451 results about "Abnormality detection" patented technology

This disclosure provides embodiments of a method, apparatus, electrical device, and computer-readable medium for detecting powder spreading anomalies. One specific implementation of the method includes: in response to determining a target powder spreading axis and performing powder spreading processing, executing a first generation step: in response to the camera device being a non-panoramic camera device, capturing an image of the target powder spreading axis at the current time to obtain a real-time captured image; utilizing the mapping relationship between pixel positions and actual movement positions, extracting a local powder spreading image corresponding to the movement position from the real-time captured image; stitching the local powder spreading image and a historical powder spreading stitched image to obtain a real-time powder spreading stitched image; in response to the movement position being the end position of powder spreading, generating a real-time anomaly detection result; in response to indicating that there is no powder spreading anomaly in the target area and the movement position is the end position of the movement, continuing laser processing. This implementation achieves real-time and accurate detection of powder spreading anomalies during the powder spreading process by continuously stitching powder spreading images.

The application relates to an air pressure detection method, an air pressure sensor chip, a battery pack and a storage medium. The method comprises the following steps: acquiring air pressure data in a battery pack under the condition that a battery management system in the battery pack is in a sleep state; performing abnormality detection according to the air pressure data to obtain a detection result; and outputting a first wake-up signal and first fault information to the battery management system under the condition that the detection result represents air pressure abnormality in the battery pack; wherein the first wake-up signal is used for waking up the battery management system, and the first fault information is used for instructing the battery management system to output air pressure abnormality prompt information. According to the application, air pressure detection can be performed when the battery management system is in a sleep mode, heat runaway monitoring is realized, and the safety of the battery pack is improved.

The present invention relates to a vehicle control system in which a plurality of ECUs of a vehicle-mounted device are communicably connected to each other, and is configured to include: a source information database (221) that stores source information (Dso) associated with a control function for each of the plurality of ECUs when the ECUs are functioning properly; an information group setting section (217) that sets an information group from the source information (Dso), the information group being composed of information combinations for different ECUs; an information collection section (211) that collects current information corresponding to the source information (Dso) from each of the ECUs targeted by the information group; and an abnormality detection section (213) that detects a situation in which any of the ECUs targeted exists abnormality, in a case where a degree of coincidence between correct answer information (Dc) calculated by an evaluation function (f) with the information group as an argument and an evaluation value (Ve) calculated by the evaluation function (f) with current information corresponding to the information group as an argument is lower than a reference.

The application discloses a source line abnormality detection circuit and method based on charge sharing. The circuit comprises a source drive array, a display panel, a comparator and a reference module. The application adds a reference capacitor with a capacitance not greater than the parasitic capacitance of the source line, and converts the size of the parasitic capacitance of the source line which is difficult to directly measure into a detection voltage which can be compared with a reference voltage by using the voltage division principle after charge sharing, so that the faults such as disconnection or short circuit with adjacent lines of the source line can be accurately judged. The application realizes online and non-invasive abnormality monitoring of the source line, and can effectively improve the reliability and maintainability of the display chip and the display panel.

The application relates to the technical field of wireless communication, and discloses a network switching method, system, device and medium based on multi-round simulation optimization, which comprises the following steps: acquiring real-time network state information to perform flow prediction, obtaining an overall flow prediction result; acquiring a load value from the overall flow prediction result, and if the load value is higher than a load threshold value, determining a high-load access point and redirecting flow to a nearby access point to obtain an initial network configuration; performing multi-round switching simulation to generate a candidate sequence, and if a preset load balancing condition is met, obtaining a preliminary switching scheme and calculating a reward value, selecting a switching scheme with the highest reward value as an optimized switching scheme; executing the optimized switching scheme, recording access point states; performing abnormality detection, and if there is an abnormal access point, adjusting a prediction method and predicting overall flow, optimizing network configuration according to a prediction result, and obtaining a final network switching configuration. The method can efficiently and stably switch wireless networks in a complex network environment.

The present invention relates to a yarn winder and a winding abnormality detection method. An automatic winder (1) is provided with: a yarn monitoring device (17) that detects a travel speed of a yarn (5) that travels from a yarn supply section (18) toward a winding device (30); and a unit control section (11) that detects an abnormality related to winding of the yarn (5). The unit control section (11) detects the abnormality based on a change over time in the travel speed detected by the yarn monitoring device (17).

