35 results about "Abnormal cell" patented technology

The invention belongs to the technical field of power battery detection, and particularly relates to a power battery abnormal monomer detection method, which comprises the following steps of: completing a data preprocessing step through parameter setting, working condition segmentation and sampling steps; and the model calculation step is completed through the steps of data set setting, value rate calculation, value rate filtering, abnormal coefficient A calculation, Boolean matrix conversion and abnormal monomer judgment. According to the method, the voltage fluctuation degree of each monomer in each message is represented through an abnormal coefficient A, Boolean matrix conversion is used, the voltage fluctuation conditions in the data blocks are aggregated, and finally the judgment of the abnormal monomers is obtained. And the voltage fluctuation condition of each message is analyzed in a detailed manner, so that the accuracy of abnormal monomer judgment can be effectively improved.

Embodiments of the present disclosure provide a software upgrading method, system, electronic device and storage medium. The software upgrading method comprises: adopting a first prediction model to predict an abnormal probability of a cell associated with a first terminal based on first space-time information of the first terminal, wherein the first prediction model is obtained by training a network behavior data collected by a second terminal on a server; and performing a corresponding avoidance operation on an abnormal cell with an abnormal probability greater than a probability threshold.

The embodiment of the invention provides a cell installation detection result display method, system and device and a storage medium, and relates to the technical field of battery manufacturing. The method comprises the following steps: acquiring an installation result and an installation image of a battery cell module; when the installation is normal, generating a correct installation picture based on the state of the battery cell module, the model of the battery cell module, the total number of the battery cell modules and the installation image; when the installation is abnormal, generating an abnormal reason, a solution and the number of abnormal battery cells based on an abnormal type in an installation detection result; marking the battery cell which is installed abnormally to obtain a marked image; and generating an installation abnormity picture based on the abnormity reason, the solution, the number of the abnormal cells, the cell state, the cell model, the total number of the cells and the mark image. Therefore, by marking the abnormal cells, the number of the cells, the polarity arrangement sequence of the cells and the cells with abnormal placement angles are identified, and specific reasons, solutions and the number of the abnormal cells of the abnormality are displayed, so that reasons for abnormal installation of the cell module are conveniently checked.

A multi-scale dual-stream abnormal cervical cell detection method that integrates pathological knowledge. The present invention relates to the problem of sparse features and difficulty in detecting abnormal cells of different sizes in the technology of abnormal cell detection in panoramic images of cervical cell pathology. Early detection of abnormal cervical cells in cervical cancer screening can increase the chance of timely treatment, but manual detection requires experienced pathologists, is time-consuming and prone to errors. The technology of abnormal cell detection in panoramic images of cervical cell pathology has the problem of sparse features of abnormal cells in panoramic images and difficulty in detecting abnormal cells of different sizes. To improve this problem, the present invention proposes a multi-scale dual-stream abnormal cervical cell detection method that integrates pathological knowledge. Experiments show that this method can effectively integrate pathological knowledge, significantly improve the quality of multi-scale detection area suggestions, robustly detect cells of different sizes, and improve the accuracy, sensitivity and specificity of cervical cell detection. It provides effective and efficient technical support for cervical cancer screening and improving pathology workflows, helping pathologists make more accurate diagnoses. The present invention is mainly used for abnormal cell detection in panoramic images of cervical cell pathology.

The invention discloses a battery anomaly detection method, device and equipment based on a sliding-mode observer, and relates to the technical field of batteries, the method comprises the following steps: obtaining real-time operation data of a to-be-detected battery, determining a real-time discharge rate according to the real-time operation data, and determining the real-time discharge rate of the to-be-detected battery according to the real-time discharge rate; calling a matched open-circuit voltage value-battery charge state mapping curve according to the real-time discharge rate; constructing an equivalent model, and constructing a nonlinear system model according to the equivalent model; constructing a sliding-mode observer according to the nonlinear system model, and predicting a predicted value of each state variable of each cell at each time node; and obtaining a measured value of the state variable of each cell at each time node in the operation cycle, marking abnormal cells according to the predicted value and the measured value of the state variable, and determining an abnormal detection result of the to-be-detected battery according to the number of the abnormal cells. According to the invention, the problem of insufficient capability of identifying hidden and slow anomalies such as soft faults and gradual faults can be solved, so that effective early warning of abnormal batteries can be realized.

