63 results about "Wavelet noise" patented technology

The invention discloses a power transmission line connection fitting fault detection method based on acoustics and electromagnetic induction, and belongs to the technical field of intelligent inspection and nondestructive detection of power transmission lines. A multi-mode sensor is carried by an unmanned aerial vehicle, ultrasonic wave, vibration, images and power frequency electromagnetic field data are synchronously collected, and a multi-dimensional original data set is constructed. Signal quality is improved by adopting wavelet noise reduction, beam forming and sound image fusion technologies, and flight vibration and electromagnetic interference are effectively suppressed by combining an adaptive filtering algorithm and a physical shielding structure. And acoustic, image and electromagnetic characteristics are extracted and normalized and fused, a dynamic threshold reference library is established, and intelligent grading discrimination of abnormity, defects and faults is realized through multi-stage early warning logic. A detection result automatically generates a report and is mapped to a three-dimensional line model, and operation and maintenance system linkage is supported. According to the method, synchronous identification of surface and internal defects is realized, the anti-interference capability is high, the detection accuracy is high, the inspection efficiency and safety are remarkably improved, and the method is suitable for intelligent operation and maintenance of the high-voltage transmission line.

The invention discloses a motor fault detection method and system based on voiceprint recognition. According to the method, an annular microphone array is adopted to collect motor sound signals in a non-contact mode, a three-channel time-frequency data set is constructed through empirical mode decomposition (EMD) and a Mel-frequency cepstral coefficient (MFCC), fault diagnosis is carried out in combination with a CNN + ResNet network, and dynamic time warping (DTW) and CNN fusion matching is supported. The system comprises a preprocessing module, a fault template library and a matching algorithm, integrates wavelet denoising and multi-beam acquisition technologies, covers a frequency band of 50Hz-20kHz, can display a fault type and trend analysis in real time, and triggers secondary verification when the confidence coefficient is insufficient. According to the scheme, the anti-interference capability is improved through array signal processing, model parameters are optimized in combination with transfer learning, non-contact detection is achieved, the real-time performance and accuracy of fault diagnosis are remarkably improved, and the method is suitable for industrial motor health monitoring.

The invention relates to the technical field of communication, and discloses an optical fiber performance automatic test method, system and device based on optical power detection. The method comprises the following steps: carrying out intelligent scanning detection on an optical fiber network, generating optical fiber resource mapping data, obtaining an OTDR measurement configuration table through dynamic analysis, executing optical pulse injection and signal acquisition to obtain a time domain response characteristic curve, obtaining an optical fiber performance parameter set through wavelet denoising and peak value identification processing, and obtaining the optical fiber performance parameter set. And performing fault analysis by using deep learning and expert rules to obtain diagnosis decision data, and finally generating an optical fiber state evaluation report through digital twin modeling. According to the invention, remote automatic testing, intelligent fault diagnosis and visual monitoring management of the optical fiber network can be realized, and the operation and maintenance efficiency and reliability of the optical fiber communication network are improved.

The invention provides a multi-stage embedded control equipment state sensing and energy cascade scheduling system. Comprising a master control decision center module, a distributed edge embedded node module, an equipment full-dimension state sensing module, an energy dynamic optimization scheduling module, a fault prediction and self-healing control module, a cross-protocol communication interconnection module and a man-machine cooperative command module. According to the invention, through constructing a three-layer time domain control chain of edge node nanosecond-level signal processing, cloud second-level optimization scheduling and equipment hour-level strategy presetting, seamless cooperation of turbine bearing pedestal micro-vibration monitoring and a power grid peak regulation strategy is realized, and real-time wavelet noise reduction preprocessing of embedded nodes is combined with cloud LSTM life prediction. A taboo search algorithm is driven to dynamically reconstruct a power supply scheme, and the pain point of control response lag in a high-fluctuation scene is solved.