The application discloses a battery temperature anomaly detection method and medium. The method can include: acquiring real-time temperature sensing data of a vehicle power battery and extracting abnormal temperature sensing data; setting an abnormal temperature sensing warning level and determining the corresponding warning level according to the abnormal temperature sensing data; and extracting abnormal temperature sensing detailed data, including the abnormal temperature sensing data and the corresponding warning level. The application is based on historical data of the power battery, efficiently calculates the temperature rise rate, the temperature drop rate and the temperature difference at the same time of the battery in batches on a big data platform, sets a threshold, detects vehicles and corresponding battery modules with abnormalities in advance, reduces maintenance costs, safety accidents and improves customer experience.

This invention relates to the field of power management and anomaly detection technology, specifically to a method and system for detecting anomalies in multi-port charging power supplies based on current analysis. It is applied to a charging system containing multiple load power supply buses and several branch switching transistors. The method includes: extracting and sampling AC ripple current from the total current signal of the multiple load power supply buses and each branch; performing delay mapping on the AC ripple current to construct a multi-dimensional phase space matrix and calculate a Poincaré cross-section scatter plot; calculating the current topological information entropy based on the scatter distribution probability and comparing it with the baseline information entropy to generate an information entropy residual; comparing the information entropy residual with a safety manifold boundary threshold range, determining a charging anomaly when it exceeds the threshold, outputting a hardware interrupt signal to control the state of the corresponding branch switching transistor, and generating a diagnostic report containing physical feature parameters extracted based on the multi-dimensional phase space matrix. This invention enables early identification of anomalies in multi-port charging systems and rapid hardware-level response.

The application relates to the technical field of Internet of Things data processing, and discloses a local reasoning and abnormality detection method for a wireless sensor network, which comprises the following steps: constructing a hypergraph model according to a sensor node set in the sensor network and corresponding association relations, and defining an energy function; applying a sensitivity constraint to the potential function, so that the potential function satisfies a bounded difference condition; determining a constraint range of coupling strength and a truncation order m; performing local deterministic approximate reasoning to obtain a conditional edge probability of a target sensor node; calculating an abnormality score of the target sensor node, and performing abnormality detection. In the wireless sensor network, a hypergraph Gibbs model with a sensitivity constraint is constructed, and based on strong spatial mixing ensured by theory, the application realizes the probability reasoning of a deterministic error bound only by relying on a limited-step local communication, so that the explainable abnormality detection and positioning are completed on a resource-limited edge device.

The application relates to the field of intelligent driving of rail transit, and discloses a real-time monitoring and early warning system for the safety state of a rail car based on deep learning, which comprises the following modules: a multi-modal data acquisition module, which is used for deploying sensors on key components of the rail car and collecting time series data including vibration, temperature, pressure and operation parameters; a cross-modal feature conversion module, which is used for encoding the collected time series data into a three-channel color image; a safety state evaluation module, which is used for deep modeling and feature learning on the three-channel color image, real-time prediction of a current state classification result of the rail car, and obtaining of a safety state evaluation result of the rail car; and an early warning and intelligent decision module, which is used for performing abnormality detection and alarm prompting on the rail car when potential risks exist according to the safety state evaluation result. The application realizes high-precision early fault identification and automatic early warning.

Embodiments of the present application provide an unsupervised visual detection method for assembly abnormalities of industrial structural parts and related equipment, relating to the technical field of industrial visual detection. The method comprises: extracting local patch features and constructing a memory bank through a normal sample training set, reconstructing features based on the memory bank, generating a memory index histogram descriptor for representing local statistical structures, simultaneously constructing a feature similarity graph and performing graph enhancement processing to obtain a graph-enhanced reconstructed feature representation, and then constructing an associated memory index histogram memory bank and a global feature memory bank; performing the same processing on the image to be detected, obtaining the candidate normal sample most similar to the structure of the image to be detected through two-stage candidate sample screening, performing similarity matching based on the global feature memory bank to obtain a logical abnormality score, and fusing it with the local abnormality score obtained based on the local patch memory bank to obtain the final abnormality detection result. The present application has the advantages of high detection accuracy, strong robustness, and no need for abnormal samples.

The application discloses a landslide danger assessment method under rainfall conditions and relates to the technical field of landslide disaster early warning, and comprises the following steps: a multi-source sensing monitoring network is constructed, surface deformation data, deep state data and environmental parameter data of a landslide body are collected in real time, based on the data monitored by the multi-source sensing monitoring network, an abnormality detection algorithm is used to identify precursor events before landslides, and the precursor events are classified into micro-disturbance events, significant abnormality events, pre-landslide precursor events and landslide occurrence events. According to the application, a segmented state transition equation is constructed based on the three-stage theory of creep, the initial creep, constant-speed creep and accelerated creep stages are automatically identified by means of the stability coefficient and displacement acceleration, and evolution modes such as exponential decay, rainfall driving and exponential growth are respectively adopted, so that the whole process from rainfall infiltration to instability can be accurately described, and the early warning accuracy is improved.