The application discloses a kind of based on UMLC and ICA's electrochemical energy storage cell health state rapid detection method, medium and program product, belong to electrochemical energy storage power station monitoring and battery management technical field.This method is by BMS real-time acquisition battery cluster in each cell monomer voltage, monomer temperature and battery cluster current and other operating data, constructs the characteristic vector containing voltage and temperature mean, standard deviation and deviation, and is combined with the unsupervised machine learning clustering (UMLC) and incremental capacity analysis (ICA) and other technologies not dependent on historical training data, identify and extract the key features of abnormal cell, to quickly diagnose cell health state.This method does not need historical data, with higher detection efficiency and interpretability, can be directly applied to on-site energy storage power station, realize to cell fast and accurate consistency analysis screening and positioning abnormal cause.

A normal set of cells is characterized using flow cytometry. A centroid and radius are defined for a set of clusters in an n-dimensional space corresponding to a normal maturation for a cell lineage in the normal set of cells. A test set of cells is characterized using flow cytometry and the characterization is compared to the defined set of clusters. Support Vector Machine (SVM) subroutines are employed to identify reference populations of interest by generating multidimensional boundary definitions. These boundary definitions may be used to identify reference populations to use in defining or refining a centroid line or a radius or radii defining a set of normal clusters, and to characterize and compare a test set of cells to the defined set of normal clusters.

The invention relates to a method for identifying abnormal battery cells in a battery pack. The method comprises the following steps: step S1, acquiring accumulated equalization time of each single battery cell in the battery pack in a preset time window; s2, for each single cell, calculating a relative self-discharge rate based on the accumulative equalization time; s3, for each single cell, judging whether the relative self-discharge rate exceeds a preset threshold value or not; and S4, under the condition that the relative self-discharge rate exceeds the preset threshold value, determining that the corresponding single battery cell is an abnormal battery cell. According to some embodiments of the invention, an algorithm for online calculation of the relative self-discharge rate of a single cell based on the accumulative equalization time is provided, so that a suspicious cell can be recognized online in real time, whether the suspicious cell is abnormal can be judged, early warning can be performed in combination with means such as remote diagnosis, and the accuracy and the reliability of the system are improved. Therefore, the abnormal condition of the battery cell is effectively prevented.

The invention provides a cell traffic mutation detection method and device and a medium, and relates to the technical field of networks. The method comprises the following steps: acquiring a same-time characteristic service data sequence of a cell; preliminarily screening out suspected abnormal cells in which abnormal mutation occurs in the same-time characteristic service data sequence based on Pettitt inspection; and judging whether the suspected abnormal cell is a comprehensive abnormal cell or not according to the same-time characteristic service data sequence of the suspected abnormal cell in combination with test related data obtained by Pettit test and associated data of cell service metadata. According to the method and the device, the same-time characteristic service data sequence of the cell is selected, the suspected abnormal cell is quickly and preliminarily screened out by using the Pettitt test, finally, the cell abnormity is comprehensively researched and judged by fusing multi-dimensional information, the Pettitt test is high in speed, small in burden and suitable for full-amount scanning, the data analysis amount of subsequent comprehensive research and judgment can be reduced, the analysis efficiency is improved, and the method and the device are suitable for large-scale popularization and application. Deep analysis is carried out on a small number of suspected targets through comprehensive research and judgment, and the recognition precision is improved.

