Sharing electric bicycle battery safety monitoring method and system based on multi-source sensor fusion and computer equipment

Abstract

The invention discloses a shared electric bicycle battery safety monitoring method and system based on multi-source sensor fusion and computer equipment, and belongs to the technical field of shared electric bicycle battery supervision. The method comprises the following steps: acquiring multi-source battery position monitoring data and multi-dimensional battery state data of a shared electric bicycle through a plurality of sensors deployed in a battery compartment; based on the monitoring time and the battery monitoring position, time-space synchronization is carried out on multi-source battery position monitoring data, battery positioning is carried out, the battery state change trend is obtained through comparison of multi-dimensional battery state data of adjacent time sequences, then the battery health degree in the current state is evaluated, and battery life prediction is carried out. And according to a battery life prediction result, matching a multi-level risk index, when the multi-dimensional battery state data meets a risk index threshold value of a corresponding monitoring dimension, triggering a corresponding early warning mechanism, and performing multi-dimensional battery risk early warning in combination with battery positioning information. The method has the effects of improving the safety performance of the shared electric bicycle battery and detecting the battery abnormity in time.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of shared electric bicycle battery supervision, and in particular to a shared electric bicycle battery safety monitoring method and system based on multi-source sensor fusion and a computer device. BACKGROUND

[0002] At present, with the popularity of shared electric bicycles, higher requirements are put forward for the safety of the batteries of shared electric bicycles.

[0003] Shared electric bicycles are placed outdoors for a long time and are affected by external environments such as rain, sun exposure, high temperature and other harsh environments, which may affect the battery life of the electric bicycle, and even cause battery failure or line failure, which is prone to cause fire hazards. The existing battery monitoring method of the shared electric bicycle is usually checked one by one by the management personnel on site, but the placement, scheduling and user use of the shared electric bicycle will change the location of the electric bicycle, and the placement amount of the shared electric bicycle is large, which not only needs to consume a large amount of manpower for inspection, but also the inspection result is limited by the experience of the inspection personnel, and it is difficult to timely investigate each shared electric bicycle as the electric bicycles flow, which is prone to missed detection, false detection, and failure to timely investigate risks. For the above related technologies, there is further improvement space for the battery safety monitoring of shared electric bicycles. SUMMARY

[0004] In view of the insufficient battery safety supervision of the shared electric bicycle in the prior art, the problem that the battery risk investigation of the flowing electric bicycle is not timely and effective, resulting in missed detection, false detection and untimely risk investigation, the present application provides a shared electric bicycle battery safety monitoring method and system based on multi-source sensor fusion and a computer device, which can detect and track the battery state in multiple dimensions in real time by setting multiple sensors in the battery compartment, and monitor the battery of the shared electric bicycle throughout its life cycle, thereby improving the safety performance of the battery of the shared electric bicycle and timely detecting battery abnormalities.

[0005] In the first aspect, the above application aims to achieve the following technical solutions: A shared electric bicycle battery safety monitoring method based on multi-source sensor fusion, the method comprising: Obtaining multi-source battery position monitoring data of a shared electric bicycle, performing spatio-temporal synchronization processing on the multi-source battery position monitoring data based on monitoring time and battery monitoring position to obtain battery positioning information of the shared electric bicycle; Obtaining multi-dimensional battery state data, comparing adjacent time series data of the multi-dimensional battery state data respectively to obtain the battery state change trend of each monitoring dimension; According to the battery state change trend, the battery health degree in the current state is evaluated, and the battery life prediction is performed based on the battery health degree evaluation result, and the multi-level risk index matching is performed according to the battery life prediction result. According to the matching result, when the multi-dimensional battery state data meets the risk index threshold of the corresponding monitoring dimension, the corresponding early warning mechanism is triggered, and the multi-dimensional battery risk early warning is performed in combination with the battery positioning information.

[0006] In a preferred example, the application can be further configured to: according to the matching result, when the multi-dimensional battery state data meets the risk index threshold of the corresponding monitoring dimension, the corresponding early warning mechanism is triggered, and the multi-dimensional battery risk early warning is performed in combination with the battery positioning information, including: According to the risk index matching result, the multi-dimensional battery state data is compared with the risk index threshold of the corresponding dimension respectively, and the multi-dimensional parameter comparison result in the current state is obtained; According to the multi-dimensional parameter comparison result, when the risk index threshold of the corresponding monitoring dimension is met, the corresponding early warning mechanism is triggered, and the alarm information is generated in combination with the battery positioning information and sent to the management end for multi-dimensional battery risk early warning, wherein the multi-dimensional battery risk early warning includes but is not limited to under-voltage early warning, overload protection early warning, and leakage detection early warning.

[0007] In a preferred example, the application can be further configured to: according to the battery state change trend, the battery health degree in the current state is evaluated, and the battery life prediction is performed based on the battery health degree evaluation result, and the multi-level risk index matching is performed according to the battery life prediction result, including: The multi-dimensional battery state data is input into the pre-trained SOH model, the battery state change trend is compared with the pre-set battery state variable in the model, the battery SOH value is generated according to the comparison result, and the battery health degree is evaluated; The number of times of battery charging and discharging and the battery capacity in the current state are counted, and the number of times of battery charging and discharging and the battery capacity are compared with the preset factory data respectively, and the ratio of the number of times of battery charging and discharging and the ratio of the battery capacity are obtained; According to the battery health degree evaluation result, the battery charging and discharging times ratio and the battery capacity ratio, the battery life is comprehensively predicted, and the multi-level risk index matching is performed according to the battery life prediction result.

