227 results about "Faulty cell" patented technology

A system for facilitating battery fault prediction is configurable to: (i) access a set of raw data comprising battery sensor data associated with a physical battery and operation data associated with operation of the physical battery; (ii) obtain an estimated battery state for the physical battery by utilizing the battery sensor data as input to a battery digital twin; (iii) obtain a battery fault prediction by utilizing (a) the estimated battery state obtained via the battery digital twin and (b) operation input based on the operation data as input to a battery fault prediction model, and wherein the battery fault prediction comprises one or more likelihood metrics indicating a likelihood of one or more battery faults occurring within one or more predetermined time periods; and (iv) cause presentation of an alert via a battery fault notification system.

The invention relates to the field of battery fault detection, in particular to a battery system health state evaluation method and system based on multi-dimensional feature fusion, and the method comprises the steps: S1, obtaining original operation data of a battery system, and carrying out the preprocessing of the original operation data to obtain a standardized data matrix; s2, based on the standardized data matrix, extracting health state features of a plurality of preset dimensions to form an original feature set; s3, constructing an incidence relation model among the features in the original feature set, and performing nonlinear fusion processing based on the incidence relation model to generate a low-dimensional fusion feature vector; s4, performing principal component analysis based on the low-dimensional fusion feature vector to extract a principal component, calculating a T2 statistical magnitude and an SPE statistical magnitude, and constructing a comprehensive health index; and S5, when the comprehensive health index exceeds a preset threshold value, analyzing the contribution degree of each feature in the original feature vector to the comprehensive health index, and positioning the fault single battery according to the contribution degree. The problems of insensitive fault symptoms, inaccurate fault positioning and high false report and missing report rate are solved.

The invention relates to a self-adaptive cooperative control system and method for a sodium-ion battery energy storage system, and relates to the technical field of energy storage system control. An EMS-BMS-PCS cooperative control module is customized, a three-level architecture dynamically adjusts a voltage threshold value, and the SOC is corrected; the multi-stage active safety protection module comprises battery cell monitoring, fault battery cell ejection, modular battery replacement and three-stage fusing protection; the power grid response module PCS performs high-frequency sampling and supports grid-connected and off-grid switching and AGC / AVC service; the intelligent collaborative optimization engine integrates data to generate a charging and discharging strategy, and early warning is performed 14 days in advance for predictive maintenance; the layered distributed control module is used for realizing battery cell-to-system level management; and the double-ring network communication redundancy module ensures real-time transmission of instructions. According to the invention, the DoD and capacity utilization rate of the sodium-ion battery is improved, and the system economy is enhanced; heat spreading is blocked through multi-stage protection, the maintenance time is shortened, and the safety is improved; millisecond-level response meets the high-order demand of a power grid, predictive maintenance reduces the operation and maintenance cost, and the method is suitable for multiple energy storage scenes.

The invention discloses a battery fault diagnosis method and device, and belongs to the technical field of battery management. The method comprises the following steps: synchronously acquiring multi-dimensional signals in a battery operation process through a multi-modal sensor array; performing encoding processing on the multi-dimensional signal through a pulse encoder to obtain a standardized pulse time sequence; based on a federated transfer learning framework, training the quantum pulse neural network in combination with a physical constraint loss function to obtain a trained battery fault diagnosis model; inputting the standardized pulse time sequence into the battery fault diagnosis model, and calculating a battery fault category and a thermal runaway probability through quantum inference; and triggering a corresponding security policy according to the thermal runaway probability and a preset threshold. By adopting the technical means of multi-mode signal fusion, quantum calculation acceleration and distributed learning, accurate and rapid diagnosis of battery faults is realized, and the method has the advantages of high precision, low delay and low power consumption.

The invention relates to a battery internal short circuit early warning method and system based on a physical information neural network, and belongs to the technical field of battery fault detection, and the method comprises the steps: constructing a first-stage PINN model through a linearized Butler-Volmer equation, and carrying out the training through a multi-source signal of a battery; taking the output of the first-stage PINN model as prior input, and constructing a second-stage PINN model by using a nonlinear electrochemical-thermal-mechanical coupling equation, and training the second-stage PINN model; using the trained first-stage PINN model and the trained second-stage PINN model to output prediction results of the voltage and the expansive force of the target battery; comparing the difference between the prediction result of the model and the measured value of the sensor to generate a voltage residual error and an expansive force residual error; and realizing identification and alarm of the short circuit risk in the target battery based on the voltage residual error and the expansive force residual error. According to the method, a multi-fidelity PINN hierarchical modeling mechanism is introduced, so that high-precision characterization and prediction of the internal state of the battery can be realized by using experimental data and mechanism model information at the same time under different precision and complexity hierarchies.

