Intelligent monitoring method and device for battery installation stability of pure electric mining wide-body vehicle and computer equipment

Abstract

The invention relates to an intelligent monitoring method and device for battery installation stability of a pure electric mining wide-body vehicle and computer equipment. The method comprises the following steps: acquiring current battery stability monitoring data transmitted by each sensor on the pure electric mining wide-body vehicle through an anti-interference data acquisition strategy; based on the current battery stability monitoring data, through a multi-scale feature fusion module, current fusion monitoring features of the pure electric mining wide-body vehicle are generated; and on the basis of the current fusion monitoring characteristics, current battery installation stability early warning information of the pure electric mining wide-body vehicle is identified through a network dynamic early warning strategy. By adopting the method, the battery installation stability monitoring efficiency of the pure electric mining wide-body vehicle can be improved.

Description

Technical Field

[0001] This application relates to the field of monitoring technology for new energy mining equipment, and in particular to an intelligent monitoring method, device and computer equipment for monitoring the battery installation stability of a pure electric wide-body mining vehicle. Background Technology

[0002] In the field of pure electric wide-body mining vehicles, battery installation stability is directly related to safety hazards such as cell expansion and thermal runaway. If the battery shifts or experiences poor contact during operation, it may lead to short circuits, leakage, or overheating, potentially causing fire or explosion. Mining vehicles often operate under bumpy, high-load conditions; if the battery fixing structure is loose, vibration can easily cause internal cell deformation or separator damage, further triggering thermal runaway. Therefore, improving battery installation stability monitoring is a current research focus.

[0003] Existing solutions mostly employ a mechanical fixing and parameter monitoring mode combining bolt fastening with a single sensor (such as a strain gauge or accelerometer), or rely on periodic manual inspections and static torque testing. These methods struggle to address the multi-physical coupling effects under complex mining conditions. When the mining truck is in motion, the battery installation system is subjected to the combined effects of vertical vibration, lateral impact, temperature cycling, and bolt preload decay. Traditional single-parameter models cannot decouple the cross-influence of these factors, resulting in a large monitoring error rate. Furthermore, the harsh environment of the mining area, including high levels of dust and electromagnetic interference, distorts sensor signals. Offline detection modes cannot provide timely warnings of sudden loosening faults during operation, and the delay from fault occurrence to manual detection is often too long, leading to low efficiency in monitoring the battery installation stability of pure electric wide-body mining trucks. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium, and computer program product for intelligent monitoring of battery installation stability in pure electric wide-body mining vehicles, addressing the aforementioned technical problems.

[0005] Firstly, this application provides an intelligent monitoring method for the battery installation stability of a pure electric wide-body mining vehicle, including:

[0006] By employing an anti-interference data acquisition strategy, current battery stability monitoring data transmitted by various sensors on the pure electric mining wide-body vehicle is collected.

[0007] Based on the current battery stability monitoring data, the current fused monitoring features of the pure electric mining wide-body vehicle are generated through a multi-scale feature fusion module.

[0008] Based on the current integrated monitoring characteristics, a network dynamic early warning strategy is used to identify the current battery installation stability warning information of the pure electric mining wide-body vehicle.

[0009] Optionally, the step of collecting current battery stability monitoring data transmitted by various sensors on the pure electric mining wide-body vehicle through an anti-interference data acquisition strategy includes:

[0010] The sensor data transmitted by each sensor is acquired, and the data of each sensor is adjusted by the vibration signal conditioning module to obtain optimized sensor data.

[0011] The optimized sensor data is processed by noise optimization to obtain denoised sensor data, and wavelet packet decomposition is performed on the denoised sensor data to obtain the current battery stability monitoring data transmitted by each sensor.

[0012] Optionally, before generating the current fused monitoring features of the pure electric mining wide-body vehicle based on the current battery stability monitoring data through the multi-scale feature fusion module, the method further includes:

[0013] The current battery stability monitoring data are spatiotemporally aligned to obtain the synchronous monitoring data.

[0014] For each of the synchronous monitoring data, a feature extraction strategy is used to extract the time-domain features, frequency-domain features, and time-frequency-domain features of the pure electric mining wide-body vehicle.

[0015] Optionally, the step of generating the current fused monitoring features of the pure electric mining wide-body vehicle based on the current battery stability monitoring data through a multi-scale feature fusion module includes:

[0016] Based on the time-domain features, frequency-domain features, and time-frequency-domain features, a multi-dimensional feature vector is constructed.

[0017] The multidimensional feature vector is subjected to feature fusion processing through a weighted fusion strategy to obtain the current fused monitoring features of the pure electric mining wide-body vehicle.