[0008] In a preferred example, the application can be further configured to: the multi-source battery position monitoring data of the shared electric bicycle is obtained, the multi-source battery position monitoring data is processed in space-time synchronization based on the monitoring time and the battery monitoring position, and the battery positioning information of the shared electric bicycle is obtained, including: The Beidou positioning data and the GPS positioning data of the shared electric bicycle are acquired, time asynchronous processing is performed on the Beidou positioning data and the GPS positioning data through a pre-trained spatio-temporal Bayesian network, and the Beidou positioning data and the GPS positioning data synchronized in monitoring time are obtained. The Beidou positioning data and the GPS positioning data of the same monitoring time and the same battery monitoring position are subjected to spatial deviation calibration processing, and battery positioning information synchronized in time and space is obtained.

[0009] In a preferred example, the application can be further configured as follows: the Beidou positioning data and the GPS positioning data of the shared electric bicycle are acquired, time asynchronous processing is performed on the Beidou positioning data and the GPS positioning data through a pre-trained spatio-temporal Bayesian network, and the Beidou positioning data and the GPS positioning data synchronized in monitoring time are obtained, including: The Beidou positioning data and the GPS positioning data of the shared electric bicycle are acquired, and signal delay features of the Beidou positioning data and the GPS positioning data are extracted through a pre-trained spatio-temporal Bayesian network. Position coordinate information of each battery observation point is acquired, common features between signal delay features of the same position coordinate information are analyzed, and signal delay common features are obtained. Mean value calculation is performed on the signal delay common features of all battery observation points, delay time compensation processing is performed on the Beidou positioning data and the GPS positioning data, and the Beidou positioning data and the GPS positioning data synchronized in monitoring time are obtained.

[0010] In a preferred example, the application can be further configured as follows: the Beidou positioning data and the GPS positioning data of the same monitoring time and the same battery monitoring position are subjected to spatial deviation calibration processing, and battery positioning information synchronized in time and space is obtained, including: After the monitoring time is synchronized, the Beidou positioning data and the GPS positioning data of the same monitoring time and the same battery monitoring position are acquired, and positioning data deviation of adjacent monitoring time is counted. Position correlation between each battery observation point is acquired, and spatial correlation coefficients of corresponding observation positions are superimposed on the Beidou positioning data and the GPS positioning data. Based on the positioning data deviation and the spatial correlation coefficients, a pre-trained spatio-temporal Bayesian network is used to analyze positioning deviation probability of each battery monitoring position in a moving process, and spatial deviation calibration processing is performed on the maximum positioning deviation probability.

[0011] In a preferred example, the application can be further configured as follows: the Beidou positioning data and the GPS positioning data of the same monitoring time and the same battery monitoring position are subjected to spatial deviation calibration processing, and battery positioning information synchronized in time and space is obtained, further including: Based on the battery positioning information, the battery displacement status and displacement count are obtained. Combined with the preset battery abnormal movement index, it is determined whether the battery has moved abnormally. When the battery moves abnormally, an abnormal alarm is triggered.

[0012] In a preferred embodiment, this application can be further configured as follows: the acquisition of multi-dimensional battery state data, and the comparison of adjacent time-series data of the multi-dimensional battery state data to obtain the battery state change trend of each monitoring dimension, includes: Acquire battery temperature data and smoke data, compare battery temperature data and smoke data from adjacent time series to obtain battery temperature fluctuations and smoke change fluctuations, and analyze battery temperature change trends and smoke change trends. Obtain battery state of charge (SOC) data and determine the trend of SOC change by comparing SOC data from adjacent time series.

[0013] Secondly, the above-mentioned inventive objective of this application is achieved through the following technical solutions: A shared electric bicycle battery safety monitoring system based on multi-source sensor fusion, wherein the system is applied to the aforementioned shared electric bicycle battery safety monitoring method based on multi-source sensor fusion, and the system includes: The battery positioning module is used to acquire multi-source battery location monitoring data of shared electric bicycles, and to perform spatiotemporal synchronization processing on the multi-source battery location monitoring data based on the monitoring time and battery monitoring location to obtain the battery positioning information of the shared electric bicycles. The battery status monitoring module is used to acquire multi-dimensional battery status data, compare adjacent time-series data of the multi-dimensional battery status data, and obtain the battery status change trend of each monitoring dimension. The risk indicator matching module is used to assess the battery health under the current state based on the battery state change trend, predict the battery life based on the battery health assessment results, and perform multi-level risk indicator matching according to the battery life prediction results. The risk warning module is used to trigger a corresponding warning mechanism when the multi-dimensional battery status data meets the risk indicator threshold of the corresponding monitoring dimension based on the matching results, and to perform multi-dimensional battery risk warning in combination with the battery location information.

[0014] Thirdly, the above-mentioned objectives of this application are achieved through the following technical solutions: A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described method for monitoring the battery safety of shared electric bicycles based on multi-source sensor fusion.

[0015] Fourthly, the above-mentioned objectives of this application are achieved through the following technical solutions: A computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for monitoring the battery safety of shared electric bicycles based on multi-source sensor fusion.

