Mining area information management method and system

Abstract

The invention provides a mining area information management method and system, and belongs to the technical field of data processing, and the method comprises the steps: inputting target data into a target autoregression integral moving average model, and obtaining the fault probability of mining area equipment; wherein the target data are operation parameters of mining area equipment, and the target autoregression integral moving average model is obtained by training the autoregression integral moving average model according to historical operation parameters of the mining area equipment and a target loss function; the target loss function is determined according to the influence weight of the historical operation parameters of the equipment in the mining area on the fault result; and sending early warning information to the target equipment based on the fault probability of the mining area equipment. According to the mining area information management method and system provided by the invention, the accuracy and reliability of mining area information management can be improved.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of data processing, and more specifically, relates to a mining area information management method and system. Background Art

[0002] In today's mining area production and operation, the stable operation of equipment plays a crucial role in ensuring production efficiency, reducing costs, and ensuring safe production. With the continuous expansion of the mining scale in the mining area and the increasing complexity of equipment, the impact of equipment failures has become more and more serious. Equipment failures not only lead to production stagnation, causing huge economic losses, but may also trigger safety accidents, threatening the lives of workers.

[0003] Traditional mining area equipment management methods mainly rely on regular preventive maintenance and emergency repairs after failures occur. Although regular preventive maintenance can reduce the probability of equipment failures to a certain extent, due to the lack of prediction of the equipment operation status, there are problems of over-maintenance or under-maintenance.

[0004] Therefore, an accurate and reliable mining area information management method is needed. Summary of the Invention

[0005] The purpose of the present disclosure is to provide a mining area information management method and system to improve the accuracy and reliability of mining area information management.

[0006] In the first aspect of the embodiments of the present disclosure, a mining area information management method is provided, including: Inputting target data into a target autoregressive integrated moving average model to obtain the failure probability of mining area equipment; wherein the target data is the operation parameters of mining area equipment, the target autoregressive integrated moving average model is obtained by training the autoregressive integrated moving average model according to the historical operation parameters of equipment in the mining area and a target loss function, and the target loss function is determined according to the influence weight of the historical operation parameters of equipment in the mining area on the failure result; Sending a warning message to the target equipment based on the failure probability of the mining area equipment.

[0007] In the second aspect of the embodiments of the present disclosure, a mining area information management system is provided, including: A failure probability determination module, configured to input target data into a target autoregressive integrated moving average model to obtain the failure probability of mining area equipment; wherein the target data is the operation parameters of mining area equipment, the target autoregressive integrated moving average model is obtained by training the autoregressive integrated moving average model according to the historical operation parameters of equipment in the mining area and a target loss function, and the target loss function is determined according to the influence weight of the historical operation parameters of equipment in the mining area on the failure result A fault warning module for sending warning information to a target device based on the fault probability of mining area equipment.

[0008] In a third aspect of the embodiments of the present disclosure, there is provided an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned mining area information management method are implemented.

[0009] In a fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned mining area information management method are implemented.

[0010] The beneficial effects of the mining area information management method and system provided by the embodiments of the present disclosure are as follows: By using the target autoregressive integrated moving average model, the present disclosure can predict the fault probability of equipment based on the operating parameters of mining area equipment. The historical operating parameters of equipment in the mining area are considered during the training process, which enables the model to learn the normal and abnormal modes of equipment operation, thereby improving the accuracy of fault prediction. The present disclosure determines the target loss function according to the influence weight of the historical operating parameters of equipment in the mining area on the fault result, which can train the autoregressive integrated moving average model more accurately, improve the accuracy and reliability of fault prediction, and further enhance the accuracy and reliability of mining area information management. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings required for the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present disclosure. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0012] Figure 1 It is a flowchart of the mining area information management method provided by an embodiment of the present disclosure; Figure 2 It is a structural block diagram of the mining area information management system provided by an embodiment of the present disclosure; Figure 3 It is a schematic block diagram of the electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0013] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, those skilled in the art should understand that the present disclosure can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present disclosure.

[0014] To make the objectives, technical solutions, and advantages of the present disclosure clearer, the following will be described through specific embodiments in conjunction with the accompanying drawings.

[0015] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a mining area information management method provided for an embodiment of the present disclosure. The method includes: S101: Input target data into a target autoregressive integrated moving average model to obtain the failure probability of mining area equipment.