[0018] Optionally, the step of identifying the current battery installation stability warning information of the pure electric mining wide-body vehicle based on the current fusion monitoring characteristics and through a network dynamic early warning strategy includes:

[0019] Based on the current fusion monitoring characteristics, the attenuation process features of the pure electric mining wide-body vehicle are identified through a two-way time-series feature modeling strategy.

[0020] Based on the characteristics of each of the aforementioned attenuation processes, the installation correlation index data of the pure electric mining wide-body vehicle are identified through a genetic optimization network.

[0021] Based on the installation-related index data, the current battery installation stability warning information of the pure electric mining wide-body vehicle is identified.

[0022] Optionally, the step of identifying the current battery installation stability warning information of the pure electric mining wide-body vehicle based on the installation-related index data includes:

[0023] The installation-related index data are weighted according to preset index weight values ​​to obtain installation status index data.

[0024] Based on the installation status index data, the current battery warning level of the pure electric mining wide-body vehicle is identified, and based on the current battery warning level, the current warning content and the current warning handling strategy of the pure electric mining wide-body vehicle are queried in the warning database.

[0025] The current warning content and the current warning processing strategy of the pure electric mining wide-body vehicle are used as the current battery installation stability warning information of the pure electric mining wide-body vehicle.

[0026] Secondly, this application also provides an intelligent monitoring device for the battery installation stability of a pure electric wide-body mining vehicle, comprising:

[0027] The data acquisition module is used to acquire current battery stability monitoring data transmitted by various sensors on the pure electric mining wide-body vehicle through an anti-interference data acquisition strategy.

[0028] The generation module is used to generate the current fused monitoring features of the pure electric mining wide-body vehicle based on the current battery stability monitoring data and through the multi-scale feature fusion module.

[0029] The identification module is used to identify the current battery installation stability warning information of the pure electric mining wide-body vehicle based on the current fusion monitoring characteristics and through a network dynamic early warning strategy.

[0030] Optionally, the acquisition module is specifically used for:

[0031] The sensor data transmitted by each sensor is acquired, and the data of each sensor is adjusted by the vibration signal conditioning module to obtain optimized sensor data.

[0032] The optimized sensor data is processed by noise optimization to obtain denoised sensor data, and wavelet packet decomposition is performed on the denoised sensor data to obtain the current battery stability monitoring data transmitted by each sensor.

[0033] Optionally, the device further includes:

[0034] The synchronization module is used to perform spatiotemporal alignment processing on the current battery stability monitoring data to obtain the synchronization monitoring data.

[0035] The extraction module is used to extract the time-domain features, frequency-domain features, and time-frequency-domain features of the pure electric mining wide-body vehicle from the synchronous monitoring data through a feature extraction strategy.

[0036] Optionally, the generation module is specifically used for:

[0037] Based on the time-domain features, frequency-domain features, and time-frequency-domain features, a multi-dimensional feature vector is constructed.

[0038] The multidimensional feature vector is subjected to feature fusion processing through a weighted fusion strategy to obtain the current fused monitoring features of the pure electric mining wide-body vehicle.

[0039] Optionally, the identification module is specifically used for:

[0040] Based on the current fusion monitoring characteristics, the attenuation process features of the pure electric mining wide-body vehicle are identified through a two-way time-series feature modeling strategy.

[0041] Based on the characteristics of each of the aforementioned attenuation processes, the installation correlation index data of the pure electric mining wide-body vehicle are identified through a genetic optimization network.

[0042] Based on the installation-related index data, the current battery installation stability warning information of the pure electric mining wide-body vehicle is identified.

[0043] Optionally, the identification module is specifically used for:

[0044] The installation-related index data are weighted according to preset index weight values ​​to obtain installation status index data.

[0045] Based on the installation status index data, the current battery warning level of the pure electric mining wide-body vehicle is identified, and based on the current battery warning level, the current warning content and the current warning handling strategy of the pure electric mining wide-body vehicle are queried in the warning database.

[0046] The current warning content and the current warning processing strategy of the pure electric mining wide-body vehicle are used as the current battery installation stability warning information of the pure electric mining wide-body vehicle.

[0047] Thirdly, this application provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in any one of the first aspects.

