309results about How to "Reduce false positive rate" patented technology

The invention discloses an ultrasonic welding quality online detection system and method, and belongs to the technical field of laser non-contact measurement. According to the invention, the laser vibration measurement probe is rigidly coupled to the welding head to construct a follow-up-common-optical-path measurement unit, so that synchronous acquisition of vibration signals with zero mass loading is realized; further extracting an attenuation section after welding is finished from the signal, and inverting an equivalent modal damping ratio representing an interface energy dissipation state based on an exponential attenuation model; meanwhile, multi-dimensional physical indexes such as an energy transfer efficiency index Itrans and an input stability index Iin are calculated, and in combination with an energy absorption state index, collaborative fusion is carried out through a weighted fusion formula to obtain a comprehensive quality score; and finally, realizing quality attenuation early warning based on time sequence trend analysis of a scoring sequence. On-line sensing of the deep dynamic state in the welding process is achieved, the early defect recognition sensitivity and the system anti-interference capacity are remarkably improved, and the predictive maintenance capacity of quality degradation is achieved.

The invention discloses a multi-mode defect automatic classification method, device and equipment and a storage medium. The method comprises the following steps: acquiring a microscope image, an X-ray image and defect feature information data of a to-be-detected product; first classification processing is preferentially carried out based on the microscope image, when the first classification processing result meets a first preset reliability condition, the first classification processing result is taken as a final classification result, and when the first classification processing result does not meet the first preset reliability condition, the final classification result is taken as a final classification result. Performing feature fusion based on the X-ray image and the defect feature information data, and executing second classification processing; when the second classification processing result meets a second preset reliability condition, the second classification processing result serves as a final classification result, and when the second classification processing result does not meet the second preset reliability condition, defect type judgment is conducted based on key parameters in the defect feature information data, and the final classification result is output; the classification accuracy and efficiency can be improved, and the error recognition rate is reduced.

The invention relates to a point cloud denoising method of a photon counting laser radar and an intelligent denoising system, and belongs to the technical field of photon laser radar data processing. The technical problems that the performance of a fixed parameter denoising method is seriously unbalanced under different ground feature and complexity scenes, and high denoising rate and high signal fidelity cannot be considered at the same time are solved. Synchronously acquiring an optical image and an original photon point cloud of the target area; identifying the dominant ground feature type of the laser spot area through real-time semantic segmentation; calculating scene complexity based on the point cloud data and determining the grade of the scene complexity; querying a preset two-dimensional parameter mapping table according to the combination of the surface feature type and the scene complexity level, and dynamically obtaining an optimal denoising parameter set; and finally, the parameter set is utilized to drive adaptive denoising processing, and signal points and noise points are distinguished by calculating the local density and direction consistency of the points and constructing a two-dimensional discrimination space. The method is mainly used for real-time processing platforms such as unmanned aerial vehicles, and the point cloud denoising precision, the signal retention rate and the topographic feature fidelity are remarkably improved.

The invention relates to the technical field of solid state disks, in particular to a solid state disk ID and hardware state synchronization method, a controller, a system and a medium. Comprising the following steps: S1, before a system enters a dormant state, acquiring and persistently storing initial identification information of NVMe equipment by a driving layer; s2, after the system is awakened from the dormant state, executing multiple rounds of identifier query operation on the NVMe equipment; s3, calculating an identifier change rate based on a multi-round query result and the initial identifier information, and if the identifier change rate is lower than a first preset threshold value, judging that the interference is temporary interference, and maintaining an equipment link; if the identifier change rate is higher than a first preset threshold value, entering a step S4; and S4, acquiring real-time state parameters of the physical layer of the NVMe equipment, verifying the real-time state parameters, recovering the link if the real-time state parameters pass the verification, and resetting the NVMe equipment if the real-time state parameters do not pass the verification. Compared with the prior art, through state analysis, cross validation and joint judgment, the misjudgment rate caused by instantaneous change of the ID of the equipment is remarkably reduced.

The application discloses a kind of key feature transformer health state detection systems, it is related to power equipment monitoring technical field, including: data acquisition module, data processing module, confidence calculation module, fault determination module and result output module;Data acquisition module synchronously acquires transformer oil tank surface vibration signal and neutral point direct current data;Data processing module calculates the phase difference of vibration signal and the coherence coefficient of vibration signal and direct current data;Confidence calculation module calculates mechanical fault confidence;Fault determination module judges whether mechanical fault confidence exceeds preset threshold, exceeds and then carries out winding loosening positioning processing, generates loosening coordinate;Otherwise, the multi-band resampling of vibration signal is carried out and the coherence coefficient data is recalculated;Result output module outputs loosening coordinate or interference warning signal;The application can improve the accuracy of transformer health state detection, ensure the reliability of fault positioning.

