241 results about "Independent component analysis" patented technology

A multi-source domain adaptive electroencephalogram (EEG) emotional state classification method based on knowledge distillation are provided. First, data is obtained for band-pass filtering, and artifacts are removed by an independent component analysis technology. Second, EEG features are extracted by using a differential entropy method, and a three-dimensional EEG time series is converted into a two-dimensional sample matrix. Then, a training set and a test set are defined in two task scenarios, respectively. A pseudo-label triple loss based on marginal sampling is combined with a maximum mean discrepancy. Knowledge is learned from different source domains, so that a plurality of single-source models are utilized to the greatest extent, and a more powerful model is implemented with less time consumption. Finally, the classification accuracy is used to evaluate the performance of the model in the two task scenarios.

The invention discloses a morphological gradient region replacement method based on SAM semantic segmentation and user guidance, and relates to the technical field of computer vision and image processing, and the method comprises the steps: carrying out the semantic segmentation of a to-be-processed image through an SAM model, extracting a multi-level semantic feature, carrying out the standardization and dimension reduction, extracting a causal factor based on independent component analysis, and carrying out the user guidance. A directed causal factor association graph is generated through Granger causal relationship test, and a causal attribution probability graph is generated through reverse mapping; constructing a structured causal graph, and generating a causal mask through a graph convolutional network; encoding the original interaction signal into a guide thermodynamic diagram; constructing a diffusion equation, forming a gradual change control equation by dynamically fusing and guiding the intensity distribution of the thermodynamic diagram and an image semantic diffusion item, and iteratively solving the gradual change control equation; generating an anisotropic morphological operation kernel according to the geometric curvature characteristics of each region in the replacement mask; and fusing the optimized replacement mask with the target content based on a gradient domain optimization algorithm to generate a gradient replacement image.

The invention discloses an intelligent brain-controlled muscle electrical stimulation rehabilitation therapeutic apparatus, and relates to the technical field of electrical stimulation rehabilitation therapeutic apparatuses, the intelligent brain-controlled muscle electrical stimulation rehabilitation therapeutic apparatus comprises an electroencephalogram signal acquisition module, an electromyographic signal acquisition module and a mixed signal processing module, the mixed signal processing module is connected with the electroencephalogram signal acquisition module and the electromyographic signal acquisition module; the method is used for preprocessing electroencephalogram and electromyogram signals, fusing multi-modal features and classifying motion intentions. By installing the mixed signal processing module, preprocessing, multi-modal feature fusion and motion intention classification of electroencephalogram and electromyogram signals are achieved, a preprocessing unit can effectively remove ocular artifacts and power frequency noise, meanwhile, independent component analysis and a dynamic baseline calibration strategy are adopted, the signal quality is further improved, and the accuracy of motion intention classification is improved. According to the multi-mode signal processing mode, the limitation of single signal processing in the prior art is overcome, and the accuracy and effectiveness of rehabilitation treatment are improved.

The invention discloses a GIS equipment defect accurate positioning method and system based on acoustic visualization, and relates to the technical field of defect localization, and the method comprises the steps: collecting a vibration acoustic mixed signal in an equipment operation state, and separating the vibration acoustic mixed signal into a pure acoustic signal and a vibration signal through independent component analysis; an acoustic characteristic spectrum is constructed for the pure acoustic signals, a sound field propagation path model is generated, and meanwhile a corresponding relation graph of equipment components and the acoustic characteristic spectrum is established; and determining a source component and a specific position of the abnormal acoustic characteristic spectrum through an acoustic reverse tracking positioning algorithm in combination with the sound field propagation path model and the corresponding relation map. According to the method, by combining vibration acoustic conjoint analysis and acoustic reverse tracking, high-precision positioning of defects of hidden parts in the GIS equipment is achieved, the positioning precision and the recognition accuracy are improved, recognizable defect types are expanded, and the method is suitable for GIS equipment of different structures.

