284 results about "Online evaluation" patented technology

The invention relates to the technical field of building construction monitoring, and discloses a method for evaluating mechanical properties of a steel structure building construction whole process based on digital twinning. The method comprises the steps of establishing a digital twin model fusing multi-source information, and performing real-time linkage with a sensor network arranged on site. Collected data such as deformation, temperature and wind speed are processed through dynamic fusion and an anomaly recognition algorithm, model parameters are continuously corrected, and real-time dynamic high-fidelity mapping of the mechanical state in the construction process is achieved. And based on the updated model, the intelligent analysis module performs cooperative calculation, autonomously identifies construction abnormity, quantitatively predicts potential risks, generates a process optimization decision instruction and feeds back the process optimization decision instruction to a site. According to the method, a closed-loop regulation and control mechanism from data perception, model analysis to decision execution is constructed, and accurate online evaluation of construction mechanical properties and active prediction control of safety risks are realized.

The invention relates to the technical field of SRAM (Static Random Access Memory) memory anti-radiation testing, and discloses an SRAM memory anti-radiation testing method and system based on running state injection, and the method comprises the following steps: system initialization, mapping preparation and time sequence baseline establishment; carrying out model quantitative compiling, sensitivity analysis and physical bit candidate generation; generating a running state injection plan and loading a test case; performing operation state execution, disturbance injection and synchronous monitoring acquisition; multi-source triggering, weight read-back and fault decoupling judgment are carried out; and performing quantitative evaluation on anti-radiation performance, constructing a degradation curve and outputting a report. The system corresponds to the method. According to the invention, a hardware-in-the-loop operation state injection and online evaluation technology is constructed, and the technical problems of guidance and position limited disturbance / equivalent irradiation injection based on weight bit level sensitivity and logic-physical mapping are solved.

The invention relates to the field of power system operation and maintenance, in particular to a power transformation equipment operation and maintenance risk online assessment method and system. A power transformation equipment operation and maintenance risk online evaluation system comprises a data acquisition module, a weight configuration module, a sequence risk evaluation module, a collaborative decision game module and a disposal scheme output module. According to the method, a multi-source data fusion and dynamic threshold mechanism is introduced, real-time state quantity, historical maintenance records, operation modes and external weather information are uniformly mapped to a convolution-long and short-term memory network, key features are adaptively amplified in a feature weighting layer, redundant features are weakened, and collaborative recognition of short-term fluctuation and long-term degradation is achieved; compared with a traditional fixed threshold value or single monitoring quantity model, the method can keep sensitive and steady risk early warning capacity under the complex working conditions of severe weather, heavy load operation and the like, the false alarm rate and the missing report rate are greatly reduced, potential faults are locked in advance, and sudden power failure events are avoided.

The invention relates to the technical field of power equipment operation and maintenance and state monitoring, in particular to an optical fiber transformer health state assessment method and system based on feature fusion. According to the invention, sampling signals of a plurality of optical fiber current transformers are collected and preprocessed; constructing a historical data matrix for principal component analysis, establishing a principal component space and calculating a square prediction error control limit value; constructing a simulated fault data set and projecting the simulated fault data set to a principal component space to calculate a square prediction error time sequence; performing wavelet packet decomposition on the square prediction error time sequence to extract a normalized energy feature vector, and training a one-dimensional convolutional neural network model; projecting the real-time sampling signal to a principal component space to judge whether the real-time sampling signal exceeds the limit or not; if yes, the health state level is output through the trained model. According to the invention, accurate grading and real-time online evaluation of the health state of the optical fiber transformer are realized.

The invention discloses a power battery health degree online evaluation method and system based on a charging curve, and the method comprises the steps: dynamically dividing a characteristic interval of a constant-current charging stage and a constant-voltage charging stage through monitoring the voltage and current data in a charging process in real time; extracting time domain and frequency domain characteristic parameters in the characteristic interval; inputting the time domain and frequency domain characteristic parameters into a health degree evaluation model subjected to transfer learning optimization, and generating a fusion health degree index at least comprising a battery capacity attenuation coefficient and an internal resistance change vector; and outputting a final health degree evaluation result and residual service life prediction through an adaptive weighting algorithm based on the fused health degree index in combination with historical cycle data and operating environment parameters of the battery. According to the embodiment of the invention, high-precision and non-intrusive online evaluation and life prediction of the health degree of the battery can be realized, and the real-time performance, accuracy and engineering applicability of evaluation are improved.