The invention discloses a laser marking quality automatic evaluation method based on machine vision. The method comprises the following steps of S1, collecting a laser marking image and performing preprocessing; s2, inputting the preprocessed image into an image segmentation network constructed based on FastSAM to generate a segmentation mask image; s3, extracting a marking area communication block according to the segmented mask image, and constructing an image sub-area set; s4, normalizing the sizes of the image sub-regions, constructing three-channel enhanced input, inputting the three-channel enhanced input into an image coding network constructed based on the OfficientViT, and extracting an image-level feature vector; s5, inputting the image-level feature vector into an ArcFace angle interval classification module, and outputting a defect type classification result; s6, calculating a multi-dimensional quality scoring index; and S7, inputting the multi-dimensional quality scoring indexes into a weighting function to generate a comprehensive scoring result, comparing the comprehensive scoring result with a qualified threshold, and outputting an evaluation result. According to the method, a region perception image segmentation strategy and a lightweight feature coding mechanism are combined, and automatic identification and quality evaluation of character defects in the laser marking image are realized.

The application discloses a spunlace non-woven fabric rewinding equipment collaborative control method and system based on the Internet of Things, and relates to the field of electric digital data processing.The method comprises the following steps: obtaining historical data and preprocessing to obtain a plurality of three-dimensional data sequence sets of roll diameter-torque-tension under normal working conditions; dividing the plurality of three-dimensional data sequence sets into a plurality of roll diameter slice sample groups and screening to obtain a non-woven fabric flat data set; performing nonlinear fitting on the non-woven fabric flat data set and constructing non-woven fabric flat upper and lower tracks; based on the non-woven fabric flat upper and lower tracks, real-time marking of an abnormal data interval in the current rewinding process is performed, and abnormality determination is performed in cooperation with an image detection mechanism; after the current rewinding process is completed, the non-woven fabric flat upper and lower tracks are updated and optimized. The application can dynamically adapt to roll diameter changes, accurately mark abnormal intervals and accurately determine abnormal working conditions in cooperation with an image detection mechanism, thereby effectively improving the quality control level of spunlace non-woven fabric rewinding production.

The invention discloses a file system event processing method and device based on an intelligent filtering rule, and the method comprises the steps: obtaining a file system original event of a monitoring directory, carrying out the cross-platform standardization processing, and extracting event feature vectors of four dimensions: time, a file, a process and a path; the method comprises the following steps: constructing a rule base containing software operation modes such as an editor, a compiler and a version control tool, performing mode matching on an event sequence, calculating confidence, determining a filtering strategy type based on a matching result, executing corresponding processing, and dynamically optimizing system parameters through statistical analysis. The technical problems that an existing file monitoring system is serious in event redundancy and frequent in false triggering are solved, effective file operation and temporary intermediate operation can be intelligently distinguished, invalid synchronous triggering is greatly reduced, the accuracy is improved to 95% or above from 60-70% of a traditional scheme, and invalid event processing is reduced by 90% or above.

The invention provides a passenger vehicle door anti-pinch control method and system based on visual identification. Belongs to the technical field of intelligent traffic and vehicle safety control. The method comprises the following steps: acquiring a vehicle door area video picture through a video acquisition module, and generating vehicle door area original video data; performing video preprocessing according to the original video data of the vehicle door area to generate preprocessed video data; inputting the preprocessed video data into a target recognition module, recognizing a human body or a carried object target, and generating target recognition data; performing target feature extraction according to the target identification data to generate target feature data; according to the passenger-carrying vehicle door anti-pinch control method based on visual identification, the response speed of vehicle door anti-pinch is increased, a response can be made immediately when a target just enters a dangerous area, and potential safety hazards caused by response lag are reduced.