The invention provides a large-scale satellite three-dimensional image data processing method, medium and system, and belongs to the technical field of satellite three-dimensional image data processing.The method comprises the steps that Gaussian filtering and wavelet noise reduction preprocessing is conducted on an image, and then cooperative computing of a GPU and a CPU is achieved based on a computing task distribution function. Through multi-scale feature extraction and matrix optimization, a stable feature matrix and a variable feature matrix are obtained. A quadtree spatial index is adopted to carry out data partitioning, and SIFT feature extraction and K-means clustering are combined to optimize feature representation. And establishing a stereoscopic image registration model, determining an optimal splicing sequence through a minimum spanning tree algorithm, realizing image splicing by adopting a progressive texture fusion method, and finally generating a high-precision three-dimensional earth surface model. According to the invention, the unification of processing efficiency and precision is realized, and the technical problem that the processing efficiency of large-scale stereoscopic image data is difficult to improve on the premise of ensuring the processing precision in the prior art is solved.

The invention relates to the technical field of mechanical stress and thermal deformation monitoring, in particular to a combustion fine adjustment method based on full-hearth expansion monitoring, which is characterized in that expansion sensor arrays are arranged on each layer of a main burner area of a boiler hearth, and vibration monitoring units are arranged in a layered manner from a main burner to an SOFA air area synchronously; normal deformation, three-dimensional expansion displacement data and vibration spectrum data of the four furnace walls are collected; generating a standardized monitoring data set through wavelet noise reduction and temperature compensation processing, fusing boiler operation parameters, and inputting the boiler operation parameters into the reinforcement learning model to generate a combustor adjustment instruction; water-cooled wall expansion rate change data is collected in real time to optimize model weight and update a control strategy, and a closed-loop feedback mechanism is formed. According to the method, through multi-source sensing data fusion and dynamic modeling, sub-meter analysis of thermal load distribution and quick response of the combustion state are achieved, the boiler operation efficiency is improved, and the service life of equipment is prolonged.

The invention relates to the technical field of industrial water system safety monitoring, in particular to an intelligent source tracing method for a process medium leaked in circulating water, which comprises the following steps of: acquiring multi-dimensional operating parameters such as conductivity, pH value, turbidity, dissolved oxygen, temperature, pressure and characteristic ion concentration; a standardized water quality parameter matrix is generated after space-time alignment and wavelet noise reduction; the method comprises the following steps: extracting an abnormal fluctuation signal by using a leakage feature recognition model based on transfer learning, simulating a diffusion process through a three-dimensional leakage diffusion model, realizing leakage source positioning by combining reverse particle tracking and kernel density estimation, associating a high-probability leakage region with upstream process equipment, extracting backtracking path features, and matching a process medium feature library, thereby realizing leakage source positioning. The leakage medium type is judged; and finally generating a structured traceability report. According to the method, high-precision identification, positioning and medium analysis of process leakage in a complex circulating water system can be realized, and the method has relatively high practicability and popularization value.

The invention discloses a stress analysis method for bridge incremental launching construction, and particularly relates to the field of stress analysis. According to the method, a mechanical state matrix is generated by combining wavelet noise reduction and Kalman filtering through distributed optical fibers, a piezoelectric force sensor, a vibrating wire stress meter and other equipment and real-time data; a pushing system-temporary support-beam body coupling dynamic mechanical model is established, and a generalized alpha method is adopted for solving and Bayesian optimization calibration parameters are adopted; key parameters are identified on line through a three-level progressive framework, boundary conditions are dynamically updated in combination with a total station and a laser tracker, and supporting rigidity self-adaptive adjustment is achieved through fuzzy PID control. Model confidence evaluation adopts a residual norm-modal confidence criterion-Bayesian update three-level mechanism, finally, stress distribution, support reaction and displacement deviation are calculated based on a correction model, and a safety index, threshold alarm and risk analysis report is generated through a fuzzy comprehensive evaluation method and fed back to a construction control center in real time.