[0048] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0049] Fifthly, this application provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0050] The aforementioned intelligent monitoring method, device, and computer equipment for battery installation stability of pure electric mining wide-body trucks collect current battery stability monitoring data transmitted from various sensors on the pure electric mining wide-body truck through an anti-interference data acquisition strategy. Based on the current battery stability monitoring data, a multi-scale feature fusion module generates current fused monitoring features of the pure electric mining wide-body truck. Based on the current fused monitoring features, a network dynamic early warning strategy identifies current battery installation stability warning information of the pure electric mining wide-body truck. This solution, through real-time integration of an anti-interference data acquisition strategy and multi-sensor battery installation stability monitoring, ensures the comprehensiveness and integrity of the collected sensor data. Furthermore, the multi-sensor data, through multi-scale feature fusion, provides multi-angle feedback of monitoring information from different levels of the pure electric mining wide-body truck, effectively eliminating monitoring errors in battery installation stability and ensuring the timely acquisition of monitoring information. Finally, this solution utilizes a network dynamic early warning strategy to efficiently assess the collected fusion monitoring features, thereby ensuring the timeliness of fusion information analysis and evaluating fusion monitoring features from multiple perspectives. This comprehensively improves the monitoring efficiency of battery installation stability for pure electric mining wide-body vehicles. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 This is a flowchart illustrating an intelligent monitoring method for the battery installation stability of a pure electric wide-body mining vehicle in one embodiment.

[0053] Figure 2This is a flowchart illustrating an example of intelligent monitoring of battery installation stability in a pure electric wide-body mining vehicle in one embodiment.

[0054] Figure 3 This is a structural block diagram of an intelligent monitoring device for battery stability installation in a pure electric wide-body mining vehicle, as shown in one embodiment.

[0055] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0057] The intelligent monitoring method for battery installation stability of pure electric mining wide-body trucks provided in this application embodiment can be applied to an intelligent monitoring system for battery installation stability of pure electric mining wide-body trucks. This system can be applied to a terminal, which can be, but is not limited to, various personal computers, laptops, mid-range computers, etc. The terminal monitors battery installation stability through real-time integrated anti-interference data acquisition strategies and multi-sensor monitoring. This ensures the comprehensiveness and integrity of the collected sensor data. Furthermore, the multi-sensor data, through multi-scale feature fusion, provides multi-angle feedback of monitoring information of the pure electric mining wide-body truck at different levels, effectively eliminating monitoring errors in battery installation stability and ensuring timely acquisition of monitoring information. Finally, this solution uses a network dynamic early warning strategy to efficiently assess the collected fused monitoring features, ensuring both timely analysis of fused information and multi-angle evaluation of fused monitoring features, thereby comprehensively improving the monitoring efficiency of battery installation stability of pure electric mining wide-body trucks.

[0058] In one exemplary embodiment, such as Figure 1 As shown, a method for intelligent monitoring of battery installation stability in a pure electric wide-body mining vehicle is provided. Taking the application of this method to a terminal as an example, the method includes the following steps S101 to S103. Wherein:

[0059] Step S101: Using an anti-interference data acquisition strategy, collect the current battery stability monitoring data transmitted by each sensor on the pure electric mining wide-body vehicle.

[0060] In this embodiment, the terminal, through the FPGA module in the ARM (Acorn RISC Machine) + FPGA (Field Programmable Gate Array) heterogeneous platform designed by the staff of this solution, collects sensor data transmitted from sensors at various locations on the pure electric mining wide-body vehicle in real time, and processes the data to obtain the current battery stability monitoring data transmitted by each sensor. These sensors include, but are not limited to, vibration sensors, strain sensors, preload sensors, temperature sensors, and dust sensors. The FPGA module adds nanosecond-level timestamps to the multi-source data such as vibration and strain, achieves spatiotemporal alignment through extended Kalman filtering, and performs signal denoising using wavelet packet decomposition and CNN, thereby obtaining the current battery stability monitoring data transmitted by each sensor. The specific acquisition process will be described in detail later.

[0061] Step S102: Based on the current battery stability monitoring data, the current fused monitoring features of the pure electric mining wide-body vehicle are generated through the multi-scale feature fusion module.

[0062] In this embodiment, the terminal uses the ARM processor in the ARM + FPGA heterogeneous platform designed by the staff of this solution to extract multi-scale features from the current battery stability monitoring data and perform feature fusion processing to obtain the current fused monitoring features of the pure electric mining wide-body vehicle. These multi-scale features include, but are not limited to, time-domain features, frequency-domain features, and time-frequency-domain features.

[0063] Step S103: Based on the current fusion monitoring characteristics, identify the current battery installation stability warning information of the pure electric mining wide-body vehicle through the network dynamic early warning strategy.

[0064] In this embodiment, the terminal identifies the current battery installation stability warning information of the pure electric mining wide-body vehicle based on the current fused monitoring features and through a network dynamic warning strategy. This network dynamic warning strategy is constructed using a hybrid LSTM-GA-BP network dynamic warning model, including bidirectional LSTM (Long Short-Term Memory) time-series feature modeling, a genetic algorithm (GA) optimizing a BP (Back Propagation Neural Network), and an installation status index and warning strategy module. This allows for accurate analysis of the current warning content and the current warning processing strategy for the pure electric mining wide-body vehicle. The specific identification process will be explained in detail later.