The invention relates to an SCR system self-adaptive flow guide regulation and control method based on real-time flow field feedback, and belongs to the technical field of flue gas denitration. The method comprises the following steps: acquiring inlet flue gas flow velocity distribution and outlet partition NOx concentration distribution; establishing a flow field and concentration field uniformity online evaluation rule, and constructing an initial knowledge base based on adaptive regulation and control logic; dynamically adjusting the angle of the adjustable guide plate according to the uniformity evaluation result, synchronously recording the state change of the flow field, and iteratively updating the regulation and control knowledge base; and an exclusive data interaction link of diversion regulation and control and partition ammonia spraying control is established, and flow field pre-judgment information sharing and ammonia spraying parameter presetting are achieved. The real-time collaborative optimization of the flow field and the concentration field in the SCR system is realized, the denitration efficiency and the ammonia escape control precision are improved, and the self-adaption and intelligent regulation and control capabilities of the system are enhanced.

The invention relates to the technical field of power system inertia evaluation, in particular to a random mode switching driven power distribution network equivalent inertia online evaluation method and system, and the method comprises the steps: carrying out the priori definition of a group of hidden operation modes based on the equivalent inertia of a power distribution network, and constructing an unobservable Markov chain; a double-layer hidden Markov jump system model is constructed, the bottom layer is an unobservable Markov chain, and the upper layer is a continuous dynamic behavior model for describing the power distribution network; on the basis of PMU high-resolution time sequence disturbance data, deducing the probability of a system maximum probability dominant operation mode and the probability of each hidden operation mode; and carrying out multi-mode probability adaptive weighting on each equivalent inertia estimation value based on the probability of the dominant operation mode and each hidden operation mode so as to obtain the equivalent inertia estimation value of the power distribution network on line. Through the method, the problem that the equivalent inertia of the power distribution network is difficult to quickly, accurately, dynamically and adaptively assess online under the conditions of high permeability of new energy and frequent switching of working conditions is effectively solved.

The invention discloses an old people health risk assessment method based on artificial intelligence. The method comprises the following steps: collecting and preprocessing multi-source health original data of target old people; constructing a feature set, and generating a multi-modal feature vector; performing parameter training on the improved MTGP model to obtain a trained improved MTGP model; generating an online evaluation feature vector and inputting the online evaluation feature vector into the trained improved MTGP model to obtain a health risk prediction result; calculating a health risk score; performing time sequence analysis and trend identification analysis, and outputting a health risk level; generating risk early warning information; and the health risk archives are displayed and called, so that fusion of multi-source health data, joint evaluation of the multi-task health risk of the old people and dynamic identification of the change trend of the health risk are realized.

The invention provides a new energy station high-voltage voltage transformer error evaluation method and system, and the method comprises the steps: collecting the voltage phasors of all measurement nodes in a preset time period at a transformer substation and a new energy station at the same time, obtaining the equipment parameters of a voltage transformer and the line parameters between the measurement nodes, and constructing a measurement data set; the method comprises the following steps: constructing a corresponding adjacency matrix and a node characteristic matrix by extracting line impedance and node working condition characteristics based on a power system line topological structure and data in a measurement data set, and obtaining a time sequence diagram structure data set according to the adjacency matrix and the node characteristic matrix; constructing a graph neural network, and training the graph neural network based on the time sequence graph structure data set; and inputting the voltage phasor of each measurement node, and based on the output result of the trained graph neural network, judging the state of the voltage transformer through a preset threshold value. According to the scheme, online evaluation of the error state of the voltage transformer can be realized, and the accuracy and interpretability of error evaluation are improved.

