50results about How to "Reduce false alarms" patented technology

This invention provides a method and system for remote meter reading and water usage information management for smart water meters. The method mainly includes: receiving raw data frames containing information such as cumulative flow values ​​and collection timestamps, and performing multi-dimensional quality checks to generate collection status identifiers; dividing the water usage interval into valid collection intervals and pending confirmation intervals based on the identifiers; calculating the measured water usage in the valid intervals and extracting abnormal features to generate initial abnormal events; generating a completion sequence for the pending confirmation intervals based on boundary flow values, historical water usage characteristics, and regional balance constraints; determining a supplementary reading control strategy and issuing supplementary reading instructions based on the completion sequence and other information; performing secondary verification of the initial abnormal events based on the supplementary data, and outputting the final abnormal result and meter reading data. This method improves the accuracy of water usage anomaly detection and the reliability of meter reading data through data quality grading, interval hierarchical management, and closed-loop verification of abnormal events.

This utility model relates to a water leakage detection device, comprising a PCB board, two copper foil electrodes disposed on the PCB board, and an electronic control board electrically connected to the two copper foil electrodes. The device is characterized in that the two copper foil electrodes are arranged side-by-side with a gap between them, and the PCB board has a through-hole corresponding to the gap. The advantages of this utility model are that water vapor or small water droplets generated in high-temperature and high-humidity environments are less likely to form on the PCB board, reducing false alarms, improving work efficiency, and the overall structure is simple and easy to install and disassemble.

The application discloses a radar target stable tracking method under a shielding environment, and comprises the following steps: a northeast two-dimensional coordinate system is established, and a target ship state is mapped into a state vector; a Kalman filter is used for prediction, a residual error and an innovation covariance matrix are calculated in combination with actual observation, and an elliptical threshold is constructed; if the observation falls into the threshold, the state is updated; otherwise, the observation is judged as a mismatched observation, and short-time missed detection prediction is performed; a sliding time window is set, when the number of mismatched observations in the window reaches a threshold, shielding judgment is performed in combination with the geometric relationship among the predicted positions of the ship and the target and the boundary of a static obstacle; if the condition is met, a shielding maintaining mode is entered, and the target track is continuously estimated by adjusting filter parameters or a predicted track; when a plurality of continuous observation frames fall into the threshold and the geometric shielding is removed, normal tracking is recovered through smooth transition. The application can effectively solve the problem of tracking interruption caused by the shielding of a radar target, and improve the continuity and stability of tracking under a shielding environment.

The present disclosure provides an axle temperature early warning monitoring method and device, electronic equipment and storage medium, which can be applied to the field of rail transit technology. The axle temperature early warning monitoring method comprises: analyzing an axle temperature data set from a sensor to obtain temperature rise rate data; determining a time interval in which the first temperature rise rate changes to the second temperature rise rate according to the temperature rise rate data; in the case that the length of the time interval is less than or equal to a preset threshold, determining the axle temperature data corresponding to the time interval in the axle temperature data set as jump data; and performing early warning monitoring according to other axle temperature data in the axle temperature data set except the jump data.

The application relates to the technical field of intelligent transportation and carbon governance, in particular to a passenger car carbon emission monitoring and regulation system and method based on multi-source spatio-temporal data. The application solves the problem of scattered and inconsistent data by preprocessing and uniformly mapping multi-source spatio-temporal data. A three-dimensional carbon emission calculation model of vehicle-space unit-time period is constructed to realize accurate calculation of single-trip carbon emission of a single vehicle and positioning of high-carbon emission hotspots. A clustering algorithm is used to complete differentiated division of user groups. A dynamic early warning threshold is generated based on a warning threshold prediction model, regional carbon emission targets and historical data to reduce false positives and false negatives. A warning type-policy tool-adaptation object mapping rule library is established, and a regulation strategy is generated by combining early warning signals and real-time data to realize automatic and accurate generation of regulation strategies from problem identification. The model parameter, early warning threshold and mapping rule are optimized by using policy implementation effect data to form a monitoring, early warning, regulation, optimization closed-loop management and realize accurate regulation.