[0065] Based on the above scheme, by integrating anti-interference data acquisition strategies in real time and using multiple sensors for battery installation stability monitoring, the comprehensiveness and integrity of the collected sensor data can be ensured. Furthermore, the multi-sensor data, through multi-scale feature fusion, provides multi-angle feedback of monitoring information for the pure electric mining wide-body vehicle at different levels, effectively eliminating monitoring errors in battery installation stability and ensuring timely acquisition of monitoring information. Finally, this scheme employs a network dynamic early warning strategy to efficiently assess the collected fused monitoring features, ensuring both timely analysis of fused information and multi-angle evaluation of fused monitoring features, thereby comprehensively improving the efficiency of battery installation stability monitoring for the pure electric mining wide-body vehicle.

[0066] Optionally, an anti-interference data acquisition strategy is used to collect current battery stability monitoring data transmitted by various sensors on the pure electric mining wide-body vehicle. This includes: acquiring sensor data transmitted by each sensor, and adjusting the data of each sensor separately through a vibration signal conditioning module to obtain optimized sensor data; processing the optimized sensor data for noise optimization to obtain denoised sensor data, and performing wavelet packet decomposition processing on the denoised sensor data to obtain current battery stability monitoring data transmitted by each sensor.

[0067] In this embodiment, the terminal acquires sensor data transmitted from each sensor and adjusts the data of each sensor through a vibration signal conditioning module to obtain optimized sensor data. This vibration signal conditioning module is a sub-unit within an FPGA (Field-Programmable Gate Array) module. This sub-unit employs a programmable gain amplifier and an eighth-order Bessel filter to effectively suppress passband ripple and enhance stopband attenuation. A 24-bit ADC (Analog-to-Digital Converter) is used for strain signal conditioning, ensuring an effective bit depth of 20 bits. An intrinsically safe power supply is used to power the module, and the input stage integrates a TVS diode (Transient Voltage Suppressor) and a resettable fuse, meeting the safety standards for mining equipment.

[0068] Then, the terminal performs noise optimization processing on the optimized sensor data to obtain denoised sensor data, and then performs wavelet packet decomposition on the denoised sensor data to obtain the current battery stability monitoring data transmitted by each sensor. Specifically, the FPGA (Field Programmable Gate Array) module synchronously acquires vibration signals at a sampling rate of 10kHz, strain signals at a sampling rate of 1kHz, and temperature and dust signals at a sampling rate of 1Hz to obtain the optimized sensor data transmitted by each sensor. Next, the terminal adds a 100ns timestamp to all optimized sensor data. Then, the terminal preprocesses the optimized sensor data using moving average filtering and median filtering to effectively eliminate impulse noise and salt-and-pepper noise, improving the vibration signal signal-to-noise ratio to 85dB. The ARM processor runs a wavelet packet decomposition algorithm on the preprocessed denoised sensor data to decompose the vibration signal into 32 sub-frequency bands. It accurately extracts the energy ratio of the 80-120Hz frequency band as the bolt loosening feature and uses the extracted bolt loosening features transmitted by each sensor as the current battery stability monitoring data transmitted by each sensor.

[0069] Based on the above scheme, the FPGA (Field Programmable Gate Array) module constructed by this scheme adds nanosecond-level timestamps to multi-source data such as vibration and strain. Spatiotemporal alignment is achieved through extended Kalman filtering, and signal denoising is completed by combining wavelet packet decomposition and CNN (Convolutional Neural Network). This effectively avoids the problem of sensor signal distortion caused by harsh environments such as large dust and high electromagnetic interference in mines, and maximizes the accuracy of real-time sensor data acquisition.

[0070] Optionally, before generating the current fused monitoring features of the pure electric mining wide-body vehicle based on the current battery stability monitoring data through the multi-scale feature fusion module, the method further includes: performing spatiotemporal alignment processing on the current battery stability monitoring data to obtain the synchronous monitoring data; and extracting the time-domain features, frequency-domain features, and time-frequency-domain features of the pure electric mining wide-body vehicle from the synchronous monitoring data through a feature extraction strategy.

[0071] In this embodiment, the terminal performs spatiotemporal alignment processing on each current battery stability monitoring data to obtain each synchronized monitoring data. Specifically, this spatiotemporal alignment method employs the Extended Kalman Filter (EKF) algorithm, which iteratively updates the state vector xk containing multiple physical quantity information through the state space equation, achieving nanosecond-level time synchronization with synchronization errors controlled within 10μs.

[0072] During spatiotemporal synchronization, the terminal constructs a state-space equation to describe the dynamic characteristics of multiple sensors:

[0073]

[0074] Where, x k The state vector contains information such as vibration, strain, torque, and temperature; f / h is a nonlinear function; Q / R is the noise covariance matrix; w k / v k For process / measurement noise.

