65 results about "Fault grading" patented technology

The embodiment of the invention provides an energy storage system fault processing method and device, equipment, a medium and a product, and relates to the field of photovoltaic power generation, the method solves the problem of low fault processing efficiency in the prior art by constructing a cloud-side-end cooperative fault processing architecture, changes the traditional static threshold judgment logic, and improves the fault processing efficiency. A decision-making mode combining multi-source information fusion and dynamic prediction is adopted, firstly, preliminary diagnosis of real-time data is achieved through edge calculation, the instantaneity of response is ensured, and then historical trend analysis, equipment health prediction and multi-dimensional real-time state evaluation are fused through a cloud platform. According to the method, the dynamic fault evaluation capable of accurately reflecting the actual severity and development trend of the fault is generated, so that the system can be adaptive to equipment aging and environment change, and a grading response strategy accurately matched with the fault grade is triggered, thereby realizing the crossing from passive alarm to active and accurate fault management and control, and improving the fault processing efficiency.

The invention discloses an insulation fault edge self-healing method and device for a power conversion system, and belongs to the technical field of fault diagnosis and automatic maintenance of power electronic equipment, and the method comprises the steps: obtaining multi-modal sensing data, synchronously collected by a multi-modal sensor array, of the power conversion system; a preset lightweight CNN-Transform hybrid model is used to process the multi-modal sensing data, and a feature vector of each modal is obtained; fusing each modal feature vector by adopting a dynamic weight attention mechanism to obtain a fused fault feature vector; classifying the fused fault feature vectors based on a fault classifier, and determining a fault level; and according to the determined fault level, sending a corresponding control instruction to an execution mechanism, and triggering a hierarchical self-healing action. According to the invention, fault identification and self-healing decision can be rapidly completed, and the accuracy of fault detection is effectively improved.

The invention relates to the technical field of cubic hydraulic press monitoring, in particular to a cubic hydraulic press health monitoring method and system based on an intelligent sensor, and the system comprises a health monitoring terminal, a data sensing module, a data processing module, a health diagnosis module, a fault management module, a diagnosis positioning module, a cooperative influence module and a rear-end execution module. According to the method, the time domain, the frequency domain and the time domain-frequency domain combined features are extracted, meanwhile, the state change slope is quantified, early warning of the equipment degradation trend is achieved, a fault type-abnormal feature-weight mapping table is constructed, a fault core component and the specific position are accurately positioned, and the fault core component is accurately determined by matching with digital twinborn visual marks. And meanwhile, the internal relation between components is quantified by constructing a component incidence matrix, the health influence coefficient of the cooperative component is calculated in combination with a fault grade coefficient, key components affected by faults are recognized in advance, a cooperative damage list is formed, and operation and maintenance personnel are assisted to intervene in advance.

The invention discloses a bus voltage multi-dimensional real-time monitoring and analyzing method, system, equipment and medium, and belongs to the technical field of power system monitoring and fault prediction.The method comprises the steps that high-frequency synchronous sampling is conducted on bus voltage signals, discrete time sequence voltage signals are obtained and preprocessed, preprocessed voltage signals are obtained, and the discrete time sequence voltage signals are obtained; the method comprises the following steps: synchronously extracting multi-dimensional characteristic parameters of voltage, obtaining a characteristic parameter set, calculating a health degree index comprehensively representing a voltage state by utilizing a dynamic weighted fusion algorithm based on the characteristic parameter set, calculating an abnormal degree of a current value according to a historical data sequence of the health degree index, and performing fault grade judgment according to the abnormal degree. And performing trend extrapolation based on the health degree index and the historical data sequence of the key parameters in the characteristic parameter set, and generating predictive maintenance suggestions. According to the method, the crossing from passive alarm to predictive maintenance is realized, and the intelligent level and the operation and maintenance reliability of state monitoring of the power system are remarkably improved.