This invention belongs to the field of bridge quality inspection technology, specifically a method for evaluating the quality of box girders based on the MH wavelet average evolved power spectrum. The method includes: selecting a qualified standard beam, deploying vibration sensors to collect vertical acceleration time-history signals; preprocessing the signals by performing wavelet transform, calculating the squared modulus of the wavelet coefficients and normalizing them to obtain a three-dimensional evolved power spectrum, and then averaging the time dimension to obtain the average evolved power spectrum; extracting three characteristic parameters—frequency at maximum power, half-power bandwidth, and skewness—using the standard beam spectrum as a benchmark; repeating the above steps on the beam to be evaluated, comparing the deviations of the characteristic parameters, and combining a grading threshold and a differentiated review process to determine the quality, and statistically analyzing the batch data dispersion to provide feedback on the stability of the beam manufacturing process. This invention achieves non-destructive, batch, and accurate evaluation of box girder quality, and can effectively identify hidden defects such as insufficient elastic modulus of concrete and prestress loss.

The material detection image defect enhancement method based on multi-light source complementation of the application comprises the following steps: collecting and identifying parameters, processing the parameters by a ternary mapping model, and outputting noise feature prediction values and multi-light source initial parameters; adjusting multiple light sources after optimizing the multi-light source initial parameters to obtain optimized parameters, and collecting a noisy image of a material to be detected through a detection camera; inputting the noise feature prediction values, the optimized parameters, and the noisy image into a preset conditional GAN anti-noise model with light source constraints, and generating a defect enhancement image; when the parameter optimization criterion is not met, adjusting the optimized parameters, collecting a new noisy image, and repeating the steps until the parameter optimization criterion is met, and outputting the defect enhancement image, through the cooperation of multi-light source parameter adjustment and the introduction of the conditional GAN, a defect enhancement image with obvious and accurate features is generated, and through the introduction of an artificial intelligence function library and computer visual and auditory training and reinforcement of the model, the accuracy of subsequent defect recognition can be greatly improved.

The utility model relates to the technical field of quality detection, and particularly discloses glass substrate detection equipment which comprises a rack, a tray, a horizontal driving assembly, a first light source assembly, a second light source assembly and an image acquisition assembly, the image acquisition assembly comprises a lifting driving assembly mounted in the detection chamber and an image collector driven by the lifting driving assembly to lift; according to the equipment, the first light source assembly and the image acquisition assembly are matched to detect the reflective quality of the glass substrate, and the second light source assembly and the image acquisition assembly are matched to detect the transmissive quality of the glass substrate, so that the closed and multi-mode quality detection of the glass substrate is realized, and the influence of external environment light on a detection result is reduced; the detection efficiency and accuracy are remarkably improved, and the labor cost and the misjudgment rate are reduced.

A kind of detection method and device of fake APP, terminal, the method includes: determining training data;Keyword extraction is carried out to the brief introduction of each pair of target APP and the brief introduction of suspected APP, and the data vector of each keyword is determined;Determine the weight value of each keyword, and the data vector of each keyword in the target APP is weighted based on the weight value Operation is carried out to obtain target APP data vector, and obtain suspected APP data vector;The vector comparison result of target APP data vector and suspected APP data vector is calculated, the absolute value of the vector comparison result is determined as first data vector, and the square of the vector comparison result is determined as second data vector;Obtain the training text vector of the pair of target APP and suspected APP;Training fake detection model.The present application can enhance the association between keywords in model training phase, reduce the misjudgment rate.

This invention relates to the field of intelligent auditing, and more particularly to a graph neural network method and system for mining hidden relationships among multiple sets of enterprise accounts. The method includes: acquiring multiple sets of accounts of a target enterprise, extracting entity and transaction information, and constructing a heterogeneous graph network containing multiple types of nodes such as enterprises, individuals, bank accounts, and transaction vouchers, as well as multiple types of edges such as fund transfers, control, and voucher associations; inputting the heterogeneous graph into a pre-trained GNN, aggregating neighbor features through graph convolutional layers, and updating node embedding vectors; based on the embedding vectors, using an attention mechanism to calculate the confidence of hidden relationships between node pairs, and filtering suspicious related node pairs; performing path reasoning and backtracking on suspicious node pairs, mining multiple paths, and generating a chain of evidence for related paths. This application, by constructing a heterogeneous graph containing multiple types of nodes and edges, comprehensively captures entities such as enterprises, individuals, accounts, and vouchers and their multidimensional relationships, solving the problem that existing methods are unable to comprehensively characterize complex relationship scenarios and capture hidden relationships.