[0075] Updated iteratively as follows:

[0076]

[0077] Achieve nanosecond-level time synchronization and solve the problem of sampling rate differences between different sensors.

[0078] For the vibration signal, a 5-layer Daubechies wavelet packet decomposition (db8 basis function) is used to refine the signal into 32 sub-frequency bands. A convolutional neural network (CNN) is then used to automatically learn noise features, and a function is applied to denoise the signal.

[0079]

[0080] Among them, W j Let θ be the wavelet packet coefficient of the j-th layer, and θ be the CNN network parameters.

[0081] Then, the terminal extracts the time-domain features, frequency-domain features, and time-frequency-domain features of the pure electric mining wide-body vehicle from each synchronous monitoring data using a feature extraction strategy.

[0082] Specifically, the feature extraction methods are as follows:

[0083] 1) Time-domain characteristics: Calculate the peak factor of the vibration signal. , cliff Root mean square Parameters such as strain signal and dynamic strain range Miner damage accumulation These indicators quantify the changes in signals over time.

[0084] 2) Frequency domain features: The energy proportion E of the bolt loosening characteristic frequency band (80-120Hz) is extracted by fast Fourier transform (FFT). 80-120 The energy E of the support resonant frequency (200-300Hz) 200-300 Key frequency domain characteristics are identified, and the frequency domain entropy value is calculated to analyze the signal frequency distribution characteristics. The frequency domain entropy calculation method is as follows:

[0085]

[0086] pi is the normalized power spectrum.

[0087] 3) Time-frequency domain characteristics: The time spectrum is generated by using short-time Fourier transform (STFT), and the time-frequency entropy is further calculated to capture the variation law of the signal under the joint distribution of time and frequency.

[0088] ,

[0089]

[0090] Based on the above scheme, by performing spatiotemporal synchronization processing on multi-source sensor data, the problem of time inconsistency caused by differences in the sampling rates of different sensors is effectively solved. Then, feature data in the time domain, frequency domain, and time-frequency domain are comprehensively extracted, thereby effectively capturing various related features of battery stability and improving the comprehensiveness of feature extraction.

[0091] Optionally, based on the current battery stability monitoring data, a multi-scale feature fusion module is used to generate the current fused monitoring features of the pure electric mining wide-body vehicle, including: constructing a multi-dimensional feature vector based on each time domain feature, each frequency domain feature, and each time-frequency domain feature; and performing feature fusion processing on the multi-dimensional feature vector through a weighted fusion strategy to obtain the current fused monitoring features of the pure electric mining wide-body vehicle.

[0092] In this embodiment, the terminal constructs a multi-dimensional feature vector based on various time-domain features, frequency-domain features, and time-frequency-domain features. This multi-dimensional feature vector can be a 128-dimensional feature vector.

[0093] Then, the terminal performs feature fusion processing on the multi-dimensional feature vector using a weighted fusion strategy to obtain the current fused monitoring features of the pure electric mining wide-body vehicle. The execution process of this weighted fusion strategy involves using learnable weights w... i The coefficients α after normalization by the Softmax function i Calculate the fused feature vector F fusion Finally, the terminal will fuse the feature vectors as the current fused monitoring features of the pure electric mining wide-body vehicle.

[0094] Based on the above scheme, by performing feature fusion on multi-scale features, the importance of key features in the assessment of battery installation status is effectively highlighted, and the assessment effect of battery installation stability is improved while ensuring the subsequent assessment of battery installation stability.

[0095] Optionally, based on the current fusion monitoring characteristics, a network dynamic early warning strategy is used to identify the current battery installation stability warning information of the pure electric mining wide-body vehicle, including: based on the current fusion monitoring characteristics, a bidirectional time-series feature modeling strategy is used to identify the characteristics of each attenuation process of the pure electric mining wide-body vehicle; based on the characteristics of each attenuation process, a genetic optimization network is used to identify the installation correlation index data of the pure electric mining wide-body vehicle; and based on the installation correlation index data, the current battery installation stability warning information of the pure electric mining wide-body vehicle is identified.

[0096] In this embodiment, based on the current fusion monitoring features, the terminal identifies the characteristics of each degradation process of the pure electric wide-body mining vehicle through a bidirectional time-series feature modeling strategy. Specifically, the terminal inputs a sliding window (length 500, step size 50) feature vector containing multi-scale fusion features into a network composed of two layers of bidirectional LSTM (128 neurons each). Through the collaborative calculation of forget gates, input gates, output gates, and cell states, the time-series features of battery installation state degradation are deeply mined, effectively capturing features such as the slow decay of bolt preload. The calculation process is as follows:

[0097]