The invention provides a gas ultrasonic transducer fast matching method, device and equipment and a storage medium, original measurement data such as flight time are obtained by deploying an ultrasonic transducer in a gas ultrasonic flowmeter in a gas conveying pipeline, and multi-dimensional data acquisition is carried out in combination with other sensor parameters. Wavelet noise reduction and dynamic time warping processing are carried out on collected signals, signal quality and time sequence consistency are improved, time domain, frequency domain, environment and statistical features are extracted, and multi-dimensional feature vectors are formed. Modeling is carried out through a time sequence feature branch and an environment feature branch, weighted fusion is carried out by adopting an attention mechanism, and the recognition capability of the model on key features is enhanced. A machine learning model is trained based on fusion features, a multi-objective loss function and a data enhancement strategy are adopted, the prediction precision and generalization ability of the model are improved, and a compensation value is output to calibrate the original traffic in real time. According to the method, the accuracy and stability of gas flow measurement in a complex environment are effectively improved, and the method has a good engineering application prospect.

The invention relates to the technical field of signal analysis, and discloses a primary frequency modulation large disturbance signal peak value analysis method, which comprises the following steps: collecting a primary frequency modulation large disturbance signal and carrying out filtering processing of multi-band noise separation; performing multi-scale decomposition on the filtered disturbance signal, extracting a dynamic entropy of a multi-scale signal sequence, and performing dynamic entropy denoising on the disturbance signal to obtain a denoised disturbance signal; and calculating a potential peak position of the denoised disturbance signal, and carrying out multi-condition verification on the potential peak position to obtain peak information for frequency modulation disturbance analysis. Based on spectrum energy distribution, specific wavelet bases are selected for different noise frequency bands for noise reduction, the wavelet noise reduction performance is improved, the energy distribution complexity and the structure complexity of the disturbance signals on different scales are extracted, the dynamic characteristics of the disturbance signals are captured more comprehensively, the noise reduction precision is improved, and the noise reduction efficiency is improved. And the accuracy of wind power integration fault identification and equipment life monitoring in the peak value analysis process is improved.

The invention relates to the technical field of equipment parameter optimization, and discloses a liquid cooling system parameter optimization method and system for a data center. The method comprises the steps of performing wavelet noise reduction processing on thermal load data of equipment, and constructing a time sequence heat generation model; the thermodynamic model and the time sequence heat generation model are fused to generate a comprehensive heat model, an objective function and constraint conditions are set, and a parameter combination is output; the parameter optimization model generates a standard parameter combination based on the parameter combination, the standard parameter combination is substituted into the parameter optimization model for evaluation, and an optimal parameter combination is output; the operation parameters of the liquid cooling system are adjusted in real time, the actual system operation data of the liquid cooling system are collected, the actual system operation data are compared with the expected equipment thermal load data of the data center, the parameter deviation is obtained, and the operation parameters are dynamically adjusted based on the parameter deviation. According to the invention, the efficiency and accuracy of parameter optimization of the liquid cooling system are improved.

The invention relates to the technical field of industrial data processing, in particular to a model-driven FlinkSQL (Structured Query Language) dynamic optimization method, which comprises the following steps of: generating candidate SQL (Structured Query Language); carrying out parallel acquisition and noise reduction processing; constructing a causal dependency graph and embedding the graph; constructing a spatio-temporal feature vector and performing steady-state judgment; performing disturbance sandbox verification and stability judgment; a fault-tolerant strategy is injected, and DML is compiled and produced; and deploying tasks and monitoring and updating in real time. Physical signals of industrial equipment are stripped through a wavelet noise reduction technology, then operation indexes of the Flink platform are subjected to structured expression in combination with causal dependency graph embedding, quantitative classification is performed on current operation and ideal steady state, robustness is verified through multiple cycles, adaptive parallelism and a fusing strategy are injected into SQL, and the method has the advantages of being high in robustness and high in reliability. And the reference base point is automatically updated according to the monitoring result, so that the problems of low SQL execution efficiency, insufficient stability and difficulty in adapting to complex industrial scenes caused by neglecting environment change and system load fluctuation during operation are effectively solved.

The invention discloses a residual capacity balance control method and system for an aged lithium battery, and relates to the technical field of new energy materials and devices, and the method comprises the steps: inputting quantum magnetic field response data and infrasonic wave signals into a single-chip microcomputer, carrying out the wavelet noise reduction and histogram equalization processing based on an STM32 single-chip microcomputer, and generating an acoustic-magnetic coupling feature matrix; inputting a dynamic pheromone equalization model based on the acoustic-magnetic coupling characteristic matrix, calculating a capacity difference coupling coefficient between the battery packs through an ant colony optimization algorithm, and generating a capacity redistribution path topological graph; according to the capacity redistribution path topological graph, the energy transfer direction is controlled through a bidirectional Buck-Boost circuit, and an equalizing current threshold value is dynamically adjusted based on the quantum spin resonance magnetic field gradient; according to the invention, the quantum magnetic field response data of the aged lithium battery pack and the infrasonic wave signal generated by electrolyte decomposition are collected, so that the physical and chemical states in the battery are accurately monitored.