[0016] Among them, the target data is the operating parameters of mining area equipment, and the target autoregressive integrated moving average model is obtained by training the autoregressive integrated moving average model based on the historical operating parameters of equipment in the mining area and a target loss function. The target loss function is determined based on the influence weight of the historical operating parameters of equipment in the mining area on the failure result.

[0017] In this embodiment, the target data is the operating parameters of mining area equipment. Mining area equipment may include shearers, roadheaders, rock drifters, hoists, scraper conveyors, etc. The operating parameters may include temperature, pressure, rotational speed, current, voltage, etc. Different operating parameters can reflect the operating conditions of the equipment from different aspects. For example, too high a temperature may mean that there are heat dissipation problems or abnormal wear of internal components in the equipment; abnormal pressure may indicate blockage or leakage of components such as pipelines and valves in the equipment.

[0018] The autoregressive integrated moving average model (ARIMA) is a statistical model used for time series prediction, which consists of three parts: autoregressive (AR), differencing (I), and moving average (MA). The target autoregressive integrated moving average model is a trained model that can accurately predict the operating parameters of mining area equipment in the future for a period of time. The historical operating parameters refer to the operating parameter data recorded by mining area equipment in the past for a period of time. The target loss function is used to measure the degree of difference between the model prediction result and the actual failure result. It is determined based on the influence weight of the historical operating parameters of equipment in the mining area on the failure result.

[0019] Specifically, the determination process of the target loss function is determined in the following manner: In this embodiment, the process of determining the target loss function according to the influence weights of the historical operation parameters of the equipment in the mining area on the fault results includes: Training a target random forest model based on the historical operation parameters of the equipment in the mining area and their corresponding fault results; Calculating the Gini impurity of the target random forest model, and determining a first weight based on the Gini impurity of the target random forest model. The first weight is the Gini influence weight of each historical operation parameter on the fault result; Determining the out-of-bag accuracy based on the out-of-bag data of the target random forest model, and determining a second weight based on the out-of-bag accuracy. The second weight is the out-of-bag influence weight of each historical operation parameter on the fault result; Determining the influence weight of each historical operation parameter on the fault result based on the first weight and the second weight; Determining the target loss function based on the influence weight of each historical operation parameter on the fault result.

[0020] In this embodiment, a target random forest model can be trained based on the historical operation parameters of the equipment in the mining area and their corresponding fault results. In this process, the number of decision trees in the random forest can be determined according to experience or the number of decision trees when solving similar problems. Other hyperparameters of the random forest can be set according to the reference values of the model and continuously iterated during the training process to finally obtain the target random forest model.

[0021] Considering that the Gini impurity is an index to measure the purity of the sample set, during the node splitting process of the decision tree, the importance of features can be evaluated by calculating the change in Gini impurity before and after splitting. For each decision tree in the target random forest model, calculate the reduction in Gini impurity of each historical operation parameter during node splitting, and then average the reduction in Gini impurity of this parameter in all decision trees to obtain the Gini influence weight of this parameter. The greater the Gini influence weight, the greater the contribution of this parameter to distinguishing the fault result during the decision tree splitting process.

[0022] Secondly, during the training process of the random forest, for each decision tree, approximately one-third of the data is usually not used to train this tree, and this data is called out-of-bag data. Each tree has its own out-of-bag data, which can be used as a dataset for unbiased evaluation of the model. Using the out-of-bag data to predict the trained random forest model, the initial accuracy of the model on the out-of-bag data is obtained, denoted as , which reflects the performance of the model on the data not participating in the training. For each feature, randomly shuffle the values of this feature in the out-of-bag data, and then use the shuffled out-of-bag data for prediction again to obtain the new accuracy, denoted as , that is, the out-of-bag accuracy. The purpose of shuffling the feature values is to disrupt the true relationship between the feature and the target variable, thereby observing the change in model performance. The importance score of a feature can be obtained by calculating the degree of decrease in accuracy, that is . If the accuracy of the model drops significantly after a certain feature is shuffled, it indicates that the feature has an important impact on the prediction result of the model, and its importance score is high; conversely, if the accuracy drop is not obvious, it means that the importance of the feature is relatively low.

[0023] It should be noted that the above Gini impurity and out-of-bag accuracy are accurately scores of the degree of importance, so both should be normalized.

