95 results about "Support vector machine classification" patented technology

The invention relates to the technical field of unmanned aerial vehicle detection, and discloses a common-aperture unmanned aerial vehicle detection method and system, and the method comprises the steps: obtaining multi-sensor original data and a state data set, and carrying out the standardization; in combination with the state data set, performing state updating and de-noising processing; if data missing or abnormal fluctuation is detected, filling and removing and time sequence storage are carried out, and a historical track sequence is formed; performing feature calculation to obtain a motion feature vector; classifying by using a support vector machine to obtain a target motion mode classification label; if the trajectory is an evasive type or an aggressive type, triggering a high-priority tracking process, and training by using a long-short-term memory network to obtain a predicted trajectory coordinate point set; unifying the coordinates to a global reference framework to obtain a global prediction trajectory, and calculating an intersection point of the global prediction trajectory and a preset no-fly zone to obtain an intersection detection result; generating a real-time alarm signal; and performing comprehensive threat assessment to obtain a threat target detection conclusion. According to the method, the threat assessment accuracy can be improved.

The invention provides an AI-based trachinotus ovatus juvenile fish culture water parasite prediction and prevention method and system, and the method comprises the steps: collecting multi-source data from a culture water body through a sensor array, including a nucleic acid signal, a fish school behavior track and an environment parameter sequence, and obtaining an original data set; unifying the data format and the acquisition frequency according to the original data set by adopting a time sequence alignment method, and obtaining an aligned feature flow; aiming at the aligned feature flow, applying a convolutional neural network to extract a space-time pattern of a nucleic acid signal and an abnormal index of a fish school behavior, and determining an extracted feature set; if the abnormal index in the extracted feature set exceeds a preset threshold value, a causal association between environmental parameters and parasitic risks is classified through a support vector machine, and a preliminary risk level is judged; simulating a water body change scene according to the comprehensive causal model to obtain a predicted trajectory of parasite propagation; and determining a quantitative score of the parasite risk and generating a prevention and control instruction sequence by comparing the predicted trajectory with the real-time monitoring data.

The invention relates to the technical field of laser cladding repair, and provides a positioning and clamping system and method for repairing the surface of a large working roll of a steel mill based on laser cladding, a three-field coupling prediction model of a temperature field, a stress field and a displacement field is established, and a partial least squares regression algorithm is combined with a Kalman filter to realize multi-step prospective prediction. According to the predicted thermal deformation, self-adaptive compensation control is implemented through a three-layer cascade compensation mechanism composed of a hydraulic drive, a piezoelectric ceramic driver and a laser head adjusting mechanism. The system adopts a time domain, frequency domain and time-frequency domain joint analysis method to extract vibration characteristics, vibration types are classified and identified through a support vector machine, and an active-passive hybrid suppression strategy is adopted for different vibration sources. High-precision positioning and stable clamping of the large working roller in the laser cladding repairing process are achieved, and the thickness uniformity and the surface quality of a cladding layer are remarkably improved.

The invention relates to the technical field of soil moisture content monitoring, and discloses a method and a system for accurately monitoring soil moisture content through remote sensing inversion of an unmanned aerial vehicle. Acquiring original spectral data of different soil types and environmental conditions through a spectral sensor to obtain an initial multispectral image data set; dividing soil types by using a support vector machine classification method according to pixel reflection characteristics to form a soil type grouping set; calculating a multispectral band reflectivity variance for each group, and screening candidate bands to construct a set; processing the candidate wave band set through a random forest regression model, adjusting the weight in combination with an environment variable, and performing iterative screening to form an optimized wave band combination sequence; extracting spectral features of the optimized wave band, and carrying out weighted fusion on the soil variation region to output a processed image; and calculating the soil moisture content by using a linear inversion model based on the pixel reflectivity of the processed image, and outputting a distribution diagram when the deviation reaches the standard. The method is suitable for different soil and environments, the wave band is accurately selected, the precision is improved, and high-quality data is provided for agricultural and environmental governance.