The invention provides a fault identification method applied to a battery management system and a server, and the method comprises the steps: constructing a battery fault feature correlation map, determining a reference fault feature set and a fault type set, carrying out the evolution trajectory extraction of an operation feature sequence collected in the real-time operation process of a battery, and generating a feature evolution trajectory set; inputting the feature evolution trajectory set into a preset multi-level fault reasoning model, and performing hierarchical progressive reasoning on a matching relationship between the feature evolution trajectory set and a battery fault feature association map to obtain multi-level fault probability distribution; and fault propagation path backtracking is carried out based on the multi-level fault probability distribution and the battery fault feature association map, a candidate fault path set is generated, confidence evaluation and sorting are carried out on the candidate fault path set, and a target fault path in the first sorting and corresponding fault positioning information are output. According to the invention, the accuracy, reliability and comprehensiveness of battery fault identification can be effectively improved.

The invention discloses a state monitoring method and system for an outdoor emergency power supply. Firstly, original data such as battery internal resistance, charging efficiency, temperature fluctuation and load abrupt change are collected to form an initial data set; and then noise suppression and fusion processing are carried out on the data set to obtain a smoothed battery parameter sequence. And constructing a dynamic trend vector by analyzing the differential change of the sequence, judging a potential anomaly level according to the slope of the dynamic trend vector, and outputting an anomaly probability score. And identifying an inter-parameter interaction cluster based on clustering analysis, and performing causal reasoning on a dominant cluster to determine a fault dominant factor. And finally, in combination with the real-time state, the environmental parameters and historical defect information, constructing a modeling matrix, and executing multi-dimensional clustering to identify specific fault types such as bearing wear, insulation aging and the like. If the fault is caused by internal resistance abnormity, an interference source is further positioned, and an accurate fault position is output. According to the invention, the battery fault monitoring accuracy and positioning capability in a complex environment can be effectively improved.

The invention belongs to the technical field of electric ships and fault detection. The invention discloses a digital twin electric ship power battery fault detection method based on artificial intelligence. The method is characterized by comprising the following steps: step 1, a data acquisition layer captures a battery operation state and environmental parameters in real time by deploying multiple types of sensors; 2, the digital twinborn layer realizes dynamic mapping of a physical battery system by constructing a high-fidelity virtual model; establishing a multi-physical field coupling model based on electrochemical characteristics, thermodynamic behaviors and structural parameters of the power battery; 3, the fault prediction layer extracts the harmonic component of the voltage curve, the spatial distribution mode of the temperature gradient and other multi-dimensional features through time-frequency analysis, and captures the gradual change trend of the internal resistance of the battery in combination with a sliding window technology; and 4, the application layer converts a prediction result into an operable engineering decision, and constructs a closed-loop operation and maintenance system. According to the method, efficient battery fault detection can be realized.

The invention relates to a battery fault chain blocking method and system based on dynamic knowledge graph driving. The method comprises the following steps: simulating a fault process of a battery and outputting a basic physical data set; performing time sequence deformation correction on the basic physical data set to obtain an enhanced multi-source time sequence data set; constructing an initial knowledge graph by taking the fault type as a node and the propagation conditional probability as an edge weight, and updating the initial knowledge graph by using the enhanced multi-source time sequence data set to obtain a dynamic knowledge graph; simulating a three-dimensional heat spreading path in a digital twin environment according to the current fault parameter and the dynamic knowledge graph, solving an optimal control parameter and generating a physical execution instruction set; and encrypting and pushing the physical execution instruction set to a corresponding edge device for execution. According to the method, the fault propagation probability is modeled in real time by using the dynamic knowledge graph, and the intervention strategy is optimized by combining the digital twin environment preview, so that the bottlenecks of diagnosis dissection, response hysteresis and data dependence of the traditional method are broken through.