The invention relates to the technical field of alarms, and discloses an infrastructure catastrophe sound-light alarm system with a fault self-checking capability, and the system comprises a data collection module which is configured to synchronously collect a sound signal, an optical signal, an electrical parameter and an environmental parameter of an alarm; the data preprocessing module is configured to perform noise suppression, normalization and abnormal value elimination on the acquired data; the feature extraction module is configured to extract a sound time-frequency domain feature, an optical signal fluctuation feature, a circuit stability feature and an environment correlation feature; the fault diagnosis module is configured to perform fault type judgment by adopting a multi-modal fusion model and a predefined rule base; and the grading processing module is configured to execute emergency response, maintain early warning or self-adaptive adjustment strategies according to the fault grades. According to the audible and visual alarm fault self-checking system, multi-modal data fusion, self-calibration, mobile detection and graded response are integrated, and the reliability of industrial safety early warning is improved through multi-dimensional data collaborative analysis and dynamic adjustment.

The invention relates to the technical field of power plant equipment detection, and discloses a power plant equipment fault detection system based on an AI image recognition algorithm. The system comprises six core modules, namely an equipment image acquisition module, a fault feature analysis module, a fault propagation modeling module, a fault area judgment module, a fault level classification module and a fault structure output module. Wherein the equipment image acquisition module acquires real-time monitoring image data of power plant equipment, extracts equipment feature points through region segmentation, establishes a feature point topological relation in combination with equipment types, and generates an equipment feature topological graph; a fault feature analysis module performs multi-dimensional feature extraction based on the topological graph, and calculates a feature point similarity matrix to construct a fault feature association network; the subsequent modules sequentially establish a fault propagation model, screen a fault core area set and generate a fault level label group, and finally the fault structure output module generates a fault classification atlas to assist accurate detection and efficient management of power plant equipment faults.

The invention provides a terminal temperature monitoring and fault automatic diagnosis method for an intelligent measurement switch, which relates to the technical field of fault diagnosis and comprises the following steps of: dynamically tracking the terminal temperature to obtain long and short term temperature time-varying characteristics; if the preset temperature anomaly judgment condition is met, starting and ending timestamps are called; calling local multi-source monitoring data to obtain multi-source time sequence monitoring data; dividing the data into P multi-source monitoring data segments; performing segmented fault diagnosis based on dynamic fluctuation characteristics, and outputting P initial fault prediction results; state transition probability correction is carried out, and P-1 updated fault prediction results are obtained; and carrying out time feature fusion decision, outputting a to-be-intervened fault, and triggering fault grading early warning processing. According to the invention, the technical problem that the fault diagnosis delay and false alarm risk are increased because the fault state of the intelligent measurement switch is judged only through static fault mode identification in the prior art and intervention measures cannot be timely responded or adjusted in the fault development process is solved.

The invention provides an electric energy metering fault grading detection method and system for an intelligent electric meter, and relates to the technical field of electric energy metering, and the method comprises the steps: collecting a general meter observation signal of a transformer area general meter, carrying out the signal separation processing, generating an independent source signal, carrying out the inconsistency analysis of the independent source signal and the load data reported by a corresponding household intelligent electric meter, and carrying out the fault detection. The method comprises the steps of judging whether metering abnormity exists in a household intelligent electric meter or not, generating a first-level wide area screening list, executing directional diagnosis based on load curve waveforms, event records, power utilization behavior modes and transformer area topological association for each target user in the first-level wide area screening list, and generating a second-level directional diagnosis result. The technical problems that in the prior art, the electric energy metering detection dimension is single, and the anomaly recognition accuracy and reliability are low are solved. The technical effects of rapidly screening potential abnormal ammeters through a first level and effectively judging specific metering fault types through a second level are achieved, and the accuracy and reliability of electric energy metering abnormity identification are improved.