[0024] For example, for the score based on Gini impurity , and the score based on out-of-bag data , calculate the normalized weights respectively according to and . Among them is the number of historical operation parameters, represents the Gini impurity score of the th operation parameter, represents the out-of-bag data score of the th operation parameter, represents the Gini impurity score of the th operation parameter, represents the Gini impurity score of the th operation parameter, represents the out-of-bag data score of the th operation parameter, represents the Gini influence weight of the th operation parameter, represents the out-of-bag influence weight of the th operation parameter.

[0025] Finally, determine the final weight by combining the two normalized weights. It can be through weighted average, such as setting a balance coefficient .

[0026] Specifically, determine the influence weight of each historical operation parameter on the fault result based on the first weight and the second weight, including: Determine the balance coefficient based on the correlation between each historical operation parameter; Determine the influence weight of each historical operation parameter on the fault result based on the balance coefficient, the first weight, and the second weight.

[0027] In this embodiment, finally determine the influence weight of each historical operation parameter on the fault result, that is . The influence weight of each historical operating parameter on the fault result.

[0028] The balance coefficient can be determined according to the number of relevant data pairs. For example, the balance coefficient is determined based on the correlation between each historical operating parameter, including: In response to the number of relevant data pairs being greater than the first correlation number, the reference value of the balance coefficient is reduced based on the first balance step length to obtain the balance coefficient; In response to the number of relevant data pairs being less than or equal to the first correlation number, the reference value of the balance coefficient is used as the balance coefficient; A relevant data pair is a data pair composed of two historical operating parameters whose correlation is greater than the first correlation threshold.

[0029] In this embodiment, the balance coefficient is the weight corresponding to the Gini influence weight of each historical operating parameter on the fault result; Considering that the weight obtained based on Gini impurity mainly focuses on the role of a single feature during node splitting, and relatively less consideration is given to the interaction and dependence relationships between features, which will affect the accurate assessment of feature importance.

[0030] During the process of evaluating by shuffling the feature values based on out-of-bag data, the interaction effects between features on the model performance will be indirectly considered, because the change in model performance is the comprehensive result of all features and their interaction effects.

[0031] Therefore, when the number of relevant data pairs is large, that is, greater than the first correlation number, the reference value of the balance coefficient can be reduced according to the first balance step length. Whether two data (operating parameters) can form a relevant data pair can be measured by calculating the Pearson correlation coefficient between the two data to measure the linear correlation degree between the two features. If it is greater than the preset threshold, the two data form a relevant data pair; otherwise, they cannot form a relevant data pair. The first correlation number, the first correlation threshold, and the reference value of the balance coefficient can be set according to experience.

[0032] It should be noted that whether a data forms a relevant data pair with another data does not affect the calculation and determination of this data with other data.

[0033] In this embodiment, considering that when determining the influence weight of historical operating parameters on the fault result, the relationships between various parameters need to be comprehensively considered. If the correlation between two historical operating parameters is very strong, their influences on the fault result may overlap. Therefore, considering adjusting the first balance step length through the number of the first relevant data pairs and the average correlation intensity can more accurately allocate the Gini influence weight and the out-of-bag influence weight, avoid overestimating or misestimating the influence weight of relevant parameters, and make the finally determined influence weight more truly reflect the unique contribution of each parameter to the fault result.

[0034] For example, the first balance step size can be calculated by a first formula, and the first formula can be: , where is the first balance step size, is the maximum balance step size, is the number of relevant data pairs, is the average value of the correlations of all relevant data pairs, is the first correlation threshold.

[0035] The logic of the first formula is that when is larger, that is, the number of relevant data pairs is more, is closer to , that is, it is necessary to reduce the balance coefficient by a larger step size to more significantly reduce the proportion of the weight obtained based on the Gini impurity. Considers the influence of the correlation strength of relevant data pairs. When is closer to 1, it indicates that the correlation of relevant data pairs is stronger, the value of is larger,

[0036] In this embodiment, the influence of time on the loss function is also considered. Therefore, the time influence weight can be further considered on the basis of determining the target loss function of the autoregressive integrated moving average model for the influence weights of each historical operating parameter on the fault result.

[0037] For example, the process of determining the target loss function according to the influence weights of the historical operating parameters of the equipment in the mining area on the fault result includes: Determining the target loss function of the autoregressive integrated moving average model based on the time influence weight and the influence weights of each historical operating parameter on the fault result.

