A battery early warning method and device for a mine new energy vehicle

Abstract

The application discloses a battery early warning method and device for a mining new energy vehicle, relates to the technical field of mining vehicle detection, and solves the technical problem that the existing battery early warning method for the mining new energy vehicle is difficult to timely perform early warning due to poor transmission conditions of a working environment, thereby causing low vehicle operation safety; the method comprises the following steps: acquiring temperature detection data of the mining new energy vehicle in real time, determining a plurality of to-be-analyzed points based on the temperature detection data at the current time; performing temperature anomaly detection on each to-be-analyzed point to obtain temperature detection results of each to-be-analyzed point; generating a to-be-transmitted sequence based on the plurality of detection data; performing feature extraction on the to-be-transmitted sequence to obtain a transmission sequence; transmitting the transmission sequence to a cloud temperature analysis platform; the transmission sequence is obtained by performing feature extraction on the data, the transmission time is shortened, the data can be quickly transmitted to the cloud temperature analysis platform for deep analysis, and the timeliness of temperature fault early warning is ensured.

Description

Technical Field

[0001] This application belongs to the field of mining vehicle detection technology, specifically a battery early warning method and device for new energy mining vehicles. Background Technology

[0002] Compared with traditional diesel vehicles, mining new energy vehicles can save a significant amount of operating costs each year. In the common mining scenarios of "light load uphill, heavy load downhill", potential energy can be converted into electrical energy for storage, effectively increasing the range of a single charge and reducing the energy consumption of the whole vehicle. In recent years, traditional construction machinery has been caught in the dilemma of high energy consumption and high carbon emissions, and green development has become the key to the industry's transformation and upgrading.

[0003] Due to equipment limitations, the local computing power of the processors in mining new energy vehicles is typically limited. Therefore, detected data needs to be transmitted to a cloud platform for in-depth analysis to ensure the safe operation of these vehicles. However, mining vehicles mostly operate in open-pit or underground mines, where signal transmission is extremely unstable, especially when transmitting large amounts of data. This can easily lead to transmission interruptions or congestion, preventing timely in-depth analysis of the detected data and consequently affecting the safety of the mining vehicles. Therefore, a battery early warning method for mining new energy vehicles is urgently needed. Summary of the Invention

[0004] This application provides a battery early warning method and device for mining new energy vehicles, which solves the technical problem that existing battery early warning methods for mining new energy vehicles are difficult to provide timely warnings due to poor transmission conditions in the working environment, resulting in low vehicle operation safety.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] Firstly, a battery early warning method for mining new energy vehicles is provided, including:

[0007] Real-time acquisition of temperature detection data from mining new energy vehicles, the temperature detection data including the detection data of each individual battery cell at the corresponding time; the detection data includes the battery coordinates of the individual battery cell and the temperature value at the corresponding time; based on the temperature detection data at the current time, several points to be analyzed are determined;

[0008] The temperature values ​​corresponding to each point to be analyzed are analyzed to obtain the temperature detection results for each point to be analyzed; warnings are issued based on the abnormal points and corresponding temperature values ​​in the temperature detection results.

[0009] Acquire detection data of several points to be analyzed at several times, and generate a sequence to be transmitted based on the detection data; extract features from the sequence to be transmitted to obtain the transmission sequence, and transmit the transmission sequence to the cloud temperature analysis platform.

[0010] Based on the above technical solution, in the battery early warning method and device for mining new energy vehicles provided in this application, the following steps are taken: Temperature detection data of the mining new energy vehicle is acquired in real time; several points to be analyzed are determined based on the current temperature detection data; temperature anomaly detection is performed on each point to be analyzed to obtain the temperature detection results for each point; an early warning is issued based on the anomalies and corresponding temperature values ​​in the temperature detection results; detection data of several points to be analyzed at several times is acquired, and a transmission sequence is generated based on the detection data; feature extraction is performed on the transmission sequence to obtain the transmission sequence, and the transmission sequence is transmitted to the cloud temperature analysis platform; a simple preliminary analysis of the battery detection data is performed using local processing equipment to promptly check for simple abnormal faults; and by extracting features from the data to obtain the transmission sequence, the amount of data transmitted is minimized, enabling the data to be quickly transmitted to the cloud temperature analysis platform for in-depth analysis, further ensuring the timeliness of temperature fault early warning.

[0011] In conjunction with the first aspect above, in one possible implementation, determining several points to be analyzed based on the temperature detection data at the current moment includes:

[0012] Extract the detection data corresponding to each individual cell from the temperature detection data, and extract the cell coordinates and temperature values ​​from the detection data; construct the three-dimensional coordinate points of the individual cell based on the cell coordinates and temperature values; fit each three-dimensional coordinate point into a temperature change surface;

[0013] Using the three-dimensional coordinate points corresponding to the battery coordinates of each individual cell as reference points, the points to be analyzed are generated based on the temperature change surface and each reference point.

