Overall health state assessment method, device and equipment of mining equipment and medium

Abstract

The invention provides an overall health state assessment method and device for mining equipment, equipment and a medium, and relates to the technical field of deep learning. The method comprises the following steps: acquiring operation data of mining equipment based on a sensor network; performing preprocessing and feature extraction on the operation data to obtain a first monitoring feature; performing data dimension reduction on the first monitoring feature to determine a second monitoring feature; and on the basis of the second monitoring feature and a pre-constructed fault prediction model, the fault condition of the mining equipment is predicted to obtain a prediction result, and the prediction result comprises a fault probability and prediction time. By performing overall health state evaluation on the mining equipment, potential faults of the equipment can be found in advance, and the possibility and time of fault occurrence can be predicted. Therefore, maintenance personnel can take corresponding prevention measures, the problems of production interruption, safety accidents and the like caused by equipment faults are avoided, and the reliability and the safety of the equipment are improved.

Description

Technical Field

[0001] The present application relates to the field of deep learning technology, and in particular to a method, device, equipment and medium for evaluating the overall health status of mining equipment. Background Art

[0002] With the development and modernization of the mining industry, the scale and complexity of mining equipment are also increasing. At the same time, due to long-term harsh working environment, high-load operation and lack of timely maintenance, mining equipment generally suffers from problems such as wear, failure and failure. This not only brings huge safety risks to mining production, but also leads to a decrease in production efficiency and an increase in costs.

[0003] Therefore, in order to timely discover and solve problems with mining equipment and ensure the safety and efficient operation of mines, the overall health status assessment of mining equipment came into being. Through multi-dimensional and full-cycle monitoring and analysis of equipment, accurate and timely assessment and prediction of the health status of equipment can be achieved, providing a scientific basis for equipment maintenance and production planning. In related technologies, there are some shortcomings in the overall health status assessment of mining equipment. First: Difficulty in data acquisition: To conduct an overall health status assessment, a large amount of equipment operation data and sensor information needs to be collected. However, some equipment may lack a complete data acquisition system, or the data acquisition process is not completely reliable, which leads to difficulties and inaccuracies in data acquisition. Second: Difficulty in feature extraction and selection: Extracting and selecting meaningful features from a large amount of equipment data is very important for evaluating the health status of equipment. However, current technology still has challenges in feature extraction and selection, and more research is needed to determine the most effective feature set and algorithm. Summary of the invention

[0004] The present application provides a method, device, equipment and storage medium for evaluating the overall health status of mining equipment, aiming to solve at least one of the technical problems in the related art to a certain extent.

[0005] In a first aspect, the present application provides a method for evaluating the overall health status of mining equipment, comprising:

[0006] Based on the sensor network, obtain the operation data of mining equipment;

[0007] Preprocessing and feature extraction are performed on the operation data to obtain a first monitoring feature;

[0008] Performing data dimension reduction on the first monitoring feature to determine a second monitoring feature;

[0009] Based on the second monitoring feature and the pre-built fault prediction model, the fault condition of the mining equipment is predicted to obtain a prediction result, which includes a fault probability and a prediction time.

[0010] In a second aspect, the present application provides a device for evaluating the overall health status of mining equipment, comprising:

[0011] A first acquisition module is used to acquire operation data of mining equipment based on a sensor network;

[0012] A second acquisition module, used for preprocessing and feature extraction of the operation data to obtain a first monitoring feature;

[0013] A determination module, configured to perform data dimension reduction on the first monitoring feature to determine a second monitoring feature;

[0014] The prediction module is used to predict the fault condition of the mining equipment based on the second monitoring feature and a pre-built fault prediction model to obtain a prediction result, wherein the prediction result includes a fault probability and a prediction time.

[0015] In a third aspect, the present application provides an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute instructions to implement a method for assessing the overall health status of mining equipment.

[0016] In a fourth aspect, the present application provides a computer-readable storage medium. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute a method for assessing the overall health status of mining equipment.