The application provides a power transformation equipment fault tripping monitoring system, method, medium and program product, and relates to the technical field of power grid fault processing. The monitoring system comprises: a data acquisition system, configured to acquire system operation data of a power grid system; if it is detected that the system operation data contains alarm information of a target substation and position change information of a switch in the target substation, the alarm information and the position change information are sent to a tripping judgment system; the tripping judgment system is configured to determine whether there is an operation and maintenance record corresponding to a time stamp; if not, it is determined that the switch has failed tripping, and the time stamp and a target switch identifier of the switch are sent to a tripping analysis system; the tripping analysis system is configured to determine system operation data of the target substation within a first preset time length corresponding to the time stamp according to the target switch identifier, and generate a fault tripping report of the switch. The application improves data collection efficiency, automatically realizes research and judgment of fault tripping, and further improves fault troubleshooting efficiency and fault processing efficiency.

This application relates to the field of relay protection technology, specifically disclosing a method, apparatus, equipment, and storage medium for evaluating secondary circuits. The method includes the following steps: obtaining an estimated fault distance associated with a fault event to be tested; determining the expected response range corresponding to the fault event based on the estimated fault distance; extracting the actual action set; performing a consistency check between the action set corresponding to the expected response range and the actual action set to obtain a consistency check conclusion; and outputting the evaluation result corresponding to the fault event based on the consistency check conclusion. By obtaining the estimated fault distance and determining the expected response range, the evaluation object is narrowed from the entire line bay to the responsibility domain corresponding to the fault location, reducing the probability of misjudgment in secondary circuit evaluation. The automated evaluation process, with fault distance as the core constraint and employing consistency check, improves the efficiency and stability of fault evaluation.

The application discloses a kind of satellite-based multi-circle layer coupling wide-area system dynamic management and control method, comprising: the global high-precision space-time reference is established by satellite constellation;According to the current own measuring point data and current associated measuring point data obtained in real time;When the current own measuring point data exceeds the first preset threshold, satellite remote sensing task is dynamically triggered, and current associated remote sensing data and current target associated measuring point data are obtained;Multi-circle layer coupling analysis determines the correlation of current event and current associated abnormal event;Ground server predicts event information using spatial correlation and time domain variation law;Satellite sends disposal instruction to ground execution terminal according to the correlation of current event and current associated abnormal event and prediction information.The application realizes global coverage real-time monitoring and closed-loop control through satellite communication, navigation, remote sensing, on-orbit intelligent computing integrated technology.The application also discloses a system, electronic equipment and storage medium for implementing the above method.

The application discloses a YOLO-based avalanche monitoring self-improvement system and method, and belongs to the technical field of intelligent geological disaster monitoring. The method collects multi-source image data through a UAV and satellite remote sensing, and realizes initial avalanche detection through YOLO. A time sequence consistency verification mechanism is used to screen high-confidence pseudo labels, and a dynamic time attenuation weight strategy is combined to construct an enhanced training set. When the pseudo labels accumulate or the performance decreases, model retraining is automatically triggered, performance evaluation is used to decide model updating or rollback, and a self-learning closed loop is formed. The application innovatively deeply integrates YOLO detection, automatic pseudo label distillation, physical parameter inversion and edge end spread deduction, realizes the whole-chain self-improvement of detection-deduction-warning-optimization, continuously improves the detection accuracy, reduces the artificial labeling amount, supports complex terrain and extreme environments such as strong reflection and dynamic blur, and reduces the early warning delay to the millisecond level.

The application relates to a cough symptom evaluation method and system based on a wearable device, wherein the method comprises the following steps: collecting an audio signal of a user, processing the audio signal to obtain a first cough evaluation coefficient of the user; obtaining an ACC signal and an ECG signal of the user through an electrocardiogram patch on the wearable device; processing the ACC signal to obtain a second cough evaluation coefficient of the user, processing the ECG signal to obtain a third cough evaluation coefficient of the user; and evaluating the cough symptom of the user based on the first cough evaluation coefficient, the second cough evaluation coefficient and the third cough evaluation coefficient. Through the application, the problem of how to accurately evaluate the cough symptom of the user is solved, the cough symptom evaluation of the fusion of three signals is realized, the misjudgment rate of the evaluation using the audio signal alone is reduced, and the accuracy of the cough symptom evaluation is improved in the case of environmental noise interference or small user coughing sound.

This application provides a motor load adaptive adjustment method based on analog circuits, relating to the field of motor control technology, including the following steps: converting the load current in the motor circuit into a first voltage signal, and generating a mode selection signal based on the amplitude and rate of change of the signal; wherein, when the amplitude of the first voltage signal exceeds a first threshold and its rate of change exceeds a second threshold, the mode selection signal indicates a dynamic response mode; otherwise, the mode selection signal indicates a steady-state adjustment mode; when the indication is a steady-state adjustment mode, the first voltage signal is introduced into a first path, which includes a first error amplifier with a first proportional coefficient; when the indication is a dynamic response mode, the first voltage signal is introduced into a second path, which includes a second error amplifier with a second proportional coefficient greater than the first proportional coefficient; generating and outputting a motor drive signal according to the adjustment signal output from the selected path.