The invention relates to the technical field of cylindrical batteries, in particular to a cylindrical battery fault prediction method, which comprises five steps of data acquisition and preprocessing, multi-dimensional time sequence feature construction, LSTM prediction model construction, model training and optimization and fault type and probability output. According to the cylindrical battery fault prediction method, three types of time sequence features are constructed, differential operation and information entropy are combined, dynamic signals of battery fault precursor are comprehensively captured, and the problem that a traditional method is single in feature is solved; a double-branch LSTM architecture is adopted, a classification branch introduces an attention mechanism to highlight key time sequence information, a regression branch optimizes long sequence training through residual connection, and the time sequence feature mining capability is improved; dual output of fault type identification and probability prediction is realized, faults are warned in advance, and the problem of prediction lag is solved.

The invention provides a battery fault processing method and device, a battery system and a battery management system, and belongs to the technical field of batteries. The battery fault processing method is used in the battery system, the battery system comprises a switch assembly and a plurality of battery packs which are physically isolated, the switch assembly is connected with the plurality of battery packs to control the connection state of the plurality of battery packs, and each battery pack in the plurality of battery packs is correspondingly provided with a detection unit; the method comprises the steps of obtaining first detection data of a first battery pack; when the first sub-data in the first detection data and the second sub-data in the first detection data are abnormal, determining that the first battery pack has a fault; and under the condition that the first detection data represents that the first battery pack has a fault, the switch assembly is controlled to disconnect the electric connection between the first battery pack and the output terminal of the battery system, so that power can be supplied through other battery packs, and the fault handling capacity of the battery system and the safety of the electric equipment are improved.

The invention discloses a three-electricity system fault analysis method, device and equipment of electric engineering equipment and a medium, and relates to the technical field of electric engineering equipment, and a three-electricity system comprises a battery system, a motor system and an electric control system; the method comprises the following steps: acquiring operation data of the electric engineering equipment based on a predefined normative network access protocol standard; determining a battery fault analysis result and a battery residual life prediction result based on the acquired battery parameter data and a preset conjoint analysis model; determining a motor fault analysis result based on the acquired motor parameter data and a preset multi-dimensional fault diagnosis architecture; determining an electric control fault analysis result based on the acquired electric control parameter data and a preset hidden fault correlation model; and through fusing the prediction result and the analysis result, based on a corresponding fusion result, determining health state quantitative information and operation and maintenance decision suggestion information of the electric engineering equipment. Problems existing in existing related schemes can be effectively solved, and applicability and accuracy of fault analysis of the electric engineering equipment are improved.

A low battery voltage protection method for a microcontroller system and a microcontroller system using the same are provided. The low battery protection method and the microcontroller system are used to prevent continuous battery drain by setting time thresholds and a count threshold. In an embodiment, when a low-voltage power-on reset voltage is not exceeded within a first preset time, the microcontroller system is forced to enter a sleep mode to prevent power consumption by an analog block. In another embodiment, when the low-voltage power-on reset voltage is exceeded, but a reset count of the microcontroller system exceeds a preset value within a second preset time, the microcontroller system is also forced to enter the sleep mode to prevent a digital block from continuously loading data, which could lead to battery failure.

The invention relates to the technical field of lithium ion battery safety monitoring, and discloses a method and a device for early warning and positioning thermal runaway of a lithium ion battery pack in advance. The method comprises the following steps: firstly, collecting real-time voltage, temperature, current and serial number data of each battery cell, and constructing a battery cell state observation tensor with a time-space label; running a battery cell thermoelectric state extended Kalman estimation algorithm based on the tensor to generate a battery cell health state partial sequence lattice; and then constructing a thermal runaway risk propagation phase space grid, finally executing manifold analysis-based local attractor region identification and early warning decision under the constraint of the grid, and outputting a high-risk source cell number and an early warning level. According to the invention, the problems of early warning lag, lack of cell group state consistency dynamic evaluation and incapability of accurately positioning fault cells caused by dependence on later physical symptoms in the prior art are solved, and the thermal runaway early warning timeliness and positioning accuracy are improved.