[0017] In a fifth aspect, the present application provides a computer program product, including a computer program, wherein the computer program is executed by a processor to perform a method for assessing the overall health status of mining equipment.

[0018] The overall health status assessment method and device for mining equipment provided in the present application first obtains the operating data of the mining equipment based on the sensor network, then pre-processes and extracts features of the operating data to obtain the first monitoring feature, then performs data dimension reduction on the first monitoring feature to determine the second monitoring feature, and finally predicts the failure of the mining equipment based on the second monitoring feature and a pre-built fault prediction model to obtain a prediction result, which includes the failure probability and prediction time. By conducting an overall health status assessment of mining equipment, potential failures of the equipment can be discovered in advance, and the possibility and time of failure can be predicted. This enables maintenance personnel to take appropriate preventive measures to avoid production interruptions, safety accidents and other problems caused by equipment failures, and improve the reliability and safety of the equipment.

[0019] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0021] Figure 1 It is a flowchart of a method for evaluating the overall health status of mining equipment according to the first embodiment of the present application;

[0022] Figure 2 is a block diagram of a device for evaluating the overall health status of mining equipment according to the present application;

[0023] Figure 3 A block diagram of an exemplary electronic device suitable for implementing the embodiments of the present application is shown.

[0024] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0025] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be construed as limiting the present application. On the contrary, the embodiments of the present application include all changes, modifications and equivalents that fall within the spirit and connotation of the appended claims.

[0026] It should be noted that the executor of the overall health status assessment method of mining equipment in this embodiment may be an overall health status assessment device for mining equipment, which may be implemented by software and / or hardware, and may be configured in an electronic device.

[0027] Existing technologies for assessing the overall health of mining equipment have some shortcomings. The following are some of the main shortcomings:

[0028] 1. Difficulty in data acquisition: To conduct an overall health status assessment, a large amount of equipment operation data and sensor information needs to be collected. However, some equipment may lack a complete data acquisition system, or the data collection process is not completely reliable, which leads to difficulties and inaccuracies in data acquisition.

[0029] 2. Difficulty in feature extraction and selection: Extracting and selecting meaningful features from a large amount of device data is very important for evaluating the health status of the device. However, current technology still has challenges in feature extraction and selection, and more research is needed to determine the most effective feature sets and algorithms.

[0030] 3. Limited model accuracy and reliability: Although existing assessment models and algorithms can estimate the health status of mining equipment, their accuracy and reliability are limited. Especially when faced with complex working conditions and equipment failure modes, existing technologies may have large errors and misjudgments.

[0031] 4. Maintenance decisions are not timely enough: Existing mining equipment health status assessment technologies mainly rely on offline analysis and periodic maintenance plans, which may not respond to equipment failures in a timely manner and may result in long production downtime.

[0032] Figure 1 is a flow chart of a method for evaluating the overall health status of mining equipment according to the first embodiment of the present application, such as Figure 1 As shown, the method includes:

[0033] S101: Acquire operation data of mining equipment based on the sensor network.

[0034] By installing sensors on mining equipment, various operating parameters of the equipment, such as vibration, temperature, pressure and other data, can be monitored in real time. The specific steps are as follows:

[0035] First, according to the type of mining equipment and the parameters to be monitored, suitable sensors can be selected. Commonly used sensors include accelerometers, temperature sensors, pressure sensors, etc. The selected sensors are installed in the key parts of the equipment to obtain accurate operating data. After that, the data collected by the sensors can be used to transfer the data to the database or cloud platform using data acquisition equipment. Wired or wireless transmission methods can be used, such as Ethernet, Wi-Fi, Bluetooth, etc. Ensure the reliability and real-time performance of data transmission, and then store the transmitted data in the database or cloud platform to establish a corresponding data storage model. Relational databases or distributed storage systems such as MySQL and Hadoop can be used. At the same time, the data is preprocessed and cleaned to remove outliers and noise interference to ensure the quality and accuracy of the data. After that, meaningful features can be extracted based on the stored large-scale equipment data through technical means such as data mining and machine learning. Statistical analysis, frequency domain analysis, time-frequency analysis and other methods can be used to identify abnormal states and trend changes of equipment. At the same time, combined with the operating rules and professional knowledge of the equipment, data analysis and fault diagnosis are carried out to provide a basis for equipment maintenance.