The invention relates to the technical field of dynamic object pose recognition and mechanical arm grabbing control algorithms, and discloses a dynamic object pose recognition and mechanical arm grabbing control algorithm. The framework comprises a multi-source heterogeneous sensing fusion module, a motion state joint estimation engine, a grabbing feasibility online evaluator and a rolling time domain grabbing controller, and low-delay collaboration is achieved through unified state space modeling and event-driven scheduling. Wherein the sensing module fuses RGB-D and inertial data to output a six-degree-of-freedom pose with covariance, the estimation engine adopts self-adaptive unscented Kalman filtering to recursion a complete motion state, the evaluator combines dynamic constraints to screen feasible grabbing postures, and the controller solves an optimal joint trajectory with obstacle avoidance constraints on line based on a self-adaptive target trajectory. And feedforward compensation is introduced to suppress dynamic disturbance. According to the technical scheme, the real-time performance is guaranteed, and meanwhile the grabbing success rate and robustness of high-speed, non-uniform-speed and sudden turning dynamic objects are remarkably improved.

The invention relates to the technical field of foundation engineering, in particular to a visual grouting quality online evaluation and self-correction system and method.The visual grouting quality online evaluation and self-correction system comprises a data acquisition module integrating various sensors; the data processing module is used for generating standardized grouting process data from the sensor data; the state analysis module evaluates the standardized data in real time by using a preset atlas analysis algorithm and an expert rule base, and identifies the grouting state and the quality condition; the geological information module generates a geological response map for auxiliary evaluation and control decision making; and the control execution module adjusts the operation parameters of the grouting equipment according to the evaluation result output by the state analysis module, and the operation parameters comprise valve opening and closing, the slurry flow speed and the grouting sequence, so that self-adaptive deviation correction control in the grouting process is achieved. According to the method, under-grouting, over-grouting and abnormal grout escape can be effectively avoided, grouting uniformity and construction quality are improved, manual intervention and misjudgment risks are reduced, and safety, efficiency and engineering reliability of grouting operation are remarkably improved.

The invention discloses a vehicle emission conformity online evaluation method and device, a storage medium, equipment and an evaluation method, and the method comprises the following steps: obtaining a remote monitoring data flow of a to-be-evaluated vehicle in a preset time period, carrying out the preprocessing of the remote monitoring data flow, and generating a valid data set; identifying and segmenting a plurality of independent driving cycles from the effective data set, and screening out the independent driving cycles with cold start characteristics and engine accumulated work not smaller than a preset cycle work threshold value as effective driving cycles; dividing the data of each effective driving cycle into a plurality of preset working condition partitions according to the operating characteristics; aiming at each preset working condition subarea, adopting a corresponding calculation model, and calculating a pollutant emission result of the target pollutant; and comparing the pollutant discharge result of the target pollutant in each subarea with a corresponding preset discharge limit value for judgment. By using the scheme of the invention, low-cost, large-scale and high-frequency emission supervision is realized.

The invention relates to an energy storage system health state online evaluation method and system based on digital twinning. The method comprises the following steps: acquiring real-time electrical data, real-time temperature data, a periodic event log and electrochemical fingerprint data of an edge end energy storage system, and preprocessing to obtain state time sequence data; extracting multi-source time sequence features from the state time sequence data according to a preset sliding time window, and performing time sequence coding to obtain a time sequence feature vector and a corresponding feature time window matrix; performing anomaly detection on the state time sequence data by adopting double criteria based on the feature time window matrix, and repairing abnormal and / or missing time sequence segments to obtain repaired time sequence data; and based on an edge end mixed digital twinborn model, performing state-parameter estimation according to the repaired time sequence data and time sequence feature vectors to obtain instantaneous state of charge estimation, local health state indexes and thermal field prediction. By adopting the method, high-precision and low-delay dynamic evaluation of the multi-dimensional health state of the energy storage system can be realized.