The invention discloses an equipment operation monitoring and fault diagnosis system based on multi-perception information fusion, and belongs to the technical field of equipment monitoring, and the system comprises the steps: collecting monitoring data in an equipment operation process, and carrying out the preprocessing of the monitoring data, so as to obtain monitoring processing data; obtaining an equipment fault label and corresponding monitoring processing data according to the historical equipment fault record; performing feature extraction on the monitoring processing data, and extracting feature parameters for reflecting the operation state of the equipment; calculating a mutual information value of each feature parameter and the fault tag by using a mutual information method, obtaining key features of which the mutual information values are greater than or equal to a key threshold value, and performing fusion through weighted summation according to a preset weight to form a multi-perception fusion feature; based on the multi-perception fusion features, fault diagnosis is carried out on the equipment by adopting a support vector machine classification algorithm, a diagnosis result is output, and finally the diagnosis result is displayed through a display and early warning module and an early warning signal is sent out.

The invention relates to the technical field of artificial intelligence, in particular to a pavement quality detection method and device based on artificial intelligence, and the method comprises the following steps: obtaining pavement images and load data, extracting crack boundary coordinates through edge detection, calculating a displacement difference to obtain crack distribution, calculating an extension rate in combination with time, and carrying out the weighted analysis of a direction difference. The method comprises the following steps: extracting crack boundary displacement difference, identifying defect evolution parameters, calculating stability and environmental sensitivity coefficients through cross coupling, judging degradation types in combination with load fluctuation, calculating defect grades through classification comparison threshold values of a support vector machine, and outputting a pavement overall quality result. Angle difference variation recognizes evolution direction difference, coupling extension rate and direction consistency depicts stability, environmental sensitivity and load fluctuation linkage calculation is introduced to present external action association, and grading is completed based on parameter and threshold difference to realize dynamic grading recognition of defect development rules.

The invention discloses a fruit and vegetable maturity inspection and classification method based on fruit and vegetable identification, and the method comprises the steps: collecting a fruit and vegetable RGB image and a near-infrared image through a high-definition camera and a near-infrared sensor, carrying out the preprocessing of denoising, enhancement, segmentation and the like, and extracting a fruit and vegetable region; extracting features such as colors, textures and shapes by using a pre-trained convolutional neural network, inputting the features into a support vector machine classification model, judging the maturity of the fruits and vegetables, and classifying the fruits and vegetables into immature fruits, mature fruits and over-mature fruits and vegetables. According to the invention, the method has a self-learning capability, can optimize the classification model through quality inspection feedback, improves the classification accuracy, and provides effective technical support for the quality control and management of fruits and vegetables.

The invention discloses an intelligent gas alarm method and system, and belongs to the technical field of gas safety monitoring. According to the method, multi-source sensing data of gas, flame, human body and valve states are integrated, and after missing value filling, abnormal value detection and correction, preprocessing of moving average filtering and feature extraction based on a fixed time window, the data are input into a support vector machine classification model for risk level identification and judgment; executing a multi-mode linkage control strategy according to the risk level, the valve state signal and the human body existence state signal; and anonymized feature data generated by the model and corresponding event tags are uploaded to a cloud end for incremental learning and model iterative updating based on weighted security performance indexes. According to the invention, multifunctional collaborative linkage and intelligent decision making are realized, the alarm threshold can be dynamically optimized, and the accuracy, environmental adaptability and long-term self-evolution capability of the system are remarkably improved.

The invention discloses a self-adaptive air pressure regulation and control system of quartz sand unpowered powder selecting equipment, and relates to the technical field of automatic control. According to the method, wind pressure and airflow disturbance signals are collected, a high-resolution map is generated through Hampel filtering and noise reduction, features are extracted through the convolutional neural network, key influence areas are identified, the problem of unstable wind pressure caused by airflow disturbance in a mountainous area is solved, and the particle separation precision is improved; a natural potential energy distribution matrix is constructed based on building floor height difference, velocity field reconstruction and airflow channel optimization are driven, technological parameters are adjusted in combination with a gradient descent algorithm, precise utilization of natural potential energy is achieved, energy consumption is reduced, uneven efficiency is improved, airflow distribution is simulated through a fluid dynamic model, and sedimentation behaviors are analyzed and predicted through particle trajectory. A support vector machine is used for classifying tracks and generating regulation and control instructions, PID control is used for stabilizing air pressure to form a closed loop, the problems that fine powder is mixed with coarse powder, coarse particles are left and the like are avoided, the equipment blockage risk is reduced, and the product purity stability is improved.