[0038] In this embodiment, on the basis of obtaining the foregoing , the time influence weight is added, which can be determined in an exponentially decaying manner. For example , where is the current time, is the historical time point of the th operating parameter, is the decay coefficient, , The closer is to 1, the slower the time decay, that is, the weight of the long-term data is relatively large; the closer

[0039] is to 0, the faster the time decay, and the weight of the recent data dominates. The decay coefficient can be determined according to experience. That is , The influence weight of the historical operation parameters obtained after considering the time influence weight on the fault result. It should be noted that normalization processing is also required.

[0040] Through the above description, the objective loss function of the target random forest can be determined , is the actual fault probability value at time and is the predicted fault probability value of the model at time

[0041] It can be concluded from the above that the present disclosure can more accurately predict the future operation status and fault probability of the equipment by combining the historical operation parameters of the mining area equipment and using the ARIMA model for time series analysis. By analyzing the autocorrelation function graph and the partial autocorrelation function graph, the autoregressive order, the differencing order, and the moving average order of the ARIMA model are determined, which helps to construct a more appropriate model structure and improve the fault prediction performance. The present disclosure trains the target random forest model to evaluate the importance of each parameter, and combines the Gini impurity and the out-of-bag accuracy to determine the influence weight, enhancing the adaptability of the present disclosure to different data features. The objective loss function is determined according to the influence weight of the historical operation parameters on the fault result, enabling the present disclosure to pay more attention to the parameters that have an important impact on fault prediction during the training process, thereby improving the accuracy of fault prediction and further enhancing the accuracy and reliability of mining area information management.

[0042] In an embodiment of the present disclosure, the mining area information management method further includes: Taking the first initial value as the autoregressive order of the autoregressive integrated moving average model, increasing the first initial value according to the first data step, and determining the autocorrelation function graph and the partial autocorrelation function graph after each increase until the autocorrelation function graph shows a trailing feature and the partial autocorrelation function graph shows a truncated feature; Taking the autoregressive order corresponding to the situation where the autocorrelation function graph shows a trailing feature and the partial autocorrelation function graph shows a truncated feature as the autoregressive order of the target autoregressive integrated moving average model.

[0043] In this embodiment, through the foregoing description, the objective loss function of the target autoregressive integrated moving average model can be determined.

[0044] In addition, the target autoregressive integrated moving average model also contains three parameters, namely the autoregressive order, the differencing order, and the moving average order.

[0045] Among them, the autoregressive order of the autoregressive integrated moving average model is determined based on the autocorrelation function graph and the partial autocorrelation function graph. The first initial value can be 0, and the first data step size can be 1. For each increased autoregressive order, the corresponding autocorrelation function (ACF) graph and partial autocorrelation function (PACF) graph are determined. The ACF graph reflects the correlation between data at different times in the time series, while the PACF graph eliminates the influence of data at intermediate times and more directly shows the correlation between data at two specific times. According to the theory of the ARIMA model, the autoregressive order is related to the truncation feature of the PACF graph, and the moving average order is related to the truncation feature of the ACF graph. When the ACF graph shows a trailing feature and the PACF graph shows a truncation feature, an autoregressive order that meets the model requirements is found. The trailing feature means that the correlation gradually weakens with time delay but does not suddenly disappear, and the truncation feature means that the correlation suddenly becomes zero after a certain order. In this way, using the features of the ACF graph and the PACF graph to screen out the appropriate autoregressive order is based on the inherent properties of the ARIMA model and the principles of time series analysis, and can effectively determine an important parameter of the model.

[0046] In this embodiment, the autocorrelation function graph and the partial autocorrelation function graph after each increase can be input into the first neural network model to determine whether there are trailing features and truncation features. The first neural network model is trained based on a large amount of data composed of autocorrelation function graphs, partial autocorrelation function graphs, and whether there are trailing features, truncation features, and stationary features corresponding to them.

[0047] The corresponding differencing order and moving average order can also be determined in the same way. The determination condition for the moving average order is: taking the first initial value as the autoregressive order of the autoregressive integrated moving average model, increasing the first initial value according to the first data step size, determining the autocorrelation function graph and the partial autocorrelation function graph after each increase until the autocorrelation function graph shows a truncation feature and the partial autocorrelation function graph shows a trailing feature.

[0048] The determination condition for the differencing order is: taking the first initial value as the autoregressive order of the autoregressive integrated moving average model, increasing the first initial value according to the first data step size, determining the autocorrelation function graph and the partial autocorrelation function graph after each increase until both the autocorrelation function graph and the partial autocorrelation function graph show stationary features.