The invention discloses an ADHD classification method based on electroencephalogram signals and a channel selection attention mechanism, and particularly relates to the technical field of electroencephalogram signal classification, and the method comprises the steps: obtaining the public electroencephalogram data of ADHD children, ADD children and HC children in task states, carrying out the preprocessing of the data, carrying out the analysis of independent components, separating data components, removing artifact components, and carrying out the classification of the ADHD children, the ADD children and the HC children; the method comprises the steps of obtaining pure electroencephalogram signals, segmenting data and dividing a data set, designing an ADHD electroencephalogram signal classification algorithm based on a multi-scale channel selective attention mechanism and a neural network, capturing features of different scales through a multi-scale CNN, focusing on correlation enhancement features among channels by using the channel selective attention mechanism, and classifying the electroencephalogram signals to obtain an ADHD electroencephalogram signal classification algorithm based on the multi-scale channel selective attention mechanism. And finally, capturing a long-distance dependency relationship through a self-attention mechanism and fusing global features.

The invention provides a method for extracting electrical characteristic signals of electrical equipment in a complex working condition environment, and belongs to the technical field of electrical equipment detection.The method comprises the steps that a multi-channel ultrasonic sensor array is arranged to collect partial discharge signals, background noise is eliminated through adaptive noise cancellation processing, and an ultra-sparse frequency band energy distribution vector is constructed; the method comprises the following steps: calling a self-adaptive time-frequency analysis model to extract instantaneous frequency, amplitude and phase parameters to form a micro-hour-frequency characteristic matrix, separating independent source signals through independent component analysis, calculating a kurtosis value and a skewness value, fusing multi-domain characteristics to construct a transient stationary comprehensive characteristic vector, matching with a standard discharge characteristic vector library to identify the discharge type and intensity, and calculating the discharge intensity. A corresponding prediction algorithm is selected according to the discharge mode, multi-parameter coupling optimization adjustment is started under a certain condition, an electrical characteristic signal description vector is finally constructed, and the technical problem that the partial discharge signal of the power equipment is difficult to accurately extract under a complex working condition environment is solved.

The invention discloses a fan operation abnormal vibration monitoring method and system based on multi-sensor fusion, and relates to the technical field of fan operation monitoring, and the method comprises the following steps: deploying a plurality of types of sensors on a fan, collecting the data of each sensor in real time, carrying out the synchronous processing of the sensor data through employing an IEEE1588 protocol, carrying out the preprocessing through combining wavelet denoising, and carrying out the monitoring of the abnormal vibration of the fan. Extracting feature data by using a principal component PCA combined independent component ICA analysis method; according to the method, multiple types of sensors are deployed on the fan, the actual conditions of the offshore wind field are considered, fine processing and feature extraction are carried out after multi-source signals are collected in real time, the abnormal vibration condition of the fan in the coastal or offshore wind field under the complex environment is accurately monitored and reliably recognized, and therefore the early abnormal features of fan operation can be captured in time; normal changes and real fault anomalies caused by environmental factors are effectively distinguished, and early discovery of faults is further realized.

The invention discloses a geotechnical engineering slope stability real-time monitoring method and a geotechnical engineering slope stability real-time monitoring system, which are characterized in that a blind source separation technology combining independent component analysis and physical constraint is introduced, an original displacement time sequence and an environment temperature time sequence of a plurality of GNSS (Global Navigation Satellite System) measuring points are regarded as multi-channel mixed signals, and statistical independence among signal sources is utilized to monitor the stability of a slope in real time. Periodic environment noise, instrument random noise and drift and real slope deformation signals are effectively separated from the mixed observation signals; and then, through correlation verification with physical quantities such as the field environment temperature and the like, automatic calibration is performed on the separated source signals, and temperature effect source signals and long-term creep source signals with physical labels are accurately identified and extracted, so that accurate elimination of noise components and high-fidelity reconstruction of pure deformation signals are realized. Therefore, the accuracy of real-time monitoring of the slope stability of geotechnical engineering can be effectively improved, and a solid data basis and a decision basis are provided for early warning and prevention of slope disasters.