[0014] In conjunction with the first aspect above, in one possible implementation, the generation of the points to be analyzed based on the temperature change surface and various reference points includes:

[0015] Obtain the set initial radius and obtain the reference point. ; using the battery coordinates corresponding to the reference point A two-dimensional region is constructed with the initial radius as the center. , ,in The initial radius of the domain;

[0016] The two-dimensional region As a constraint condition, the temperature change surface is constrained to obtain the corresponding restricted surface. ; That is, to obtain the temperature change surface and two-dimensional region. The intersection, ;

[0017] When the temperature value corresponding to the reference point is greater than its corresponding limiting surface When calculating the temperature values ​​of all three-dimensional coordinate points within the reference point, the point properties of the reference point are recorded as the point to be analyzed.

[0018] When the temperature value corresponding to the reference point is less than its corresponding limiting surface When calculating the temperature values ​​of all three-dimensional coordinate points within the reference point, the point properties of the reference point are recorded as the point to be analyzed.

[0019] In conjunction with the first aspect above, in one possible implementation, the step of detecting temperature anomalies at each point to be analyzed and obtaining temperature detection results for each point to be analyzed includes:

[0020] Obtain the temperature value corresponding to each point to be analyzed. When the temperature value is greater than the set temperature anomaly threshold, mark the point to be analyzed as an anomaly point; otherwise, mark the point to be analyzed as a secondary analysis point.

[0021] Obtain the temperature change surface at the current moment, and calculate the reference range radius corresponding to each secondary analysis point based on the temperature change surface;

[0022] Using the battery coordinates corresponding to each secondary analysis point A two-dimensional region is constructed with the reference radius as the center, and this two-dimensional region is denoted as the region to be analyzed. , ,in, The battery coordinates are The reference range radius corresponding to the secondary analysis point;

[0023] Obtain the surface of temperature change at the current moment. and the temperature change surface at the previous moment. ;

[0024] The temperature change surface Temperature change surface and the region to be analyzed Substituting the values ​​into the predefined temperature anomaly assessment function, we obtain the temperature anomaly values ​​corresponding to the secondary analysis points; one expression of the temperature anomaly assessment function is as follows:

[0025]

[0026] in, The temperature anomaly value is the temperature value corresponding to the secondary analysis point. In this embodiment, the temperature anomaly value is obtained by analyzing the temperature change value of the secondary analysis point through the temperature anomaly evaluation function. When the temperature value of each temperature value in the area to be analyzed at the current time is significantly different from the temperature value at the previous time, it indicates that the temperature value changes significantly or the range of temperature changes is large in the area to be analyzed. At this time, the anomaly of the secondary analysis point is more likely, and the corresponding temperature anomaly value is set to be larger.

[0027] When the abnormal temperature value exceeds the set abnormal temperature value threshold, the secondary analysis point is marked as an abnormal point; otherwise, the secondary analysis point is marked as a normal point.

[0028] The various anomalies, along with their corresponding temperature values ​​and temperature anomalies, are integrated into the temperature detection results.

[0029] In conjunction with the first aspect above, in one possible implementation, the calculation of the reference neighborhood radius for each secondary analysis point based on the temperature-varying surface includes:

[0030] Obtain the battery coordinates of the secondary analysis points Battery coordinates based on quadratic analysis points Constructing the first reference curve with temperature change surface Second reference curve ;in, , Get the first unit distance Second unit distance The first unit distance is the unit interval distance between various temperature value acquisition devices in the y-direction of the battery pack; the second unit distance is the unit interval distance between various temperature value acquisition devices in the x-direction of the battery pack; the first reference curve Second reference curve First unit distance Second unit distance Substitute the values ​​into the set reference range radius calculation function to obtain the reference range radius corresponding to the secondary analysis point;

[0031] One expression of the reference domain radius calculation function includes:

[0032] ;

[0033] in, The radius of the reference neighborhood corresponding to the secondary analysis point. The radius of the set reference area.

[0034] In conjunction with the first aspect above, in one possible implementation, generating the sequence to be transmitted based on several of the detection data includes:

[0035] The time of data acquisition is obtained, the temperature value in the data is extracted, and the temperature value is arranged in chronological order according to its corresponding time to generate a sequence to be transmitted.

[0036] In conjunction with the first aspect above, in one possible implementation, the step of extracting features from the sequence to be transmitted to obtain the transmission sequence includes:

[0037] Extract the temperature anomaly values ​​corresponding to each anomaly point in the temperature detection results, and substitute these anomaly values ​​into a set feature duration adjustment function to obtain the feature duration of the anomaly point; one expression of the feature duration adjustment function includes:

[0038]

[0039] in, The adjusted feature duration, This is the threshold for abnormal temperature values. This is an abnormal temperature value; The initial duration is set. The larger the temperature anomaly, the greater the degree of temperature anomaly in the individual battery. In order to ensure the accuracy of the fault analysis of the corresponding individual battery, the feature duration needs to be appropriately extended to increase more temperature data. Therefore, the larger the temperature anomaly, the longer the feature duration should be set.