[0036] Furthermore, the analysis results can be displayed in a visual way, providing users with intuitive interfaces and charts. Through the real-time alarm system, abnormal warning information can be sent to relevant personnel in a timely manner so that appropriate measures can be taken to avoid equipment failure and damage.

[0037] Through the above steps, a real-time monitoring system for mining equipment can be established, and large-scale equipment data can be used for feature extraction and analysis to provide support for the health status assessment and maintenance of mining equipment. This can timely discover potential fault hazards, improve equipment reliability and production efficiency, and reduce production costs and safety risks.

[0038] S102: Preprocessing and feature extraction are performed on the operation data to obtain a first monitoring feature.

[0039] Optionally, the operating data may be first verified, filtered and denoised, and then the operating data may be subjected to signal processing, spectrum analysis, and statistical modeling to obtain a first monitoring feature, which includes frequency domain features, time domain features, and statistical features.

[0040] It should be noted that before extracting features from the collected data, the data must first be verified, filtered, and denoised to ensure data quality and reliability. The verification stage can check the integrity, consistency, and outliers of the data, and remove data that does not meet the requirements. Filtering and denoising can use common filter technologies, such as low-pass filtering and median filtering, to eliminate high-frequency noise and interference.

[0041] Specifically, during the feature extraction process, signal processing technology can be used to analyze the operating data. By applying time-frequency analysis methods, such as short-time Fourier transform (STFT) and wavelet transform (WT), the signal can be converted into a representation in the time domain and frequency domain. Spectral analysis can reveal the frequency components and energy distribution of the signal, and help determine the frequency characteristics and abnormal spectrum of the equipment.

[0042] Specifically, based on the preprocessed operating data, statistical modeling methods such as Gaussian mixture model (GMM) and support vector machine (SVM) can be applied to model and identify the health status of the equipment. At the same time, by calculating a series of characteristic indicators, such as time domain characteristics (mean, variance, peak factor, etc.), frequency domain characteristics (spectral energy, spectrum peak, etc.) and statistical characteristics (skewness, kurtosis, etc.), the operating status and abnormal conditions of the equipment can be described from different angles.

[0043] It can be understood that through steps such as data cleaning and preprocessing, signal processing, spectrum analysis and statistical modeling, the first monitoring characteristics including frequency domain characteristics, time domain characteristics and statistical characteristics can be obtained. These characteristics provide an important basis for equipment health status monitoring and fault diagnosis.

[0044] S103: Perform data dimension reduction on the first monitoring feature to determine the second monitoring feature.

[0045] Optionally, principal component analysis or ridge regression may be performed on the first monitoring feature to reduce the data dimension of the first monitoring feature to obtain the second monitoring feature.

[0046] Specifically, the first monitoring feature can be subjected to principal component analysis (PCA) or ridge regression, which are commonly used dimensionality reduction methods, which can help further extract the more critical second monitoring feature. Below I will briefly introduce the principles and functions of these two methods. Among them, principal component analysis (PCA), PCA is a commonly used unsupervised dimensionality reduction technique that converts the original high-dimensional data into a set of new low-dimensional features through linear transformation. These new features are called principal components. The goal of PCA is to minimize the correlation between the original features while maintaining the maximum data variance. Through PCA, the original data can be projected into the principal component space to achieve dimensionality reduction from high-dimensional space to low-dimensional space, while retaining the most important information in the data.