The invention relates to a battery fault diagnosis method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring an electric signal of any battery cell included in the battery module in the charging and discharging process of the battery module; calculating the impedance of the battery cell in the frequency domain according to the electric signal; and performing Fourier mode decomposition on the impedance to obtain a plurality of intrinsic mode functions and residual components corresponding to the impedance, and performing fault diagnosis on the battery module according to the plurality of intrinsic mode functions and residual components. By adopting the method, the accuracy of battery fault diagnosis can be improved.

The invention provides a battery fault diagnosis method, device and equipment and a storage medium, and the method is applied to a cloud server, and comprises the steps: obtaining the actual operation data of a to-be-diagnosed battery and a battery resource set corresponding to the to-be-diagnosed battery; determining a target risk score of the to-be-diagnosed battery according to the actual operation data of the to-be-diagnosed battery; according to the target risk score of the to-be-diagnosed battery and the historical risk score of each associated battery, determining the sequence of the to-be-diagnosed battery and each associated battery in the battery resource set, and according to the sequence of the to-be-diagnosed battery and each associated battery in the battery resource set, determining the target fault level of the to-be-diagnosed battery; and determining a fault diagnosis result of the to-be-diagnosed battery according to the target fault level of the to-be-diagnosed battery. According to the method, multiple faults can be diagnosed at the same time, large-scale energy storage battery data analysis and processing requirements are met, multiple data conjoint analysis can be carried out on the battery, and the diagnosis precision of fault diagnosis is guaranteed.

Readings may be received from a chemical sensor disposed proximate to a battery within a housing of a smart-home device. The readings from the chemical sensor may be processed to determine whether a chemical associated with an internal environment of the battery is present inside the smart-home device. A determination may then be made as to whether the battery is damaged based on whether the chemical is present inside the smart-home device. Alternatively, the device may determine that the chemical originates from outside of the housing of the device. A sequence of mitigation actions may then be executed to remedy the faulty battery or improve the indoor air quality.

The invention discloses a communication base station lithium battery fault diagnosis method and device and electronic equipment, relates to the technical field of lithium battery monitoring and fault diagnosis, and is used for solving the problems that the communication base station lithium battery fault diagnosis is inaccurate, and the fault source is difficult to locate. According to the invention, multi-dimensional data acquisition, including voltage, current, temperature and electrochemical impedance spectroscopy, is carried out through the battery management unit; extracting static and dynamic inconsistency characteristics based on the collected data, and calculating a comprehensive inconsistency index; similarity matching is carried out by combining the impedance deviation spectrum with a fault feature library, and the fault type and grade are identified; comprehensively judging a fault source through fault monomer space positioning, electrical topological correlation analysis, impedance spectrum deep analysis and thermal behavior anomaly analysis; and the accuracy of fault diagnosis and root positioning is obviously improved.

The invention relates to the technical field of battery cell capacity fault prediction, and particularly discloses a battery fault prediction method and system based on a hierarchical health assessment model, and the method comprises the steps: obtaining an operation historical data set and an initial capacity; performing aging stage division on the operation historical data; constructing a three-level prediction model; outputting a capacity prediction result set; constructing a dynamic residual sequence in combination with the stage sensing information and the long-short-term memory network; and outputting an alarm result. Compared with the prior art that the difference of the aging stages of the battery cell is ignored, and particularly, the technical problems that the model prediction error is large and early warning is not timely under the condition that the battery cell enters the later stage of nonlinear capacity degradation are solved. The prediction adaptability and sensitivity in each stage are effectively improved, and the accuracy and timeliness of battery cell fault early warning are enhanced.

The invention relates to the technical field of data analysis, and discloses an energy storage power supply multi-dimensional data analysis system and method. The method comprises the following steps: synchronously acquiring a battery state parameter set of an energy storage power pack and determining a corresponding working domain identifier; performing fault feature analysis on the battery state parameter set according to the working domain identifier to obtain a battery fault detection result; respectively calculating a fault isolation signal, a capacity equalization signal and a driving control signal according to the battery fault detection result; and controlling the hybrid switching circuit to cut off the fault battery connection according to the fault isolation signal, controlling the LLC resonant converter to adjust the energy distribution between the batteries according to the capacity equalization signal, and controlling the PWM driving circuit to adjust the output power of the energy storage power pack according to the driving control signal. According to the method, multi-dimensional coupling analysis of the battery state is realized, the association relationship between the rapid change characteristics and parameters of the battery under the dynamic working condition can be accurately captured, and the fault response speed and the energy management precision of the energy storage power supply are improved.