[0040] A preliminary transmission sequence is obtained by intercepting the sequence to be transmitted based on the characteristic duration.

[0041] Feature extraction is performed on the initial transmission sequence to obtain several sets of transmission sequences;

[0042] The sequence to be transmitted is obtained, several temperature values ​​in the sequence are fitted into a temperature change curve, and the temperature change curve is truncated based on the characteristic duration to obtain the reference part temperature change curve corresponding to the initial transmission sequence.

[0043] The temperature values ​​in the transmission sequence are fitted into partial temperature change curves according to their chronological order at corresponding times; the partial temperature change curves corresponding to each set of transmission sequences are obtained sequentially.

[0044] Calculate the deviation between the temperature change curve of each part and the temperature change curve of the reference part; select the transmission sequence corresponding to the temperature change curve with the smallest deviation as the final transmission sequence.

[0045] In conjunction with the first aspect above, in one possible implementation, the step of extracting features from the initial transmission sequence to obtain several sets of transmission sequences includes:

[0046] The temperature values ​​in the initial transmission sequence are fitted to obtain an initial temperature change curve; a set unit time length is obtained, and the initial temperature change curve is segmented based on the unit time length to obtain several unit temperature change curve segments;

[0047] Calculate the standard deviation of the unit temperature change curve segment.

[0048] Substituting the standard deviation into the set characteristic number generation function, we obtain the characteristic number corresponding to the unit temperature change curve segment;

[0049] The initial transmission sequence is divided into several unit sequence groups based on the unit time length. Each unit sequence group corresponds one-to-one with a unit temperature change curve segment, meaning that the unit sequence group and the unit temperature change curve segment have the same time length, and the start and end times of a pair of unit sequence groups and unit temperature change curve segments are the same. Based on the feature number, a corresponding number of temperature values ​​are randomly selected from the corresponding sequence group to obtain several sets of unit feature sequences corresponding to the sequence group.

[0050] Several transmission sequences are obtained by randomly combining the unit feature sequences corresponding to different sequence groups; among them, the temperature values ​​corresponding to different transmission sequences are not exactly the same.

[0051] In conjunction with the first aspect mentioned above, in one possible implementation, the cloud-based temperature analysis platform is used to analyze the transmission sequence and obtain corresponding analysis results. It is understood that the cloud-based temperature analysis platform provides a higher level of detail in analyzing the transmission sequence than the local analysis method used by mining new energy vehicles.

[0052] Secondly, a battery early warning device for mining new energy vehicles is provided, comprising: a data acquisition module, a data analysis module, and a data transmission module;

[0053] The data acquisition module is used to acquire temperature detection data of mining new energy vehicles in real time. The temperature detection data includes the detection data of each individual battery cell at the corresponding time.

[0054] The data analysis module includes an anomaly detection unit and a transmission sequence generation unit;

[0055] The anomaly detection unit is used to determine several points to be analyzed based on the temperature detection data at the current moment; to perform temperature anomaly detection on each point to be analyzed, and to obtain the temperature detection results of each point to be analyzed; and to issue an early warning based on the anomalies in the temperature detection results and the corresponding temperature values.

[0056] The transmission sequence generation unit is used to acquire detection data of several points to be analyzed at several times, and generate a transmission sequence based on the detection data; and perform feature extraction on the transmission sequence to obtain the transmission sequence.

[0057] The data transmission module is used to transmit the transmission sequence to the cloud-based temperature analysis platform.

[0058] This application provides a battery early warning method and device for mining new energy vehicles. It can acquire temperature detection data of the mining new energy vehicle in real time; determine several points to be analyzed based on the current temperature detection data; perform temperature anomaly detection on each point to be analyzed to obtain the temperature detection results for each point; issue an early warning based on the anomalies and corresponding temperature values ​​in the temperature detection results; acquire detection data of several points to be analyzed at several times, and generate a transmission sequence based on the detection data; extract features from the transmission sequence to obtain a transmission sequence, and transmit the transmission sequence to a cloud-based temperature analysis platform; perform simple preliminary analysis of the battery detection data using local processing equipment to promptly check for simple abnormal faults; and simultaneously, by extracting features from the data to obtain the transmission sequence, minimize the amount of data transmitted and shorten the transmission time, enabling the data to be quickly transmitted to the cloud-based temperature analysis platform for in-depth analysis, further ensuring the timeliness of temperature fault early warning.

[0059] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0060] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the 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.