This application provides an apparatus and method for capturing multimode signals with fused communication and navigation, relating to the field of signal capture technology. The apparatus includes: a configurable differential correlation unit, whose configurable parameters include an enable signal and differential parameters; a configurable PMF unit, whose configurable parameters include an enable signal and correlation accumulation parameters; a configurable FFT unit, whose configurable parameters include an enable signal and the number of FFT points; a result generation unit, whose configurable parameters include a feature threshold; and, if its configurable parameters also include interpolation parameters, performing interpolation estimation on the frequency calculation result based on the interpolation parameters; and a scheduling control unit, used for parameter configuration and scheduling control of the configurable differential correlation unit, the configurable PMF unit, the configurable FFT unit, and the result generation unit. The implementation provided in this application can achieve different signal capture processes through parameter configuration in different application scenarios.

The invention relates to the technical field of vehicle control, and discloses a vehicle vibration monitoring method and device, a vehicle and a storage medium, and the method comprises the steps: obtaining a motion signal of each sensing channel; calculating to obtain an acceleration vector modulus length and an acceleration modulus length change rate based on the first motion signal, and calculating to obtain an angular velocity vector modulus length and an angular velocity modulus length change rate based on the second motion signal; generating a first preliminary vibration metric value based on the acceleration vector modulus length and the acceleration modulus length change rate, and generating a second preliminary vibration metric value based on the angular velocity vector modulus length and the angular velocity modulus length change rate; performing time sequence integration on the first preliminary vibration metric value and the second preliminary vibration metric value in the historical acquisition period by adopting a sliding window mechanism to obtain a first smooth vibration metric value and a second smooth vibration metric value; and performing fusion processing on the first smooth vibration metric value and the second smooth vibration metric value to obtain a target vibration metric value, and determining whether an effective vibration event occurs based on the target vibration metric value.

The embodiment of the invention provides a switch fan fault determination method and device, electronic equipment and a storage medium. The switch fan fault determination method comprises the steps that the fan rotating speed of a fan and temperature data corresponding to a plurality of functional components are obtained through a simple network management protocol; determining reference temperature data according to the correlation coefficient of the fan rotating speed and the temperature data; determining predicted temperature data according to the rotating speed of the fan; and determining switch fan fault information based on the reference temperature data and the predicted temperature data. According to the embodiment of the invention, fault false alarms can be reduced, and the timeliness and adaptability of fault determination are improved.

The invention discloses an anti-counterfeiting and anti-channel conflict monitoring method based on anti-counterfeiting graph codes and space-time sequence reconstruction, belongs to the technical field of anti-counterfeiting traceability and supply chain management, and can solve the problems that traditional static anti-counterfeiting is easy to copy and channel conflict monitoring is lagged. The method comprises the following steps: receiving a code scanning verification request initiated by a user terminal, and obtaining a mapping relation between unique identification information of a target product and product factory information; analyzing the unique identification information, and collecting spatio-temporal data corresponding to the code scanning verification request; constructing a spatio-temporal trajectory sequence to be detected; inputting the spatio-temporal trajectory sequence into a preset spatio-temporal sequence reconstruction model, and outputting a reconstruction sequence by performing feature compression and deconstruction on the spatio-temporal trajectory sequence; and calculating a difference metric value between the space-time trajectory sequence and the reconstruction sequence, and if the difference metric value exceeds a dynamic threshold value, judging that the product circulation is abnormal.

The invention belongs to the technical field of intelligent traffic detection and intelligent logistics supervision, and provides a track-level dynamic overrun detection method and system for a large transport vehicle, and the technical scheme is that the method comprises the steps: carrying out the cross-frame target association and tracking based on an output single-frame clustering result, and estimating the motion state of the vehicle based on Kalman filtering; transforming and aligning historical multi-frame point cloud clusters of the same target to a current frame coordinate system by using the motion state, and carrying out superposition and fusion to generate a track-level holographic point cloud cluster; geometric feature vectors are extracted from the obtained track-level holographic point cloud clusters, and vehicle types are recognized and obtained in combination with the geometric feature vectors and the trained classification model; and for the identified large transport vehicle target, carrying out adaptive slicing on the track-level holographic point cloud cluster of the large transport vehicle target along the height direction, fitting a vehicle body edge straight line in each slice to calculate the size, and combining the obtained weight data to complete dynamic overrun judgment according to a set standard. And high-precision and high-robustness over-limit detection of the large transport vehicle is realized.