Condition measuring device that measures the condition of a cutting tool (200) during a cutting operation, wherein the cutting tool (200) consists of a rotating body having one or more blade sections (202) and bringing each of the blade sections (202) into contact with a workpiece (W) during rotation in order to machine the workpiece (W), wherein the condition measuring device comprises: one or more measuring sections (101) attached to the blade section (202) or to a surrounding area of ​​the blade section to measure a condition of the blade section (202); an AD converter (103) attached to the cutting tool to obtain a measured value measured through each of the measuring sections at a predetermined sampling rate and to perform an AD conversion with respect to the measured value; a transmission section (105) which transmits the measured value from the A / D converter (103) using digital wireless communication each time the measured value is obtained; and a monitor device (120) which is provided outside the cutting tool, wherein the monitor device (120) comprises: a receiving section (122) that receives the measured value transmitted by the transmitting section (105); and a data management section (124) that causes a display section (126) to display the measured value, and a storage section (127) that causes the measured value to be stored each time the measured value is received by the receive section (122), wherein each of the measuring sections (101) comprises a strain gauge or a piezoelectric element, and the amplitudes of the measured values ​​are recorded by the strain gauge or the piezoelectric element from the chronological data of the measured values ​​received by the receiving section (122), and a difference is obtained between each of the recorded amplitudes and a reference value, and wherein the condition measuring device further comprises an abnormality detection section (125) which determines that an abnormality has occurred in the blade section (202) if the difference is greater than a reference distance value, and, when the presence of the abnormality is determined, displays information showing the occurrence of the abnormality on the display section (126).

The application discloses a high-voltage relay control method, an electronic device and a program product of a vehicle. The method is used for a high-voltage relay system comprising at least a main positive relay, a pre-charging relay and a main negative relay. The method comprises: performing a power-on process according to a power-on instruction, sequentially performing processes of main positive relay melting detection, main negative relay melting detection, a pre-charging process stage and a pre-charging completion stage, and obtaining a melting detection result; judging whether an abnormality detection condition is met; if the abnormality detection condition is not met, performing a first power-off process; and if the abnormality detection condition is met, performing a second power-off process. The application provides a high-voltage relay control process with multi-scenario stage division, dynamic detection mode switching, load discharge and bipolar melting safety protection. The high-voltage relay melting detection is accurate, and part of the relays can be prevented from being excessively worn due to the melting detection.

An abnormality detection system includes a measurement unit configured to acquire at least three-dimensional data indicating a distance to a target and a shape of the target by performing measurement, a central management unit configured to receive the three-dimensional data acquired by the measurement unit from the measurement unit, and a measurement data evaluation unit configured to hold in advance reference three-dimensional data, the reference three-dimensional data being the three-dimensional data to be a reference acquired by the measurement unit in the past, evaluate whether a difference between the three-dimensional data acquired by the measurement unit and the reference three-dimensional data is greater than or equal to a threshold value, and transmit an alarm to the central management unit when a result of the evaluation indicates that the difference is greater than or equal to the threshold value.

A data shaping apparatus includes: an abnormality detection unit configured to detect, as abnormal data, positioning data indicating an abnormal position from a positioning data group based on a movement constraint condition for a moving object, the positioning data group being a collection of positioning data at least indicating a position and a positioning time of the moving object; a first generation unit configured to generate first data from the positioning data group by replacing a position indicated by the abnormal data with a position assumed under a predetermined movement condition; and an output unit configured to output information based on the first data.

The application discloses a kind of based on layered funnel model exception detection and alarm method, device and equipment and storage medium, it is related to data processing technical field, it discloses based on layered funnel model exception detection and alarm method, comprising: to initial log data is carried out data processing, obtains structured log data;According to the structured log data and layered funnel model is carried out layered monitoring, obtains layered monitoring data, wherein the layered monitoring data includes aggregation monitoring layer data, convergence monitoring layer data and node monitoring layer data;According to the layered monitoring data is carried out exception detection, obtains exception detection result;According to the exception detection result generates hierarchical alarm information.Application scheme can improve the accuracy of exception detection and fault emergency response efficiency, while the dynamic adjustment of organization structure of adaptive mechanism can reduce the operation and maintenance management cost of monitoring system.