The present invention relates to automation of urine analysis or urinalysis (UA) with conventional cytopathological assessment tests and methods using an artificial intelligence (AI) based urine diagnostic apparatus or device or system and methods employing said apparatus or device or system for fully automated preparation of raw samples by automating and streamlining conventional laboratory processes and examination of urine samples, automated data collection, automated analysis of data using digital image recognition, and finally, automated screening for cancer suspicion in a non-invasive, non-human or pre-pathologist intervention-based automatic examination and analysis of such samples using AI based on said data analysis for preparing reports intimating to the subject or patient automated negation if no abnormal cells are detected / identified, or to forward suspicious samples from the subject or patient to confirm the possibility of suspicion for cancer risk of cancers routinely and otherwise detected based in examination of urine samples by a trained pathologist.

The invention relates to the field of intelligent medical treatment, and discloses a pathological recognition analysis method and system based on a blood detection sample. The method comprises the following steps: acquiring a blood smear microscopic image and extracting a cell contour; performing texture analysis on the interior of the contour to obtain morphological characteristics; judging a potential abnormal region based on the features; carrying out local enhancement on the abnormal region and extracting subtle difference features; based on the difference features, obtaining quantitative pathological descriptors through a deep learning model; identifying abnormal cells according to a matching result of the descriptors and the feature library; and comprehensively analyzing according to an identification result to obtain pathological quantitative indexes. Through a mode of combining local enhancement, a deep learning model and feature library matching, the problems of low blood smear abnormal cell recognition precision and poor efficiency are solved, and the accuracy and automation level of pathological analysis are improved.

The invention discloses a cell abnormal fluorescence signal intelligent identification system based on dynamic labeling, and relates to the technical field of cell detection, the system comprises an information input module, a detection control module, a scatter diagram extraction module and an abnormal signal identification module, the information input module inputs basic information and is connected with the detection control module, and the scatter diagram extraction module is connected with the abnormal signal identification module; the detection control module comprises a detection device, the detection control module sends an instruction to the detection device and starts detection, and after the detection device completes detection, the scatter diagram extraction module obtains white blood cell five-classification scatter diagram data from the detection device and converts the white blood cell five-classification scatter diagram data into an image format which can be recognized by software; and the abnormal signal identification module identifies the image transmitted from the scatter diagram extraction module, and transmits the result through an intelligent identification system.

Embodiments of the present disclosure provide a cell avoidance method, system, electronic device and storage medium. The cell avoidance method comprises: using a first prediction model to predict an abnormal probability of a cell associated with a first terminal based on first space-time information of the first terminal, wherein the first prediction model is obtained by training a network behavior data collected by a second terminal on a server; and performing a corresponding avoidance operation on an abnormal cell with an abnormal probability greater than a probability threshold.

The present invention discloses a method, apparatus, computing device, and storage medium for detecting anomalies in a subway cell. The method comprises: generating a bidirectional reference table based on sweep frequency data of two running directions of a subway line; the bidirectional reference table records the cell identifiers of coverage cells detected in the two running directions corresponding to each position data block, wherein each position data block is obtained by dividing the cell identifiers by starting from a base station of the subway line and using a preset distance as a granularity; for any coverage cell recorded in the bidirectional reference table, if the number of coverage position data blocks corresponding to the coverage cell in both running directions exceeds a preliminary judgment threshold, the cell is determined to be a preliminarily judged abnormal cell; for any preliminarily judged abnormal cell, determining the coverage status of the preliminarily judged abnormal cell based on the bidirectional reference table, and determining the abnormality of the preliminarily judged abnormal cell based on the coverage status. This method can improve the efficiency and accuracy of determining anomaly in subway cells.

The application provides a short video traffic monitoring method and device and a server, and relates to the field of communication. The method comprises the following steps: a server associates one-time online browsing of the same user to one browsing record according to information in a service code stream. The server processes the browsing record according to a preset service model to obtain an experience index of each browsing record. The server determines whether a wireless cell is a wireless side abnormal cell according to the experience index in each wireless cell. When the wireless cell is the wireless side abnormal cell, the server splices the browsing record and a corresponding quality report to obtain a composite document. The server determines abnormal information of the wireless side abnormal cell according to the composite document in the wireless side abnormal cell. The server locates an abnormal cause of the wireless side abnormal cell according to the abnormal information. The method provided in the application improves the accuracy of abnormal positioning of the wireless cell and improves the accuracy of optimization.