The application relates to the technical field of hardware equipment quality tracing, and discloses a hardware full-life-cycle quality tracing method and system based on IoT, which comprises the following steps: acquiring multi-dimensional real-time data flow and arranging the same into a real-time running data set; extracting distribution characteristics based on a historical data archive to obtain a benchmark reference space; projecting the real-time data to calculate a deviation quantitative value, correcting environmental deviation when the deviation quantitative value exceeds a threshold value to obtain a deviation result; extracting degradation characteristics to match historical trajectories to locate a degradation process; performing time sequence analysis to predict residual life to obtain a failure time window; and generating and arranging maintenance intervention instructions into a scheduling instruction set. The method realizes hardware full-life-cycle quality tracing and early abnormality early warning, improves maintenance accuracy, and reduces fault loss.

This invention belongs to the field of railway intelligent fire protection and pipeline multi-source leakage detection technology, and discloses a comprehensive intelligent leak detection and maintenance system and method for railway fire protection pipeline networks. The invention adopts a three-level hardware architecture: a station-level perception layer, a station-section-level regional aggregation layer, and a group-company-level global control layer, with a supporting execution linkage layer. The perception layer deploys IEEE1588PTP sub-millisecond synchronous multimodal acquisition units to simultaneously acquire pressure, buried acoustic signatures, and inlet / outlet flow time-series signals. The edge end incorporates convolutional FastICA blind source separation, BO-LightGBM leak identification, multi-source topology adaptive fusion positioning, and flow steady-state dual-criteria modules, dynamically adjusting the positioning dimension weights, using dual-condition judgment to reduce false alarms, and is equipped with differentiated maintenance processes for track maintenance windows and train operations. This invention is adaptable to railway scenarios with strong interference and multi-branch pipeline networks, achieving a micro-leakage identification accuracy of ≥97.4%, a normal positioning error of 0.91m, and local operation compliance with railway network security standards at the edge end. It can be widely applied to online monitoring of buried fire protection pipeline networks in various railway stations.

The present application belongs to the technical field of radar signal processing, and particularly relates to an indoor fan interference distinguishing method based on millimeter wave radar signal autocorrelation. In order to overcome the problem of poor generalization performance of the current energy threshold method and convolutional neural network method in the field of indoor personnel detection, the present application provides an indoor head-shaking fan and human target distinguishing method based on autocorrelation function. The specific operation is to calculate the maximum correlation coefficient value of radar echo under different distance gates to determine the signal periodicity, and to distinguish human signals and fan signals by using the signal periodicity. The method can be applied to personnel detection methods in different indoor scenes, and can effectively improve the anti-interference ability of the radar system to the head-shaking fan.

The application relates to the technical field of crack detection, and discloses a cement pouring surface crack detection method and system, which comprises the following steps: a high-frequency sound wave is emitted to a cement pouring surface structure by using an ultrasonic instrument; when the sound wave meets the cement pouring surface, a reflection is generated to form an echo; the echo is captured by a receiver; and whether the cement pouring surface has cracks and the depth of the cracks is identified according to the time difference of the echo. The application continuously captures crack echoes of a preset data detection amount, carries out peak amplitude sorting and difference value calculation on all captured echo segment signals, and further judges whether there is an abnormal echo fluctuation by comparing the fluctuation amplitudes, so that the double judgment mechanism can more effectively exclude invalid scattering and redundant reflection signals caused by rough cement pouring surfaces and other factors, and the risk of misjudgment or false crack alarm is greatly reduced.