The invention relates to an English text auxiliary teaching method and system based on AI vision. The method comprises the following steps: collecting a dynamic eye movement track, a mouth shape change video stream and micro-expression time sequence data when a student reads, and generating a dynamic behavior feature vector by using a convolutional neural network; and carrying out multi-dimensional matching on the vector and a preset pronunciation standard model, accurately positioning a pronunciation deviation region and an understanding difficulty point, and carrying out classification by virtue of a support vector machine to obtain a learning state label. And extracting a high-frequency deviation mode from the tag, constructing a comprehensive behavior matrix through association of a clustering algorithm and an eye movement backtracking trajectory, calculating a teaching level evaluation value, finally predicting a learning trend and determining a resource allocation weight by combining historical evaluation data and adopting a linear regression model, and optimizing and generating a personalized teaching plan. By adopting the method, pronunciation deviation and understanding disorder in English reading can be accurately positioned, so that the resource allocation weight is adaptive to the individual learning track of students, and a data-driven technical path is provided for English personalized teaching.

The invention belongs to the technical field of wireless charging, and particularly discloses a method based on a magnetic resonance type wireless charging system, which comprises the following steps of: arranging a high-temperature-resistant micro temperature sensor and an array around a magnetic resonance coil curved surface to collect real-time temperature difference data, and integrating environmental noise signals as an initial multi-dimensional parameter set to obtain a preliminary temperature difference data set; according to the preliminary temperature difference data set, applying a support vector machine classification method to separate difference signals between curved surface regions, fusing preset coordinate points in a curved surface geometric parameter correlation model, and determining region sensitivity distribution characteristics; and by adopting a Kalman filtering algorithm, carrying out time sequence smoothing processing on the regional sensitivity distribution characteristics to calibrate offset caused by inaccurate matching of temperature difference data and curved surface geometry, and then obtaining calibrated sensitivity distribution. The invention aims to solve the problem that the influence of temperature distribution difference on frequency matching cannot be accurately identified and adapted under the dynamic temperature change of a complex curved surface coil in the prior art.

The invention relates to an intelligent diagnosis method and system for the health state of a wind turbine generator. The method comprises the following steps: acquiring multi-dimensional operation data including dynamic response, thermodynamic state, electrical parameters and environmental parameters, and constructing a multi-dimensional operation characteristic matrix; utilizing a pre-trained feature screening model based on an attention mechanism to calculate potential fault correlation features; based on a preset fault mode library, performing fault classification processing by adopting a support vector machine classification algorithm to obtain a potential fault mode; calculating a risk score of each fault mode according to a preset risk quantification rule; matching and optimizing the maintenance operation set from a preset maintenance rule base to form a wind power maintenance project; and determining a maintenance priority according to the risk score and generating a maintenance priority sequence. By adopting the method, accurate fault identification, risk quantification and maintenance decision intelligence of the wind turbine generator can be realized, and the operation and maintenance efficiency and the equipment reliability are improved.

The invention relates to a food multi-modal detection data fusion analysis method and device, equipment and a medium. The method comprises the following steps: acquiring original multi-source heterogeneous data of a food spectrum, an image and a smell, and performing normalization and noise reduction preprocessing to obtain a standardized feature set; classifying and screening high-correlation features by using a support vector machine, and generating a structured description; dynamic parameters are extracted, a quality trend vector is generated through time sequence analysis, a safety score is calculated, and a qualified mark is output if the safety score reaches the standard; constructing an extension index set based on the score, inputting a dynamic model to generate an authentication update link, and combining the block chain time to obtain new-version authentication; and associating the historical records to generate an initial report, and verifying and correcting to obtain an optimized report. By adopting the method, the consistency and availability of food safety data can be improved, the credibility of safety certification is enhanced, and a systematic and efficient solution is provided for food quality safety detection.

The invention relates to the technical field of data processing, in particular to a geological disaster occurrence trend prediction system based on historical data, which comprises an anomaly recognition module, a clustering labeling module, a stress partitioning module, a trend classification module and a disaster prediction module. According to the method, by introducing a multi-level abnormal data analysis and clustering technology, potential abnormal changes can be recognized more accurately when multi-dimensional data are processed, and therefore the problem that non-linear and dynamic changes of data are neglected in a traditional method is effectively solved. By calculating the difference of the multi-dimensional data, different stress partition areas can be distinguished, trend prediction is performed based on the characteristics of the areas, and the accuracy and timeliness of disaster prediction are remarkably improved. A support vector machine classification method is utilized to integrate focusing features and stress features, not only is the adaptability of a prediction model optimized, but also a prediction result can be adjusted according to real-time data, so that support with higher timeliness and reliability is provided for decision making.