[0049] Although the autoregressive order, differencing order, and moving average order may change under the influence of the objective loss function, determining the possible autoregressive order, differencing order, and moving average order in advance can reduce the computational amount and improve efficiency. The reason is that the number of parameter combinations of the ARIMA model is relatively large. If the above parameters are not determined in advance, a large number of unnecessary parameter combinations need to be traversed during parameter search using the objective loss function, resulting in a huge computational amount. Secondly, determining reasonable parameter values in advance can provide a better starting point for model training, enabling the model to converge to the optimal solution faster when adjusting parameters based on the objective loss function.

[0050] It can be concluded from the above that the present disclosure uses the characteristics of the autocorrelation function graph and the partial autocorrelation function graph to screen the appropriate autoregressive order. By setting the initial value and data step size, gradually increasing the autoregressive order, and observing the changes in the autocorrelation function graph and the partial autocorrelation function graph until the autoregressive order that meets the model requirements is found, the computational amount can be reduced, the efficiency can be improved, the number of iterations and time for model training can be reduced, and the efficiency and accuracy of model training can be improved.

[0051] In an embodiment of the present disclosure, inputting the target data into the target autoregressive integrated moving average model to obtain the failure probability of the mining area equipment includes: Inputting the target data into the target autoregressive integrated moving average model to obtain the operating parameters of the mining area equipment within the first time period; Determining the failure probability of the mining area equipment based on the operating parameters of the mining area equipment within the first time period.

[0052] In this embodiment, the target autoregressive integrated moving average model cannot directly output the failure probability of the mining area equipment, but outputs the operating parameters of the mining area equipment within a period of time (the first time period). The first time period can be determined according to actual needs.

[0053] A pre-established failure probability calculation model can be used, with the predicted operating parameters within the first time period as the input, to output the failure probability of the equipment. The above failure probability calculation model can be a simple mapping table relationship model. It can be obtained based on simple data statistics and mapping relationships. For example, it can be determined according to the operating parameter data before and during the occurrence of failures in historical data.

[0054] For example, when the normal voltage of the engine is 220V, the number of times the historical voltage is 230V is 10 times, and the number of times the historical voltage is 230V and a failure occurs is 2 times. At this time, the failure probability corresponding to a voltage of 230V can be 20%.

[0055] It can be concluded from the above that by inputting the operating parameters predicted by the ARIMA model into the failure probability calculation model, the present disclosure can further estimate the failure probability of the equipment, providing data support for the mining area information management.

[0056] S102: Send a warning message to the target device based on the failure probability of the mining area equipment.

[0057] In this embodiment, a reasonable failure probability warning threshold can be preset according to factors such as the characteristics of the mining area equipment, the operating environment, and historical failure data.

[0058] For example, for some key equipment, since its failure may have a significant impact on the production of the entire mining area, the warning threshold can be set relatively low, such as triggering a warning when the failure probability reaches 10%; while for some secondary equipment, the warning threshold can be appropriately increased, such as 20% or higher.

[0059] The warning message can be the equipment number and the current failure probability value. The communication method can be selected from wired network, wireless network, short message, etc., to ensure that the warning message can be accurately and timely conveyed to relevant personnel or the equipment management system. The target device can be the mobile phone or terminal system of relevant personnel.

[0060] It can be concluded from the above that by setting different failure probability warning thresholds, the present disclosure improves the pertinence and reliability of failure warning. Once the failure probability of the equipment reaches or exceeds the threshold, the system can immediately send a warning message, ensuring that relevant personnel or the equipment management system can quickly learn about the potential failure risk of the equipment, and thus take corresponding measures in a timely manner.

[0061] Corresponding to the mining area information management method in the above embodiment, Figure 2 is the structural block diagram of the mining area information management system provided by an embodiment of the present disclosure. For the sake of convenience of description, only the parts related to the embodiments of the present disclosure are shown. Refer to Figure 2 The mining area information management system 20 includes: a failure probability determination module 21 and a failure warning module 22.

[0062] Among them, the failure probability determination module 21 is used to input target data into the target autoregressive integrated moving average model to obtain the failure probability of the mining area equipment; Among them, the target data is the operating parameters of the mining area equipment, and the target autoregressive integrated moving average model is obtained by training the autoregressive integrated moving average model according to the historical operating parameters of the equipment in the mining area and the target loss function, and the target loss function is determined according to the influence weight of the historical operating parameters of the equipment in the mining area on the failure result The failure warning module 22 is used to send a warning message to the target device based on the failure probability of the mining area equipment.