The invention discloses a storage battery pack health state evaluation and fault prediction method and system based on big data, and the method comprises the steps: data collection: collecting multi-source heterogeneous operation data in real time or quasi real time from a battery management system, an environment sensor and an operation and maintenance database of a target storage battery pack; data preprocessing and feature engineering: preprocessing the collected original data, and extracting a multi-dimensional health state feature vector; constructing an integrated machine learning model based on the historical data set, and establishing a model updating mechanism; performing online evaluation and prediction, and outputting a quantitative health state value, fault early warning information and a residual service life prediction value; and visualization and decision support. According to the method, multi-source data such as electrical data, working condition data, environment data and historical maintenance data are fused, deep features such as voltage consistency, capacity attenuation rate and internal resistance change trend are extracted, more comprehensive and accurate quantitative evaluation of the health state of the storage battery pack is achieved, and the one-sidedness and hysteresis of traditional single parameter judgment are fundamentally overcome.

The invention relates to a full-process intelligent control method and system for a glass bead production line, and belongs to the technical field of control systems, and the method comprises the following steps: collecting multi-source heterogeneous sensing data, and carrying out the preprocessing and time synchronization through an edge calculation node; building a dynamic simulation system of the whole glass bead production process based on a digital twinborn model; based on a reinforcement learning agent mode, outputting a deviation between preset quality targets in combination with a digital twinborn model, and adaptively generating a multi-execution-mechanism cooperative control strategy; the indexes of the generated glass beads are evaluated on line, and the evaluation result is fed back to the reinforcement learning agent mode to achieve closed-loop optimization of the control strategy; when an abnormal working condition or mass drift is detected, a fault traceability module based on causal reasoning is automatically triggered, a disturbance source is positioned, a process parameter compensation scheme is generated, and it is ensured that high-yield stable operation of the whole process is maintained without human intervention; the beneficial effect of the invention is that the intelligent control of glass bead production is improved.

The invention provides a power distribution network voltage quality online evaluation method and system supporting new energy group access, and belongs to the field of power system automation. Comprising the following steps: generating a node dynamic feature vector through multi-source data fusion and feature extraction; constructing a dynamic causal association diagram, and synchronously outputting a voltage quality multi-dimensional evaluation index and disturbance source contribution degree analysis by using a gating space-time diffusion mechanism; and generating graded early warning based on evaluation and traceability results, and generating auxiliary decision-making information of recommended control measures through strategy matching, effect simulation and multi-target optimization. The system comprises a data acquisition and fusion module, a dynamic causal association diagram construction module, a causal time sequence diagram diffusion evaluation module, an endogenous traceability analysis module, a grading early warning and decision auxiliary module and the like. According to the invention, real-time evaluation, accurate traceability and intelligent decision support of the voltage quality problem of the new energy power distribution network are realized.

The invention relates to the technical field of industrial robot precision machining, in particular to an intelligent monitoring and process parameter self-adaption regulation and control method and system which are suitable for metal plate precision cutting, composite material special-shaped part cutting, pipe three-dimensional contour cutting and other scenes. Real-time state monitoring, cut quality online evaluation, process parameter dynamic optimization and equipment health early warning in the cutting process can be achieved, and the problems that in traditional laser cutting, cut quality consistency is poor, the parameter debugging period is long, and the material utilization rate is low are solved.

A hydroelectric generating set PSS performance on-line evaluation method comprises the following steps: S1, data acquisition: acquiring input parameter measuring point data of a power grid side and a set side, and acquiring output data of a source network coordination simulation device and real-time operation data of a real machine SCADA system at the same time; wherein the power grid side input parameter measuring points comprise frequency deviation, active power and generator terminal voltage, and the unit side input parameter measuring points comprise rotating speed deviation, water head, guide vane opening, vibration in the xyz direction and a swing peak value; s2, performance index evaluation: calculating four core performance indexes including a damping ratio, a phase compensation degree, an adjusting speed and a robustness index based on the data acquired in the step S1; wherein the damping ratio reflects the oscillation decay speed, the phase compensation degree measures the compensation capability of the PSS for excitation system lag, the adjustment speed represents the dynamic response agility of the PSS, and the robustness index evaluates the capability of PSS parameters to adapt to different working conditions; and S3, online evaluation: sequentially executing data preprocessing and feature extraction, performance index calculation, adaptive threshold dynamic adjustment, fuzzy comprehensive evaluation, parameter optimization feedback and health report generation operation, and realizing real-time quantitative evaluation and parameter dynamic optimization of PSS performance.