[0098] Then, based on the characteristics of each decay process, the terminal identifies the installation correlation index data of the pure electric wide-body mining vehicle through a genetic optimization network. This genetic optimization network is a genetic algorithm (GA) optimized BP network. The identification process involves the terminal encoding the weights and thresholds of the BP network using real-number encoding, setting the population size to 20 and the chromosome length... The number of neurons in the input layer (n), hidden layer (m), and output layer (k) is determined based on the number of neurons in the output layer. Let the fitness function be (where, , ), through tournament selection (Tournament Size=3), arithmetic cross ( Gaussian mutation ( Genetic operations, such as those performed on the BP network, were used for 50 generations of iterative optimization to reduce prediction errors and improve generalization ability, thereby obtaining installation-related index data for the pure electric wide-body mining vehicle. These installation-related index data include, but are not limited to, vibration damage indicators, strain fatigue damage indicators, torque attenuation rate, and temperature influence coefficients.

[0099] Finally, based on the installation-related index data, the terminal identifies the current battery installation stability warning information for the pure electric wide-body mining vehicle. The specific identification process will be explained in detail later.

[0100] Based on the above scheme, the LSTM-GA-BP hybrid network dynamic early warning model constructed by this scheme performs real-time analysis and early warning on the collected fused feature vectors, which improves the accuracy of the analysis and the efficiency of monitoring the battery installation stability of pure electric mining wide-body vehicles.

[0101] Optionally, based on the installation-related index data, identify the current battery installation stability warning information of the pure electric mining wide-body vehicle, including: weighting the installation-related index data according to preset index weight values ​​to obtain installation status index data; identifying the current battery warning level of the pure electric mining wide-body vehicle based on the installation status index data; and querying the current warning content and current warning handling strategy of the pure electric mining wide-body vehicle in the warning database based on the current battery warning level; and using the current warning content and current warning handling strategy of the pure electric mining wide-body vehicle as the current battery installation stability warning information of the pure electric mining wide-body vehicle.

[0102] In this embodiment, the terminal performs weighted calculations on each installation-related index data according to preset index weight values ​​to obtain installation status index data. This installation status index data is a comprehensive evaluation index used to assess the stability of battery installation. This index can be represented by S, and the preset index weight values ​​are as follows: vibration damage index: 0.4; strain fatigue damage index: 0.3; torque attenuation rate: 0.2; temperature influence coefficient: 0.1. The calculation formula for this weighted calculation is as follows:

[0103]

[0104] Wherein, S1 is the vibration damage index (calculated based on ISO 2631-1 standard), S2 is the strain fatigue damage index (based on Miner's criterion), and S3 is the torque attenuation rate (…). F0 is the initial preload, and S4 is the temperature influence coefficient. ).

[0105] Then, based on installation status index data, the terminal identifies the current battery warning level of the pure electric mining wide-body vehicle. This current battery warning level can be dynamically generated by adaptively adjusting the warning threshold (Threshold) according to the 3σ principle of historical data. The calculation formula corresponding to this adaptive adjustment method of the warning threshold is as follows:

[0106]

[0107] Where, μ i and σ i S under normal conditionsi The mean and standard deviation.

[0108] The current battery warning level can be divided into yellow warning, orange warning, and red warning.

[0109] Based on the current battery warning level, the terminal queries the warning database for the current warning content and handling strategy of the pure electric mining wide-body vehicle. This warning database pre-sets the current warning content and handling strategy corresponding to different battery warning levels. For example, a yellow warning indicates the warning indicator light is yellow and the message "Battery slightly loose" is displayed on the worker's client; the current handling strategy is none. An orange warning indicates the warning indicator light is orange, and the current handling strategy is a speed limit of 15 km / h. A red warning indicates the warning indicator light is red, and the current handling strategy is to trigger an audible and visual alarm and slow down to a stop.

[0110] Finally, the terminal will use the current warning content and the current warning handling strategy of the pure electric mining wide-body vehicle as the current battery installation stability warning information of the pure electric mining wide-body vehicle.

[0111] Based on the above scheme, by comprehensively evaluating the installation status index data, and then directly adapting to the database, the current battery installation stability warning information can be generated in a timely manner, thereby achieving early warning before failure and improving the effectiveness of providing timely warning for sudden loosening failures during driving.

[0112] This application also provides an example of intelligent monitoring of battery installation stability for a pure electric wide-body mining vehicle, such as... Figure 2 As shown, the specific processing procedure includes the following steps:

[0113] Step S201: Acquire sensor data transmitted by each sensor, and adjust the data of each sensor through the vibration signal conditioning module to obtain optimized sensor data.

[0114] Step S202: For each optimized sensor data, noise optimization processing is performed to obtain each denoised sensor data, and wavelet packet decomposition processing is performed on each denoised sensor data to obtain the current battery stability monitoring data transmitted by each sensor.