[0061] Figure 1This is a schematic diagram illustrating the steps of the battery early warning method for mining new energy vehicles in this application;

[0062] Figure 2 This is a schematic diagram of the module connection of the battery early warning system for mining new energy vehicles in this application. Detailed Implementation

[0063] The technical solutions of this application will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0064] Please see Figure 1 The first aspect of this application provides a battery early warning method for mining new energy vehicles, comprising:

[0065] Real-time acquisition of temperature detection data from mining new energy vehicles, the temperature detection data including the detection data of each individual battery cell at the corresponding time; the detection data includes the battery coordinates of the individual battery cell and the temperature value at the corresponding time; based on the temperature detection data at the current time, several points to be analyzed are determined;

[0066] The temperature values ​​corresponding to each point to be analyzed are analyzed to obtain the temperature detection results for each point to be analyzed; warnings are issued based on the abnormal points and corresponding temperature values ​​in the temperature detection results; the temperature detection results are the temperature detection results of the battery equipment at the local end of the mining new energy vehicle; including each abnormal point, as well as the temperature value and temperature abnormality value corresponding to the abnormal point; it can be understood that the temperature detection results corresponding to the local end are the results obtained by analyzing the temperature data through the local segment analysis equipment. This result can indicate relatively obvious temperature abnormal points, and this temperature detection result does not have time sequence;

[0067] Acquire detection data of several points to be analyzed at several times, and generate a transmission sequence based on the detection data; extract features from the transmission sequence to obtain the transmission sequence, and transmit the transmission sequence to the cloud temperature analysis platform; the cloud temperature analysis platform obtains the corresponding temperature detection result by analyzing the time-series temperature data, which is a time-series temperature detection result; such as some battery faults that can only be obtained through complex analysis of long-term temperature value sequences.

[0068] Based on the above technical solution, in the battery early warning method and device for mining new energy vehicles provided in this application, the following steps are taken: Temperature detection data of the mining new energy vehicle is acquired in real time; several points to be analyzed are determined based on the current temperature detection data; temperature anomaly detection is performed on each point to be analyzed to obtain the temperature detection results for each point; an early warning is issued based on the anomalies and corresponding temperature values ​​in the temperature detection results; detection data of several points to be analyzed at several times are acquired, and a transmission sequence is generated based on the detection data; feature extraction is performed on the transmission sequence to obtain the transmission sequence, and the transmission sequence is transmitted to the cloud temperature analysis platform; a simple preliminary analysis of the battery detection data is performed on the local processing device to promptly check for simple abnormal faults; and feature extraction is performed on the data to obtain the transmission sequence, minimizing the amount of data transmitted, enabling the data to be quickly transmitted to the cloud temperature analysis platform for in-depth analysis, further ensuring the timeliness of temperature fault early warning; a spatial analysis method is used locally, using small signal segments for transmission to avoid large amounts of real-time data transmission; and in-depth analysis of the temperature time sequence is performed in the cloud, ensuring the timeliness of problem detection.

[0069] In one possible implementation, several points to be analyzed are determined based on the temperature detection data at the current moment, including: extracting the detection data corresponding to each individual cell from the temperature detection data, and extracting the cell coordinates and temperature values ​​from the detection data; constructing the three-dimensional coordinate points of the individual cells based on the cell coordinates and temperature values; fitting each three-dimensional coordinate point into a temperature change surface; specifically, the cell coordinates... And the temperature value T; thus constructing three-dimensional coordinate points The temperature change surface is obtained by performing second-order polynomial fitting on each three-dimensional coordinate point. The method of obtaining a surface by fitting three-dimensional coordinate points is relatively existing, and will not be elaborated on here;

[0070] Using the three-dimensional coordinate points corresponding to the battery coordinates of each individual cell as reference points, the points to be analyzed are generated based on the temperature change surface and each reference point.

[0071] In one possible implementation, the points to be analyzed are generated based on the temperature-changing surface and various reference points, including: obtaining a set initial neighborhood radius, and obtaining reference points. ; using the battery coordinates corresponding to the reference point A two-dimensional region is constructed with the initial domain radius as the center. , ,in The initial radius of the domain;

[0072] The two-dimensional region As a constraint condition, the temperature change surface is constrained to obtain the corresponding restricted surface. ; That is, to obtain the temperature change surface and two-dimensional region. The intersection, ;

[0073] When the temperature value corresponding to the reference point is greater than its corresponding limiting surface When calculating the temperature values ​​of all three-dimensional coordinate points within the reference point, the point properties of the reference point are recorded as the point to be analyzed.

[0074] When the temperature value corresponding to the reference point is less than its corresponding limiting surface When calculating the temperature values ​​of all three-dimensional coordinate points within the reference point, the point properties of the reference point are recorded as the point to be analyzed.

[0075] Specifically, obtain the temperature value of the reference point. ;when or When the reference point is used, it is recorded as the point to be analyzed, where, for The corresponding temperature value, .

[0076] In one possible implementation, temperature anomaly detection is performed on each point to be analyzed to obtain the temperature detection results of each point to be analyzed, including: obtaining the temperature value corresponding to each point to be analyzed; when the temperature value is greater than a set temperature anomaly threshold, the point to be analyzed is marked as an anomaly point; otherwise, the point to be analyzed is marked as a secondary analysis point.