The invention relates to the technical field of hydrology and water conservancy, and particularly discloses an intelligent real-time watershed flood early warning method and system, and the method comprises the steps: watershed data acquisition, fusion forecasting model construction, multi-stage early warning threshold calculation, early warning generation and online evaluation. According to the scheme, the real-time residual error of the physical hydrological model is constructed, the complex mode that the residual error changes along with the real-time rainfall intensity and the drainage basin state is learned by adopting the residual error prediction model based on machine learning, and an interpretable and steady forecast baseline and high-precision error correction are provided through a forward coupling and feedback coupling mixed architecture; the overall robustness of flood forecasting is effectively improved; dynamic inversion is carried out by using a fusion forecasting model, flood risk differences under different soil conditions are identified, the matching degree of early warning signals and actual risks is greatly improved, a comprehensive risk value is calculated in real time on a unified grid division system, and a risk zoning map is refreshed in real time along with updating of rainfall forecasting, so that the real-time prediction of the flood risk is realized. And the practicability of early warning information and the pertinence of emergency response are effectively improved.

The invention discloses a station building safety risk online assessment system based on an edge AI large model, which relates to the technical field of station building safety systems and comprises a data acquisition module, a large model reasoning module, an edge calculation module, a cloud collaboration module, a risk assessment module and a user interaction module. The multi-modal fusion module can perform fusion analysis on multi-modal data such as videos, sensors, texts and the like to form comprehensive risk assessment, the multi-modal fusion module adopts dynamic weighting, utilizes an attention mechanism and dynamically distributes weights according to the importance of modals, and through the design, the working personnel can perform multi-modal risk assessment according to the current time period, the working state or external factors. In addition, the multi-modal fusion module supports adaptive sampling and dynamic updating in the use process, and the data sampling frequency of the data acquisition module is dynamically adjusted according to the risk level, so that the flexibility of the system is further improved.

The invention discloses a wind power integration stability evaluation method based on d-axis and q-axis small disturbance, and the method comprises the steps: forming an evaluation process which can be implemented in a charged manner and is clear in index through the d-axis and q-axis dual-channel small disturbance recognition and frequency band error controlled equivalent processing of a grid-connected point in a frequency band of 2Hz-1000Hz, and improving the accuracy and consistency of broadband oscillation risk judgment; on the premise that protection is not triggered and power is limited, online evaluation is completed, compared with a single-channel method, the minimum stability margin is improved by not less than 20%, and the dangerous frequency band positioning error is not larger than 5 Hz; setting a frequency band error upper limit in a station equivalence stage, carrying out over-limit rollback and regrouping, and reducing the misjudgment rate of subsequent stability judgment; the method has the comprehensive advantages of being available in electrification, accurate in identification and reliable in judgment, enables the evaluation result to be quantified and reviewable, and can be directly used for parameter setting and grid-connected acceptance.

The invention relates to the technical field of safety monitoring of tower cranes, in particular to a tower crane jacking safety state online evaluation system based on edge calculation. Comprising a terminal sensing layer, an edge computing layer and a cloud platform layer, and the terminal sensing layer comprises a plurality of sensors arranged at key parts of a tower crane and is used for collecting physical parameters in the jacking process; the edge computing layer is connected with the terminal sensing layer through industrial embedded equipment and is used for carrying out local real-time processing and safety state evaluation on sensor data; and the cloud platform layer is used for receiving the data uploaded by the edge computing layer and carrying out historical data storage, trend prediction and remote monitoring. The tower crane jacking safety state evaluation system provided by the invention can realize local real-time processing and low-delay response and has high reliability.