[0047] Among them, Ridge Regression is an improved method of linear regression, which is often used to solve the problem of multicollinearity in regression analysis. Compared with ordinary least squares, ridge regression adds a regularization term to the regression coefficient, making the obtained regression coefficient more stable. By controlling the size of the regularization parameter, a trade-off can be made between the degree of model fit and the stability of the regression coefficient to avoid overfitting problems. Ridge regression can also be used for feature selection and dimensionality reduction, by adjusting the feature weights to reduce the dimension of the data.

[0048] When performing principal component analysis or ridge regression, the first monitoring feature can be used as input data and applied to the corresponding algorithm. The second monitoring feature can be obtained by calculating the principal component or regression coefficient. These features have lower dimensions and retain the most important information in the original features. This can reduce the number of features, simplify the complexity of data analysis and model building, and improve the interpretability and predictive power of the features.

[0049] It should be noted that before performing principal component analysis or ridge regression, the data may need to be standardized or normalized to ensure that the scales of different features are consistent. In addition, the selection of appropriate dimensionality reduction methods and parameter settings also needs to be adjusted and optimized according to the specific problems and data characteristics.

[0050] S104: Based on the second monitoring feature and the pre-built fault prediction model, predict the fault condition of the mining equipment to obtain a prediction result, which includes a fault probability and a prediction time.

[0051] Specifically, historical mining equipment data and feature data can be obtained first, and then the historical mining equipment data and feature data can be cleaned, feature extracted and normalized to obtain sample data. The sample data can then be divided into a training data set and a test data set. The long short-term memory network model or the random forest model can then be trained based on the training data set to obtain a fault prediction model. Finally, the prediction accuracy and error rate of the fault prediction model can be verified based on the test data set until the prediction accuracy and error rate meet the preset conditions, and the fault prediction model is constructed.

[0052] It should be noted that when using historical data to build a fault prediction model, it is necessary to pay attention to the timestamp information of the data. If the historical data is not in the same time range as the test data set or real-time data, it is necessary to consider issues such as time drift, which may affect the generalization ability and prediction accuracy of the model. Therefore, when performing fault prediction, the time of historical data and real-time data should be kept as close as possible to avoid the time difference from having a significant impact on the prediction results.

[0053] Specifically, we can first obtain historical mining equipment data and feature data, then clean the historical data, process missing values, outliers, etc., then ensure the integrity and reliability of the data, perform feature extraction, and extract features related to fault prediction from the original data according to the needs of the problem. Statistical features, frequency domain features, time domain features, etc. can be used, and then data normalization can be performed to map the value ranges of different features to a unified interval to eliminate the impact of different dimensions. Common normalization methods include minimum-maximum normalization and standardization. Finally, the processed data can be divided into training data sets and test data sets. Usually, it can be divided according to a certain ratio (such as 70% training set and 30% test set). Based on the training data set, select a suitable model for training. You can try to use the long short-term memory network model (LSTM) or the random forest model, etc., and choose according to the characteristics of the data and the advantages of the algorithm. During the training process, it is necessary to adjust the hyperparameters of the model, such as the learning rate, the number of iterations, etc., to obtain better performance. Use the trained model to predict the test data set and evaluate the prediction accuracy and error rate. Common evaluation indicators such as accuracy, precision, recall, F1-score, etc. can be used. If the prediction result does not meet the preset conditions, you can try to adjust the model structure, feature extraction method or sampling strategy, etc. to optimize it. Repeat the above steps until the preset prediction accuracy and error rate are achieved, and the fault prediction model is built.

[0054] It should be noted that the selection of models and parameter adjustments need to be based on specific problems and data characteristics, and multiple experiments and verifications may be required to find the optimal model and parameter combination. In addition, in practical applications, it is also necessary to monitor the performance and stability of the model and update and optimize the model in a timely manner.

[0055] Optionally, the optimized maintenance strategy for mining equipment can be updated based on the prediction results.