[0016] In summary, this application includes at least one of the following beneficial technical effects: 1. This application uses both BeiDou satellite positioning and GPS positioning to accurately locate the battery position of shared electric bicycles, and monitors multi-dimensional status data such as battery temperature, smoke, and internal status in real time to analyze changes in battery status and provide early warnings before risks occur. By assessing the battery health and predicting battery life under the current state, multi-level risk indicators are matched, and corresponding risk indicators are applied to batteries with different risk levels for differentiated and personalized monitoring. When the multi-dimensional battery status data meets the risk indicator threshold of the corresponding monitoring dimension, the corresponding early warning mechanism is triggered. Combined with battery location information, abnormal battery location and multi-dimensional risk warning are provided. This allows for comprehensive and full life cycle monitoring of shared electric bicycle batteries. Compared with manual inspection, this application can also conduct real-time and effective risk screening of batteries in mobile electric bicycles, which can improve the battery safety performance of shared electric bicycles and detect battery abnormalities in a timely manner. 2. This application sets up a multi-level battery risk early warning mechanism, which sets corresponding risk indicators and indicator thresholds for different risk levels. When the indicator threshold of the corresponding monitoring dimension is reached, the early warning mechanism is triggered to provide multi-dimensional early warning. It can set different levels of risk indicators based on the actual state of the battery and perform multi-dimensional monitoring and early warning of parameters that affect the normal operation of the battery. It can also generate alarm information in a timely manner based on the battery location information and send it to the management terminal for multi-dimensional early warning, which can effectively improve the accuracy and timeliness of battery risk monitoring under different risk levels. 3. This application uses the SOH model to assess battery health and combines multiple data affecting battery life, such as the charge-discharge ratio and battery capacity ratio, to make a comprehensive prediction of battery life. This can improve the accuracy and authenticity of battery life prediction. Based on the battery life prediction results, multi-level risk indicators are matched to monitor risks throughout the battery's entire life cycle. Attached Figure Description

[0017] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0018] Figure 1This is a flowchart illustrating the implementation of the shared electric bicycle battery safety monitoring method based on multi-source sensor fusion in this embodiment.

[0019] Figure 2 This is a flowchart illustrating the implementation of step S10 of the shared electric bicycle battery safety monitoring method in this embodiment.

[0020] Figure 3 This is a flowchart illustrating the implementation of step S101 of the shared electric bicycle battery safety monitoring method in this embodiment.

[0021] Figure 4 This is a flowchart illustrating the implementation of step S102 of the shared electric bicycle battery safety monitoring method in this embodiment.

[0022] Figure 5 This is a flowchart illustrating the implementation of step S20 of the shared electric bicycle battery safety monitoring method in this embodiment.

[0023] Figure 6 This is a flowchart illustrating the implementation of step S30 of the shared electric bicycle battery safety monitoring method in this embodiment.

[0024] Figure 7 This is a flowchart illustrating the implementation of step S40 of the shared electric bicycle battery safety monitoring method in this embodiment.

[0025] Figure 8 This is a structural block diagram of the shared electric bicycle battery safety monitoring system based on multi-source sensor fusion in this embodiment.

[0026] Figure 9 This is a schematic diagram of the internal structure of a computer device used to implement a method for monitoring the safety of shared electric bicycle batteries. Detailed Implementation

[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] It should be understood that, when used in this specification, the terms “comprising” and “including” indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0029] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification, unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “the” are intended to include the plural forms.

[0030] It should also be further understood that the term "and / or" as used in this specification refers to any combination of one or more of the associated listed items, as well as all possible combinations, and includes such combinations.

[0031] In one embodiment, such as Figure 1 As shown, this application discloses a method for monitoring the battery safety of shared electric bicycles based on multi-source sensor fusion, which specifically includes the following steps: S10: Obtain multi-source battery location monitoring data of shared electric bicycles, and perform spatiotemporal synchronization processing on the multi-source battery location monitoring data based on monitoring time and battery monitoring location to obtain battery positioning information of shared electric bicycles.

[0032] Specifically, such as Figure 2 As shown, step S10 includes: S101: Obtain BeiDou and GPS positioning data of shared electric bicycles, and perform time-asynchronous processing through a pre-trained spatiotemporal Bayesian network to obtain BeiDou and GPS positioning data that are synchronized with the monitoring time.

[0033] Specifically, a pre-trained spatiotemporal Bayesian network is used to synchronize the monitoring time of BeiDou positioning data and GPS positioning data. Data collected at the same time are calibrated for deviation to obtain BeiDou positioning data and GPS positioning data with synchronized monitoring time.

[0034] Specifically, such as Figure 3 As shown, step S101 includes: S1011: Obtain BeiDou and GPS positioning data of shared electric bicycles, and extract signal delay features of BeiDou and GPS positioning data respectively through a pre-trained spatiotemporal Bayesian network.

[0035] Specifically, multiple sensors are deployed in the battery compartment of the shared electric bicycle to monitor the battery. The BeiDou positioning module obtains the battery's BeiDou positioning data, and the GPS positioning module obtains the battery's GPS positioning data. The signal delay features of the BeiDou positioning data and GPS positioning data are extracted by a pre-trained spatiotemporal Bayesian network. The signal delay features are the time features required for the BeiDou or GPS satellite to send signals to the receiver and convert them into identifiable signals.

[0036] In this embodiment, the spatiotemporal Bayesian network represents the conditional dependencies between variables using a directed acyclic graph (DAG). It also incorporates time slices (dynamic Bayesian network) and spatial relationships for training. The network structure of this spatiotemporal Bayesian network includes a time dimension, a spatial dimension, and corresponding conditional dependencies. The time dimension includes the positioning feature data contained in each time slice t, which includes satellite status, receiver status, observations, and environmental parameters. The spatial dimension includes the geometric relationship between BeiDou satellites, GPS, and the receiver (represented by the receiving distance) and the correlation between BeiDou and GPS observations in the same time slice (represented by the covariance between BeiDou positioning observations and GPS observations at the same timestamp). The conditional dependencies include the carrier phase and pseudorange observations of BeiDou and GPS, where pseudorange observations include the geometric distance between BeiDou satellites, GPS, and the receiver at the same timestamp, clock errors, and atmospheric delays.