The invention discloses an intelligent carbon anode quality detection system, particularly relates to the field of electrolytic aluminum, and comprises a data acquisition module, a data preprocessing module, a data analysis module and a comprehensive judgment module. According to the method, a full-process data acquisition system covering raw materials, forming, roasting and appearance is constructed, accurate acquisition of multi-source data is realized by using equipment such as an X-ray fluorescence spectrometer and a hydraulic sensor, the problem of dispersion of traditional detection data is solved, and the detection accuracy of the multi-source data is improved through multi-stage pretreatment methods such as outlier elimination, sliding window filtering, temperature compensation and wavelet noise reduction. Dimension difference and sensor noise interference are effectively eliminated, and data reliability is improved. A multi-level evaluation model composed of a raw material comprehensive index, forming energy density, roasting maturity and appearance integrity is innovatively established, and intelligent comprehensive evaluation and accurate grading management and control of the carbon anode quality are achieved in combination with a dynamic weighting comprehensive quality index formula and a four-level grading mechanism.

The invention relates to the field of dam effect quantity monitoring, in particular to a dam monitoring effect quantity prediction method based on mechanism and data dual drive, which comprises the following steps of: performing noise reduction preprocessing on monitoring data by adopting a wavelet noise reduction method; constructing a monitoring effect quantity long-term prediction model; constructing a short-time proximity precise prediction model; a Newton-Raphson optimization algorithm (NRBO) is used for optimizing network hyper-parameters of a physical constraint radial basis function (PIRBF) to construct an inversion agent model of finite element model parameters, a finite element calculation result is calibrated, and finally a hybrid model is constructed to realize long-term prediction of monitoring effect quantity. A deep learning model is constructed through an aurora optimization algorithm (PLO), a Transform architecture and a gated cycle unit network (GRU) to correct a long-term prediction model error, a deep learning model result is coupled to construct a short-term approaching prediction model, and short-term approaching accurate prediction of the effect quantity is realized.

The invention discloses an intelligent substation virtual loop online transmission verification method based on GOOSE / SV closed loop test, and relates to the technical field of intelligent substation operation and maintenance. Through precise clock synchronization and an improved cross-correlation algorithm, in combination with wavelet noise reduction and spectral clustering analysis, nanosecond synchronization quality evaluation of GOOSE / SV signals is realized, and the hidden transmission risk discovery time is shortened from regular maintenance to real-time monitoring; a hierarchical hidden Markov model is adopted to analyze equipment-level to system-level behavior modes, real-time probabilistic reasoning is realized in combination with a dynamic Bayesian network and particle filtering, a multi-dimensional evaluation system is constructed, the reliability evaluation capability under complex working conditions is remarkably improved, an optimization scheme is generated based on network path characteristic analysis and bottleneck identification, and the reliability of the system is improved. Multi-scene closed-loop verification is carried out by means of a digital twin technology, safety and reliability of parameter optimization are ensured, and full-process intelligent operation and maintenance of the virtual circuit of the intelligent substation from state perception to optimization verification are realized.

The invention discloses an immersive learning method based on a wearable brain-computer interface and three-dimensional virtual simulation linkage. The system collects EEG, heart rate, galvanic skin, respiration and other multi-mode signals in real time, after band-pass filtering, ICA, wavelet noise reduction and feature extraction, attention indexes and cognitive loads are output within 200 ms by means of a TCN-GNN fusion model, a virtual scene is driven to highlight key knowledge points, step-by-step guidance or difficulty dynamic adjustment, and a learner keeps cardiac flow. The system further optimizes and designs interaction trajectory multi-modal fusion, generates a concentration curve, a cognitive load heat map and personalized tutoring suggestions, and pushes the concentration curve, the cognitive load heat map and the personalized tutoring suggestions to a teacher / parent end in real time through an end-edge-cloud architecture to realize objective quantification of cognitive states and precision of teaching feedback.