[0056] Among them, the prediction results can be used to provide optimized maintenance strategies for mining equipment. The following maintenance strategies can be formulated based on the prediction results:

[0057] Fault prevention: For equipment with frequent failures, you can try to avoid the occurrence of failures by increasing the maintenance frequency, regularly replacing wearing parts, and other measures. Fault handling: For equipment with a high failure frequency, you can establish an effective fault handling mechanism to quickly respond to and resolve failures. Maintenance plan: According to the equipment failure prediction results, make maintenance plans in advance, reasonably dispatch maintenance personnel and maintenance resources, and minimize downtime and maintenance costs. Equipment update: For old equipment, you can consider equipment updates based on its failure prediction results to improve the reliability and stability of the equipment. Combined with the probability of equipment failure and economic factors, use optimization algorithms, such as genetic algorithms or linear programming, to formulate the optimal maintenance decision strategy, including decisions on maintenance plans, parts procurement, and inventory management.

[0058] By formulating and implementing the above maintenance strategies, the reliability and stability of equipment can be effectively improved, and the impact of equipment failure can be reduced. At the same time, the service life of equipment can be increased and maintenance costs can be reduced.

[0059] This embodiment solves the following technical problems:

[0060] 1. Predict equipment failure: By evaluating the overall health status of the equipment, possible equipment failures can be predicted in advance, so that appropriate repair and maintenance measures can be taken to avoid the impact of equipment failures on production.

[0061] 2. Optimize maintenance plan: By evaluating the health status of equipment, you can determine which equipment needs repair and maintenance and when to perform the repairs, thereby optimizing the maintenance plan and improving equipment availability and production efficiency.

[0062] 3. Improve safety: By evaluating the overall health status of the equipment, potential safety hazards of the equipment can be discovered in a timely manner, and appropriate measures can be taken to repair them, thereby improving the safety of the mine.

[0063] 4. Cost savings: By evaluating the overall health status of the equipment, problems with the equipment can be discovered in a timely manner, avoiding production downtime and increased maintenance costs caused by equipment failure, thereby saving costs.

[0064] The overall health status assessment method and device of mining equipment provided in the present application first obtains the operation data of mining equipment based on the sensor network, then pre-processes and extracts features of the operation data to obtain the first monitoring feature, then performs data dimension reduction on the first monitoring feature to determine the second monitoring feature, and finally predicts the fault condition of the mining equipment based on the second monitoring feature and the pre-built fault prediction model to obtain the prediction result, which includes the fault probability and the prediction time. By evaluating the overall health status of mining equipment, potential faults of the equipment can be discovered in advance, and the possibility and time of the fault can be predicted. This enables maintenance personnel to take corresponding preventive measures to avoid production interruptions, safety accidents and other problems caused by equipment failures, and improve the reliability and safety of the equipment. It is possible to reasonably formulate maintenance plans and decisions, reduce unnecessary maintenance and overhaul, and thus optimize the utilization of maintenance resources. This helps to reduce maintenance costs and improve the efficiency and accuracy of maintenance. Maintenance and repair can be carried out before equipment failure, avoiding unexpected downtime and production interruption. This helps to improve production efficiency, reduce downtime, and maximize the continuity and stability of mine production. Through data processing and analysis, as well as the establishment of fault prediction models, valuable information can be extracted from a large amount of equipment data to provide data support for decision-making. This helps to optimize the decision-making process and improve the accuracy and effectiveness of decision-making.

[0065] Figure 2 is a block diagram of a device for evaluating the overall health status of mining equipment according to the present application, such as Figure 2 As shown, the overall health status assessment device 200 of mining equipment includes:

[0066] A first acquisition module 210 is used to acquire operation data of mining equipment based on a sensor network;

[0067] A second acquisition module 220, configured to preprocess and extract features from the operation data to obtain a first monitoring feature;

[0068] A determination module 230, configured to perform data dimension reduction on the first monitoring feature to determine a second monitoring feature;

[0069] The prediction module 240 is used to predict the fault condition of the mining equipment based on the second monitoring feature and a pre-built fault prediction model to obtain a prediction result, wherein the prediction result includes a fault probability and a prediction time.