[0115] Step S203: Perform spatiotemporal alignment processing on each current battery stability monitoring data to obtain each synchronous monitoring data.

[0116] Step S204: For each synchronous monitoring data, extract the time domain features, frequency domain features, and time-frequency domain features of the pure electric mining wide-body vehicle through a feature extraction strategy.

[0117] Step S205: Construct a multidimensional feature vector based on each time-domain feature, each frequency-domain feature, and each time-frequency domain feature.

[0118] Step S206: Perform feature fusion processing on the multidimensional feature vector using a weighted fusion strategy to obtain the current fused monitoring features of the pure electric mining wide-body vehicle.

[0119] Step S207: Based on the current fusion monitoring characteristics, the attenuation process features of the pure electric mining wide-body vehicle are identified through a two-way time-series feature modeling strategy.

[0120] Step S208: Based on the characteristics of each attenuation process, identify the installation correlation index data of the pure electric mining wide-body vehicle through a genetic optimization network.

[0121] Step S209: Perform weighted calculation on each installation-related index data according to the preset index weight values ​​to obtain installation status index data.

[0122] Step S210: Based on the installation status index data, identify the current battery warning level of the pure electric mining wide-body vehicle, and based on the current battery warning level, query the warning database for the current warning content and the current warning handling strategy of the pure electric mining wide-body vehicle.

[0123] Step S211: The current warning content and the current warning processing strategy of the pure electric mining wide-body vehicle are used as the current battery installation stability warning information of the pure electric mining wide-body vehicle.

[0124] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0125] Based on the same inventive concept, this application also provides an intelligent monitoring device for the installation stability of a pure electric wide-body mining vehicle's battery, used to implement the aforementioned intelligent monitoring method for the installation stability of a pure electric wide-body mining vehicle's battery. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the intelligent monitoring device for the installation stability of a pure electric wide-body mining vehicle's battery provided below can be found in the limitations of the intelligent monitoring method for the installation stability of a pure electric wide-body mining vehicle's battery described above, and will not be repeated here.

[0126] In one exemplary embodiment, such as Figure 3 As shown, an intelligent monitoring device for the battery installation stability of a pure electric wide-body mining vehicle is provided, comprising: a data acquisition module 310, a generation module 320, and an identification module 330, wherein:

[0127] The acquisition module 310 is used to acquire current battery stability monitoring data transmitted by various sensors on the pure electric mining wide-body vehicle through an anti-interference data acquisition strategy.

[0128] The generation module 320 is used to generate the current fused monitoring features of the pure electric mining wide-body vehicle based on the current battery stability monitoring data and through the multi-scale feature fusion module.

[0129] The identification module 330 is used to identify the current battery installation stability warning information of the pure electric mining wide-body vehicle based on the current fusion monitoring characteristics and through a network dynamic early warning strategy.

[0130] Optionally, the acquisition module 310 is specifically used for:

[0131] The sensor data transmitted by each sensor is acquired, and the data of each sensor is adjusted by the vibration signal conditioning module to obtain optimized sensor data.

[0132] The optimized sensor data is processed by noise optimization to obtain denoised sensor data, and wavelet packet decomposition is performed on the denoised sensor data to obtain the current battery stability monitoring data transmitted by each sensor.

[0133] Optionally, the device further includes:

[0134] The synchronization module is used to perform spatiotemporal alignment processing on the current battery stability monitoring data to obtain the synchronization monitoring data.

[0135] The extraction module is used to extract the time-domain features, frequency-domain features, and time-frequency-domain features of the pure electric mining wide-body vehicle from the synchronous monitoring data through a feature extraction strategy.

[0136] Optionally, the generation module 320 is specifically used for:

[0137] Based on the time-domain features, frequency-domain features, and time-frequency-domain features, a multi-dimensional feature vector is constructed.

[0138] The multidimensional feature vector is subjected to feature fusion processing through a weighted fusion strategy to obtain the current fused monitoring features of the pure electric mining wide-body vehicle.

[0139] Optionally, the identification module 330 is specifically used for:

[0140] Based on the current fusion monitoring characteristics, the attenuation process features of the pure electric mining wide-body vehicle are identified through a two-way time-series feature modeling strategy.

[0141] Based on the characteristics of each of the aforementioned attenuation processes, the installation correlation index data of the pure electric mining wide-body vehicle are identified through a genetic optimization network.

[0142] Based on the installation-related index data, the current battery installation stability warning information of the pure electric mining wide-body vehicle is identified.

[0143] Optionally, the identification module 330 is specifically used for:

[0144] The installation-related index data are weighted according to preset index weight values ​​to obtain installation status index data.

[0145] Based on the installation status index data, the current battery warning level of the pure electric mining wide-body vehicle is identified, and based on the current battery warning level, the current warning content and the current warning handling strategy of the pure electric mining wide-body vehicle are queried in the warning database.