The invention provides a high-strength steel laser-arc hybrid welding monitoring method based on acoustic feature extraction. The high-strength steel laser-arc hybrid welding monitoring method comprises the steps that firstly, laser-arc hybrid welding sound signals are collected and preprocessed; step 2, constructing a sound signal feature analysis method; step 3, extracting sound signal features; step 4, feature fusion and dimension reduction; by means of the high-strength steel laser-arc hybrid welding monitoring method based on acoustic feature extraction, frequency-band-divided wavelet noise reduction can be achieved, and noise and effective signals are effectively separated; the multi-frequency-band feature extraction can be carried out for the low-frequency band and the high-frequency band, and the joint feature extraction can be carried out for the cross-frequency band; therefore, the problem of coupling of multi-source acoustic signals of hybrid welding is solved, and meanwhile quantitative evaluation of the laser-arc energy coupling state can be achieved.

The invention discloses an intelligent ditch gate dam self-adaptive adjustment method based on the Internet of Things, relates to the technical field of drainage control, and provides a set of integrated method of multi-source data fusion, predictive diagnosis and automatic fault tolerance for fault prevention and disposal of a gate dam execution mechanism in farmland irrigation. High-quality sensing data is obtained in real time through edge calculation and a wavelet noise reduction technology, and potential anomalies are marked in time; secondly, analyzing the state of an execution mechanism by combining a historical fault record and a health model, and sending out a maintenance suggestion in advance; if a serious fault occurs, the local controller automatically starts secondary adjustment and emergency linkage to temporarily compensate downstream water supply or flood diversion; and finally, the central dispatching center iteratively updates a dispatching strategy by using a global collaborative optimization and self-learning mechanism, and the system reliability and the resource utilization efficiency are enhanced. Therefore, closed-loop management of the gate dam execution mechanism is realized, and stable operation of large-scale farmland irrigation under load and outdoor environments is ensured.

The invention discloses a rainfall monitoring method and device based on millimeter wave radar, and relates to the technical field of meteorological monitoring. The method comprises the following steps: controlling a 24 / 60GHz commercial millimeter wave radar to transmit a millimeter wave signal of an adaptive parameter to a preset area; a raindrop echo signal is received, and clutters are removed through Kalman filtering and wavelet noise reduction; extracting a one-dimensional energy feature, a two-dimensional speed feature and a speed-energy two-dimensional distribution matrix; inputting a low-error model trained by a random forest algorithm, calculating a rainfall energy value and mapping the rainfall energy value into a rainfall level; data is output through a LoRa / ZIGBEE network; the device comprises a millimeter wave radar module, a signal processing module, a calculation output module and a wireless communication module. The problems of single monitoring dimension, high cost and difficult deployment in the prior art are solved, non-contact, low-cost, high-real-time and distributed rainfall monitoring is realized, the error is less than or equal to 5%, the response period is less than or equal to 100ms, and the method is suitable for traffic, municipal administration, emergency and other scenes.

The invention relates to a multi-fault real-time early warning system for a power distribution cabinet, and relates to the technical field of power distribution cabinet detection. Partial discharge, mechanical vibration, insulation dielectric loss and environmental parameters are synchronously acquired through a distributed sensor array; performing electromagnetic interference filtering and wavelet noise reduction preprocessing on the original data, and extracting the characteristics of pulse frequency, vibration kurtosis, dielectric loss change rate and the like; a'rule base + random forest 'mixed model is adopted to identify fault types and confidence; fault positioning with the precision of + / -3cm is realized based on sensor delay inequality and a triangulation positioning algorithm, and fault components are determined in combination with a component topology mapping table; early warning levels are divided according to fault types, confidence coefficients and component importance, and customized reports are dynamically pushed; a standard signal is injected every 24 hours to generate a compensation coefficient, and the drift error of the sensor is corrected in real time.