The invention provides an iron tower voiceprint intelligent detection method and system, and belongs to the voiceprint detection technology. The method comprises the following steps: firstly, outputting a sweep frequency signal in a specific frequency range, collecting iron tower vibration response data, extracting candidate frequency through spectral analysis, and dynamically adjusting excitation frequency by using a gradient descent algorithm; hardware filtering is carried out on collected sound signals, frequency band signals related to excitation frequency are reserved, and space beam forming is carried out through a microphone array to enhance iron tower voiceprint signals. Separating iron tower vibration components from the mixed signals by utilizing independent component analysis, performing time-frequency analysis, extracting an energy ratio of a specified frequency band by adopting wavelet packet transformation, and performing deep learning processing in combination with a one-dimensional convolutional neural network to generate an energy ratio and zero-crossing rate feature vector; and finally, inputting the feature vectors into a support vector data description model, setting an initial threshold value and dynamically adjusting the initial threshold value, thereby realizing graded judgment of bolt looseness and improving detection efficiency and stability.

The invention relates to the field of biological signal processing, and particularly discloses a classification method for intrusive electroencephalogram signal motor imagery tasks, which comprises the following steps of: acquiring original electroencephalogram signals according to task requirements through an intrusive brain-computer interface system; preprocessing the electroencephalogram signal data, and removing noise in combination with a signal-to-noise ratio; performing independent component analysis to extract an electroencephalogram signal source; signal features are extracted manually, and principal component analysis dimension reduction is carried out; and putting the data into the model for training, and classifying the signals. According to the method, noise and redundant information of the electroencephalogram signals are effectively removed through combination of ICA and PCA, and the influence of artifacts on a classification result is reduced, so that the representative characteristics of the signals are improved, the classification accuracy is improved, and a good classification effect can still be ensured especially in a high-noise environment.

The invention provides a denoising method for non-stationary nonlinear magnetotelluric sounding signals, and relates to the technical field of geophysical exploration, and the method comprises the steps: obtaining magnetotelluric sounding signals from a magnetotelluric depth finder, selecting one from the obtained magnetotelluric sounding signals, carrying out the denoising of the selected magnetotelluric sounding signals, repeating the above operation, and carrying out the denoising of the selected magnetotelluric sounding signals. And carrying out de-noising processing on the other acquired magnetotelluric sounding signals. VMD (variational mode decomposition) and ICA (independent component analysis) are combined, denoising of the magnetotelluric sounding signals is realized from multiple angles of time-frequency domain and statistical property, and when effective signals are interfered by long-time high-energy non-stationary noise, the method can ensure high quality of reconstructed signals, effectively reduce the influence of manual parameter selection, and improve the denoising performance of the magnetotelluric sounding signals. Compared with the prior art, the method has the advantages that the method is high in robustness to noise, clear physical interpretation is provided, limitation of a traditional denoising method is overcome, and a more reliable and accurate data processing means is provided for the field of geophysical exploration.

The invention discloses a motor cooling control system with a fault diagnosis function, and relates to the field of motor cooling control, and the system comprises a water pump, a water pump controller, a pipeline, a plurality of sensors, and a fault diagnosis module. Early warning of faults such as pipeline blockage, pipeline leakage, water pump degradation and water pump failure is achieved, the self-adaptive compensation function is achieved, control parameters can be automatically adjusted when the performance of part of assemblies is degraded, the optimal working state of the system is maintained, and the overall reliability is improved. In order to realize the accuracy of a prediction result, blind source separation is carried out on a water pump vibration signal and a pipeline vibration signal based on an independent component analysis method, clustering sampling is carried out on sample data through a clustering algorithm, sample redundancy is reduced, meanwhile, periodic changes of motor temperature are considered when the water pump degradation degree is predicted, and the prediction accuracy is improved. And the prediction accuracy is improved.

The invention discloses a power industry electroencephalogram cap-oriented key channel screening method and system, and the method comprises the following steps: firstly, collecting electroencephalogram signals of a power worker in typical states of waking, fatigue and the like by adopting a 32 or 64 channel electroencephalogram cap, and carrying out the preprocessing operations of band-pass filtering, ICA (Independent Component Analysis), signal-to-noise ratio evaluation and the like; artifacts and inferior channels are removed, and then multi-dimensional features such as the frequency domain, the time domain, the entropy value and statistics of each channel are extracted to comprehensively score the importance of the channels. Constructing a plurality of channel subsets, verifying the recognition performance of the channel subsets through a classification model, and screening out a group of key channels with the highest information expression capability in cognitive state discrimination; according to the method, the number of electroencephalogram channels is reduced, the complexity and calculation overhead of acquisition equipment are reduced, the feasibility of real-time deployment of the model in an electric power field is improved, and the method has relatively high industry adaptability and engineering application value and is suitable for various key scenes with relatively high requirements on personnel state perception.