The invention discloses a welding anomaly detection method and a related device, and relates to the field of welding anomaly detection. According to the target welding image, weld joint segmentation points and metal element segmentation points are obtained; carrying out at least one of welding seam size anomaly detection, insufficient welding detection and broken welding detection based on the welding seam segmentation points; and weld joint position anomaly detection and / or metal element splashing anomaly detection are / is performed based on the weld joint segmentation points and the metal element segmentation points. According to the invention, the purpose of detecting the abnormity of the welding seam and the abnormity of the welded metal element is achieved.

The application relates to an abnormal behavior detection method, device and equipment and a storage medium. The method comprises the following steps: acquiring a process operation behavior sequence, dividing the process operation behavior sequence into a plurality of to-be-detected sequences, each to-be-detected sequence comprising a plurality of user process operation behaviors, and each user process operation behavior comprising a plurality of field information; performing feature extraction based on the attribute values of the plurality of field information of each process operation behavior in the to-be-detected sequence to obtain a feature vector corresponding to the to-be-detected sequence; performing abnormality detection on the feature vectors corresponding to the to-be-detected sequences, determining an abnormal feature vector as a feature vector detected as abnormal; determining the abnormality degrees of each dimension feature in the abnormal feature vector; determining the feature items existing in the abnormal feature vector based on the abnormality degrees of each dimension feature in the abnormal feature vector; and the application can improve the accuracy and efficiency of user abnormal behavior detection.

An object is to provide a noise filter that can achieve high reliability. A noise filter includes: a noise detection unit which detects a common mode noise flowing through an electric path; an amplification unit which, on the basis of the common mode noise detected by the noise detection unit, generates a cancellation signal for canceling out the common mode noise; an injection unit which injects the cancellation signal into the electric path; an abnormality detection unit which detects abnormality of the noise filter on the basis of output voltage or output current of the cancellation signal, and outputs an abnormality detection signal; and a protection circuit which inhibits an abnormal cancellation signal from being injected into the electric path, on the basis of the abnormality detection signal.

The embodiment of the present application provides an abnormality detection circuit and system. The method comprises the following steps: the abnormality detection circuit comprises a monitoring unit, an abnormal power supply unit and an oscillation circuit unit, the monitoring unit is connected with a to-be-detected position of a to-be-detected unit, the oscillation circuit unit is connected with an enable foot of the to-be-detected unit, the monitoring unit is connected with the abnormal power supply unit, the abnormal power supply unit is connected with the oscillation circuit unit, wherein the monitoring unit is used for performing abnormality monitoring on the to-be-detected unit; the abnormal power supply unit is used for providing a power supply voltage for the oscillation circuit unit after the monitoring unit detects that the to-be-detected unit is abnormal; and the oscillation circuit unit is used for inputting an oscillation signal to the enable foot of the to-be-detected unit, so as to unlock the to-be-detected unit after the to-be-detected unit is self-locked abnormally. The circuit is used to release the IO resource of the SOC and improve the processing efficiency of the domain controller.

The application discloses a kind of for the method, device, equipment and medium of tab abnormality detection in battery cell production process, comprising: the tab area image collected in battery cell production process is segmented to generate tab mask;Based on the tab mask extraction multi-scale pixel-level feature vector, and the multi-scale pixel-level feature vector is input into unsupervised probability GMM model to identify pixel-level abnormal point;The pixel-level abnormal point is analyzed to obtain candidate abnormal area, and the parameter index of the candidate abnormal area is obtained;Determine whether the parameter index meets the set tab abnormality judgment rule, if meet, it is judged as tab abnormality, and tab abnormality result is output.Therefore, the application can be widely applied to the detection of tab folding, crease, fracture, misplacement and other abnormalities on battery cell production line.

The invention provides a cable tunnel fault-tolerant sensor data fusion, anomaly detection and fault positioning method based on hybrid machine learning. Comprising the steps of multi-sensor deployment and data acquisition, sensor data preprocessing, fault adjustment machine learning model fusion, DSET fault positioning and decision making, federal learning and global model updating, edge server grading early warning and fault response and the like. Through constructing a six-level architecture of a multi-sensor layer, a preprocessing layer, a machine learning fusion layer, a DSET decision-making layer, a federal updating layer and a response layer, sensor fault self-adaption, tunnel environment adaption and cable fault accurate early warning and positioning are realized.