The application discloses a hyperspectral image anomaly detection method, device and medium, relates to the technical field of hyperspectral image processing, and comprises the following steps: acquiring a hyperspectral image, performing preliminary detection on the hyperspectral image to obtain a preliminary detection result, replacing the pixel value of each target pixel point in the hyperspectral image and the pixel value of a neighborhood pixel point to obtain an initial background image, taking the initial background image as input, training an anti-similarity optimization coding network under the constraints of reconstruction loss and anti-similarity loss to obtain a trained model, and reconstructing the initial background image by using the trained model to obtain a reconstructed background image, calculating the difference between the hyperspectral image and the reconstructed background image to obtain a hyperspectral anomaly detection image. The application can significantly improve the accuracy and robustness of target detection, and better cope with detection requirements in various complex scenes.

This invention relates to a method for detecting the edge of weak moving infrared targets based on frame difference local contrast. The method identifies the main false alarm sources—high-brightness cloud edges, blind flash noise, and the inter-frame radiometric characteristics differences of the target. It enhances the target edge through three-frame temporal difference and an improved local contrast calculation method, removing false alarm sources such as flash noise, high-brightness background, and background edges. Then, based on the generated saliency map, threshold segmentation is used to obtain the target edge detection result, and finally, the original image is retrieved to obtain the final accurate target location. This invention addresses the difficulty in simultaneously meeting the requirements of detection rate and false alarm rate for weak infrared targets under complex dynamic backgrounds in practical engineering. Experimental results show that the proposed algorithm has high stability, effectively reducing the number of false alarms and improving target detectability while ensuring detection efficiency.

This invention relates to the field of industrial system condition monitoring and intelligent early warning technology, specifically disclosing a risk early warning method and system for the cooling circuit of a liquid-cooled charging cable. The method involves collecting and preprocessing multi-dimensional time-series data composed of liquid circuit, electrical, and environmental parameters. Based on a combination of K-means clustering and rule-based judgment, five operating conditions are identified: standby, low power, high-power fast charging, peak overcharging, and derating operation. A Kalman filter-ARX model or a TCN-Transformer fusion model is then applied according to the operating condition for time-series prediction. Based on the predicted residual sequence, four trend features are extracted: cumulative residual value, growth rate, multivariate consistency, and confidence interval deviation. The final risk score is obtained by dynamically weighting the data according to the operating condition and combining it with the confidence coefficient of the abnormal duration. Finally, early warning levels are classified, and graded charging power linkage control commands are output.

The application discloses an unmanned ship underwater target intelligent identification method based on an imaging sonar, and relates to the fields of unmanned operation platforms and target identification. The application is aimed at the requirements of unmanned ship navigation and tasks, considers the task characteristics of the unmanned ship, and specifically adopts a forward-looking sonar to perform target ranging positioning and accurate identification, and based on machine learning and, realizes thorough water area perception, target detection and accurate identification for underwater targets. The application can improve the underwater target identification performance of the unmanned ship.

This invention provides a method for identifying ground faults in distribution network lines based on a time-series large model, comprising: Step S1: data acquisition and spatiotemporal alignment; Step S2: multi-scale sliding window segmentation; Step S3: calculation of physical enhancement features; Step S4: construction of a training sample set; Step S5: construction of a time-series large model with physical information enhancement; Step S6: model training; Step S7: real-time acquisition and identification of ground faults. This invention achieves high-precision, low-false-alarm ground fault detection, accurately identifies fault types and faulty lines, and effectively solves the identification challenges of extreme scenarios such as intermittent arc grounding and high-resistance grounding.

This invention relates to the field of power communication technology, and particularly to a method, apparatus, and storage medium for fault detection in communication links. The method includes: extracting signal quality features and residual distortion based on a signal eye diagram; extracting distortion event parameters based on the residual distortion to construct distortion impact features; determining application-layer experience quality features based on webpage full load time and RTP packet loss rate, and generating comprehensive link degradation features by combining them with bit error rate metrics; collecting terminal information, constructing a link congestion retransmission factor, determining link status, and adjusting the comprehensive link degradation features according to the link status; generating a graded early warning index based on the corrected degradation features and distortion impact features, and executing early warnings and dynamically adjusting monitoring strategies accordingly. This invention effectively improves the sensitivity of communication link fault detection.