The invention discloses a real-time mapping and evaluation method for the reliability of complex equipment, which is based on physical information neural networks (PINNs) and a model system engineering (MBSE) model, and is characterized in that the method comprises the following steps of: (1) carrying out real-time mapping and evaluation on the reliability of the complex equipment, and (2) carrying out real-time mapping and evaluation on the reliability of the complex equipment based on the MBSE model, and (3) carrying out real-time mapping and evaluation on the reliability of the complex equipment based on the MBSE model, and (4) carrying out real-time mapping and evaluation on the reliability of the complex equipment. The method comprises the following steps: firstly, constructing a system architecture model of equipment by utilizing MBSE, and defining reliability constraint parameters; a partial differential equation describing a component failure mechanism is extracted, a neural network agent model integrating physical information constraints is constructed, and a loss function of the neural network agent model is formed by weighting a data driving item and a physical residual item. Mapping real-time working condition parameters into PINNs input by establishing a data interface of a system architecture model and a PINNs agent model, and outputting a physical performance degradation state; and finally, calculating real-time reliability based on the probability statistical model, and dynamically feeding back the real-time reliability to the system architecture model to update a demand verification state and generate a control instruction. According to the method, the physical partial differential equation is introduced as the regularization constraint of the neural network, so that the problem of poor generalization ability of a pure data driving model under a small sample working condition is solved, and online evaluation and closed-loop control in an equipment operation stage are realized.

This application discloses a method and system for online condition assessment of permanent magnet motors based on multi-scale fuzzy entropy, relating to the technical field of permanent magnet motor fault diagnosis and reliability index analysis. It solves the technical problems of existing technologies that often rely on macroscopic parameters such as failure rate, making it difficult to quantify the degree of motor performance degradation and lacking consideration for real-time online condition assessment of permanent magnet motors, resulting in low accuracy and real-time performance of permanent magnet motor condition assessment. The method generates a radial air gap magnetic flux density difference signal based on the radial air gap magnetic flux density signal, and uses this to generate a multi-scale fuzzy entropy and a permanent magnet demagnetization assessment model. It generates the permanent magnet condition result based on the multi-scale fuzzy entropy corresponding to the online radial air gap magnetic flux density signal, and eliminates magnetic flux density background interference through the radial air gap magnetic flux density difference signal. By characterizing the subtle differences in signal complexity under different demagnetization states through multi-scale fuzzy entropy, it achieves a quantitative description of the degree of permanent magnet degradation, improving the real-time performance and accuracy of condition assessment.

The application provides a bearing health state online evaluation method and system based on morphological profile analysis and federal evolution hypergraph, aiming at solving the problems of poor model self-adaptability, difficult cross-device knowledge migration and easy to be submerged early weak fault characteristics of the prior art under dynamic working conditions. The method captures the geometric profile evolution of bearing micro-damage by constructing a morphological multi-scale profile feature extraction engine, topologically preserving morphological decomposition of the vibration signal; adopts a Bayesian Poisson online learning algorithm to realize dynamic threshold adaptive updating and early warning of the health index; introduces an evolutionary hypergraph neural network to model the high-order multi-element fault propagation relationship between the bearing and the adjacent components; finally, through a federal edge collaborative framework, the incremental aggregation and knowledge migration of the cross-device model are realized under the premise of protecting data privacy. The application significantly improves the robustness of bearing fault diagnosis under variable working conditions and the sensitivity of early warning, and provides a lightweight and evolving solution for intelligent operation and maintenance in distributed industrial scenarios.

The invention relates to the technical field of alkaline water electrolysis hydrogen production, and discloses a multi-parameter fusion gas-liquid separation effect online evaluation method, which comprises the following steps: acquiring alkali liquor mass fraction concentration, fluid temperature, actual mixing density and mass flow signals on a backflow alkali liquor pipeline of a gas-liquid separator in real time; dynamically calculating the theoretical density of the bubble-free sodium carbonate solution under the current working condition according to the mass fraction concentration of the alkali solution and the fluid temperature which are collected in real time; calculating the absolute deviation between the theoretical density and the actual mixing density; performing real-time noise level analysis on the mass flow signals; according to a comparison result of the absolute deviation and a preset density deviation threshold value; and outputting a separation result judgment result and executing corresponding alarm or interlocking control. The theoretical density of the bubble-free sodium carbonate liquid is dynamically calculated in the control unit in real time according to the online measured mass fraction concentration and temperature of the alkali liquid, and reliable separation result evaluation under the real-time concentration change working condition is achieved.