The application relates to the technical field of circuits, and discloses an intelligent induction conveying belt, which comprises a conveying belt module, a feeding mechanism, a sensor module, a control module, a signal processing unit, an alarm module, a fault grade judgment module and a manual reset switch, the conveying belt module is used for conveying materials, the feeding mechanism is arranged at the inlet end of the conveying belt, and the sensor module is used for detecting the running state of the conveying belt. The intelligent induction conveying belt is provided with the conveying belt module, the feeding mechanism, the control module and the fault grade judgment module, the control module realizes the hardware level time sequence control of the conveying belt module and the feeding mechanism through an RC delay circuit and a linkage control unit, the conveying belt is started first, and the feeding mechanism is started in delay; when the machine is stopped due to faults, the control module synchronously cuts off the power supply of the feeding mechanism, so that continuous feeding after the machine is stopped is avoided. The problem of material accumulation at the inlet caused by the asynchronization of starting and stopping in the traditional system is solved from the root, the system can be restarted without manual cleaning, and the production efficiency is improved.

The application relates to an intelligent isolation bearing online monitoring system, an installation process and a monitoring method. The system integrates force value, angular acceleration and displacement monitoring functions on the basis of an isolation bearing, is composed of an upper sealing plate, a rubber body, a lower sealing plate and a monitoring system, is used for simultaneously monitoring vertical loads transmitted from an upper building to a lower foundation and angular acceleration and horizontal displacement of the isolation bearing, and is composed of a ring-shaped pressure sensor, an inertial measurement unit (IMU), a displacement sensor, a data acquisition and transmission module, a cloud server and a monitoring platform. The system adopts a full-sensor external modular structure, is matched with a six-order Kalman fusion algorithm, a multi-parameter coupling early warning criterion, an IMU dynamic drift calibration model, and a special pre-tightening and anti-loosening installation process, is suitable for various working conditions, realizes synchronous acquisition of multi-dimensional parameters of a bearing, data noise reduction fusion and fault grading early warning, and can realize real-time monitoring of stress, angular acceleration and displacement states of a building isolation bearing.

The invention provides a steer-by-wire angle signal loss adaptive gain compensation method, which comprises the following steps: synchronously acquiring real-time angle signal sets of a hand feeling simulator and a steering actuator, carrying out signal loss detection and fault grading on the real-time angle signal sets to obtain a fault grade, and generating a redundancy switching strategy based on the fault grade; acquiring a historical angle signal set of a plurality of past sampling periods according to a redundancy switching strategy, and calculating an angle compensation amount according to the historical angle signal set; acquiring real-time vehicle parameters, generating a time-varying gain coefficient based on the real-time vehicle parameters, and calculating an adaptive gain compensation angle by using the time-varying gain coefficient and the angle compensation amount; and acquiring historical motor current of a past sampling period, calculating motor output current according to the adaptive gain compensation angle, performing gradient limitation on the motor output current by using the historical motor current, and performing steering control according to the motor output current after gradient limitation.

The invention discloses an extended-range commercial vehicle whole vehicle fault processing method and system based on multistage grading and safety degradation control, and relates to the technical field of new energy vehicle control and whole vehicle fault diagnosis. Meanwhile, a system priority identifier to which a fault source controller unit belongs is obtained, a degradation control strategy type is determined through a constructed fault processing priority matrix, corresponding limiting parameters are matched, and hierarchical control is carried out on the extended-range power system; and sending the fault grade and degradation control state information to an instrument for display, monitoring the state change of the fault source controller unit, and dynamically updating the fault evaluation model. According to the invention, safe and stable operation of the extended-range commercial vehicle in a complex fault environment is realized.