[0077] Obtain the temperature change surface at the current moment, and calculate the reference range radius corresponding to each secondary analysis point based on the temperature change surface;

[0078] Using the battery coordinates corresponding to each secondary analysis point A two-dimensional region is constructed with the reference radius as the center, and this two-dimensional region is denoted as the region to be analyzed. , ,in, The battery coordinates are The reference range radius corresponding to the secondary analysis point;

[0079] Obtain the surface of temperature change at the current moment. and the temperature change surface at the previous moment. ;

[0080] The temperature change surface Temperature change surface and the region to be analyzed Substituting the values ​​into the predefined temperature anomaly assessment function, we obtain the temperature anomaly values ​​corresponding to the secondary analysis points; one expression of the temperature anomaly assessment function is as follows:

[0081]

[0082] in, The temperature anomaly value is the temperature value corresponding to the secondary analysis point. In this embodiment, the temperature anomaly value is obtained by analyzing the temperature change value of the secondary analysis point through the temperature anomaly evaluation function. When the temperature value of each temperature value in the area to be analyzed at the current time is significantly different from the temperature value at the previous time, it indicates that the temperature value changes significantly or the range of temperature changes is large in the area to be analyzed. At this time, the anomaly of the secondary analysis point is more likely, and the corresponding temperature anomaly value is set to be larger.

[0083] When the abnormal temperature value is greater than the set abnormal temperature value threshold, the secondary analysis point is marked as an abnormal point; otherwise, the secondary analysis point is marked as a normal point. The specific value of the abnormal temperature value threshold is set by experts based on the test results. When the abnormal temperature value is greater than the abnormal temperature value threshold, it indicates that the probability of the single cell being abnormal is high. When the abnormal temperature value is less than or equal to the abnormal temperature value threshold, it indicates that the probability of the single cell being abnormal is low.

[0084] Each anomaly point, along with its corresponding temperature value and temperature anomaly value, is integrated into the temperature detection result. Understandably, it is necessary to calculate the temperature anomaly value corresponding to the point to be analyzed, which is an anomaly point. The specific calculation process is the same as the process of calculating the temperature anomaly value of the secondary analysis point.

[0085] In one possible implementation, the reference radius of each secondary analysis point is calculated based on the temperature-varying surface, including: obtaining the battery coordinates of the secondary analysis points. Battery coordinates based on quadratic analysis points Constructing the first reference curve with temperature change surface Second reference curve ;in, , Get the first unit distance Second unit distance The first unit distance is the unit interval distance between various temperature value acquisition devices in the y-direction of the battery pack; the second unit distance is the unit interval distance between various temperature value acquisition devices in the x-direction of the battery pack; the first reference curve Second reference curve First unit distance Second unit distance Substitute the values ​​into the set reference range radius calculation function to obtain the reference range radius corresponding to the secondary analysis point;

[0086] One expression of the reference domain radius calculation function includes:

[0087] ;

[0088] in, The radius of the reference neighborhood corresponding to the secondary analysis point. The reference radius is set by experts based on experience. In this embodiment, the radius of the reference range for the corresponding three-dimensional point is set by calculating the degree of temperature change at the corresponding three-dimensional coordinate point of the battery. The greater the degree of temperature change near the three-dimensional coordinate point, the greater the temperature anomaly of the battery, resulting in a larger area affected by the battery. In order to ensure accurate analysis of the temperature value of the point to be analyzed, it is necessary to expand the corresponding reference area to ensure that the subsequent analysis range can cover the temperature changes of other individual cells in the vicinity of the point to be analyzed due to the temperature anomaly. Therefore, a larger reference radius is set.

[0089] In one possible implementation, generating a sequence to be transmitted based on several of the detection data includes: obtaining the time of detection data acquisition, extracting temperature values ​​from the detection data, and arranging the temperature values ​​in chronological order according to their corresponding times to generate a sequence to be transmitted.

[0090] In one possible implementation, feature extraction of the transmission sequence to obtain the transmission sequence includes: extracting temperature anomaly values ​​corresponding to each anomaly point in the temperature detection results, substituting the temperature anomaly values ​​into a set feature duration adjustment function to obtain the feature duration of the anomaly point; one expression of the feature duration adjustment function includes:

[0091]

[0092] in, The adjusted feature duration, This is the threshold for abnormal temperature values. This is an abnormal temperature value; The initial duration is set. The larger the temperature anomaly, the greater the degree of temperature anomaly in the individual battery. In order to ensure the accuracy of the fault analysis of the corresponding individual battery, the feature duration needs to be appropriately extended to increase more temperature data. Therefore, the larger the temperature anomaly, the longer the feature duration should be set.

[0093] A preliminary transmission sequence is obtained by extracting the sequence to be transmitted based on the characteristic duration. Specifically, several temperature values ​​close to the current time are extracted from the sequence to be transmitted based on the characteristic duration. For example, if the characteristic duration is 0.5 hours, then the temperature values ​​within 0.5 hours of the current time in the sequence to be transmitted need to be extracted and these temperature values ​​are integrated into the preliminary transmission sequence.