[0146] The current warning content and the current warning processing strategy of the pure electric mining wide-body vehicle are used as the current battery installation stability warning information of the pure electric mining wide-body vehicle.

[0147] The various modules in the aforementioned intelligent monitoring device for battery installation stability of pure electric wide-body mining vehicles can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0148] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements an intelligent monitoring method for the battery installation stability of a pure electric wide-body mining vehicle. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0149] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0150] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of an intelligent monitoring method for the battery installation stability of a pure electric wide-body mining vehicle.

[0151] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program being executed by a processor to implement the steps of an intelligent monitoring method for the battery installation stability of a pure electric wide-body mining vehicle.

[0152] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of an intelligent monitoring method for the battery installation stability of a pure electric mining wide-body vehicle.

[0153] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0154] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0155] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0156] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for intelligent monitoring of battery installation stability in a pure electric wide-body mining vehicle, characterized in that, The method includes: By employing an anti-interference data acquisition strategy, current battery stability monitoring data transmitted by various sensors on the pure electric mining wide-body vehicle is collected. Based on the current battery stability monitoring data, the current fused monitoring features of the pure electric mining wide-body vehicle are generated through a multi-scale feature fusion module. Based on the current integrated monitoring characteristics, a network dynamic early warning strategy is used to identify the current battery installation stability warning information of the pure electric mining wide-body vehicle.

2. The method according to claim 1, characterized in that, The method employs an anti-interference data acquisition strategy to collect current battery stability monitoring data transmitted from various sensors on the pure electric wide-body mining vehicle, including: The sensor data transmitted by each sensor is acquired, and the data of each sensor is adjusted by the vibration signal conditioning module to obtain optimized sensor data. The optimized sensor data is processed by noise optimization to obtain denoised sensor data, and wavelet packet decomposition is performed on the denoised sensor data to obtain the current battery stability monitoring data transmitted by each sensor.

3. The method according to claim 1, characterized in that, Before generating the current fused monitoring features of the pure electric mining wide-body vehicle based on the current battery stability monitoring data through the multi-scale feature fusion module, the method further includes: The current battery stability monitoring data are spatiotemporally aligned to obtain the synchronous monitoring data. For each of the synchronous monitoring data, a feature extraction strategy is used to extract the time-domain features, frequency-domain features, and time-frequency-domain features of the pure electric mining wide-body vehicle.

4. The method according to claim 3, characterized in that, Based on the current battery stability monitoring data, the multi-scale feature fusion module generates the current fused monitoring features of the pure electric mining wide-body vehicle, including: Based on the time-domain features, frequency-domain features, and time-frequency-domain features, a multi-dimensional feature vector is constructed. The multidimensional feature vector is subjected to feature fusion processing through a weighted fusion strategy to obtain the current fused monitoring features of the pure electric mining wide-body vehicle.

5. The method according to claim 1, characterized in that, The step of identifying the current battery installation stability warning information of the pure electric mining wide-body vehicle based on the current fusion monitoring characteristics and through a network dynamic early warning strategy includes: Based on the current fusion monitoring characteristics, the attenuation process features of the pure electric mining wide-body vehicle are identified through a two-way time-series feature modeling strategy. Based on the characteristics of each of the aforementioned attenuation processes, the installation correlation index data of the pure electric mining wide-body vehicle are identified through a genetic optimization network. Based on the installation-related index data, the current battery installation stability warning information of the pure electric mining wide-body vehicle is identified.

6. The method according to claim 5, characterized in that, The step of identifying the current battery installation stability warning information of the pure electric mining wide-body vehicle based on the installation correlation index data includes: The installation-related index data are weighted according to preset index weight values ​​to obtain installation status index data. Based on the installation status index data, the current battery warning level of the pure electric mining wide-body vehicle is identified, and based on the current battery warning level, the current warning content and the current warning handling strategy of the pure electric mining wide-body vehicle are queried in the warning database. The current warning content and the current warning processing strategy of the pure electric mining wide-body vehicle are used as the current battery installation stability warning information of the pure electric mining wide-body vehicle.

7. An intelligent monitoring device for the battery installation stability of a pure electric wide-body mining vehicle, characterized in that, The device includes: The data acquisition module is used to acquire current battery stability monitoring data transmitted by various sensors on the pure electric mining wide-body vehicle through an anti-interference data acquisition strategy. The generation module is used to generate the current fused monitoring features of the pure electric mining wide-body vehicle based on the current battery stability monitoring data and through the multi-scale feature fusion module. The identification module is used to identify the current battery installation stability warning information of the pure electric mining wide-body vehicle based on the current fusion monitoring characteristics and through a network dynamic early warning strategy.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images