The invention relates to the technical field of geodetic survey and structural health monitoring, and discloses a GNSS-RTK coordinate domain error correction method, which comprises the following steps: acquiring GNSS-RTK dynamic observation data to form a mixed signal time sequence; executing an improved adaptive noise complete empirical mode decomposition algorithm on the sequence to obtain an intrinsic mode function component; identifying and eliminating high-frequency components representing Gaussian white noise based on an energy coefficient, and reconstructing residual components into a signal sequence after primary noise reduction; inputting the noise reduction sequence into a rapid independent component analysis model for blind source separation; and finally, carrying out sorting and phase and amplitude uncertainty correction on the separated independent components, and outputting a multi-path error model and a structure dynamic deformation signal. According to the method, the problem of blind source separation failure or low precision caused by strong noise covering source signal statistical characteristics is solved through a strategy of first noise reduction and then separation, and an effective physical signal can be accurately extracted from a strong noise background.

The invention discloses an intelligent control system for a tea processing process and a control method based on technological parameter optimization, and relates to the technical field of tea processing. By integrating the high-precision sensor and the intelligent decision-making module, comprehensive monitoring and real-time optimization of key technological parameters of tea processing are realized, data accuracy is ensured through pyroelectric infrared and SAW humidity sensors and the like, and the intelligent decision-making module automatically adjusts the processing parameters by using a deep belief network and an ant colony algorithm, so that the processing accuracy is improved. The production efficiency is improved, manual errors are reduced, meanwhile, technological parameters are accurately controlled by adopting an advanced data processing algorithm, variation mode decomposition and independent component analysis ensure stable tea quality, in addition, external and internal data are integrated to optimize the processing technology, heating, ventilation and other parameters are accurately controlled, and energy consumption and cost are reduced.

The invention relates to the field of optical fiber vibration signal processing, and discloses a vibration signal identification method of an optical fiber vibration sensor in a high-noise environment, which comprises the following steps of: S1, preprocessing an optical fiber vibration signal, eliminating a direct current component, performing amplitude normalization and eliminating redundant correlation; s2, separating the preprocessed signals by using an independent component analysis technology, and extracting independent signals of different vibration sources; s3, performing time alignment on the separated signals by using a dynamic time warping algorithm, and calculating an alignment path distance between the signals; and S4, judging whether the vibration signal is abnormal or not according to comparison between the alignment path distance and a preset threshold value. According to the method, independent component analysis and dynamic time warping technologies are combined, and accurate separation and efficient identification of vibration signals and environmental noise are realized through non-Gaussian optimization and time axis dynamic alignment without depending on prior mark data and a data driving model.

The invention provides a brain-controlled unmanned aerial vehicle group method based on brain-computer deep collaborative fusion. The method comprises the following steps: firstly, designing a steady-state visual evoked brain control signal acquisition normal form, and generating a visual stimulation signal through combined frequency-phase coding; secondly, the electroencephalogram signals are preprocessed through filtering, independent component analysis and the like; then, constructing an intention decoding network with deep fusion of space-time frequency features, extracting multi-scale features of the electroencephalogram signals by using a convolutional neural network, and performing deep fusion decoding through a space-time frequency Transform module to realize accurate prediction of brain control intention; thirdly, a virtual pilot algorithm and an artificial potential field algorithm are used for flight decision making of the unmanned aerial vehicle group; and finally, displaying the flight state of the unmanned aerial vehicle in real time through a visual interface constructed by PyQt5. The method has the advantages that the brain control intention of the user can be accurately decoded, the formation control and obstacle avoidance capability of the unmanned aerial vehicle group is effectively improved, and meanwhile, a visual interface and personalized setting are provided.