The invention provides a battery fault diagnosis method, device and system based on artificial intelligence, relates to the technical field of artificial intelligence, and aims to carry out cross-feature convolution fusion on the basis of determining a working condition mode of monitoring data of each attribute so as to deeply mine a multi-attribute collaborative change relationship and improve the fault diagnosis accuracy. The early-stage weak fault features dispersed in different channels are subjected to superposition enhancement, invalid interference caused by working condition fluctuation is filtered, the weak fault features are prevented from being submerged by normal fluctuation and noise, and the early-stage fault recognition capability is greatly improved. Meanwhile, global perception feature representation with multi-attribute collaborative features and full-cycle evolution features is constructed on the premise that disturbance suppression is carried out on cross-feature enhancement vectors, quantitative evaluation can be carried out on progressive evolution of battery faults, a diagnosis model can be combined with the fault development trend to carry out fault pre-judgment in advance, and the fault diagnosis accuracy is improved. And fault deterioration is delayed or prevented from the source.

The invention belongs to the field of direct-current power supply systems for transformer substations, and particularly relates to an intelligent portable storage battery pack open circuit prevention detection method and device. The method comprises the following steps: judging whether a direct-current system operates normally or not through output voltage of a charger and initial voltage of a direct-current bus, if so, connecting a step-down silicon chain to the direct-current bus in series and connecting a storage battery pack to a direct-current power supply system to enable the storage battery pack to bear a conventional load of the direct-current power supply system, and judging whether the loading capacity of the conventional load of the storage battery is qualified or not; if the loading capacity of the conventional load of the storage battery is qualified, the simulated load is connected to a direct-current power supply system, whether the impact resistance of the storage battery is qualified is judged, if the impact resistance of the storage battery is qualified, the simulated load is disconnected, the voltage reduction silicon chain is in short circuit, the final voltage of the direct-current bus is obtained, and whether the performance of the storage battery pack is qualified is judged; the method can comprehensively check the effectiveness of the storage battery, discover the fault of the storage battery in time, verify whether the system can bear a normal load or not, and ensure the operation safety of the DC system.

The invention provides a fault detection system and method for multi-source data fusion of a new energy automobile. The method comprises the following steps: determining an abnormal charge index of a battery charge state according to a consistency characteristic of a battery cell voltage and a gradient characteristic of a battery pack current in the new energy automobile; according to the temperature rise rate of each cell measurement point and the temperature difference characteristic between the cell measurement points, determining the temperature difference abnormal characteristic of the new energy vehicle, and according to the temperature difference abnormal characteristic and the flow decline gradient in the cooling liquid flow information, determining the out-of-control risk index of the battery temperature in the new energy vehicle; and performing dependency fusion on the charge anomaly index and the out-of-control risk index to obtain an anomaly probability of the battery in the new energy automobile, when the anomaly probability is greater than a fault threshold value of the battery of the new energy automobile, triggering fault early warning, and positioning a fault battery cell through the characteristic contribution degree of each battery cell. Based on the above scheme, fusion detection of the temperature characteristic and the electrical characteristic of the battery fault in the new energy automobile can be realized.

The invention provides a fault early warning method and system for a transformer substation storage battery and electronic equipment, and relates to the technical field of battery management. According to the dynamic threshold adjustment method based on the battery aging grade, the fault identification threshold is optimized by considering the actual proportion condition of the storage batteries with different aging degrees in the battery pack, so that the threshold setting is more suitable for the real state of the battery pack; therefore, the technical problem that the hierarchical fault identification of the battery pack is not accurate enough under the condition that different storage batteries are matched for use in the battery pack is effectively solved, and the accuracy and efficiency of the fault threshold of the storage batteries of the transformer substation can be considered.