The application discloses a light detection method and device, computer equipment and a storage medium, and belongs to the technical field of computers. The method comprises the following steps: adjusting the colors of multiple parts of a virtual object, wherein the color of each part of the multiple parts refers to the color required to be presented by each part during light detection, and the colors of different parts of the multiple parts are different; acquiring an image frame, wherein the image frame comprises the virtual object located in a light area; based on the colors of the multiple parts, the image frame is segmented into multiple sub-images, and each sub-image of the multiple sub-images corresponds to one part of the virtual object; and acquiring a light detection result of each sub-image, wherein the light detection result of each sub-image indicates whether the part corresponding to each sub-image is abnormal in light. The application can accurately lock the part of the virtual object that has the light abnormality problem, and improves the accuracy of light abnormality detection.

The application provides a vehicle remote control method, an electronic device and a vehicle. Through the decentralization and non-tamperable characteristics of the blockchain, the centralized server single-point failure and data tampering risks are completely eliminated, and the overall security of the remote control process is significantly improved. All operation records are chained to form non-tamperable audit logs, facilitating subsequent tracing and responsibility identification. By using the smart contract of the blockchain, each real-world vehicle use permission scenario is converted into a digital rule that can be automatically executed and cannot be tampered with, the current authorized scenario is automatically determined, and the allowed remote control is realized under the current authorized scenario, thereby converting the rigid permission switch management into an intelligent permission management process. The security verification of the request behavior is realized based on the abnormality detection of the historical control request. Through the combination of the dynamic authorized scenario determination and the abnormal request behavior detection, the safe and convenient remote control service can be intelligently provided without reducing the security.

The application relates to the technical field of transformer monitoring, and discloses a main transformer multi-dimensional state online monitoring method based on big data analysis, which comprises the following steps: mapping a transformer body into a knowledge graph node, dynamically calculating an edge weight, obtaining a dynamic knowledge graph, combining the dynamic knowledge graph with a three-dimensional data matrix, generating an evolution rule set and a parameter threshold, reasoning on the basis of the evolution rule set, and outputting a rule priority. Through multi-dimensional data fusion and dynamic rule evolution, the application realizes high self-adaptation and accurate abnormality detection of main transformer state monitoring, and the core advantage lies in a flexible architecture which is not model-driven, so that the detection logic can be dynamically adjusted through a rule self-evolution system without relying on a fixed model, equipment aging and working condition evolution are adapted to, a full-parameter sensor network covers four core areas, working condition information is integrated, a three-dimensional data matrix is formed, and comprehensive data support is provided for abnormality detection.

The application discloses a kind of based on multi-source data's electric quantity abnormality monitoring method and system, method includes: calculating historical load fluctuation coefficient and carrying out first level division, obtain user terminal set;Real-time load data sequence is obtained and real-time load feature is extracted;Combining static attribute data and real-time load feature, user terminal set is carried out second level division, and obtain user terminal sub-set;Based on historical load fluctuation coefficient interval, target user terminal is selected in sub-set and electric quantity abnormality detection is carried out, and obtain abnormality degree set;Calculate dispersion and adopt screening strategy to optimize abnormality degree set, and obtain target abnormality degree set;According to target abnormality degree, the electric quantity abnormality degree of each user terminal in sub-set is determined.The application realizes the accuracy and high efficiency of electric quantity abnormality monitoring by the synergistic mechanism of double-layer classification, representative selection, dynamic detection, dispersion optimization and result inference.

An endoscope system includes an endoscope and a processor device. The processor device functions as an abnormality detection unit, an abnormality information generation unit, and an abnormality information management unit. The abnormality detection unit detects an abnormality of the endoscope by using information detected by an image sensor of the endoscope. The abnormality information generation unit generates abnormality information including sensor information detected by the image sensor at a time of abnormality detection and in a predetermined period before and after the abnormality detection and operating information of the endoscope. The abnormality information management unit stores the abnormality information in a memory.

The application relates to the field of vehicle detection, and provides a vehicle operation state real-time monitoring method and system based on Internet of Things, which comprises the following steps: performing multistage pretreatment on original signals collected by a plurality of source sensors of a vehicle to obtain standardized multimodal data flow; inputting an edge computing unit, performing feature extraction on the standardized multimodal data flow through a multi-domain feature extraction algorithm to obtain a comprehensive feature vector, and performing abnormality detection through a manifold alignment algorithm to obtain a feature data packet with a priority label; performing channel allocation on a multi-channel communication interface through a game theory model to obtain a target transmission scheme, uploading the feature data packet to the cloud according to the target transmission scheme to obtain a time sequence feature database; and inputting the time sequence feature database into a cloud digital twin model, performing fault diagnosis on the time sequence feature database through a residual fusion algorithm to obtain a structured fault diagnosis report. The application improves the driving safety of the vehicle.