[0063] In one embodiment of the present disclosure, the mining area information management system 20 includes: a target loss function determination module, configured to train a random forest model based on the historical operation parameters of the equipment in the mining area and their corresponding fault results to obtain a target random forest model; Calculate the Gini impurity of the target random forest model, and determine a first weight based on the Gini impurity of the target random forest model. The first weight is the Gini influence weight of each historical operation parameter on the fault result; Determine the out-of-bag accuracy based on the out-of-bag data of the target random forest model, and determine a second weight based on the out-of-bag accuracy. The second weight is the out-of-bag influence weight of each historical operation parameter on the fault result; Determine the influence weight of each historical operation parameter on the fault result based on the first weight and the second weight; Determine the target loss function based on the influence weight of each historical operation parameter on the fault result.

[0064] In one embodiment of the present disclosure, the target loss function determination module is specifically configured to determine a balance coefficient based on the correlation between each historical operation parameter; Determine the influence weight of each historical operation parameter on the fault result based on the balance coefficient, the first weight, and the second weight.

[0065] In one embodiment of the present disclosure, the target loss function determination module is further specifically configured to, in response to the number of relevant data pairs being greater than a first relevant number, reduce the reference value of the balance coefficient based on a first balance step length to obtain the balance coefficient; In response to the number of relevant data pairs being less than or equal to the first relevant number, use the reference value of the balance coefficient as the balance coefficient; The relevant data pair is a data pair composed of two historical operation parameters whose correlation is greater than a first relevant threshold.

[0066] In one embodiment of the present disclosure, the model parameter determination module is configured to use a first initial value as the autoregressive order of the autoregressive integrated moving average model, increase the first initial value according to a first data step length, and determine the autocorrelation function graph and the partial autocorrelation function graph after each increase until the autocorrelation function graph shows a trailing feature and the partial autocorrelation function graph shows a truncated feature; Use the autoregressive order corresponding to the situation where the autocorrelation function graph shows a trailing feature and the partial autocorrelation function graph shows a truncated feature as the autoregressive order of the target autoregressive integrated moving average model.

[0067] In one embodiment of the present disclosure, the fault probability determination module 21 is specifically configured to input target data into the target autoregressive integrated moving average model to obtain the operation parameters of the mining area equipment within a first time period; Determine the fault probability of the mining area equipment based on the operation parameters of the mining area equipment within the first time period.

[0068] In one embodiment of the present disclosure, the target loss function determination module is specifically further configured to determine the target loss function of the autoregressive integrated moving average model based on the time influence weight and the influence weight of each historical operating parameter on the fault result.

[0069] See Figure 3 , Figure 3 which is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure. As Figure 3 shown, the electronic device 300 in this embodiment may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The above-mentioned processors 301, input devices 302, output devices 303, and memories 304 communicate with each other through a communication bus 305. The memory 304 is used to store computer programs, and the computer programs include program instructions. The processor 301 is configured to execute the program instructions stored in the memory 304. Among them, the processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above system embodiments, such as Figure 2 the functions of the modules 21 to 22 shown.

[0070] It should be understood that in the embodiments of the present disclosure, the so-called processor 301 may be a central processing unit (CPU), and this processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0071] The input device 302 may include a touchpad, a fingerprint acquisition sensor (for acquiring the fingerprint information and the direction information of the fingerprint of the user), a microphone, etc., and the output device 303 may include a display (such as an LCD), a speaker, etc.

[0072] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A part of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0073] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure may execute the implementation manners described in the first and second embodiments of the mine area information management method provided by the embodiments of the present disclosure, and may also execute the implementation manner of the electronic device described in the embodiments of the present disclosure, which will not be elaborated herein.

[0074] In another embodiment of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, all or part of the processes in the method of the above embodiments are implemented. It can also be completed by instructing relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0075] The computer-readable storage medium may be an internal storage unit of the electronic device in any of the foregoing embodiments, such as the hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on the electronic device. Further, the computer-readable storage medium may also include both the internal storage unit and the external storage device of the electronic device. The computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store the data that has been output or will be output.

[0076] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this disclosure.

[0077] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described electronic devices and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0078] In several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed couplings, direct couplings, or communication connections to each other can be indirect couplings or communication connections through some interfaces or units, and can also be electrical, mechanical, or other forms of connection.