[0037] The system collects satellite observation sequences and corresponding battery real-time positioning data of BeiDou and GPS at multiple time steps, inputs them into a Bayesian network, learns the conditional probability distribution through a Bayesian estimation algorithm, and verifies it using a Gaussian distribution. It then uses Bayesian inference to estimate the time delay based on the verified probability distribution. The accuracy of the time delay estimation is evaluated by the root mean square error of the time delay estimation. When the preset accuracy is achieved, the signal delay characteristics of BeiDou positioning data and GPS positioning data are obtained.

[0038] S1012: Obtain the location coordinate information of each battery observation point, analyze the common characteristics of signal delay features among the same location coordinate information, and obtain the common characteristics of signal delay.

[0039] Specifically, based on the size of the battery module of the shared electric bicycle and the multiple sensors deployed in the battery compartment, the location coordinate information of each marked battery observation point is obtained. By comparing the signal delay characteristics of adjacent time sequences of the same location coordinates, i.e. adjacent monitoring times, that is, the common characteristics between signal delay times, such as the average time required to receive and convert multiple signals into identifiable signals, the common characteristics of signal delay are used as the signal delay characteristics.

[0040] S1013: The average value is calculated by using the common characteristics of signal delay at all battery observation points. Delay time compensation processing is performed on the BeiDou positioning data and GPS positioning data to obtain BeiDou positioning data and GPS positioning data that are synchronized with the monitoring time.

[0041] Specifically, the common characteristics of signal delay at all battery observation points are obtained and the mean is calculated. The calculated mean is used as the delay time compensation for the positioning data. Corresponding delay compensation processing is performed on the BeiDou positioning data and GPS positioning data to obtain BeiDou positioning data and GPS positioning data that are synchronized with the monitoring time.

[0042] S102: Spatial deviation calibration processing is performed on BeiDou positioning data and GPS positioning data at the same monitoring time and the same battery monitoring location to obtain spatiotemporally synchronized battery positioning information.

[0043] Specifically, such as Figure 4 As shown, step S102 includes: S1021: After the monitoring time is synchronized, acquire BeiDou positioning data and GPS positioning data at the same monitoring time and the same battery monitoring location, and calculate the positioning data deviation between adjacent monitoring times.

[0044] Specifically, after the monitoring time is synchronized, BeiDou positioning data and GPS positioning data at the same monitoring time and the same battery monitoring location are obtained, and the positioning data deviation between adjacent monitoring times, such as coordinate deviation, is calculated. This also includes the battery attitude deviation obtained by the attitude sensor deployed in the battery compartment.

[0045] S1022: Obtain the positional correlation between each battery observation point, and superimpose the spatial correlation coefficient of the corresponding observation location onto the BeiDou positioning data and GPS positioning data respectively.

[0046] Specifically, the location correlation between various battery observation points is obtained, such as the sequential connection relationship between different battery observation points or the distance relationship between different battery observation points. Based on the location correlation, the spatial relationship coefficients or constraints of the corresponding observation positions are superimposed on the BeiDou positioning data and GPS positioning data respectively.

[0047] S1023: Based on the positioning data deviation and spatial correlation coefficient, the positioning deviation probability of each battery monitoring location during the movement process is analyzed by a pre-trained spatiotemporal Bayesian network, and the spatial deviation calibration process is performed by selecting the positioning deviation probability with the largest probability.

[0048] Specifically, based on the positioning data deviation and spatial correlation coefficient, the positioning deviation probability of each battery monitoring location during the movement process is analyzed by a pre-trained spatiotemporal Bayesian network. The BeiDou positioning data and GPS positioning data of the same monitoring location with the largest positioning deviation probability are selected for spatial deviation calibration.

[0049] The spatiotemporal Bayesian network in this embodiment includes: The GPS and BeiDou positioning data are aligned by time acquisition. The GPS and BeiDou positioning data collected at each timestamp are time-unified to form spatiotemporal feature data in the format (data acquisition timestamp, BeiDou positioning coordinates, GPS positioning coordinates). Each spatiotemporal feature data is used as a network node, and a Bayesian network is constructed according to the acquisition time. The spatiotemporal feature data is then sliced ​​according to specific time series, transforming it into multiple subsets with the same time step. The covariance of each subset is calculated, and the covariance calculation expression is shown below: (1) in, This represents the covariance of each subset of data. This indicates the number of spatiotemporal feature data in the corresponding subset. , Indicates the first The BeiDou positioning coordinate observations and GPS positioning coordinate observations in the spatiotemporal feature data. , These are the average values ​​of the BeiDou positioning coordinate observations and the GPS positioning coordinate observations, respectively.

[0050] Obtain the covariance distribution of each subset of data, perform Gaussian distribution validation, and calculate the correlation coefficient. The expression for calculating the correlation coefficient is shown below: (2) in, The correlation coefficient is... , The standard deviations of the BeiDou positioning coordinate observations and the GPS positioning coordinate observations are used as the probability distribution conditions of the edges between adjacent network nodes to complete the training of the Bayesian network.