The invention discloses a small molecule binding protein design method. The method comprises the following steps: S1, a structure acquisition step: acquiring a compound structure of a target small molecule ligand and protein; s2, a candidate sequence generation step: generating a candidate protein sequence set by adopting a protein generation model and adjusting parameters corresponding to the protein generation model according to the compound structure in the step S1; s3, a primary screening step; compounding the candidate protein sequence set in the step S2 with the small molecule ligand in the step S1, predicting a compound structure I, and screening a potential sequence from the compound structure I; s4, a fine screening stage: compounding the potential sequence screened in the step S3 with the small molecule ligand in the step S1, predicting a compound structure II, and screening a preferred protein sequence I from the compound structure II. Through deep fusion of AI generation and physical screening, a layer-by-layer progressive accurate screening funnel is constructed, and the false positive rate is greatly reduced.

This utility model relates to the field of glove sorting technology and discloses an automatic sorting device for latex gloves by size and specifications. It includes a frame assembly, a transport mechanism on the inner middle layer of the frame assembly, a laser emitter attached to the outer surface of the transport mechanism, a top frame on the top of the frame assembly, and a support platform fixedly mounted on the rear middle of the frame assembly. A pushing component is mounted on the top side of the support platform. Through a detection system composed of a laser emitter and a laser receiver, by analyzing the range and duration of laser beam obstruction, key glove size parameters such as palm width and finger length can be accurately measured, improving detection accuracy, reducing manual inspection errors, effectively reducing misjudgment rates, and improving product quality consistency. A signal transmission controller processes the detection data in real time and drives the electric cylinder, coordinating with the continuous conveying of the transport mechanism, significantly improving sorting efficiency compared to manual methods and reducing labor costs.

The application provides a child skull fracture automatic detection method and device based on generated data augmentation. The method comprises the following steps: acquiring a first child brain CT image set, and performing pixel labeling and preprocessing to obtain fracture data, suture data and normal data; obtaining a trained fracture lesion generation model and a suture generation model according to the fracture data, the suture data and the normal data; randomly sampling Gaussian noise for multiple times, inputting the Gaussian noise into the fracture lesion generation model and the suture generation model to obtain generated fracture CT patch data and generated suture CT patch data; training a candidate fracture detection model according to the fracture data, the suture data, the normal data, the generated fracture CT patch data and the generated suture CT patch data, and outputting a fracture detection model; and acquiring a second child brain CT image, and detecting the second child brain CT image according to the fracture detection model. The fracture lesion data and the suture data are augmented, so that the resolution of fractures and sutures can be improved.

The present invention provides a method, system, and related apparatus for evaluating the energy efficiency of photovoltaic modules in mountainous areas based on spatiotemporal heterogeneous conditions, comprising the following steps: Step 1, calculating the module power generation efficiency coefficient and the string power generation corresponding to a single inverter due to the consistency factor of photovoltaic string module installation; Step 2, obtaining the maximum effective power generation per unit installed capacity and the second-level active power of the string corresponding to the maximum power generation; Step 3, obtaining the actual power generation of the string corresponding to a single inverter for energy efficiency evaluation; Step 4, calculating the theoretical power generation of the string for energy efficiency evaluation; Step 5, calculating the ratio between the actual power generation of the string for energy efficiency evaluation and the theoretical power generation of the string for energy efficiency evaluation, and using it as the module energy efficiency evaluation index; The present invention effectively solves the problems of inconsistent module installation and uneven spatial distribution of irradiance caused by mountainous terrain, and significantly improves the accuracy and reliability of module energy efficiency evaluation.

This invention relates to the field of image analysis technology, specifically to a machine vision-based quality inspection system for new energy vehicle wiring harnesses and cable ties assembly. The system includes: an image acquisition module that uses polarimetric stereo technology to acquire multi-angle images; a geometric reconstruction and reference extraction module that calculates the surface normal field of the insulation layer and separates the background field of the cable's cylindrical curvature and the micro-indentation residual field, thereby extracting the global axial and radial curvature moduli of the cable; a feature decoupling analysis module that calculates the contour-shaping migration flow field of the indentation micro-residual field relative to the standard contour, and performs anisotropic decomposition of the flow field based on the global axial direction of the cable to obtain the axial slip index; and a quality inspection module that determines an adaptive slip judgment threshold based on the cable's radial curvature modulus, thereby generating inspection results. This invention solves the problems of difficulty in sensing micro-deformation on reflective cylindrical surfaces and the difficulty in decoupling slip risk from assembly tolerances, thus improving the accuracy of wiring harness and cable tie assembly quality inspection.