[0094] Feature extraction is performed on the initial transmission sequence to obtain several sets of transmission sequences;

[0095] The sequence to be transmitted is obtained, and several temperature values ​​in the sequence are fitted into a temperature change curve. The temperature change curve is then truncated based on a characteristic duration to obtain a reference portion of the temperature change curve corresponding to the initial transmitted sequence. Specifically, the temperature change curve segment closest to the current moment is truncated based on the characteristic duration. For example, if the characteristic duration is 0.5 hours, then the temperature change curve segment within 0.5 hours of the current moment needs to be truncated and used as the reference portion of the temperature change curve.

[0096] The temperature values ​​in the transmission sequence are fitted into partial temperature change curves according to their chronological order at corresponding times; the partial temperature change curves corresponding to each set of transmission sequences are obtained sequentially.

[0097] Calculate the deviation between the temperature change curves of each part and the temperature change curve of the reference part; specifically, obtain the partial temperature change curves. Temperature change curves of the reference section ; through formula The deviation value was calculated. The transmission sequence corresponding to the temperature change curve with the smallest deviation value is selected as the final transmission sequence.

[0098] Because the communication environment of mining new energy vehicles is poor in their actual working environment, such as mine shafts and mines, communication quality issues can easily lead to communication interruptions and transmission congestion when transmitting large amounts of data between the mining new energy vehicles and the cloud temperature analysis platform. Therefore, this embodiment uses a unique feature extraction method to reduce the temperature values ​​in the transmission sequence to obtain the transmission sequence. The amount of data in the transmission sequence is greatly reduced compared to the amount of data in the sequence to be transmitted, while the transmission sequence can retain the characteristics of the data in the sequence to be transmitted to a high extent. In conjunction with the previous screening of individual cells, some important, abnormal, and limited data that can reflect abnormal individual cells are prioritized for transmission to the cloud temperature analysis platform. It is worth noting that in another embodiment, the above method for obtaining the transmission sequence is also used to obtain the transmission sequences of voltage and current, which are transmitted together.

[0099] In one possible implementation, feature extraction is performed on the preliminary transmission sequence to obtain several sets of transmission sequences, including: fitting the temperature values ​​in the preliminary transmission sequence to obtain a preliminary temperature change curve; obtaining a set unit time length, and segmenting the preliminary temperature change curve based on the unit time length to obtain several unit temperature change curve segments;

[0100] To calculate the standard deviation of a unit temperature change curve segment, the following formula can be used: ;

[0101] ;

[0102] in, The corresponding unit temperature change curve segment, The average value of the corresponding unit temperature change curve segment. This represents the end time of the corresponding unit temperature change curve segment. This represents the start time of the corresponding unit temperature change curve segment;

[0103] Substituting the standard deviation into the set characteristic number generation function, the characteristic number corresponding to the unit temperature change curve segment is obtained; one expression of the characteristic number generation function includes:

[0104] ;

[0105] in, The adjusted feature number, This refers to the standard feature number, which is the number of temperature values ​​per unit time length in the initial transmission sequence. It's understandable that since temperature values ​​are collected at fixed time intervals, It is a fixed value, which is the result of rounding down the ratio of the unit time length to the acquisition time interval; Let the standard deviation be ; when the standard deviation is The larger the value, the greater the fluctuation of the temperature change curve segment, and the more feature points need to be retained to accurately reflect the characteristics of temperature change; at this time, the corresponding feature number is closer to the value of the standard feature number.

[0106] The initial transmission sequence is divided into several unit sequence groups based on a unit time length. Each unit sequence group corresponds one-to-one with a unit temperature change curve segment, meaning the time length of each unit sequence group is consistent with the start and end times of the unit temperature change curve segment. Based on the feature number, a corresponding number of temperature values ​​are randomly selected from the corresponding sequence group to obtain several sets of unit feature sequences corresponding to the sequence group. It can be understood that the number of unit feature sequences corresponding to each sequence group is the same and is a predetermined number. In this embodiment, the number of unit feature sequences corresponding to each sequence group is 50.

[0107] Several transmission sequences are obtained by randomly combining the unit feature sequences corresponding to different sequence groups; among them, the temperature values ​​corresponding to different transmission sequences are not exactly the same.

[0108] In one possible implementation, the cloud-based temperature analysis platform is used to analyze the transmission sequence and obtain corresponding analysis results. It is understood that the cloud-based temperature analysis platform provides a higher level of detail in analyzing the transmission sequence than the local analysis methods used by mining new energy vehicles.

[0109] In one possible implementation, transmitting the transmission sequence to the cloud temperature analysis platform includes: a primary transmission and a secondary transmission, wherein the primary transmission is transmitting the transmission sequence corresponding to each anomaly point, and the secondary transmission is transmitting the transmission sequence corresponding to each individual cell in the area to be analyzed corresponding to each anomaly point.

