weight for the overall severity, and the preset influence weight for the final severity, respectively. This represents the severity level of the nth occurrence of the i-th historical fault type corresponding to the operating equipment. S222. Analyze the fault impact index GS of the corresponding operating equipment: ; Wherein, GN represents the number of historical fault types that have occurred in the corresponding operating equipment. The preset type influence weight for the i-th historical fault type that occurs in the corresponding operating equipment.

[0034] It should be noted that the severity level of the fault is determined by the maintenance personnel through an assessment of the fault according to a preset evaluation standard and recorded in the maintenance record or repair log.

[0035] The impact index of each fault type is analyzed by combining different fault types, their frequency of occurrence, severity, and the severity of the last occurrence. In particular, the severity of the last occurrence is introduced to reflect the recent dynamics of the equipment under the corresponding fault type, so as to more comprehensively reflect the actual impact of the fault type on energy consumption.

[0036] In step Sa22, the analysis method for the performance degradation index XS is as follows: ; Where YN1 represents the number of types of historical operating data for the corresponding operating device. For the volatility of the i-th type of historical operating data corresponding to the operating equipment, For the preset data influence weight of the i-th type of historical operating data of the corresponding operating equipment, plk and bdk respectively preset deviation influence weight and preset fluctuation influence weight.

[0037] In step S2, the prediction of the future aging index of the corresponding operating equipment based on the current operating data specifically includes: Sb21. Based on the analysis method of the current aging index, obtain the historical aging degree of the corresponding operating equipment at multiple historical moments and the corresponding second historical operating data; Sb22. Take the historical operation data and the corresponding historical aging index of a historical moment, the historical aging degree of the next adjacent historical moment, and the duration between the next adjacent historical moment as a set of sample data, and then obtain multiple sets of sample data. Sb23. After the pre-built deep learning model is pre-trained using the multiple sets of sample data, the current operating data, current aging level, and required future duration of the corresponding operating device are used as inputs to output the predicted value of the future aging index.

[0038] In step S3, matching energy consumption impact indices to various operating data of the corresponding operating equipment based on historical data specifically involves: S31. Calculate the standard deviation of the historical energy consumption values ​​of the corresponding operating equipment as its energy consumption volatility. S32. Calculate the ratio of the volatility of various historical operating data to the energy consumption volatility of the corresponding operating equipment, and use it as the energy consumption driving index of the corresponding type of operating data. S33. Sort the various operating data of the corresponding operating equipment in ascending order, starting from the number 1, according to the size of the energy consumption drive index; S34. Calculate the energy consumption impact index of various operating data for the corresponding operating equipment: ; ; This refers to the energy consumption impact index of the i-th type of operating data for the corresponding operating equipment. The weight of the level influence of the i-th type of operating data for the corresponding operating equipment. The pre-set weights for the i-th type of running data are manually assigned. Let i be the sequence number of the i-th type of running data. The sum of the sequence numbers of each operating data of the corresponding operating device is represented by k1 and k2, which are the first preset weight and the second preset weight, respectively.

[0039] The energy consumption driving index is quantified by the ratio of energy consumption volatility to operational data volatility. This accurately identifies the operational parameters that have the greatest impact on energy consumption volatility. The energy consumption driving index is used to rank various operational data to reflect their influence on energy consumption. The final energy consumption impact index is obtained by combining the influence level with manually preset weights. This improves the effectiveness of the energy consumption impact index for each operational data point, thereby enhancing the accuracy of energy consumption optimization at the operational data adjustment level.

[0040] In step S4, the process of predicting multiple predicted energy consumption values ​​based on various current operating data using corresponding preset first neural network models, and then obtaining a first future energy consumption value based on energy consumption impact index analysis, specifically involves: ; This represents the first future energy consumption value of the corresponding operating equipment at time t. This represents the number of current operating data types for the corresponding running device. This represents the predicted energy consumption value corresponding to the i-th type of current operating data of the corresponding operating device at time t in the future.