[0079] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of this disclosure.

[0080] In addition, the functional units in each embodiment of this disclosure can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0081] The above is only the specific implementation manner of this disclosure, but the protection scope of this disclosure is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or substitutions within the technical scope disclosed by this disclosure, and these modifications or substitutions should all be covered by the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be subject to the protection scope of the claims.

Claims

1. A mining area information management method, characterized in that: include: Input the target data into the target autoregressive integrated moving average model to obtain the failure probability of the mining equipment; Wherein, the target data is the operating parameters of the equipment in the mining area, the target autoregressive integral moving average model is obtained by training the autoregressive integral moving average model according to the historical operating parameters of the equipment in the mining area and the target loss function, and the target loss function is determined according to the influence weight of the historical operating parameters of the equipment in the mining area on the fault results; Based on the failure probability of the mining equipment, early warning information is sent to the target equipment.

2. The mining area information management method according to claim 1, characterized in that: The process of determining the target loss function according to the influence weight of the historical operating parameters of the equipment in the mining area on the failure result includes: Training the random forest model based on the historical operating parameters of the equipment in the mining area and the corresponding fault results to obtain a target random forest model; Calculating the Gini impurity of the target random forest model, and determining a first weight based on the Gini impurity of the target random forest model, where the first weight is the Gini influence weight of each historical operating parameter on the fault result; Determine an out-of-bag accuracy based on the out-of-bag data of the target random forest model, and determine a second weight based on the out-of-bag accuracy, where the second weight is an out-of-bag influence weight of each historical operating parameter on the fault result; Determine the influence weight of each historical operating parameter on the fault result based on the first weight and the second weight; The target loss function is determined based on the influence weight of each historical operating parameter on the fault result.

3. The mining area information management method according to claim 2, characterized in that: The determining the influence weight of each historical operating parameter on the fault result based on the first weight and the second weight includes: Determining a balance coefficient based on the correlation between the various historical operating parameters; The influence weight of each historical operating parameter on the fault result is determined based on the balance coefficient, the first weight and the second weight.

4. The mining area information management method according to claim 3, characterized in that: The determining of the balance coefficient based on the correlation between the historical operating parameters includes: In response to the number of correlation data pairs being greater than a first correlation number, reducing a reference value of a balancing coefficient based on a first balancing step length to obtain the balancing coefficient; In response to the number of correlation data pairs being less than or equal to a first correlation number, using a reference value of the balancing coefficient as the balancing coefficient; The correlation data pair is a data pair consisting of two historical operating parameters whose correlation is greater than a first correlation threshold.

5. The mining area information management method according to claim 1, characterized in that: Also includes: Using the first initial value as the autoregressive order of the autoregressive integrated moving average model, increasing the first initial value according to the first data step length, and determining an autocorrelation function graph and a partial autocorrelation function graph after each increase until the autocorrelation function graph shows a tailing feature and the partial autocorrelation function graph shows a truncation feature; The autoregressive order corresponding to the occurrence of tailing characteristics in the autocorrelation function graph and the occurrence of truncation characteristics in the partial autocorrelation function graph is used as the autoregressive order of the target autoregressive integrated moving average model.

6. The mining area information management method according to claim 1, characterized in that: The target data is input into the target autoregressive integral moving average model to obtain the failure probability of the mining equipment, including: Input the target data into the target autoregressive integrated moving average model to obtain the mining equipment operating parameters in the first period; The failure probability of the mining equipment is determined based on the mining equipment operating parameters in the first time period.

7. The mining area information management method according to claim 2, characterized in that: The process of determining the target loss function according to the influence weight of the historical operating parameters of the equipment in the mining area on the fault result includes: The target loss function of the autoregressive integral moving average model is determined based on the time impact weight and the impact weight of each historical operating parameter on the fault result.

8. A mining area information management system, characterized in that: include: A failure probability determination module is used to input the target data into a target autoregressive integral moving average model to obtain the failure probability of the mining equipment; The target data is the operating parameters of the equipment in the mining area. The target autoregressive integrated moving average model is obtained by training the autoregressive integrated moving average model based on the historical operating parameters of the equipment in the mining area and the target loss function. The target loss function is determined based on the weight of the impact of the historical operating parameters of the equipment in the mining area on the fault results. The fault warning module is used to send warning information to the target equipment based on the failure probability of the mining equipment.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images