The invention discloses a multi-gear double-electric-drive-axle fault processing method based on intelligent fault isolation, and relates to the technical field of new energy automobiles, and the method comprises the following steps: S1, fault grading detection: based on a built-in sensor of an electric drive axle, collecting operation parameters of two motors in real time, and grading faults according to the collected parameters; s2, part decoupling control: for different fault levels and fault parts, cutting off mechanical / electric signal coupling between the fault parts and other parts; and S3, dynamic strategy adjustment. According to the multi-gear double-electric-drive-axle fault processing method based on intelligent fault isolation, fault types can be recognized more accurately through fine fault grade division, mechanical / electric signal coupling of fault components and other components is cut off according to different fault grades and fault components, decoupling processing of faults of the multi-gear electric drive axles is achieved, and the fault processing efficiency is improved. Therefore, the accuracy and the efficiency of fault processing are improved, and the reliability and the safety of the system are enhanced.

The invention discloses a vehicle fault pushing method, apparatus and device, and a storage medium, and the method comprises the steps: determining vehicle fault information based on vehicle operation data, the vehicle fault information comprising a vehicle current fault, a vehicle potential fault, and a fault predicted occurrence time corresponding to the potential fault; based on a pre-constructed mapping relationship between faults and fault levels, determining a fault level corresponding to each target fault of the vehicle, each target fault including a current fault of the vehicle and a potential fault of the vehicle; determining a fault pushing priority corresponding to each target fault based on the fault level and the fault predicted occurrence time; and pushing each target fault in sequence based on the fault pushing priority. According to the method, the current fault of the vehicle and the potential fault containing the predicted occurrence time can be pushed at the same time, all the faults are pushed in sequence according to the fault pushing priority, the process of determining the fault processing priority through secondary analysis of the after-sales terminal and the research and development terminal is omitted, and the fault processing efficiency and timeliness are remarkably improved.

The invention discloses a sintering pallet wheel fat liquoring fault grading method and system, electronic equipment and a storage medium, and the method comprises the following steps: S1, collecting actual pallet chain data information, and obtaining a pallet chain array; s2, obtaining a trolley number and a serial number of an initial trolley; s3, the initial trolley is searched and recognized, after the initial trolley is recognized, each passing wheel is recognized, positioned and numbered, an automatic greasing device is used for conducting automatic greasing on the wheels, and whether greasing succeeds or not is judged; and S4, according to the current fat liquoring judgment result and the historical fat liquoring judgment result of each wheel on each trolley, the current fault grade of each wheel is obtained. The system can replace manual work to achieve automatic identification, positioning, recording and analysis, through automatic fat liquoring and accurate fault grading, the fat liquoring states of hundreds of wheels can be monitored in real time, the wheels with fat liquoring faults can be identified in time and graded, and workers can conveniently process serious faults in priority.

The invention discloses an unmanned AGV power transmission system vibration diagnosis monitoring method, device and equipment, and relates to the technical field of equipment state monitoring. Collecting state monitoring data of a plurality of driving transmission parts of the unmanned AGV by using a vibration monitoring device; performing working condition identification and noise filtering on the state monitoring data by using a density-based clustering algorithm so as to filter noise and other working condition data except the normal working condition to obtain normal working condition data; and carrying out feature extraction on the normal working condition data, inputting the extracted multi-dimensional feature data into a Gaussian mixture model to obtain a fault level early warning result, inputting the multi-dimensional feature data into a fault diagnosis model based on a convolutional neural network to obtain an unmanned AGV fault type diagnosis result, and carrying out visual display on the results. According to the invention, weak and transient fault features can be accurately captured, accurate fault grading early warning and fault diagnosis are realized, and the operation reliability and the operation efficiency of the unmanned AGV are improved.

The embodiment of the invention discloses an industrial robot automatic charging and fault grading system. A specific embodiment of the method comprises the following steps: a battery detection device is configured to perform fusion processing on a pre-collected multi-source environmental perception data set to generate robot current pose data with a semantic tag, and send the robot current pose data to a fault classification device; the charging device is configured to generate robot charging state data according to the received robot charging fault level, and transmit the robot charging state data to the mobile terminal; the mobile terminal is configured to render the received robot charging state data and cinder ladle temperature data collected in advance so as to generate a temperature change curve. According to the embodiment, the inspection continuity is improved, the fault grading time and the charging period are shortened, and the operation loss is reduced.