The invention relates to the field of distributed optical fiber sensing signal noise reduction, in particular to a distributed optical fiber sensing signal noise reduction method based on reinforcement learning enhancement. The method comprises the following steps: S1, generating a distributed optical fiber sensing signal original image matrix; s2, setting a two-dimensional wavelet noise reduction hyper-parameter set; s3, generating an action set; s4, based on a Markov decision process, performing enhanced model training on the two-dimensional wavelet noise reduction hyper-parameter setting of the original image matrix of the distributed optical fiber sensing signal; and S5, carrying out noise reduction on the original image matrix of the distributed optical fiber sensing signal. According to the method, the spatial correlation between image pixel points can be effectively utilized, reinforcement learning updating is automatically carried out on the wavelet noise reduction hyper-parameters, and the noise adaptability of the algorithm is improved. In addition, in the algorithm training process, a reference-free reward function is established, a known noise-free clean signal does not need to be used as a reference, and the algorithm is more suitable for being used in actual engineering.

The invention discloses a new energy station cable terminal partial discharge signal identification method and system, and the method comprises the following steps: collecting an original signal, carrying out the preprocessing of the original signal, and carrying out the wavelet threshold noise reduction processing, and obtaining a noise reduction signal; performing sliding slicing processing on the denoised one-dimensional long time sequence signal, and inputting the processed signal into the constructed partial discharge identification model to train the model; and inputting the target signal into the trained partial discharge identification model to obtain a time position and a continuous range of a real partial discharge event in the long time sequence signal, thereby realizing effective identification and separation of the partial discharge signal and corona interference of the cable terminal of the new energy field station. Wavelet noise reduction, a time window and one-dimensional convolutional network depth feature recognition are integrally designed, partial discharge signals can be stably recognized in the strong noise and mixed pulse scene of the new energy station cable terminal, and a reliable data basis is provided for insulation state evaluation and operation and maintenance early warning of the new energy station cable terminal.

The invention relates to a long-term monitoring and early warning method suitable for a large-span steel frame beam, and the method specifically comprises the steps: laying a distributed fiber grating sensor network at a key stress part of a target steel frame beam, and synchronously collecting an original deformation signal in real time; a temperature compensation algorithm and a wavelet noise reduction algorithm are used for preprocessing the collected various original deformation signals; identifying the deformation state of the key stress part through an improved conjugate beam method on the basis of the multiple original deformation signals after preprocessing and the structural model information of the target steel frame beam; constructing a steel frame beam deformation prediction model, and predicting the future deformation trend of the target steel frame beam by using the preprocessed historical and real-time signal time sequence data; and a steel frame beam abnormal deformation diagnosis model based on the graph neural network is constructed, abnormal recognition is performed on the deformation state of the key stress part based on a preset threshold value, and early warning is performed on the abnormal part in combination with the future deformation trend of the target steel frame beam.

The invention discloses a distributed optical fiber temperature-sensitive fire detection algorithm based on CNN-LSTM and an attention mechanism, and aims to solve the problems of high false alarm rate, response lag and poor scene adaptability in the traditional detection technology. According to the system, temperature data are collected through a distributed optical fiber sensing unit at the interval of 2 seconds and the spatial resolution of 0.5 m, after Z-Score standardization, db4 wavelet noise reduction and 12-dimensional feature enhancement preprocessing, the temperature data are input into a CNN-LSTM hybrid model to extract spatial and temporal features, key areas and moments are focused in combination with an attention mechanism, and a fire risk index of 0-100 is output. Model training adopts transfer learning and a Focal Loss function to realize cross-scene rapid adaptation and sample imbalance processing, and parameters are updated through incremental learning every 30 days. Practice shows that compared with a traditional threshold value method, the method has the advantages that the false alarm rate is reduced by more than 80%, smoldering fire early warning is advanced by 25 seconds, and the method can be widely applied to fire safety monitoring of complex scenes such as tunnels, transformer substations and comprehensive pipe galleries.