[0070] Optionally, the determining module is specifically used to:

[0071] Perform principal component analysis or ridge regression on the first monitoring feature to reduce the data dimension of the first monitoring feature to obtain the second monitoring feature.

[0072] Optionally, the prediction module is further used to:

[0073] Obtain historical mining equipment data and feature data;

[0074] Performing data cleaning, feature extraction and data normalization processing on the historical mining equipment data and feature data to obtain sample data;

[0075] Dividing the sample data into a training data set and a test data set;

[0076] Training a long short-term memory network model or a random forest model based on the training data set to obtain a fault prediction model;

[0077] The prediction accuracy and error rate of the fault prediction model are verified based on the test data set until the prediction accuracy and error rate meet the preset conditions, and then the construction of the fault prediction model is completed.

[0078] Optionally, the prediction module is further used to:

[0079] According to the prediction results, the optimization maintenance strategy of the mining equipment is updated.

[0080] Optionally, the second acquisition module is specifically used to:

[0081] Verifying, filtering and denoising the operating data;

[0082] The operation data is subjected to signal processing, spectrum analysis, and statistical modeling to obtain a first monitoring feature, wherein the first monitoring feature includes a frequency domain feature, a time domain feature, and a statistical feature.

[0083] According to an embodiment of the present application, the present application also provides an electronic device, a readable storage medium and a computer program product.

[0084] Figure 3 6 is a block diagram of an electronic device according to the present application. For example, the electronic device 600 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0085] Reference Figure 3, the electronic device 600 may include one or more of the following components: a processing component 602 , a memory 604 , a power component 606 , a multimedia component 608 , an audio component 610 , an input / output (I / O) interface 612 , a sensor component 614 , and a communication component 616 .

[0086] The processing component 602 generally controls the overall operation of the electronic device 600, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 602 may include one or more processors 620 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 602 may include one or more modules to facilitate the interaction between the processing component 602 and other components. For example, the processing component 602 may include a multimedia module to facilitate the interaction between the multimedia component 608 and the processing component 602.

[0087] The memory 604 is configured to store various types of data to support operations on the electronic device 600. Examples of such data include instructions for any application or method operating on the electronic device 600, contact data, phone book data, messages, pictures, videos, etc. The memory 604 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0088] The power supply component 606 provides power to the various components of the electronic device 600. The power supply component 606 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 600.

[0089] The multimedia component 608 includes a touch screen that provides an output interface between the electronic device 600 and the user. In some embodiments, the touch screen may include a liquid crystal display (LCD) and a touch panel (TP). The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor can not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 608 includes a front camera and / or a rear camera. When the electronic device 600 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have a focal length and optical zoom capability.

[0090] The audio component 610 is configured to output and / or input audio signals. For example, the audio component 610 includes a microphone (MIC), and when the electronic device 600 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 604 or sent via the communication component 616.

[0091] In some embodiments, the audio component 610 also includes a speaker for outputting audio signals.

[0092] I / O interface 612 provides an interface between processing component 602 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0093] The sensor assembly 614 includes one or more sensors for providing various aspects of status assessment for the electronic device 600. For example, the sensor assembly 614 can detect the open / closed state of the electronic device 600, the relative positioning of components, such as the display and keypad of the electronic device 600, and the sensor assembly 614 can also detect the position change of the electronic device 600 or a component of the electronic device 600, the presence or absence of user contact with the electronic device 600, the orientation or acceleration / deceleration of the electronic device 600, and the temperature change of the electronic device 600. The sensor assembly 614 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 614 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 614 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0094] The communication component 616 is configured to facilitate wired or wireless communication between the electronic device 600 and other devices. The electronic device 600 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 616 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 616 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0095] In an exemplary embodiment, the electronic device 600 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above-mentioned method for assessing the overall health status of mining equipment.