The invention discloses an intelligent civil engineering construction management method and system, and relates to the technical field of civil engineering construction management, and the method comprises the following steps: obtaining the vibration data of N construction devices and the mixed vibration data of M monitoring points; and judging whether the mixed vibration data is greater than a preset threshold, if so, performing multi-feature matching with a preset vibration fingerprint database, determining responsible equipment according to a matching result, and outputting contribution degrees and vibration measured values in a descending order. According to the method, environmental interference is eliminated through preprocessing, multi-dimensional decomposition of the mixed vibration data is realized through independent component analysis, and double criteria of time domain waveform difference and frequency domain energy matching degree are combined, so that the recognition accuracy of responsible equipment is remarkably improved, and the recognition efficiency is improved. A three-dimensional geologic model is further constructed through ground penetrating radar scanning and soil layer test data, spatial distribution and attenuation characteristics of different soil layers are accurately reflected, and misjudgment of responsible equipment caused by soil layer difference is avoided.

The invention belongs to the technical field of signal processing, and particularly discloses an acoustic emission signal denoising method based on multi-method fusion, and the method comprises the steps: collecting an acoustic emission signal through an acoustic emission sensor; a band-pass frequency range is determined by adjusting the frequency range based on a plurality of evaluation indexes, and the evaluation indexes are determined by analyzing the difference between the first signal sample and the second signal sample; the first signal sample and the second signal sample are samples collected when no cavitation phenomenon exists and when the cavitation phenomenon exists respectively; wavelet threshold de-noising is carried out, and a signal after background noise is removed is obtained; through independent component analysis, a target signal and an interference signal are separated. According to the invention, by combining a plurality of denoising technologies, accurate suppression of different types of noise is realized, the denoising effect can be ensured in a complex environment, the signal-to-noise ratio of the acoustic emission signal is effectively improved, and the quality and reliability of the signal are ensured.

The invention discloses a cable partial discharge signal noise separation mode identification method and system, and particularly relates to the technical field of cable partial discharge detection, in a multi-cable stacking environment, partial discharge signals are synchronously collected through multiple types of sensors such as a high-frequency current sensor, an ultrasonic sensor and an electromagnetic antenna; performing band-pass filtering, wavelet denoising and multi-channel synchronous alignment on the acquired signals to suppress background noise and retain key features of partial discharge pulses; separating the mixed signals by adopting independent component analysis; calculating a decision coefficient based on an inter-channel correlation coefficient, a signal-noise power ratio and an amplitude dynamic range, and judging whether to introduce a denoising method based on deep learning; for the waveform after noise separation, executing an amplitude re-calibration process so as to correct amplitude scaling uncertainty, and extracting multi-dimensional time domain, frequency domain and phase features; and a support vector machine and other machine learning algorithms are combined to realize automatic identification of partial discharge types.

The invention provides an industrial process small fault detection method based on slow independent feature probability difference, and belongs to the technical field of industrial process fault detection. The technical problem that traditional PCA is low in small fault detection rate is solved. According to the technical scheme, industrial data are standardized, slow-varying and fast-varying feature spaces are extracted through slow feature analysis SFA, and a probability difference detection index is constructed for the slow-varying features in combination with JS divergence and a sliding window; performing ICA (Independent Component Analysis) on the quick change features to construct a slow independent principal component, and constructing a slow independent feature probability difference index in combination with JS divergence and a sliding window; and adopting a Bayesian strategy to fuse the two feature probability difference indexes to generate a comprehensive detection index BIC. The method has the beneficial effects that noise-containing quick change features are denoised through ICA, the probability difference is enhanced by using JS divergence, noise interference is suppressed, and the tiny fault detection rate is remarkably improved.

The invention discloses a motor imagery electroencephalogram signal recognition method based on a PSD and an optimized SVM. The method comprises the steps that motor imagery electroencephalogram signal data collection is conducted on a testee in a visual interface auxiliary state; a Butterworth filter and an independent component analysis method are adopted to remove noise and artifacts of the motor imagery electroencephalogram signal data; carrying out PSD feature extraction on the preprocessed motor imagery electroencephalogram signal data; optimizing parameters of a support vector machine (SVM) by adopting a particle swarm optimization (PSO) algorithm; and performing feature classification on the motor imagery electroencephalogram signals subjected to PSD feature extraction by using the optimized SVM, and determining a recognition result of the motor imagery electroencephalogram signals. And optimizing the kernel function parameters of the support vector machine by using the global optimization capability of the particle swarm optimization algorithm to achieve the optimal classification performance. Target recognition accuracy is a key part for researching a brain-computer interface. Along with the improvement of the target recognition accuracy, the accuracy of the online brain-computer interface can be greatly improved.