[0110] Please see Figure 2 Secondly, a battery early warning device for mining new energy vehicles is provided, comprising: a data acquisition module, a data analysis module, and a data transmission module;

[0111] The data acquisition module is used to acquire the temperature detection data of mining new energy vehicles in real time. The temperature detection data includes the detection data of each individual battery cell at the corresponding time.

[0112] The data analysis module includes an anomaly detection unit and a transmission sequence generation unit;

[0113] The anomaly detection unit is used to determine several points to be analyzed based on the temperature detection data at the current moment; to perform temperature anomaly detection on each point to be analyzed, and to obtain the temperature detection results for each point to be analyzed; and to issue an early warning based on the anomalies in the temperature detection results and the corresponding temperature values.

[0114] The transmission sequence generation unit is used to acquire detection data of several points to be analyzed at several times, and generate a transmission sequence based on the detection data; and perform feature extraction on the transmission sequence to obtain the transmission sequence.

[0115] The data transmission module is used to transmit the transmission sequence to the cloud-based temperature analysis platform.

[0116] Some of the data in the above formula are calculated by removing dimensions and taking their numerical values. The formula is the closest to the real situation obtained by software simulation of a large amount of collected data. The preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0117] How this application works:

[0118] The system acquires real-time temperature detection data from mining new energy vehicles; identifies several points to be analyzed based on the current temperature detection data; performs temperature anomaly detection on each point to obtain the temperature detection results; issues warnings based on anomalies and corresponding temperature values ​​in the temperature detection results; acquires detection data for several points to be analyzed at several times, and generates a transmission sequence based on the detection data; extracts features from the transmission sequence to obtain a transmission sequence, which is then transmitted to a cloud-based temperature analysis platform; performs a simple preliminary analysis of the battery detection data using local processing equipment to promptly check for simple abnormal faults; and extracts features from the data to obtain the transmission sequence, minimizing the amount of data transmitted so that the data can be quickly transmitted to the cloud-based temperature analysis platform for in-depth analysis, further ensuring the timeliness of temperature fault warnings.

[0119] The above embodiments are only used to illustrate the technical methods of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of this application without departing from the spirit and scope of the technical methods of this application.

Claims

1. A battery early warning method for new energy mining vehicles, characterized in that, include: Acquire temperature detection data for mining new energy vehicles, the temperature detection data including detection data of each individual battery cell at a corresponding time; the detection data includes the battery coordinates of the individual battery cell and the temperature value at the corresponding time; Several points to be analyzed are determined based on the temperature detection data at the current moment; The temperature values ​​corresponding to each point to be analyzed are analyzed to obtain the temperature detection results of each point to be analyzed; Warnings are issued based on anomalies in the temperature detection results and their corresponding temperature values. Acquire detection data of the point to be analyzed at several times, and generate a sequence to be transmitted based on the detection data; Feature extraction is performed on the sequence to be transmitted to obtain the transmission sequence, including: Extract the temperature anomaly values ​​corresponding to each anomaly point in the temperature detection results, and substitute the temperature anomaly values ​​into the set feature duration adjustment function to obtain the feature duration of the anomaly point. A preliminary transmission sequence is obtained by intercepting the sequence to be transmitted based on the characteristic duration. Feature extraction is performed on the initial transmission sequence to obtain several sets of transmission sequences; The sequence to be transmitted is obtained, several temperature values ​​in the sequence are fitted into a temperature change curve, and the temperature change curve is truncated based on the characteristic duration to obtain the reference part temperature change curve corresponding to the initial transmission sequence. The temperature values ​​in the transmission sequence are fitted into partial temperature change curves according to their chronological order at corresponding times; the partial temperature change curves corresponding to each set of transmission sequences are obtained sequentially. Calculate the deviation between the temperature change curve of each part and the temperature change curve of the reference part; select the transmission sequence corresponding to the temperature change curve with the smallest deviation as the final transmission sequence; The transmission sequence is sent to a cloud-based temperature analysis platform.

2. The battery early warning method for a mining new energy vehicle according to claim 1, characterized in that, The determination of several points to be analyzed based on the current temperature detection data includes: Extract the detection data corresponding to each individual cell from the temperature detection data, and extract the cell coordinates and temperature values ​​from the detection data; construct the three-dimensional coordinate points of the individual cell based on the cell coordinates and temperature values; fit each three-dimensional coordinate point into a temperature change surface; Using the three-dimensional coordinate points corresponding to the battery coordinates of each individual cell as reference points, the points to be analyzed are generated based on the temperature change surface and each reference point.

3. The battery early warning method for a mining new energy vehicle according to claim 2, characterized in that, The generation of the points to be analyzed based on the temperature change surface and various reference points includes: Obtain the set initial radius and obtain the reference point. ; using the battery coordinates corresponding to the reference point A two-dimensional region is constructed with the initial radius as the center. , ,in The initial radius of the domain; The two-dimensional region As a constraint condition, the temperature change surface is constrained to obtain the corresponding restricted surface. ; When the temperature value corresponding to the reference point is greater than its corresponding limiting surface When calculating the temperature values ​​of all three-dimensional coordinate points within the reference point, the point properties of the reference point are recorded as the point to be analyzed. When the temperature value corresponding to the reference point is less than its corresponding limiting surface When calculating the temperature values ​​of all three-dimensional coordinate points within the reference point, the point properties of the reference point are recorded as the point to be analyzed.