The invention relates to the technical field of strip mill fault detection, in particular to a strip mill transmission shaft fault early warning method and system based on digital twinning. The method comprises the following steps: deploying multiple types of sensors at key parts of a transmission shaft of a strip mill, collecting real-time operation data, and performing time domain and frequency domain extraction on the operation data to obtain effective fault features; establishing a multi-dimensional evaluation index system, and dynamically adjusting fault priorities according to effective fault features; a grading standard is formulated according to the severity of the fault, an early warning threshold value of each grade is set, and fault early warning is carried out according to the corresponding grade; the system comprises a current data acquisition and feature extraction module, a fault condition priority dynamic adjustment module and a fault grading early warning module. By means of the mode, the fault priority is dynamically adjusted, operation and maintenance resource waste and production risk out-of-control are avoided, the accuracy and timeliness of transmission shaft fault early warning are improved, and the continuity and stability of strip steel production are guaranteed.

The application discloses a wind turbine monitoring big data analysis system based on voiceprint recognition multi-mode fusion analysis and belongs to the technical field of power grid monitoring big data analysis; and is used for solving the technical problems of poor data processing and analysis effect and poor diversified early warning effect of the prior art; by integrating multi-mode data such as voiceprints, vibrations and temperatures, the traditional single-sensor monitoring data island phenomenon can be avoided, the data dimension can be improved from 3D to 23D, complete input is provided for fault diagnosis; the first identifier and the second identifier realize accurate association of data and equipment, and ensure the accuracy of subsequent preprocessing and analysis; environmental noise is removed through preprocessing, the signal-to-noise ratio of the voiceprint signal is effectively improved, and the feature extraction accuracy is improved, reliable data can be provided for subsequent fault analysis; based on label classification storage, the data security is improved; through the distributed storage characteristics of the block chain and the fault influence quantitative analysis, slight and serious fault grading early warning can be realized.

This application proposes a method and related apparatus for graded fault location detection in a charging system. The method includes: if a charging pile receives a charging request, controlling the charging system to execute a first-level circuit continuity detection strategy and determining the first-level detection result; if the first-level detection result is qualified, controlling the charging system to start charging; if a charging fault is detected during the charging process, controlling the charging system to execute a second-level circuit continuity detection strategy and determining the second-level detection result; if the charging pile is in standby mode, controlling the charging system to execute a third-level circuit continuity detection strategy and determining the third-level detection result. This allows for graded detection under different charging states of the charging pile, improving the accuracy of fault location, increasing maintenance efficiency, and enabling the probability of fault detection before charging to improve preventative measures. Faults occurring during charging can also be clearly located, improving the clarity of responsibility allocation.

The application discloses a kind of defect grading method, device, equipment and storage medium.The method comprises: obtaining defect image to be graded;The defect image to be graded is input to the grading model pre-trained;According to the output result of grading model, the defect level of defect image to be graded is determined;Wherein, the grading model is obtained by training the grading network pre-constructed based on defect grading dataset;The grading network includes feature extraction structure, regression structure and classification structure;Defect grading dataset includes at least one group of defect grading data, and each group of defect grading data includes defect image sample and defect image sample matched reference level;The number of reference level is less than the number of defect level.This technical solution solves the problem of low defect grading refinement degree, can realize fine-grained defect grading while effectively improving the accuracy of defect grading to meet the diversified workpiece needs of users.

The invention discloses a data analysis system and method applied to power fault detection, and relates to the technical field of circuit fault detection.The method comprises the steps that multi-source core data are collected in a segmented mode and preprocessed, and a target feature set is obtained through scene admission judgment, homology verification and time sequence rationality verification; carrying out correlation logic analysis on the pressure value, the contact area value and the wire resistance variation based on the target feature set, and outputting a logic analysis result; according to a logic analysis result, respectively establishing corresponding relations among the contact area value, the pressure value and the lead resistance influence quantity, and integrating the two corresponding relations to construct a lead resistance total influence quantity calculation model; and substituting the pressure value and the contact area value which are acquired in real time into the model, and completing fault grading judgment according to the obtained total influence quantity of the wire resistance.