[0041] The first neural network model is pre-trained by using multiple sets of historical operating data of corresponding types, corresponding historical energy consumption values, and corresponding time series as training samples.

[0042] In step S4, the second future energy consumption value is predicted by the corresponding preset second neural network model based on the future aging index of the corresponding operating equipment. The second neural network model is pre-trained by using multiple sets of historical aging indices of the corresponding operating equipment, the corresponding historical energy consumption values, and the corresponding time series as training samples.

[0043] In step S5, if the overall future energy consumption value of a corresponding operating device is greater than its preset energy consumption threshold at the same future time, it is marked as an abnormal device. That is, if the overall future energy consumption value of a certain operating device at a future time t is greater than the preset energy consumption threshold of that device at a future time t, then that device is marked as an abnormal device. The preset energy consumption threshold is set based on the timely completion of the production plan.

[0044] In step S6, the energy consumption impact index of various operating data of each abnormal device is obtained. According to the order of the energy consumption impact index, the adjustment priority of various operating data of the corresponding abnormal device is obtained. According to the production plan, the operator can quickly find the abnormal device while ensuring the timely completion of the production plan. The operator can also realize the adjustment priority of the abnormal device according to the magnitude of the comprehensive future energy consumption value. At the same time, according to the adjustment priority of the operating data, the various operating data of the device are adjusted in sequence to efficiently reduce energy consumption.

[0045] Example 2 See Figure 2 As shown, the present invention also provides a mine energy consumption monitoring and optimization system based on big data, specifically including: The central processing unit, and the data acquisition module, aging analysis module, index matching module, first prediction module, second prediction module, anomaly screening module and priority strategy module that are connected in communication with the central processing unit; The data acquisition module is used to acquire the current operating data and historical data of each operating device. The historical data includes historical operating data, historical maintenance data, and historical energy consumption values. The aging analysis module is used to analyze the current aging index of the corresponding operating equipment through historical data, and then combine the current operating data to predict the future aging index of the corresponding operating equipment. The index matching module is used to match energy consumption impact indices to various operating data of corresponding operating equipment based on historical data; The first prediction module is used to predict multiple predicted energy consumption values ​​based on various types of current operating data through corresponding preset first neural network models, and then to obtain the first future energy consumption value based on energy consumption impact index analysis. The second prediction module is used to predict the second future energy consumption value based on the future aging index of the corresponding operating equipment through a corresponding preset second neural network model. The anomaly screening module is used to calculate the comprehensive future energy consumption value of the corresponding operating equipment by averaging the first future energy consumption value and the second future energy consumption value. If the comprehensive future energy consumption value of the corresponding operating equipment is greater than its preset energy consumption threshold at the same time in the future, it is marked as an abnormal device. The priority strategy module is used to obtain the energy consumption impact index of various operating data of each abnormal device, and to obtain the adjustment priority of various operating data of the corresponding abnormal device according to the order of the energy consumption impact index.

[0046] The specific implementation of the functions of each module is the same as that in Example 1, and will not be repeated here.

[0047] Example 3 The present invention also provides an electronic device, including: a processor, a transmitting device, an input device, an output device, and a memory. The processor may be implemented using a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit, or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory may be implemented using a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), and is used to store computer program code. The computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes a method as described in any of the above possible implementation methods.

[0048] Example 4 The present invention also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a processor of an electronic device, cause the processor to perform a method as described in any of the above possible implementations.

[0049] The beneficial effects of this invention are as follows: This invention analyzes the current aging index of corresponding operating equipment using historical data, predicts the future aging index of the corresponding operating equipment based on current operating data, matches energy consumption impact indices to various operating data of the corresponding operating equipment based on historical data, and then predicts the comprehensive future energy consumption based on various current operating data, energy consumption impact indices, and future aging indices. This allows for accurate monitoring and screening of equipment with abnormal energy consumption, and the determination of adjustment priorities for various operating data based on each energy consumption impact index, thereby improving the efficiency and accuracy of energy consumption optimization.