This invention belongs to the field of daily chemical product testing and analysis technology. It discloses an intelligent screening method, device, equipment, and storage medium for sulfur / sulfonate surfactants. The method involves pretreatment of the sample and high-resolution mass spectrometry (UHPLC-MS / MS) scanning, converting the sample into an mzXML file. All secondary mass spectrometry peaks in the file are screened to identify target secondary mass spectrometry peaks containing characteristic ions. The mass and peak intensity of all corresponding precursor ions are extracted. If the mass difference between two precursor ions is within the range of sulfur isotope mass difference and the peak intensity ratio is within a specified range, the precursor ion with the lower mass is selected as the quasi-molecular ion. A predicted molecular formula is generated, and matching structural information is retrieved from a database. Simulated fragmentation is used to obtain a simulated secondary mass spectrum, which is compared with the actual secondary mass spectrum to determine the predicted structure and identify sulfur / sulfonate surfactants. This intelligent processing of high-resolution mass spectrometry data improves data processing efficiency, sensitivity, and accuracy.

The embodiment of the invention provides a mobile terminal service availability inspection method based on system state matrix driving, which belongs to the technical field of physics, and specifically comprises the following steps: constructing a system service state matrix; detecting a structure dimension, a behavior dimension, a signal dimension, an abnormal dimension and a user perception dimension by using a multi-modal probe system, mapping detection results into corresponding discrete state values, and filling and updating a system service state matrix according to the discrete state values; dynamically deciding a subsequent inspection path and a detection priority by combining a real-time environment state and a user behavior mode of the mobile terminal on the basis of each dimension state value filled in the system service state matrix and a predefined association rule; and controlling the multi-mode probe system to execute a corresponding detection action according to the inspection path, and generating an availability evaluation result of the target system service based on the final state of the system service state matrix. Through the scheme disclosed by the invention, the inspection efficiency, accuracy and adaptability are improved.

This invention belongs to the field of sports training image monitoring technology, specifically involving a method and system for monitoring physical fatigue images during high-altitude sports training. It involves continuous video acquisition of trainees in the training area, extracting fatigue-sensitive biomechanical parameters using a human posture estimation network and calculating progressive change trends. An early warning is generated when the combination of a decrease in stride symmetry index and an increase in trunk forward tilt angle meets preset fatigue triggering conditions. Environmental corrections are applied to the early warning threshold based on altitude and temperature. Facial image color features are used to track precursors of facial color changes caused by decreased blood oxygenation; a high-priority early warning is generated when abnormal facial color is synchronized with fatigue indicators.

The present application relates to the technical field of hydrological test and tree ring analysis, and particularly relates to a flood event detection method and system based on tree ring density, X-ray micro-density scanning is performed on the core samples of multiple target trees in the riverbank flooding zone to obtain early and late wood density profiles, a maximum late wood density time sequence is subjected to a flood stress mechanism recognition constraint Bayesian variable point detection to output candidate event years, a within-ring density gradient curve is extracted for the candidate event years, a flood growing season time window is determined according to the relative position of the density peak within the ring, a common occurrence test is performed on the multiple target trees after the phenology synchronization calibration to filter local terrain interference, and a historical flood density anomaly chronology containing the occurrence year, the growing season time window and the event intensity grade is output, which provides a physical reconstruction basis for the flood frequency analysis of a mountainous basin in a period when instrument records are missing.

This invention relates to a high-voltage interlock precision fault location system and method based on a multi-level resistor network, relating to the field of electric vehicle battery management systems (BMS). The system includes a battery management system and at least two high-voltage connectors. The battery management system is equipped with a resistance detection circuit. Each high-voltage connector contains an interlock resistor with a known resistance value. The interlock resistor is electrically connected to the resistance detection circuit, forming a high-voltage interlock detection loop. The battery management system locates the specific high-voltage connector where the fault has occurred by detecting changes in the resistance value of the high-voltage interlock detection loop. This invention achieves precise fault location, multi-level state identification, and graded safety control for high-voltage interlock faults, significantly improving fault diagnosis efficiency and vehicle availability while ensuring the safety of the high-voltage system.