The invention requests to protect a motor imagery electroencephalogram signal enhancement method based on graph attention. The method comprises the following steps: firstly, carrying out multi-stage preprocessing on an original electroencephalogram signal, including band-pass filtering and baseline drifting, and removing artifacts in combination with independent component analysis, then, extracting time information of each channel by utilizing a one-dimensional convolutional network so as to capture time sequence characteristics in a motor imagery process, on the basis, constructing a graph attention network, taking the electroencephalogram signal channels as nodes, and taking the electroencephalogram signal channels as the nodes; the method comprises the following steps of: dynamically modeling and optimizing the internal relation between channels, strengthening motor imagery related channels such as C3, C4 and Cz by combining priori knowledge, further introducing a time attention network to identify and enhance key time slices rich in discrimination information, and finally, forming a high-dimensional feature matrix by fusing space-enhanced and time-enhanced electroencephalogram features, so as to realize the recognition and enhancement of the motor imagery related channels. And inputting into a classifier for pattern recognition.

The invention relates to the technical field of vibration monitoring, in particular to a rotating machine vibration protection method and system based on particle swarm optimization, and the method comprises the steps: obtaining a corrected load torque based on a polynomial fitting temperature compensation algorithm in combination with a real-time environment temperature and a sensor output voltage, and synchronously calculating an actually measured vibration amplitude; configuring the number of variational mode decomposition layers according to the real-time rotating speed of the rotor to obtain a preprocessed vibration signal, adjusting the number of independent component analysis iterations according to the load torque, separating the preprocessed vibration signal to obtain independent vibration components, and generating a feature vector; calibrating adaptive resonance theory network parameters based on a particle swarm optimization algorithm, obtaining a normalized feature vector, calculating the similarity with a fault feature template, outputting a diagnosis result, calculating the deviation between an actually measured vibration amplitude and a normal vibration threshold, and performing compensation according to the diagnosis result and the deviation. According to the scheme, the fault diagnosis accuracy of the rotary mechanical vibration protection system is effectively improved through multi-working-condition self-adaptive diagnosis.

The invention discloses an electroencephalogram fatigue detection method based on fusion of a graph convolutional network and Transform, and belongs to the technical field of artificial intelligence and electroencephalogram signal analysis. The method comprises the steps that multichannel electroencephalogram signals are collected, and band-pass filtering, power frequency notch, independent component analysis, standardization and other preprocessing are conducted on the signals; constructing an inter-channel graph structure based on a Pearson's correlation coefficient, and extracting spatial features by using a graph convolutional network; inputting the spatial features of the plurality of continuous time windows into Transform to carry out time sequence modeling; and finally, realizing fatigue state recognition through a full-connection network and a Softmax classifier. According to the method, the spatial topological structure and the time dynamic evolution of the EEG signal can be modeled at the same time, the accuracy and the real-time performance of fatigue detection are remarkably improved, and the method has good generalization ability and edge deployment ability and is suitable for traffic driving monitoring, intelligent health and other scenes.

The invention discloses an ICA (independent component analysis)-based blind source risk factor identification method for digital twin arch dam behavior detection. A comprehensive monitoring and analysis system consisting of a Wavelet Scattering Network wavelet scattering network, a PCA (principal component analysis) dimension reduction module, an ICA independent component analysis module, an Apache Kafka data transmission module and a digital twin system is adopted. According to the method, the arch dam operation data collected in real time is processed and analyzed, potential blind source risk factors are identified, and the evaluation result is output. The system firstly performs multi-scale feature extraction by using a wavelet scattering network, then performs noise reduction and dimension reduction processing on extracted high-dimensional data by using PCA, and then identifies independent risk factor signals through an ICA module. And finally, transmitting the processed data to a digital twinborn platform through Apache Kafka so as to realize real-time monitoring and health assessment of the whole life cycle of the arch dam.