The invention relates to the technical field of battery fault processing, in particular to a battery fault prediction method and device, a vehicle and a storage medium. According to the embodiment of the invention, each time sequence segment is firstly extracted, then the data generated by the battery in each time sequence segment is collected, the inter-segment data features formed by the data among the time sequence segments are calculated according to the data in each time sequence segment, and finally the inter-segment data features are input into the fault prediction model. And obtaining an initial fault prediction result, and further processing the initial fault prediction result to obtain a final fault prediction result. According to the method, whether the battery has the fault or not is predicted by adopting the inter-segment data features formed between the segments of the battery data, and the relevance between the inter-segment data features and the battery fault is relatively high, so that the accuracy of battery fault prediction can be improved.

This application relates to a battery fault early warning method, apparatus, computer device, computer-readable storage medium, and computer program product. The method includes: denoising impedance data of multiple batteries to obtain denoised impedance data; using each denoised impedance data point as a data point and calculating the local density corresponding to each data point; dynamically adjusting a density threshold based on the local density of each data point to obtain a density threshold for each data point; classifying all data points into multiple groups based on the density thresholds corresponding to different data points; calculating the distance between any two groups; and determining that a battery fault exists among the multiple batteries if the distance between any two groups is greater than a preset distance. This method can promptly detect battery faults, issue early warnings, and facilitate further processing.

The application relates to a battery fault detection method and device and a computer readable storage medium. The method comprises the following steps: obtaining relevant data of a battery module; calculating the impedance and impedance average of each single battery in the battery module in a preset frequency range according to the relevant data; calculating the correlation coefficient of each single battery in different preset frequency ranges; calculating the difference between the average value generated by the correlation coefficients of multiple single batteries in different preset frequency ranges and the correlation coefficient of each single battery, sorting the difference value, and obtaining the difference ranking value of each single battery in different preset frequency ranges; calculating the standard deviation and average value of the difference ranking value of each single battery in different preset frequency ranges, determining the preset threshold of the score of the single battery, scoring the single battery, and screening out the single battery with faults according to the score of each single battery. The method can quickly and accurately detect the single battery with faults in the battery module.

The application discloses a battery health state evaluation method and system based on parameter identification, and aims to solve the problem that there is no timely, reliable and accurate battery fault detection method. The method constructs a battery model; based on the Levenberg-Marquardt (LM) algorithm, the model parameters of different batteries are identified respectively by combining the actual measurement data of different batteries, and a plurality of characteristic parameters representing the health states of the batteries to be measured are obtained; for each characteristic parameter and the corresponding residual loss, the batteries to be measured are analyzed by using the quartile range method or the median absolute deviation method, and the corresponding abnormal battery in each characteristic parameter is obtained; and the health states of the batteries to be measured are evaluated according to the distribution of the characteristic parameters. The method realizes efficient evaluation of the health state of the lithium ion battery and accurate positioning of the abnormal battery, and provides theoretical support and technical optimization scheme for the battery safety management system.

This invention discloses a method, apparatus, electronic device, and storage medium for assessing the lifespan of an energy storage system. The method includes: acquiring individual battery cell cyclic aging data and energy storage system design parameters; simulating the energy storage system and calculating the health status of individual battery cells; using a general generating function method to calculate the equivalent expected health status of the overall energy storage system; rating the health status of individual battery cells; selecting battery cells for re-cycling based on the rating results until they reach retirement standards, and using the number of cycles as the lifespan of the energy storage system. This invention's method, by calculating the health status of individual battery cells, can directly identify batteries with weak health. By rating individual battery cells and selecting them for re-cycling, faulty cells can be isolated and protected. Through iterative calculation, the degradation of all battery cells in the energy storage system can be balanced, overcoming the deficiency in existing technologies that do not consider the overall energy storage system architecture when assessing the lifespan of an energy storage system.

An energy storage module fault detection method, apparatus and system, a computer device, a storage medium, and a computer program product. The method comprises: determining a target detection angle of an internal visual probe on the basis of battery position information of an energy storage module (step S201); controlling the internal visual probe to enter the interior of the energy storage module, so as to collect internal module images of the energy storage module inside the energy storage module at the target detection angle by means of the internal visual probe (step S202); and performing fault identification on the internal module images by means of a trained fault detection model to obtain a target fault detection result of the energy storage module, the target fault detection result including a battery fault detection result and a wiring fault detection result for the energy storage module (step S203). By using the method, the convenience of fault detection for the energy storage module can be improved.