The invention discloses a feeding machine bottom belt slipping detection method and device, electronic equipment and a storage medium. The method comprises the following steps: determining a first signal; determining a working condition state according to the first signal; matching the detection strategy according to the working condition state to obtain a first strategy; and performing slip detection according to the first strategy. According to the method, the current working condition of the material transportation system is determined according to the obtained first signal, the corresponding detection strategy is matched according to the obtained working condition, and slip detection is performed on the material transportation system according to the obtained detection strategy, so that multi-device signals and the detection strategy can be combined; when a plurality of associated signals continuously appear at the same time according to a specific fault logic mode, an alarm is triggered, so that the occurrence of false alarms is greatly reduced.

The utility model provides a pipeline valve chamber monitoring, alarming and closing system, and relates to the technical field of pipelines, the system comprises a pressure acquisition module, a human-computer interface module, a plurality of calculation modules and a plurality of output modules; the pressure acquisition module is connected with a valve chamber in the pipeline and is used for acquiring the pressure of the valve chamber; the man-machine interface module is used for selecting a target alarm condition based on the number of the pressure acquisition modules; the plurality of calculation modules are connected with the pressure acquisition module and the human-computer interface module and are used for calculating the pressure drop rate of the valve chamber according to the pressure; determining whether the pressure drop rate meets a target alarm condition or not; and the output modules are connected with the calculation modules and used for outputting a valve closing instruction when the pressure drop rate meets the target alarm condition. Thus, on one hand, the user can select the target alarm condition, the user demand is met, and the user experience is improved; and on the other hand, the selected target alarm condition can reduce the occurrence of false alarm and false turn-off.

The application provides a manufacturing process abnormality correlation discrimination method and device, electronic equipment and storage medium, and belongs to the technical field of industrial internet and intelligent manufacturing. The method comprises the following steps: acquiring abnormality occurrence time corresponding to a device abnormality event and associated process parameter data; constructing an abnormality analysis time window based on the abnormality occurrence time, and extracting variation characteristics of the process parameter data in the window; performing correlation analysis on the device abnormality and the process parameter variation according to the variation characteristics, and generating abnormality correlation characteristics; comparing the abnormality correlation characteristics with a preset abnormality correlation rule, determining an abnormality cause type according to a comparison result, and the abnormality cause type comprises a device abnormality or a process abnormality; and generating an abnormality discrimination result based on the abnormality cause type. The application can effectively reduce the false alarm rate of abnormality alarms, improve the explainability of abnormality information and the operation and maintenance disposal efficiency.

The invention relates to the technical field of cable testing, in particular to a marine cable insulation aging state evaluation method based on sea condition influence, and the method comprises the steps: obtaining a dielectric loss factor frequency spectrum through a broadband dielectric spectrum test, and extracting a body aging characteristic quantity to distinguish environment reversible interference and irreversible insulation aging; the mechanical damage degree and the damage development rate are obtained by applying mechanical pulse excitation and analyzing stress wave propagation characteristics; establishing a leakage current-temperature relation through a non-destructive voltage withstand test, calculating an insulation safety margin and identifying a dominant aging mode; and further fusing multi-source degradation data to construct a probability evolution model, predicting the future change process of each degradation index, and obtaining the probability distribution and confidence interval of the residual life of the cable, thereby realizing the comprehensive evaluation and life prediction of the insulation aging state of the marine cable.

The invention discloses an optical cable defect detection method and a terminal, and the method comprises the steps: obtaining multi-sensor data of an optical cable, and extracting data features from the multi-sensor data; acquiring a preset model library, and associating and filtering the data features by using the preset model library to generate a fusion feature packet; the fusion feature packet is analyzed based on the improved D-S evidence theory, the defect type and the comprehensive confidence coefficient of the optical cable are obtained, an optical cable inspection report is generated according to the multi-sensor data corresponding to the fusion feature packet, the defect type and the comprehensive confidence coefficient, accurate detection of optical cable defects can be achieved, and the inspection accuracy and efficiency are improved.