[0096] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 604 including instructions, and the above instructions can be executed by the processor 920 of the electronic device 600 to complete the above method. Alternatively, the computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0097] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0098] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for evaluating the overall health status of mining equipment, characterized in that: include: Based on the sensor network, obtain the operation data of mining equipment; Preprocessing and feature extraction are performed on the operation data to obtain a first monitoring feature; Performing data dimension reduction on the first monitoring feature to determine a second monitoring feature; Based on the second monitoring feature and the pre-built fault prediction model, the fault condition of the mining equipment is predicted to obtain a prediction result, which includes a fault probability and a prediction time.

2. The method according to claim 1, characterized in that The performing data dimension reduction on the first monitoring feature to determine the second monitoring feature includes: Perform principal component analysis or ridge regression on the first monitoring feature to reduce the data dimension of the first monitoring feature to obtain the second monitoring feature.

3. The method according to claim 1, characterized in that Before predicting the fault condition of the mining equipment based on the second monitoring feature and the pre-built fault prediction model to obtain a prediction result, the method further includes: Obtain historical mining equipment data and feature data; Performing data cleaning, feature extraction and data normalization processing on the historical mining equipment data and feature data to obtain sample data; Dividing the sample data into a training data set and a test data set; Training a long short-term memory network model or a random forest model based on the training data set to obtain a fault prediction model; The prediction accuracy and error rate of the fault prediction model are verified based on the test data set until the prediction accuracy and error rate meet the preset conditions, and then the construction of the fault prediction model is completed.

4. The method according to claim 1, characterized in that: After predicting the fault condition of the mining equipment based on the second monitoring feature and the pre-built fault prediction model to obtain a prediction result, the method further includes: According to the prediction results, the optimization maintenance strategy of the mining equipment is updated.

5. The method according to claim 1, characterized in that The preprocessing and feature extraction of the operation data to obtain a first monitoring feature includes: Verifying, filtering and denoising the operating data; The operation data is subjected to signal processing, spectrum analysis, and statistical modeling to obtain a first monitoring feature, wherein the first monitoring feature includes a frequency domain feature, a time domain feature, and a statistical feature.

6. A device for evaluating the overall health status of mining equipment, characterized in that: include: A first acquisition module is used to acquire operation data of mining equipment based on a sensor network; A second acquisition module, used for preprocessing and feature extraction of the operation data to obtain a first monitoring feature; A determination module, configured to perform data dimension reduction on the first monitoring feature to determine a second monitoring feature; The prediction module is used to predict the fault condition of the mining equipment based on the second monitoring feature and a pre-built fault prediction model to obtain a prediction result, wherein the prediction result includes a fault probability and a prediction time.

7. The device according to claim 6, characterized in that in, The determining module is specifically used for: Performing principal component analysis or ridge regression on the first monitoring feature to reduce the data dimension of the first monitoring feature to obtain the second monitoring feature, Wherein, the prediction module is also used for: Obtain historical mining equipment data and feature data; Performing data cleaning, feature extraction and data normalization processing on the historical mining equipment data and feature data to obtain sample data; Dividing the sample data into a training data set and a test data set; Training a long short-term memory network model or a random forest model based on the training data set to obtain a fault prediction model; The prediction accuracy and error rate of the fault prediction model are verified based on the test data set until the prediction accuracy and error rate meet the preset conditions, and then the construction of the fault prediction model is completed. and updating the optimized maintenance strategy of the mining equipment according to the prediction results, Wherein, the second acquisition module is specifically used for: Verifying, filtering and denoising the operating data; The operation data is subjected to signal processing, spectrum analysis, and statistical modeling to obtain a first monitoring feature, wherein the first monitoring feature includes a frequency domain feature, a time domain feature, and a statistical feature.

8. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 5 when executed by a processor.

10. A computer program product, characterized in that The invention comprises a computer program, which is used to implement the method according to any one of claims 1 to 5 when the computer program is executed by a processor.

Images