The invention specifically relates to the technical field of electric loader mechanical diagnosis, and discloses an electric loader intelligent fault diagnosis method based on a multi-motor cooperation characteristic, and the method comprises the steps: S1, multi-source loader data collection: obtaining the multi-source loader data in real time; s2, data preprocessing and preliminary diagnosis: constructing a multi-source loader data set; s3, edge calculation and feature extraction: constructing a multi-source loader feature data set; s4, fault diagnosis and fault positioning: judging the fault level of the loader, and positioning the fault position; s5, generating and issuing a control strategy: formulating a fault maintenance control strategy; s6, strategy execution and feedback optimization: optimizing the loader fault diagnosis model; according to the method, the real-time performance and accuracy of fault diagnosis are improved by constructing the loader fault diagnosis model, calculating the influence of the multi-motor coupling relationship on the fault of the electric loader and taking the cooperative working characteristics among the motors as the judgment factors of fault diagnosis through the combination of the edge and the cloud.

The invention discloses a distribution network integrated power supply fault pre-judgment system adaptive to a distributed power supply, which relates to the technical field of intelligent operation and maintenance of power equipment, and specifically comprises a multi-dimensional power supply index acquisition module, a module for defining an acquisition object, synchronously acquiring multi-dimensional data, extracting four core parameters and a multi-dimensional combined control domain construction module. A change rate is calculated through four core parameters, a multi-dimensional feature vector is formed, a health sample set is constructed based on historical data of equipment in a health operation period, a deviation degree of a real-time feature vector and a health domain is quantified through a Hotelling statistic, an abnormal feature set is constructed through a fault grading and pre-judging processing module, and a fault classification and pre-judging processing module is used. The weighted similarity is calculated by matching the fault knowledge base, and the fault volatility is constructed in combination with the Hotelling statistics, so that the risk of power failure shutdown of the integrated power supply of the distribution network is reduced and the power supply stability of the distribution network is ensured by pre-judging potential faults in advance and giving out disposal guidance.

The application discloses a kind of unmanned mine car layered diagnosis method, it is related to unmanned mine car field, comprising: S1, construction fault classification and coding system, fault is classified according to source classification, generates only main fault code and sub fault code;According to fault severity, influence range and recoverability, establish multistage fault evaluation model, give grade to each fault;S2, main fault code, sub fault code, fault grade and corresponding processing strategy are written into configuration file, and the configuration is loaded when mine car starts;S3, real-time acquisition and fusion multi-source data, extract abnormal characteristics;S4, real-time data characteristics are matched with fault library, calculate fault probability, execute corresponding hierarchical control strategy;S5, execute closed-loop feedback optimization, upload the data of fault diagnosis and processing process to cloud, to optimize fault library and diagnostic algorithm model.The realization is to unmanned mine car fault from loop, site to reason Layered accurate positioning.

The application discloses a forced air cooling frequency converter fault prediction decision assistance system and particularly relates to the technical field of frequency converter fault detection, which comprises a forced air cooling frequency converter multidimensional sensing module, a multidimensional fault feature extraction module, a hybrid intelligent prediction module, a forced air cooling frequency converter fault grading module, a forced air cooling frequency converter decision generation module and a forced air cooling frequency converter man-machine interaction module; the forced air cooling frequency converter multidimensional sensing module collects multidimensional sensing data of the forced air cooling frequency converter, including electrical data, heat dissipation data and environmental data, and performs preprocessing to obtain a multidimensional parameter set; the application constructs a hierarchical architecture of a first-level basic prediction, a second-level accurate prediction and a comprehensive fusion prediction, the first-level prediction reduces the calculation load, improves the early warning capability, the second-level prediction only focuses on abnormal samples, realizes the accurate output of probability, life and fault type, and the comprehensive prediction dynamically weights and fuses the results of each level, thereby improving the operation efficiency and the prediction accuracy.