The invention discloses a power transmission system online elasticity evaluation and neural network interpretation method and system, and belongs to the technical field of power system elasticity evaluation. The method comprises the following steps: calculating wind speed change based on a typhoon wind field evolution model, and constructing a system vulnerability model; establishing a power transmission system response process in an extreme disaster scene as a Markov decision process; combining a system vulnerability model with a Markov decision process to construct a time-space map attention network estimation elasticity index; key links influencing system elasticity are identified through interpretability analysis; and evaluating the elasticity of the power transmission system on line by using the time-space map attention network and outputting explanatory information. The problems that an existing method is low in calculation efficiency and lacks guidance after evaluation are solved, the efficiency and accuracy of elasticity evaluation in the extreme disaster scene are improved, visual guidance is provided for system elasticity improvement, and safe operation of a power transmission system is guaranteed.

The invention discloses a method for rapidly generating non-uniform structure characteristics and mechanical properties of a weld zone, and belongs to the technical field of welding quality assessment, and the method comprises the following steps: S1, obtaining a characteristic temperature-time curve representing a weld thermal history through a dynamic temperature measurement method; s2, inputting the characteristic temperature-time curve and the chemical components of the base metal into a thermal-metallurgical coupling model, and predicting a non-uniform microstructure phase distribution diagram of the weld seam area; and S3, based on a semi-empirical mechanical model, mapping the non-uniform microstructure phase distribution diagram into a mechanical property distribution diagram of the welding seam area, and completing rapid identification of the microstructure characteristics and the mechanical properties. According to the rapid generation method for the non-uniform structure characteristics and the mechanical properties of the welding seam area, rapid and non-destructive identification of the non-uniform structure and the properties of the welding seam is achieved, the defects of lag and damage of a traditional method are overcome, and an effective means is provided for online evaluation of the welding quality and process optimization.

The application discloses an insulation level online evaluation method applied to a vehicle-mounted metal closed device, which comprises an insulation main body, a grounding shielding layer, flexible insulation glue, a monitoring sensor, a terminal processor and a background data analysis center; the grounding shielding layer is uniformly arranged on the outer surface of the insulation main body, the local area of the insulation main body, where the monitoring sensor is arranged, is not provided with the grounding shielding layer, the shell of the monitoring sensor is annularly contacted with the grounding shielding layer after the monitoring sensor is arranged, the shell of the monitoring sensor and the grounding shielding layer completely wrap the insulation main body to form the metal closed device, the flexible insulation glue is filled between the bottom surface of the monitoring sensor and the insulation main body, the terminal processor is arranged near the insulation main body and is used with the vehicle, signal transmission is realized through wired connection between the terminal processor and the monitoring sensor, and data exchange is realized through wireless connection between the terminal processor and the background data analysis center. The metal closed grounding shielding effect and the partial discharge detection precision of the insulation main body can be considered, the monitoring principle is scientific and reasonable, the structure is simple and reliable, the shielding effect is good, the anti-interference capability is strong, the detection sensitivity is high, the cost is low, economic benefits are outstanding, and technical progress is remarkable.

The application is a multi-stage prediction method for contactor electrical life based on clustering analysis and time sequence network, comprising: performing AC contactor life test, and obtaining key features through feature importance and correlation analysis screening; taking the key features of single action of the contactor as a feature mode, and constructing a contact wear factor based on mode similarity measurement; performing fuzzy C-means clustering on the contact wear factor, dividing the contactor life test process into multiple degradation stages, taking the divided degradation stages as training labels, and taking the key features as inputs to train the degradation stage online evaluation model; taking the key features of each degradation stage and the corresponding residual life to form a stage data set, training a parallel time sequence network, and obtaining a residual life prediction model of each stage to predict the residual life of the contactor. The characteristics of the multi-stage performance degradation process of the contactor and the problem of the relatively one-sided feature extraction of a single model are comprehensively considered, and the accuracy of the life prediction is improved.