[0051] Using the positioning data deviation as the covariance in the Bayesian network and the spatial correlation coefficient as the probability distribution condition of the edges between adjacent network nodes in the Bayesian network, the positioning deviation probability of each battery monitoring location during the movement process is output.

[0052] It should be noted that before performing spatiotemporal calibration, discrete values ​​and outliers in the data are removed, and missing values ​​are filled by interpolation.

[0053] In this embodiment, the method further includes: obtaining the battery displacement status and displacement count based on the battery positioning information, combining the preset battery abnormal movement index to determine whether the battery has moved abnormally, and performing an abnormal alarm when the battery moves abnormally.

[0054] Specifically, during the positioning process after the battery completes spatiotemporal synchronization, the battery displacement status and displacement count are obtained. In this embodiment, the abnormal battery movement indicators include the battery position being no more than 1 meter away from the shared electric bicycle position, and the battery displacement count not exceeding 3 times within a set time period. When the battery displacement status or battery displacement count reaches the abnormal battery movement indicators, it is determined that the current battery has moved abnormally. Therefore, it is necessary to perform abnormal alarm processing when abnormal movement is detected, such as reporting the abnormal battery movement information to the management personnel. It should be noted that the abnormal movement indicators can be set according to actual needs and are not limited to one of the methods in this embodiment.

[0055] S20: Acquire multi-dimensional battery state data, compare adjacent time-series data of the multi-dimensional battery state data, and obtain the battery state change trend of each monitoring dimension.

[0056] Specifically, such as Figure 5 As shown, step S20 includes: S201: Acquire battery temperature data and smoke data, compare battery temperature data and smoke data from adjacent time series to obtain battery temperature fluctuations and smoke change fluctuations, and analyze battery temperature change trends and smoke change trends.

[0057] Specifically, temperature sensors and smoke sensors deployed in the battery compartment of shared electric bicycles collect battery temperature data and smoke data respectively. When the battery temperature exceeds 60°C, an abnormal alarm is triggered to monitor overheating. By comparing battery temperature data and smoke data at adjacent time intervals, i.e., adjacent monitoring times, the battery temperature fluctuation and smoke change fluctuation are obtained. The battery temperature fluctuation trend, such as cooling or heating, is analyzed, and the smoke change trend, such as smoke value increase or decrease, is analyzed simultaneously.

[0058] S202: Obtain battery state of charge data, and determine the trend of battery state of charge change by comparing the state of charge data of adjacent time series.

[0059] Specifically, battery state of charge (SOC) data is obtained, such as by representing the battery SOC value with the remaining charge. The SOC value is compared with the SOC value of adjacent time series. When the SOC value shows a downward trend, the battery SOC value deteriorates. In this embodiment, the SOC data of adjacent time series are battery state-related data collected or detected at adjacent detection times.

[0060] In this embodiment, the battery power loss rate can also be analyzed by acquiring the change in the remaining battery power. The battery state of charge can be determined by the power loss rate. The faster the power loss rate, the worse the battery state of charge.

[0061] S30: Assess the battery health under the current state based on the battery status change trend, predict battery life based on the battery health assessment results, and match multi-level risk indicators according to the battery life prediction results.

[0062] Specifically, such as Figure 6 As shown, step S30 includes: S301: Input multidimensional battery state data into a pre-trained SOH model, compare the battery state change trend with the preset battery state variables in the model, and generate battery SOH values ​​based on the comparison results to assess battery health.

[0063] Specifically, multi-dimensional battery state data, such as voltage, current, temperature, charge / discharge time changes, and peak capacity shifts, are input into a pre-trained SOH (State of Health) model. The actual detected battery state trend-related values ​​are compared with the corresponding battery state variables in the model, and the ratio is used as the battery's SOH value to assess battery health. It should be noted that the battery health is assessed based on the changes in the SOH value corresponding to the battery state trend. If the health declines abnormally and the SOH value changes non-linearly, it indicates an anomaly.

[0064] In this embodiment, the SOH (State of Health) model assesses battery health by estimating the degree of battery degradation based on empirical curves through the recording of various battery characteristic parameters such as voltage, current, and temperature after a complete number of cycles. It also extracts data such as charge / discharge curves, battery relaxation, and internal resistance changes from the complete records of various battery characteristic parameters, recording degradation characteristics such as constant current charging time, voltage plateau changes, and peak shifts in incremental capacity curves. These recorded degradation characteristics are then correlated and mapped with the preliminary health assessment to form an SOH (State of Health) mapping relationship, thus constructing the SOH model. The SOH model in this embodiment contains the mapping relationship between the health obtained from various battery characteristic parameters and the corresponding degradation characteristics.

[0065] S302: Calculate the number of battery charge / discharge cycles and battery capacity under the current state, and compare the number of battery charge / discharge cycles and battery capacity with the preset factory data to obtain the battery charge / discharge cycle ratio and battery capacity ratio.

[0066] Specifically, the battery charge / discharge cycles and capacity are counted under the current condition. The actual number of charge / discharge cycles is compared with the maximum number of charge / discharge cycles set at the factory to obtain the battery charge / discharge cycle ratio. The current maximum capacity of the battery is compared with the maximum capacity of the battery at the time of manufacture to obtain the battery capacity ratio.

[0067] S303: Based on the battery health assessment results, the battery charge-discharge cycle ratio, and the battery capacity ratio, a comprehensive prediction of battery life is made, and multi-level risk indicators are matched according to the battery life prediction results.