[0050] In the description of this specification, the references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0051] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0052] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A big data-based mine energy consumption monitoring and optimization method, characterized in that, The method comprises the following steps: obtaining current operation data and historical data of each operation device, wherein the historical data comprises historical operation data, historical maintenance data and historical energy consumption values; analyzing the current aging index of the corresponding operation device through historical data analysis, and predicting the future aging index of the corresponding operation device in combination with the current operation data; matching the energy consumption influence index for each type of operation data of the corresponding operation device according to the historical data; obtaining a plurality of predicted energy consumption values by respectively passing each type of current operation data through a corresponding preset first neural network model, and then obtaining a first future energy consumption value through energy consumption influence index analysis; obtaining a second future energy consumption value through a corresponding preset second neural network model according to the future aging index of the corresponding operation device; performing mean value calculation on the first future energy consumption value and the second future energy consumption value to obtain a comprehensive future energy consumption value of the corresponding operation device; if the comprehensive future energy consumption value of the corresponding operation device is greater than a preset energy consumption threshold at the same time in the future, marking the operation device as an abnormal device; obtaining the energy consumption influence index of each type of operation data of each abnormal device, and obtaining the adjustment priority of each type of operation data of the corresponding abnormal device in order of the size of the energy consumption influence index.

2. The big data based mine energy consumption monitoring and optimization method according to claim 1, characterized in that, The current aging index of the corresponding operation device is analyzed through historical data analysis, specifically as follows: analyze the deviation degree PL and the fluctuation rate BD of various historical operation data of the corresponding operation device; analyze the failure influence index GS of the corresponding operation device through historical maintenance data, and analyze the performance degradation index XS according to PL and BD; analyze the current aging index LS of the corresponding operation device: LS = gsk × GS + xsk × XS; wherein gsk and xsk are preset failure weights and preset performance weights, respectively.

3. The big data based mine energy consumption monitoring and optimization method according to claim 2, characterized in that, The analysis method of the deviation degree PL is specifically as follows: ； wherein, is a deviation degree of the i-th historical operation data corresponding to the running device, is a data amount of the i-th historical operation data obtained, is a value of the i-th historical operation data at the t-th moment, is a preset expected value corresponding to the i-th historical operation data at the t-th moment.

4. The big data based mine energy consumption monitoring and optimization method according to claim 2, characterized in that, The analysis method of the fluctuation rate BD is specifically as follows: obtain a preset expected data segment corresponding to a preset expected value of historical operation data; divide the corresponding historical operation data into a plurality of sub-segments by taking the same and continuous preset expected values in a preset expected data segment as a sub-segment; calculate the standard deviation of each sub-segment in the historical operation data; respectively take the mean value of the standard deviation of various historical operation data to obtain the fluctuation rate of the corresponding historical operation data.

5. The big data based mine energy consumption monitoring and optimization method according to claim 2, characterized in that, The analysis method of the failure influence index GS is specifically as follows: analyze the influence index YS of each historical failure type of the corresponding operation device; ; ； wherein, is an impact index of the i-th historical fault type occurred to the running equipment, is the number of occurrences of the i-th historical fault type of the running equipment, is a comprehensive severity level of the i-th historical fault type of the running equipment, is a severity level of the i-th historical fault type of the running equipment at the last occurrence; pk, ck and lk are respectively a preset number-of-times impact weight, a preset comprehensive degree impact weight and a preset last degree impact weight, is a severity level of the n-th occurrence of the i-th historical fault type of the running equipment; analyze the failure influence index GS of the corresponding operation device. ； Wherein, GN is the number of the historical fault types corresponding to the running equipment, is the preset type influence weight of the i-th historical fault type corresponding to the running equipment.