The invention provides an online temperature control coordinated regulation and control method and system for diamond fretsaw electroplating baths, and relates to the technical field of process control over the temperature of the electroplating baths, and the method comprises the steps that the temperature of each electroplating bath and the flow rate of a plating solution are collected through a sensor, and the heat conduction strength is calculated in combination with the distance between the baths; determining a risk slot position according to the heat conduction intensity, marking the priority, and expanding to obtain an interfered slot position; packaging interference risk data through an instant sharing protocol, and transmitting and acquiring feedback information through a high-speed communication bus; correcting abnormal data, marking risk attributes to generate a temperature fluctuation vector, extracting peak value characteristics to obtain a production line wave and trend, and generating a linkage adjustment instruction sequence; kalman filtering is adopted to optimize instructions and distribute the instructions, and response delay is monitored; and if the delay exceeds the threshold value, classifying abnormal modes through a support vector machine to obtain a defect prediction label, and iteratively adjusting the current density and the pH value of the plating solution. The process defects caused by temperature fluctuation and delay are effectively avoided, and the stability of the electroplating process is guaranteed.

The invention relates to an intelligent newborn nursing system and method based on cry recognition. The system comprises a real-time data acquisition module for acquiring real-time sound, environment data and a surrounding image sequence of the newborn; the voiceprint anomaly judgment module filters the sound signals to extract features, classifies cry types through a support vector machine, and fuses environment data to generate an anomaly demand identifier; the image attitude decision-making module takes the identifier as a trigger, analyzes the image sequence to obtain abnormal attitude information of the newborn, and integrates related data to obtain an emergency demand comprehensive decision-making basis; the instruction iteration planning module generates a response instruction sequence based on the basis, combines execution feedback update parameters, fuses historical nursing data and a current deviation level, and generates a nursing execution plan containing dynamic execution opportunity, hierarchical monitoring nodes and an adaptive feedback period. According to the system, the problems that traditional nursing depends on manpower, response lags behind and the misjudgment rate is high are solved through cooperation of the modules, and continuous and accurate intelligent nursing is provided for newborns.

The invention relates to the technical field of 5G mobile communication networks, and discloses an intelligent control method and system for 5GMIFI equipment, and the method comprises the steps: collecting the real-time operation data of a plurality of pieces of 5GMIFI equipment through a sensor network, and carrying out the classification through a support vector machine, and obtaining an equipment state set; analyzing signal overlapping areas of adjacent equipment to evaluate interference risks; in combination with the interference risk and the real-time network load, determining a load unbalanced equipment group by using K-means clustering; group spectrum features are extracted and compared with historical data, and a channel allocation scheme needing to be optimized is determined; selecting a low-interference channel and obtaining a power parameter to obtain initial power optimization configuration; simulating network environment change, and predicting a stability index by using a support vector machine to determine a final power adjustment value; and applying the adjustment value and evaluating the network efficiency improvement degree, and if the threshold value is not reached, performing iterative optimization. The method can improve the equipment state sensing accuracy, reduce the interference risk, dynamically adapt to the network change, and guarantee the stable operation of the equipment group.

The invention relates to a cable tunnel fire thin smoke image recognition and risk assessment method and system, and belongs to the technical field of power equipment on-line monitoring and fault diagnosis, and the method comprises the following steps: carrying out the real-time image collection of a cable tunnel, and employing a contrast limited adaptive histogram equalization algorithm to enhance the local contrast of an image; a pre-trained YOLOv11n-seg instance segmentation model is used to identify the enhanced image, a thin smoke area is accurately segmented, and a mask file is generated; and calculating the smoke coverage area based on the mask file, calculating the smoke rising dip angle by adopting a minimum circumscribed triangle algorithm, and calculating the smoke transmissivity according to the Lambert-Beer law. And inputting a feature vector formed by the three feature parameters into a support vector machine classification model trained by historical data, and automatically outputting a fire hazard level judgment result, thereby realizing early accurate early warning of the tunnel fire.