[0068] Specifically, the battery health assessment results, the battery charge-discharge cycle ratio, and the battery capacity ratio are quantitatively analyzed. Based on the decay rate of each quantified value, the remaining lifespan is assessed by predicting the time required for each parameter of the battery in the current state to reach the preset lifespan threshold or the remaining charge-discharge cycle count. This yields the battery lifespan prediction result. The battery lifespan prediction result is then matched with preset multi-level risk indicators. When the battery lifespan prediction result falls within the range of the corresponding risk level, the corresponding indicator is matched with the current battery and associated with the corresponding level of early warning strategy.

[0069] The multi-level risk indicators in this embodiment are shown in the table below: Table 1 S40: Based on the matching results, when the multi-dimensional battery status data meets the risk indicator threshold of the corresponding monitoring dimension, the corresponding early warning mechanism is triggered, and multi-dimensional battery risk early warning is carried out in combination with battery location information.

[0070] Specifically, such as Figure 7 As shown, step S40 includes: S401: Based on the risk indicator matching results, the multi-dimensional battery state data is compared with the risk indicator thresholds of the corresponding dimensions to obtain the multi-dimensional parameter comparison results under the current state.

[0071] Specifically, based on the risk indicator matching results, multi-dimensional battery status data such as battery temperature, smoke concentration, and remaining power are compared with the corresponding risk indicator thresholds. For example, if the temperature exceeds 60℃, it is judged as abnormal. Based on the comparison results, multi-dimensional parameter comparison results for the current state are generated.

[0072] S402: Based on the multi-dimensional parameter comparison results, when the risk indicator threshold of the corresponding monitoring dimension is met, the corresponding early warning mechanism is triggered, and alarm information is generated and sent to the management terminal in combination with battery location information to conduct multi-dimensional battery risk early warning.

[0073] Specifically, based on the results of multi-dimensional parameter comparison, when the risk indicator thresholds of the corresponding monitoring dimensions such as temperature, smoke, and power are met, the corresponding early warning mechanism is triggered, such as battery overheating, battery + smoke joint judgment to determine whether the battery is on fire, and abnormal power loss warning. Combined with battery location information, the data is packaged to obtain alarm information and sent to the management terminal for multi-dimensional battery risk warning. The management terminal includes the shared electric bicycle management personnel, battery manufacturers, and electric bicycle riders.

[0074] The multi-dimensional battery risk warning in this embodiment includes, but is not limited to, undervoltage warning, overload protection warning, and leakage detection warning. Multiple warning items and warning thresholds can be set according to actual needs.

[0075] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0076] In one embodiment, a shared electric bicycle battery safety monitoring system based on multi-source sensor fusion is provided. This system corresponds one-to-one with the shared electric bicycle battery safety monitoring method based on multi-source sensor fusion described in the above embodiments. Figure 8 As shown, this shared electric bicycle battery safety monitoring system based on multi-source sensor fusion includes a battery positioning module, a battery status monitoring module, a risk indicator matching module, and a risk early warning module. Detailed descriptions of each functional module are as follows: The battery positioning module is used to acquire multi-source battery location monitoring data of shared electric bicycles. Based on the monitoring time and battery monitoring location, the multi-source battery location monitoring data is spatiotemporally synchronized to obtain the battery positioning information of the shared electric bicycles.

[0077] The battery status monitoring module is used to acquire multi-dimensional battery status data, compare adjacent time-series data of the multi-dimensional battery status data, and obtain the battery status change trend of each monitoring dimension.

[0078] The risk indicator matching module is used to assess the battery health under the current state based on the battery status change trend, predict the battery life based on the battery health assessment results, and perform multi-level risk indicator matching according to the battery life prediction results.

[0079] The risk warning module is used to trigger the corresponding warning mechanism when the multi-dimensional battery status data meets the risk indicator threshold of the corresponding monitoring dimension based on the matching results, and to conduct multi-dimensional battery risk warnings in combination with battery location information.

[0080] Preferably, the risk warning module includes: The multidimensional parameter comparison submodule is used to compare the multidimensional battery state data with the corresponding risk indicator thresholds based on the risk indicator matching results, and obtain the multidimensional parameter comparison results under the current state.

[0081] The multi-dimensional risk warning submodule is used to trigger the corresponding warning mechanism when the risk index threshold of the corresponding monitoring dimension is met based on the comparison results of multi-dimensional parameters. It also generates alarm information by combining battery location information and sends it to the management terminal for multi-dimensional battery risk warning. The multi-dimensional battery risk warning includes, but is not limited to, undervoltage warning, overload protection warning, and leakage detection warning.

[0082] Preferably, the risk indicator matching module includes: The battery health assessment submodule is used to input multidimensional battery state data into a pre-trained SOH model, compare the battery state change trend with the preset battery state variables in the model, and generate the battery SOH value based on the comparison results to assess the battery health.

[0083] The battery charge / discharge and capacity comparison submodule is used to count the number of battery charge / discharge cycles and battery capacity under the current state. It compares the number of battery charge / discharge cycles and battery capacity with the preset factory data to obtain the battery charge / discharge cycle ratio and battery capacity ratio.

[0084] The battery life prediction and index matching submodule is used to comprehensively predict battery life based on battery health assessment results, battery charge-discharge cycle ratio, and battery capacity ratio, and to match multi-level risk indicators according to the battery life prediction results.