4. The battery early warning method for a mining new energy vehicle according to claim 1, characterized in that, The process of detecting temperature anomalies at each point to be analyzed and obtaining the temperature detection results for each point to be analyzed includes: Obtain the temperature value corresponding to each point to be analyzed. When the temperature value is greater than the set temperature anomaly threshold, mark the point to be analyzed as an anomaly point; otherwise, mark the point to be analyzed as a secondary analysis point. Obtain the temperature change surface at the current moment, and calculate the reference range radius corresponding to each secondary analysis point based on the temperature change surface; Using the battery coordinates corresponding to each secondary analysis point A two-dimensional region is constructed with the reference radius as the center, and this two-dimensional region is denoted as the region to be analyzed. , ,in, The battery coordinates are The reference range radius corresponding to the secondary analysis point; Obtain the surface of temperature change at the current moment. and the temperature change surface at the previous moment. ; The temperature change surface Temperature change surface and the region to be analyzed Substitute the set temperature anomaly evaluation function to obtain the temperature anomaly value corresponding to the secondary analysis point; When the abnormal temperature value exceeds the set abnormal temperature value threshold, the secondary analysis point is marked as an abnormal point; otherwise, the secondary analysis point is marked as a normal point. The various abnormal points, along with their corresponding temperature values ​​and abnormal temperature values, are integrated into the temperature detection results.

5. The battery early warning method for a mining new energy vehicle according to claim 4, characterized in that, The calculation of the reference range radius for each secondary analysis point based on the temperature-varying surface includes: Obtain the battery coordinates of the secondary analysis points Battery coordinates based on quadratic analysis points Constructing the first reference curve with temperature change surface Second reference curve Get the first unit distance Second unit distance ; the first reference curve Second reference curve First unit distance Second unit distance Substitute the values ​​into the set reference range radius calculation function to obtain the reference range radius corresponding to the secondary analysis point; One expression of the reference domain radius calculation function includes: ； in, The radius of the reference neighborhood corresponding to the secondary analysis point. The radius of the set reference area.

6. The battery early warning method for a mining new energy vehicle according to claim 1, characterized in that, The step of generating a sequence to be transmitted based on several of the detection data includes: The time of data acquisition is obtained, the temperature value in the data is extracted, and the temperature value is arranged in chronological order according to its corresponding time to generate a sequence to be transmitted.

7. The battery early warning method for a mining new energy vehicle according to claim 1, characterized in that, The feature extraction of the preliminary transmission sequence yields several sets of transmission sequences, including: The temperature values ​​in the initial transmission sequence are fitted to obtain an initial temperature change curve; a set unit time length is obtained, and the initial temperature change curve is segmented based on the unit time length to obtain several unit temperature change curve segments; Calculate the standard deviation of the unit temperature change curve segment; substitute the standard deviation into the set characteristic number generation function to obtain the characteristic number corresponding to the unit temperature change curve segment; The initial transmission sequence is divided into several unit sequence groups based on a unit time length, and each unit sequence group corresponds one-to-one with a unit temperature change curve segment; based on the feature number, a corresponding number of temperature values ​​are randomly selected from the corresponding sequence group to obtain several unit feature sequences corresponding to the sequence group. Several transmission sequences are obtained by randomly combining the unit feature sequences corresponding to different sequence groups.

8. A battery early warning method for a mining new energy vehicle according to claim 7, characterized in that, One expression of the feature number generation function includes: ； in, The adjusted feature number, For the set standard feature number, The standard deviation is denoted as .

9. A battery early warning device for a mining new energy vehicle, based on the operation of a battery early warning method for a mining new energy vehicle according to any one of claims 1 to 8, characterized in that, include: Data acquisition module, data analysis module, and data transmission module; The data acquisition module is used to acquire temperature detection data of mining new energy vehicles in real time. The temperature detection data includes the detection data of each individual battery cell at the corresponding time. The data analysis module includes an anomaly detection unit and a transmission sequence generation unit; The anomaly detection unit is used to determine several points to be analyzed based on the temperature detection data at the current moment; to perform temperature anomaly detection on each point to be analyzed, and to obtain the temperature detection results of each point to be analyzed; and to issue an early warning based on the anomalies in the temperature detection results and the corresponding temperature values. The transmission sequence generation unit is used to acquire detection data of several points to be analyzed at several times, and generate a transmission sequence based on the detection data; and perform feature extraction on the transmission sequence to obtain the transmission sequence. The data transmission module is used to transmit the transmission sequence to the cloud-based temperature analysis platform.

Images