6. The big data based mine energy consumption monitoring and optimization method according to claim 2, characterized in that, The analysis method of the performance degradation index XS is specifically as follows: ； YN1 is the number of historical operation data corresponding to the operation equipment, is the deviation degree of the i-th historical operation data corresponding to the operation equipment, is the fluctuation rate of the i-th historical operation data corresponding to the operation equipment, is the preset data influence weight of the i-th historical operation data corresponding to the operation equipment, and plk and bdk are preset deviation influence weight and preset fluctuation influence weight, respectively.

7. The big data based mine energy consumption monitoring and optimization method according to claim 2, characterized in that, The future aging index of the corresponding operation device is predicted in combination with the current operation data, specifically as follows: obtain the historical aging degree of the corresponding operation device at a plurality of historical time points and the corresponding second historical operation data according to the analysis method of the current aging index; take the historical operation data corresponding to a historical time point, the corresponding historical aging index, the historical aging degree corresponding to the next adjacent historical time point and the time length between the next adjacent historical time point as a group of sample data, and then obtain a plurality of groups of sample data; After the pre-built deep learning model is pre-trained through the multiple sets of sample data, the current running data, the current aging degree and the required future time length of the corresponding running equipment are taken as inputs, and a predicted value of the future aging index is output. 8.The big data based mine energy consumption monitoring and optimization method according to claim 1, characterized in that, The energy consumption influence index corresponding to each type of running data of the corresponding running equipment is matched according to historical data, specifically as follows: The standard deviation of the historical energy consumption value of the corresponding running equipment is calculated as the energy consumption fluctuation rate thereof, The ratio of the fluctuation rate of each type of historical running data of the corresponding running equipment to the energy consumption fluctuation rate is calculated as the energy consumption driving index of the corresponding type of running data; According to the size of the energy consumption driving index, each type of running data of the corresponding running equipment is sorted from small to large in order, starting from 1; The energy consumption influence index of each type of running data of the corresponding running equipment is calculated as follows: ； ； an energy consumption influence index corresponding to the i-th operation data of the operation device, a grade influence weight corresponding to the i-th operation data of the operation device, a manually preset weight of the i-th operation data, a serial number of the i-th operation data, a sum of serial numbers of each operation data corresponding to the operation device, and k1 and k2 are respectively a first preset weight and a second preset weight. 9.The big data based mine energy consumption monitoring and optimization method according to claim 8, characterized in that, The first future energy consumption value is analyzed according to the energy consumption influence index, specifically as follows: ； is a first future energy consumption value corresponding to the running device at a future time t, is a number of current running data corresponding to the running device, is a predicted energy consumption value corresponding to the i-th current running data of the running device at the future time t.

10. A big data-based mine energy consumption monitoring and optimization system, applying the big data-based mine energy consumption monitoring and optimization method according to any one of claims 1 to 9, characterized in that, It includes: A data acquisition module is configured to acquire current running data and historical data of each running equipment, wherein the historical data includes historical running data, historical maintenance data and historical energy consumption values; An aging analysis module is configured to analyze the current aging index of the corresponding running equipment through the historical data, and to predict the future aging index of the corresponding running equipment in combination with the current running data; An index matching module is configured to match the energy consumption influence index for each type of running data of the corresponding running equipment according to the historical data; A first prediction module is configured to predict a plurality of predicted energy consumption values by using a corresponding pre-set first neural network model according to each type of current running data, and to analyze a first future energy consumption value according to the energy consumption influence index; A second prediction module is configured to predict a second future energy consumption value by using a corresponding pre-set second neural network model according to the future aging index of the corresponding running equipment; An abnormality screening module is configured to calculate a comprehensive future energy consumption value of the corresponding running equipment by averaging the first future energy consumption value and the second future energy consumption value, and to mark the corresponding running equipment as an abnormal equipment if the comprehensive future energy consumption value of the corresponding running equipment is greater than a pre-set energy consumption threshold at the same time in the future; A priority strategy module is configured to acquire the energy consumption influence index of each type of running data of each abnormal equipment, and to obtain the adjustment priority of each type of running data of the corresponding abnormal equipment in order of the size of the energy consumption influence index.

Images