[0085] Preferably, the battery positioning module includes: The positioning data acquisition submodule is used to acquire BeiDou positioning data and GPS positioning data of shared electric bicycles. It performs time asynchronous processing through a pre-trained spatiotemporal Bayesian network to obtain BeiDou positioning data and GPS positioning data that are synchronized with the monitoring time.

[0086] The spatiotemporal calibration submodule is used to perform spatial deviation calibration processing on BeiDou positioning data and GPS positioning data at the same monitoring time and the same battery monitoring location to obtain spatiotemporally synchronized battery positioning information.

[0087] Preferably, the location data acquisition submodule includes: The feature extraction unit is used to acquire BeiDou positioning data and GPS positioning data of shared electric bicycles, and extract the signal delay features of the BeiDou positioning data and the GPS positioning data respectively through a pre-trained spatiotemporal Bayesian network. The feature commonality analysis unit is used to acquire the location coordinate information of each battery observation point, analyze the common features between the signal delay features of the same location coordinate information, and obtain the signal delay common features. The time synchronization processing unit is used to calculate the average value by using the common characteristics of signal delays from all battery observation points, and to perform time delay compensation processing on the BeiDou positioning data and GPS positioning data to obtain BeiDou positioning data and GPS positioning data that are synchronized with the monitoring time.

[0088] Preferably, the spatiotemporal calibration submodule includes: The deviation analysis unit is used to acquire BeiDou positioning data and GPS positioning data at the same monitoring time and the same battery monitoring location after the monitoring time is synchronized, and to calculate the positioning data deviation between adjacent monitoring times. The location correlation analysis unit is used to obtain the location correlation relationship between various battery observation points, and to superimpose the spatial correlation coefficient of the corresponding observation location onto the BeiDou positioning data and GPS positioning data respectively. The spatial calibration unit is used to analyze the positioning deviation probability of each battery monitoring location during the movement process based on the positioning data deviation and the spatial correlation coefficient through a pre-trained spatiotemporal Bayesian network, and select the positioning deviation probability with the largest probability for spatial deviation calibration processing.

[0089] Preferably, the battery positioning module further includes: The battery displacement monitoring submodule is used to obtain the battery displacement status and displacement count based on the battery positioning information, and combined with the preset battery abnormal movement index, to determine whether the battery has moved abnormally, and to perform abnormal alarm processing when the battery moves abnormally.

[0090] Preferably, the battery status monitoring module includes: The parameter acquisition submodule is used to acquire battery temperature data and smoke data, compare battery temperature data and smoke data in adjacent time series to obtain battery temperature fluctuations and smoke change fluctuations, and analyze battery temperature change trends and smoke change trends.

[0091] The charge change analysis submodule is used to acquire battery state of charge data and determine the trend of battery state of charge change by comparing the state of charge data of adjacent time series.

[0092] Specific limitations regarding the shared electric bicycle battery safety monitoring system based on multi-source sensor fusion can be found in the limitations of the shared electric bicycle battery safety monitoring method based on multi-source sensor fusion mentioned above, and will not be repeated here. Each module in the aforementioned shared electric bicycle battery safety monitoring system based on multi-source sensor fusion 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.

[0093] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. 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, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores battery safety monitoring data for shared electric bicycles. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a shared electric bicycle battery safety monitoring method based on multi-source sensor fusion.

[0094] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements a method for monitoring the battery safety of shared electric bicycles based on multi-source sensor fusion.

[0095] Those skilled in the art will recognize that the units of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application of the technical solution and the constraints involved. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the invention.

[0096] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical functional division. In actual implementation, there may be other division methods, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored.

[0097] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0098] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the specification of the present invention.

Claims

1. A shared e-bike battery safety monitoring method based on multi-source sensor fusion, characterized in that, The method comprises: obtaining multi-source battery position monitoring data of shared electric bikes, performing spatio-temporal synchronization processing on the multi-source battery position monitoring data based on monitoring time and battery monitoring position to obtain battery positioning information of the shared electric bikes; obtaining multi-dimensional battery state data, comparing adjacent time series data of the multi-dimensional battery state data respectively to obtain battery state change trend of each monitoring dimension; evaluating battery health degree in the current state according to the battery state change trend, predicting battery life based on the battery health degree evaluation result, and matching multi-level risk indicators according to the battery life prediction result; according to the matching result, triggering a corresponding early warning mechanism when the multi-dimensional battery state data meets the risk indicator threshold of the corresponding monitoring dimension, and combining the battery positioning information to perform multi-dimensional battery risk early warning.

2. The shared e-bike battery safety monitoring method based on multi-source sensor fusion according to claim 1, characterized in that, According to the matching result, when the multi-dimensional battery state data meets the risk indicator threshold of the corresponding monitoring dimension, the corresponding early warning mechanism is triggered, and the battery positioning information is combined to perform multi-dimensional battery risk early warning, which comprises: According to the risk indicator matching result, the multi-dimensional battery state data is compared with the risk indicator threshold of the corresponding dimension to obtain the multi-dimensional parameter comparison result in the current state; according to the multi-dimensional parameter comparison result, when the risk indicator threshold of the corresponding monitoring dimension is met, the corresponding early warning mechanism is triggered, and the alarm information is generated by combining the battery positioning information and sent to the management end for multi-dimensional battery risk early warning, wherein the multi-dimensional battery risk early warning includes but is not limited to under-voltage warning, overload protection warning and leakage detection warning.