The invention discloses a tree line discharge fault grading early warning processing method, relates to the technical field of line fault early warning, and solves the problems that in the prior art, the early weak discharge signal detection capability is insufficient, and a risk grading and monitoring early warning coordinated full-process closed-loop management system is lacked. According to the method, firstly, accurate grading of line risks is realized based on a Weibull probability model and multi-dimensional consequence evaluation, and a decision basis is provided for subsequent differentiated operation and maintenance; traditional instantaneous value judgment is replaced with long-time-window trend analysis, the fault development rate is extracted through piecewise linear fitting, the weak signal detection threshold value is remarkably reduced, and hidden danger symptoms are captured in advance; and finally, the risk level is dynamically matched with a three-level early warning mechanism to form differentiated configuration of inspection frequency, response time efficiency and disposal intensity, so that the system can trigger early warning in a fault germination stage, the fault is prevented from evolving to a tripping threshold value, meanwhile, the operation and maintenance resource utilization rate is greatly improved, and the safety level of the power distribution network in a complex environment is enhanced.

The invention relates to the technical field of fault diagnosis of scientific research instruments and equipment, and discloses an injection pump electrical fault diagnosis method based on multi-parameter fusion. The method comprises the following steps: establishing a communication link with an injection pump control unit to obtain real-time operation state data; connecting the design database to analyze a reference value in the electrical design specification; a parameter difference index is obtained through difference analysis, and grading diagnosis is activated when the parameter difference index exceeds the limit. In grading diagnosis, a plurality of detection areas are defined according to an assembly drawing, simulation monitoring points are configured to collect current fluctuation and temperature change information of each area, and a fault tendency coefficient is calculated according to the current fluctuation and temperature change information; and in combination with the measured resistance characteristics, the safe current range and the fault duration, evaluating the fault level and importance factor of each region, and finally calculating to obtain a comprehensive electrical state index. According to the method, accurate positioning of the electrical fault of the injection pump from the whole machine to a specific circuit area is achieved, and early prediction of the fault can be achieved by analyzing the dynamic parameter change trend.

The invention provides a negative pressure cooperative multi-source fusion shield segment defect treatment method and system, and relates to the technical field of tunnel engineering components, and the method comprises the following steps: hoisting a shield segment into a closed negative pressure treatment cabin for positioning and interference elimination; identifying original defect features according to the quality detection model; inputting the defect original features into the D-S evidence theory optimized by the multi-source fusion network to quantify and grade a defect grading result; when the defect grading result is the first level, defect integrated processing is conducted on the shield segment through a reinforcement learning strategy network, and a first-level repairing result is obtained; when the defect grading result is a second level, planning a repairing scheme for the shield segment in real time through a greedy algorithm to obtain a second-level repairing result; and performing quality scoring on the repair result, and when the quality score does not reach the standard, generating an adjustment parameter through a reinforcement learning strategy network until the quality score reaches the standard, thereby forming a defect processing scheme. The problems of out-of-control quality of the duct piece and potential safety hazards of long-term service of the tunnel are solved.

The invention relates to the technical field of power equipment fault diagnosis, and discloses a doubly-fed asynchronous motor stator winding turn-to-turn short circuit fault diagnosis method and system, and the method comprises the steps: extracting a flux linkage residual error through a doubly-fed asynchronous motor mathematical model before and after a fault, and achieving the fault detection through the comparison of the amplitude of the flux linkage residual error and a self-adaptive threshold value. Compared with an existing model-based method, the method has the advantages that the calculation workload is reduced, accurate fault positioning and fault grade judgment are realized, and online rapid fault diagnosis can be realized.