The invention relates to a cell switching method and device, electronic equipment and a storage medium. The cell switching method comprises the following steps: determining that a first cell meets a preset condition, wherein the preset condition represents uplink data jamming due to occurrence of advanced timing abnormity; according to the abnormal information of a target cell in a first tracking area, determining a second cell, the first tracking area being a tracking area to which the first cell belongs, and the target cell being a cell having advanced timing abnormity; and switching from the first cell to the second cell. According to the method, switching to other abnormal cells can be avoided while the abnormal serving cell is quitted in time, the problem of uplink data jamming caused by abnormal timing in advance of the serving cell is remarkably solved, and the user experience is improved.

The embodiment of the invention relates to the field of electrolytic cell monitoring, and discloses an electrolytic cell chamber voltage monitoring method, electronic equipment and a storage medium. The method comprises the following steps: acquiring voltage sampling data of each small chamber in the electrolytic cell; performing projection and reverse reconstruction processing on the voltage sampling data by using a pre-established kernel principal component analysis model to obtain a reconstructed voltage value; the reconstructed voltage value is used for indicating the theoretical normal voltage of the cell under the current operation condition; calculating a difference value between the voltage sampling data of each small chamber and the reconstruction voltage value to obtain a reconstruction residual error of each small chamber; performing clustering analysis on the reconstruction residual error of each small chamber to obtain at least two residual error clusters; and determining an abnormal cell according to the residual cluster to which each cell belongs. Therefore, the abnormal small chamber can be positioned.

The utility model provides a separating device for plasma samples, which comprises a bottom plate, a channel plate and a top plate, a plasma channel is arranged on the channel plate, the bottom plate and the top plate respectively cover the upper surface and the lower surface of the channel plate to seal the plasma channel on the channel plate, and at least one interception area is arranged on the plasma channel. The plasma separating device is low in manufacturing and using cost, small in size and convenient to carry and use, does not need to be provided with a centrifugal machine, and can be used for separating plasma in time in areas with underdeveloped or underdeveloped medical resources or grassroots and under the emergency conditions that no electric power resource exists or electric power is in shortage or is stopped. The plasma separating device disclosed by the utility model has expandability, can be connected in parallel to form a multi-channel mode to timely process a large-dose blood sample when necessary, can also perform expandability of targeted transformation, and can be used for primarily judging whether abnormal cells exist in blood or not, such as whether macrophages and cancer cells are increased or appear or not; and preliminary judgment of corresponding indexes can be assisted.

The present application discloses a method, apparatus, device and storage medium for determining abnormal cells, and relates to the field of communication technology. The determination method includes: respectively obtaining a first service parameter of a first network standard and a second service parameter of a second network standard of a target cell. Respectively determining a first load state of the first network standard and a second load state of the second network standard; the first load state is obtained based on a first data service parameter, and the second load state is obtained based on a second data service parameter. Respectively determining a first user perception state of the first network standard and a second user perception state of the second network standard. Determining the abnormal type of the target cell based on the first load state, the second load state, the first user perception state and the second user perception state. Thus, cells of the abnormal collaborative network are obtained in a timely manner.

Resistive random access memories (ReRAMs) suffer from read disturb phenomena due to the same voltage polarity used by read and program operations despite at different voltages. After multiple reads, according to the characteristics of each cell, the number of reads can be large or small, and abnormal cells are obviously switched after much less number of reads than other cells. Thus, a process including a set or reset operation of the ReRAM cell is followed by a clear operation. The clear operation includes applying a clear voltage greater than the read voltage and less than the program voltage. Subsequently, a read operation is performed to identify those ReRAM cells that have switched from their intended state. In one embodiment, a reprogramming operation is performed to fix a resistance filament of a ReRAM cell identified as suffering from a read disturb.