3. The shared e-bike battery safety monitoring method based on multi-source sensor fusion of claim 1, wherein, According to the battery state change trend, the battery health degree in the current state is evaluated, and the battery life is predicted based on the battery health degree evaluation result, and the multi-level risk indicators are matched according to the battery life prediction result, which comprises: inputting the multi-dimensional battery state data into the pre-trained SOH model, comparing the battery state change trend with the pre-set battery state variable in the model, generating the battery SOH value according to the comparison result to evaluate the battery health degree; statistically counting the battery charge and discharge times and the battery capacity in the current state, comparing the battery charge and discharge times and the battery capacity with the preset factory data respectively to obtain the battery charge and discharge times ratio and the battery capacity ratio; according to the battery health degree evaluation result, the battery charge and discharge times ratio and the battery capacity ratio, the battery life is comprehensively predicted, and the multi-level risk indicators are matched according to the battery life prediction result.

4. The shared e-bike battery safety monitoring method based on multi-source sensor fusion of claim 1, wherein, The method comprises: obtaining Beidou positioning data and GPS positioning data of shared electric bikes, performing time asynchronous processing on the Beidou positioning data and GPS positioning data through a pre-trained spatio-temporal Bayesian network to obtain Beidou positioning data and GPS positioning data synchronized in monitoring time; performing spatial deviation calibration processing on the Beidou positioning data and GPS positioning data of the same monitoring time and the same battery monitoring position to obtain spatio-temporal synchronized battery positioning information.

5. The shared e-bike battery safety monitoring method based on multi-source sensor fusion according to claim 4, characterized in that, The Beidou positioning data and GPS positioning data of the shared electric bicycle are acquired, time asynchronous processing is performed on the Beidou positioning data and GPS positioning data through a pre-trained spatio-temporal Bayesian network, and monitored time-synchronized Beidou positioning data and GPS positioning data are obtained. The Beidou positioning data and GPS positioning data of the shared electric bicycle are acquired, and signal delay features of the Beidou positioning data and the GPS positioning data are extracted through a pre-trained spatio-temporal Bayesian network. The position coordinate information of each battery observation point is acquired, common features between signal delay features of the same position coordinate information are analyzed, and signal delay common features are obtained. Mean value calculation is performed on the signal delay common features of all battery observation points, delay time compensation processing is performed on the Beidou positioning data and the GPS positioning data, and monitored time-synchronized Beidou positioning data and GPS positioning data are obtained.

6. The shared e-bike battery safety monitoring method based on multi-source sensor fusion according to claim 5, characterized in that, The Beidou positioning data and GPS positioning data of the same monitoring time and the same battery monitoring position are subjected to spatial deviation calibration processing, and spatio-temporally synchronized battery positioning information is obtained. After the monitoring time is synchronized, the Beidou positioning data and GPS positioning data of the same monitoring time and the same battery monitoring position are acquired, and positioning data deviation of adjacent monitoring times is counted. The position correlation relationship between each battery observation point is acquired, and spatial correlation coefficients of corresponding observation positions are superimposed on the Beidou positioning data and the GPS positioning data. Based on the positioning data deviation and the spatial correlation coefficient, the positioning deviation probability of each battery monitoring position in the moving process is analyzed through a pre-trained spatio-temporal Bayesian network, and the maximum positioning deviation probability is selected for spatial deviation calibration processing.

7. The shared e-bike battery safety monitoring method based on multi-source sensor fusion according to claim 4, characterized in that, The Beidou positioning data and GPS positioning data of the same monitoring time and the same battery monitoring position are subjected to spatial deviation calibration processing, and spatio-temporally synchronized battery positioning information is obtained. According to the battery positioning information, battery displacement state and displacement frequency are acquired, a preset battery abnormal movement index is combined, it is judged whether the battery has abnormally moved, and abnormal alarm processing is performed when the battery has abnormally moved.

8. The shared e-scooter battery safety monitoring method based on multi-source sensor fusion of claim 1, wherein, The multi-dimensional battery state data is acquired, adjacent time sequence data comparison is performed on the multi-dimensional battery state data, and the battery state change trend of each monitoring dimension is obtained. Battery temperature data and smoke data are acquired, battery temperature fluctuation and smoke change fluctuation are obtained by comparing adjacent time sequence battery temperature data and smoke data, and battery temperature change trend and smoke change trend are analyzed. Battery state of charge data is acquired, and battery state of charge change trend is judged according to adjacent time sequence state of charge data comparison.

9. A shared e-bike battery safety monitoring system based on multi-source sensor fusion, characterized in that, The system is applied to the shared electric bicycle battery safety monitoring method based on multi-source sensor fusion in any one of claims 1-8, and the system comprises: A battery positioning module is configured to acquire multi-source battery position monitoring data of a shared electric bicycle, perform spatio-temporal synchronization processing on the multi-source battery position monitoring data based on monitoring time and battery monitoring position, and obtain battery positioning information of the shared electric bicycle. The battery state monitoring module is configured to acquire multi-dimensional battery state data, compare adjacent time series data of the multi-dimensional battery state data respectively, and obtain a battery state change trend of each monitoring dimension; The risk index matching module is configured to evaluate a battery health degree in a current state according to the battery state change trend, perform battery life prediction based on a battery health degree evaluation result, and perform multi-level risk index matching according to a battery life prediction result. The risk early warning module is configured to trigger a corresponding early warning mechanism when the multi-dimensional battery state data meets a risk index threshold of a corresponding monitoring dimension according to a matching result, and perform multi-dimensional battery risk early warning in combination with the battery positioning information.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the shared electric bicycle battery safety monitoring method based on multi-source sensor fusion according to any one of claims 1 to 8.

Images