The invention relates to the technical field of safety intelligent monitoring of constructional engineering, and discloses a safety assessment and early warning method and system for a dangerous and large engineering project based on multi-source data. According to the multi-source data-based dangerous engineering project safety assessment early warning method, sensor data, video monitoring data, equipment operation data and environment data are subjected to quality assessment and standardization processing; real-time fusion of multi-source data is realized by adopting a weighted fusion technology; performing dimension reduction compression on the high-dimensional features through principal component analysis and independent component analysis, and compressing feature dimensions from hundreds of dimensions to dozens of dimensions; performing risk assessment by adopting a hybrid analysis method combining an expert rule and machine learning; rapid early warning response is realized through adaptive threshold adjustment, and system performance is continuously optimized through incremental learning. According to the method, high-precision and high-real-time safety assessment early warning can be realized under the condition of limited computing resources, and the safety management and control level of the dangerous engineering is effectively improved.

The invention relates to the technical field of gear box state evaluation, and discloses a vehicle gear box state evaluation method, which comprises the following steps: S1, collecting physical and chemical performance data of oil in a gear box; s2, preprocessing the collected data through an independent component analysis (ICA) method, and screening out a data set which can be used as model input; dividing the model input data set into a test data set and a training data set; s3, improving a RBMO (Red Blue Mark Optimization) algorithm, including initializing an RBMO population through a Latin hypercube sampling method to improve the population initialization uniformity; a spiral search strategy is introduced in the RBMO foraging stage, so that the red-mouth blue-streak search efficiency is improved; in the RBMO attack stage, a weight factor is introduced to optimize the position update of the red-beaked blue-streak, and an improved red-beaked blue-streak optimization algorithm IRBMO and the like are obtained; according to the method, the defect of blindness of parameter selection in the training process is overcome, and the prediction precision of the regression prediction model is improved.

The invention discloses a leakage monitoring method based on an LNG fuel gas system. The leakage monitoring method comprises the steps that a self-adaptive frequency modulation continuous wave active acoustic scanning network is established; blind source separation is carried out on mixed signals in acoustic scanning network abnormal events by adopting self-adaptive kernel independent component analysis; constructing a leakage feature mapping model of the physical information neural network; leakage source accurate positioning and quantification based on acoustic tomography and Bayesian reasoning are carried out; multi-modal decision fusion is carried out based on the multi-dimensional data sources received in parallel, a false alarm suppression mechanism is set, and time continuity verification and space consistency verification are carried out; establishing a reinforcement learning model for autonomously optimizing a monitoring strategy according to environment change and system state, and realizing adaptive optimization; the strategy network after self-adaptive optimization is deployed at the cloud, actions are generated regularly according to the current state, the actions are issued to the regional gateway and the edge node for execution, and iterative updating is carried out, so that the monitoring accuracy in a complex environment is improved, and the false alarm rate is reduced.

The invention discloses a phase modifier bearing fault diagnosis method, which belongs to the technical field of power equipment fault diagnosis, and comprises the following steps of: analyzing independent components, performing blind source separation on a received phase modifier bearing vibration signal, and extracting three types of independent source signals of impact, abrasion and noise; the gradient driving window length is self-adaptive, and the window length of short-time Fourier transform is dynamically adjusted based on the instantaneous frequency gradient of the independent source signal; wavelet packet frequency band energy screening: performing wavelet packet decomposition on the signal after window length adaptive processing, screening a fault characteristic frequency band based on an energy contribution rate, and reconstructing the signal; and enhancing stochastic resonance, and inputting the reconstructed signal into a stochastic resonance system. According to the method, independent component analysis, gradient driving window length self-adaption, wavelet packet frequency band energy screening and stochastic resonance enhanced fourth-order diagnosis chain are constructed, so that multi-stage cooperative processing of phase modifier bearing faults is realized, and the technical problems of time-frequency resolution contradiction, insufficient feature decoupling and weak generalization ability are effectively solved.