The invention discloses a cell switching method and device, electronic equipment and a storage medium, and belongs to the technical field of communication, and the cell switching method comprises the steps: determining whether a service cell of a terminal is a redirection abnormal cell or not; under the condition that the service cell is a redirection abnormal cell, whether a measurement event is reported or whether cell switching is carried out is determined based on the signal quality of the service cell; and under the condition that the serving cell is not the redirection abnormal cell and the neighbor cell of the serving cell comprises the redirection abnormal cell, determining whether to report the measurement event based on the cell specific offset of the neighbor cell.

The invention relates to the technical field of new energy automobile batteries, and particularly discloses a system and a method for disassembling a new energy automobile battery. According to the method, battery structure topological data are obtained through three-dimensional laser scanning and industrial CT, electrochemical state data are synchronously collected, firstly, a basic disassembling path is planned based on a shell fragility coefficient and a battery cell distance, secondly, the path is optimized according to a bolt connection rigidity coefficient, a rigidity weak area is preferentially disassembled to release stress, and finally, the reliability of the battery is improved. The method comprises the following steps: firstly removing a bolt stable structure, then positioning an active abnormal cell through an internal resistance spectrum phase angle abrupt change point, mapping the active abnormal cell to a three-dimensional space to form a risk point, and finally fusing the structure risk and the electrical risk to generate a dual optimization path: firstly removing the bolt stable structure, and then avoiding an abnormal cell area. The risks of shell breakage, cell extrusion and thermal runaway are recognized in advance, and the disassembly safety and the recovery rate are improved through two-time path optimization.

This application relates to a method for identifying abnormal cells in lithium iron phosphate batteries, comprising the following steps: collecting the voltage values ​​of n individual cells after charge and discharge; performing basic statistical calculations, including the mean, standard deviation, median, and quartiles; determining abnormalities using the standard deviation method, the interquartile range method, and the median absolute deviation method, respectively; performing a comprehensive determination: if at least two abnormality determination methods identify an abnormality, the individual cell is confirmed as an abnormal cell; if only one abnormality determination method identifies an abnormality, further analysis is performed; quantifying the degree of abnormality by calculating the abnormality index for each abnormal cell; and classifying the abnormal cells based on their voltage data. This method for identifying abnormal cells in lithium iron phosphate batteries can more accurately screen out cells that affect the overall battery capacity, facilitating targeted maintenance of abnormal cells and thus overcoming the impact of abnormal cells on battery capacity.

The invention provides an abnormal battery cell determination method and electronic equipment. The method includes determining a control limit; wherein the control limit is determined based on the influence factor of the battery cell to be detected and the original electrical performance value of the battery cell, or the control limit is determined based on the electrical performance value after temperature compensation; the influence factor represents a factor capable of influencing the electrical performance value of the battery cell; based on the control limit, screening the battery cells, and determining discrete points in the battery cells; and determining an abnormal battery cell based on the discrete points. The control limit is determined through the influence factor of the to-be-detected battery cell and the original electrical performance value, or the control limit is determined according to the voltage attenuation rate after temperature compensation, the accuracy of the control limit is ensured, the accuracy of determining the abnormal battery cell is improved, and the efficiency of determining the abnormal battery cell can be improved.

The invention discloses an alkaline electrolytic cell performance discreteness Monte Carlo analysis method and system, and relates to the technical field of electrolytic hydrogen production, and the method comprises the following steps: constructing an electrochemical-thermodynamic-hydrodynamic multi-physics field coupling steady-state model of an alkaline electrolytic cell; based on a Monte Carlo method, probabilistic modeling is carried out on manufacturing tolerance, aging effect and operation parameter uncertainty; through large-scale random sampling simulation, quantizing discrete distribution characteristics of stack output voltage of the alkaline electrolytic cell and voltage of each small electrolytic chamber in the alkaline electrolytic cell; high-voltage abnormal cells and the influence of the high-voltage abnormal cells on the system performance are identified; and carrying out parameter sensitivity analysis, and identifying highly sensitive parameters and low sensitive parameters. The method can provide theoretical basis and method support for robust design, health monitoring, operation and maintenance optimization and manufacturing tolerance control of the alkaline electrolytic cell.