The invention discloses a system and method for measuring the rotation error of an ultra-precise rotation shaft system. The system comprises a rotation index plate, a servo motor, a spring, a main shaft, a marble platform, a movable sensor clamping device and the like. The method comprises the following steps of: controlling angles of sensors on a rotary index plate by using a rotating body, so that radial and axial sensors are positioned at optimal measurement positions; the mounting height of the rotary index plate is adjusted; after the measurement system operates stably, the three high-precision displacement sensors arranged at the optimal measurement positions are used for synchronously collecting dynamic displacement data of the main shaft of the rotary table in real time; the method comprises the following steps of: preprocessing an original signal by adopting a wavelet denoising algorithm, and then carrying out Fourier transform analysis on processed 20-turn stable operation data to obtain a frequency domain signal; and extracting a synchronous motion error and an asynchronous motion error from the measurement data subjected to noise reduction processing, and solving mathematical model parameters by using the measurement data based on a three-point method error separation principle.

The invention provides an insulation state detection method, system, equipment and medium, and relates to the field of electronic device detection.The method comprises the steps that a discharge signal of a power module is obtained, high-pass filtering and wavelet noise reduction are conducted on the discharge signal, and a discharge pulse is obtained; recording the morphology change of the bubbles at the three bonding points of the substrate, the electrode and the silica gel of the power module; analyzing the discharge pulse based on a phase resolution partial discharge map to obtain partial discharge parameter changes, and classifying the partial discharge parameter changes to obtain insulation defect types; and performing evaluation according to the morphology change of the bubbles and the insulation defect type to obtain an insulation degradation state. On the basis of collaborative analysis of bubble evolution and discharge characteristics, the insulation state of the high-voltage power module is monitored, in-situ observation of bubble evolution of a glue-solid interface is realized, discharge signal characteristics are extracted, and a mapping relation of bubble form-discharge mode-signal parameters is established.

The invention discloses a device and a method for detecting suffocating gas in deep pit operation, and belongs to the technical field of gas detection. Comprising the following steps: constructing a detection model; constructing a real-time response system through starting-up self-calibration and setting of a dynamic threshold value; multi-modal data are collected and processed, gas collection is optimized by adopting a spiral flow guide gas chamber and a turbulent flow fan, the detection precision is improved by combining wavelet noise reduction and LSTM dynamic compensation, and a detection result is obtained. Compared with the prior art, through the MXene material sensor and the multi-modal data fusion technology, the detection error rate is reduced to be smaller than or equal to + / -2% FS, and the response speed is increased by four times; an enhanced convection air chamber and dynamic power consumption management (endurance time is longer than or equal to 48 hours) are adopted to adapt to a deep pit complex environment; through three-level linkage alarm (light / sound / touch) and cloud intelligent decision, full-chain safety prevention and control from real-time monitoring to emergency response are realized, the false alarm rate is reduced by 78%, and the safety guarantee efficiency of operators is remarkably improved.

The invention provides a terahertz time-domain spectral signal noise reduction method and system for transformer aged insulating oil, and the method comprises the steps: collecting a terahertz time-domain spectral signal of an aged insulating oil sample, and carrying out the parameter optimization of variational mode decomposition through a whale optimization algorithm, according to the method, an optimized variational mode decomposition algorithm is adopted to decompose terahertz time-domain spectral signals of aged insulating oil into a series of intrinsic mode function components, then independent component analysis is adopted to separate the intrinsic mode function components into noise and effective signals, and finally the effective signals are screened out by calculating information entropy of independent components. And reconstructing the terahertz time-domain spectral signal of the aged insulating oil after noise reduction. The technical problems that the wavelet basis function and the decomposition layer number of wavelet noise reduction are difficult to determine, the noise reduction effect is restricted by the endpoint effect and mode aliasing problem of empirical mode decomposition, and the noise reduction effect of variational mode decomposition is poor are solved.

The invention belongs to the field of power distribution network fault detection, and provides a power distribution network fault traveling wave polarity discrimination method, which comprises the steps of wavelet decomposition, threshold value processing, wavelet reconstruction, differential absolute value calculation, filtering threshold value calculation, first maximum point extraction and polarity determination. According to the method, polarity judgment is performed by comparing the data subjected to wavelet denoising and differential processing with 0, so that the influence of the non-stationarity of the original data on the waveform polarity can be effectively eliminated, and the polarity judgment accuracy is improved.