The present application relates to the technical field of power quality testing, in particular to a fault prediction and health management system and method for full-process automated power quality testing, comprising the following steps: data acquisition and preprocessing; health core feature extraction; power quality fault prediction, adopting a test working condition-equipment state decoupling fault prediction technology that fuses working condition disturbance sensitive factors, generating a working condition normalized health residual vector based on health core features and test working condition information; health management and operation decision-making.The present application introduces working condition disturbance sensitive factors based on historical health sample statistics, adopts a test working condition-equipment state decoupling fault prediction technology, uses the factors to correct and normalize the sensitivity of original feature deviation, and generates a working condition normalized health residual vector.Based on the residual vector, the fault prediction can reduce false alarms and missed reports caused by working condition fluctuations, and improve the accuracy of fault prediction for the test system.

The application provides a contraband detection equipment risk early warning method and system using a cloud network end, wherein Raman spectrum data of a sample to be detected is obtained and wavelet transform is performed to generate a feature spectrum to be matched; a cloud server gathers non-alarm spectrum data uploaded by multiple terminals, and generates an environment background feature spectrum set by clustering; the feature spectrum to be matched is matched with a standard spectrum library and a background spectrum set, and based on spectrum cross-correlation, peak shift and peak shape correlation weighted operation, a comprehensive matching score is obtained; when the comprehensive matching score of the feature spectrum to be matched and any background spectrum is higher than a background suppression threshold, an adjusted contraband comprehensive matching score is generated; based on the adjusted contraband comprehensive matching score, a ratio of the highest score and the second highest score is calculated to determine a matching ambiguity coefficient, and in combination with the highest score, a preset threat level of the corresponding contraband and the matching ambiguity coefficient, a risk early warning level is output.

The application discloses a vehicle platform-oriented equipment PHM running software integrated management system, and particularly relates to the field of vehicle health management and running software cooperative control, and is used for solving the problem that the original health conclusion is difficult to be accurately applied to the current running state after the software state of a target subsystem changes; through collecting target software cluster version identification, parameter set abstract, health anchor value, fault event count and working condition bucket label, a current software state fingerprint is generated, a verified PHM reference template corresponding to the current software state is searched, on the basis of the health conclusion before the change is frozen, continuous verification is performed on the health anchor value and the fault event count, and according to the continuous consistency count or the continuous mismatch count, the PHM configuration is switched or an abnormal disposal instruction is outputted, so that the PHM conclusion continuity maintenance in the vehicle platform state change stage is completed.

The invention discloses a carbon portrait anomaly detection method for a high-energy-consumption industry, and belongs to the technical field of industrial process monitoring. The method comprises the following steps: firstly, accessing a plurality of data sources including an enterprise carbon emission direct measurement data source, a production activity data source, a production process parameter data source and an energy consumption data source to form a fusion feature vector including a carbon emission rate, a yield, a process parameter and energy consumption; secondly, extracting a carbon emission intensity feature, an efficiency feature and a time-space correlation feature based on the fusion feature vector, and constructing a dynamic carbon portrait; and finally, based on the dynamic carbon portrait data stream, adopting a multi-scale sliding window, and combining a composite model fusing a graph convolutional network and a gating cycle unit to carry out space-time mode modeling, calculating a multi-scale deviation degree fusing space-time correlation, and realizing anomaly judgment and source tracing. According to the invention, more accurate, more timely and explainable detection of carbon emission abnormity in the high-energy-consumption industry is realized.

The embodiment of the application relates to the technical field of converter operation data anomaly detection, and provides a converter operation data anomaly detection method and system based on a self-encoder, which no longer analyzes measurement data of a sensor in isolation, but explicitly introduces working condition parameters reflecting a running state of the converter into an analysis process of the self-encoder, learns an internal correlation between sensor data features and working condition vectors in a training phase of the self-encoder, establishes a normal data mode benchmark under a working condition, and can dynamically adjust an expectation of normal data according to current real-time working condition information when online detection is performed by using the trained self-encoder, so that data fluctuation caused by normal working condition switching, such as load change, is correctly identified as a normal state, and only when the data mode deviates from the normal benchmark corresponding to the current working condition, the data mode is determined as a real anomaly, so that false alarms caused by working condition change are effectively reduced.