The invention relates to the technical field of battery packs, and provides an abnormal battery cell identification method, a vehicle and a storage medium. The method comprises the following steps: screening second voltage data of each battery cell from first voltage data of each battery cell in a battery cell group at multiple moments; based on the second voltage data of each battery cell and the internal resistance of the battery cell group, determining the first internal resistance of each battery cell; carrying out replacement processing on an abnormal value in the first internal resistance of each battery cell to obtain a second internal resistance of each battery cell; based on the second internal resistance of each battery cell, determining a first outlier degree and a second outlier degree of each battery cell; and on the basis of the first outlier degree and the second outlier degree, identifying an abnormal battery cell from the plurality of battery cells of the battery cell group. According to the method, the abnormal battery cell can be accurately identified.

Disclosed herein are an abnormal cell diagnosis apparatus and method using a cell voltage deviation, which uses a method of comparing with an intermediate value of all battery cell data to acquire battery cell information according to a point in time and a situation in which a battery system is operated and using a voltage difference to find an abnormal value, and it increases the efficiency of abnormal cell detection by applying conditions according to the characteristics of the state of charge in each section. The abnormal cell diagnosis apparatus includes: a voltage measurement module configured to measure an initial open circuit voltage (OCV) or closed circuit voltage (CCV) of each battery cell; a timer configured to count a minimum rest time of each battery cell; and a processor configured to calculate a quartile distance (IQR) based on the initial OCV or CCV depending on whether the minimum rest time is satisfied, set an abnormal value criterion, and detect an abnormal cell based on the set abnormal value criterion.

To detect abnormal cell deterioration.SOLUTION: A power storage device 50 includes a plurality of cells 62A to 62D connected in series, a balancer 65 that equalizes the cell voltages of the plurality of cells by discharging, and a controller 130, and the control device 130 accumulates, for each of the cells 62A to 62D, the balance discharge amount of the balancer 65 executed to eliminate the voltage difference between the cells that occurs during charging, and determines a cell 62 in which the cumulative discharge amount, which is the cumulative value of the balance discharge amount for a predetermined period, is greater than the other cells 62 by a predetermined value or more to be abnormal deterioration.SELECTED DRAWING: Figure 12

This invention belongs to the field of battery health detection technology and discloses a health status detection system and method for new energy vehicle battery packs. It acquires key parameters such as voltage, current, temperature, and high-frequency impedance with nanosecond-level precision through a multi-channel synchronous acquisition unit of the BMS. During the vehicle's idle period after engine shutdown, a low-disturbance DC pulse excitation is injected to complete in-situ benchmark calibration. Simultaneously, it pre-detects the consistency of individual cells and marks abnormal cells, eliminating measurement errors caused by acquisition system drift, environmental disturbances, and initial cell inconsistencies. For three operating conditions—static idle, low-rate stable operation, and high-rate dynamic operation—an adaptive matching denoising algorithm is used. Combined with the mutual information entropy algorithm, core health features are extracted and redundant information is removed to ensure a high signal-to-noise ratio. In the cell estimation stage, a single-particle electrochemical model and a second-order equivalent circuit model are fused, and a lightweight CNN-LSTM network based on an attention mechanism is used for pre-training.

This invention discloses a method and system for detecting abnormal battery cells in an electrochemical energy storage system. The method first collects voltage, current, and temperature data of some individual cells in the battery module. It then uses local inverse distance weighted interpolation to initially estimate the temperature of all cells and dynamically corrects and smooths the temperature using voltage residuals to obtain a calibrated temperature field. Next, it calculates the temperature gradient index based on spatial neighborhood relationships and the voltage gradient index based on electrical connections for each cell. Finally, it integrates the temperature gradient index, voltage gradient index, and temperature change rate to construct a joint criterion, which is compared with an adaptive dynamic threshold to achieve accurate diagnosis and early warning of abnormal cells. This invention effectively overcomes the problems of high false alarm and missed early anomaly rates in existing technologies due to temperature monitoring blind spots and lack of spatial correlation analysis. It significantly improves the sensitivity and reliability of energy storage system safety monitoring without increasing hardware costs.