The invention relates to the technical field of gas extraction pipeline leakage detection, and discloses a gas extraction pipeline leakage detection method based on an optical fiber sensing technology, and the method comprises the following steps: synchronously collecting data, and constructing a standardized monitoring matrix through denoising and space-time alignment; extracting space gradient and frequency domain energy characteristics, and screening thermal and dynamic abnormal regions; a multi-dimensional feature vector is constructed, classification model mapping is input, and a leakage judgment result is generated; extracting position information, performing double-source verification on a thermal dynamic abnormal center, and generating a final leakage coordinate; and generating an alarm based on the result and the coordinates, and constructing a control instruction to drive pipeline parameter adjustment. According to the method, distributed temperature and acoustic data are synchronously collected, a standardized monitoring matrix is constructed, multi-dimensional feature fusion judgment is carried out by utilizing spatial gradient features of the temperature data and frequency domain energy features of the acoustic data, and thermal dynamic coupling feature analysis is carried out based on a support vector machine classification model; and the real leakage signal and the background environment noise can be effectively distinguished.

This invention relates to the field of process monitoring technology, and more particularly to a method for early warning of drift in injection molding process parameters based on support vector machines. The method includes: acquiring baseline parameters for each process parameter and measured values ​​of each process parameter in the current injection cycle; calculating the standard deviation based on the baseline parameters; obtaining the positive and negative cumulative amounts through two-sided recursion and determining the dominant direction; further calculating the mean vector norm of the standard deviation within a preset window to obtain the centroid distance; calculating the synchronous growth rate using the baseline coupling degree and the dominant direction; concatenating the positive and negative cumulative amounts, centroid distance, and synchronous growth rate into an enhanced feature; inputting this feature into a preset support vector machine classification model for judgment; and issuing an early warning command in response to a drift state. This invention achieves automatic, real-time early warning of gradual drift in injection molding process parameters.

The application provides an electrical equipment operation state monitoring method, which comprises the following steps: preprocessing collected voltage and current data to remove noise, determining working condition distribution mode by using a clustering algorithm and dynamically adjusting a reference standard, combining Euclidean distance matching with support vector machine classification training to construct a state classification model, and finally realizing accurate judgment on short-term fluctuation data and normal state output, and updating a database to form a cyclic optimization framework. Through the construction of a dynamic reference standard and the high confidence judgment of the classification model, the accuracy and adaptability of the equipment state monitoring are ensured, the reliability and real-time performance of the operation state evaluation are significantly improved, and technical support is provided for the safe and stable operation of the electrical equipment.

The invention is suitable for the technical field of power equipment detection, and provides a power cable damage detection device and method.The method comprises the steps that firstly, a self-adaptive multi-frequency excitation signal is adopted to scan a to-be-detected cable, and a capacitance-frequency characteristic array of the to-be-detected cable is obtained; secondly, carrying out preprocessing and weighted selection on the obtained feature data; and then, inputting the processed features into an improved support vector machine classification model for damage identification. According to the method, the decision function and the kernel function of the SVM are optimized in a targeted manner, so that the method is more suitable for a cable damage small sample and nonlinear detection scene, similarity measurement based on capacitance characteristics is introduced into the kernel function, and the training of the decision function preferentially selects the support vector with remarkable capacitance change. According to the method, the problems of low accuracy and weak generalization ability of a traditional method in waste cable damage detection are effectively solved, efficient and accurate identification of the cable damage state and type is realized, and the cable recycling rate is remarkably improved.

The invention discloses a water environment micro-plastic content rapid detection technology based on spectrum identification, and the method comprises the steps: carrying out the filtering and drying pretreatment of a sample, collecting the spectrum of the sample through ATR-FTIR, carrying out the baseline correction, smoothing and SNV transformation of the spectrum, extracting a polymer feature fingerprint spectrum interval, constructing and optimizing a support vector machine classification model, and carrying out the rapid detection of the micro-plastic content in the water environment. And finally, performing automatic qualitative identification on the type of the micro-plastic polymer by using the model, and performing quantitative analysis based on a correction curve. According to the invention, through a machine learning identification model, the whole-process rapid and automatic detection of micro-plastics in a water environment from a sample to an analysis result is realized, the defects of tedious pretreatment, strong subjectivity of artificial identification and inaccurate quantification of a traditional method are overcome, single-sample detection can be completed within one hour, and the method has high-throughput screening capability.

The invention belongs to the technical field of deepwater oil and gas field drilling gas cut monitoring, and particularly relates to a deepwater drilling gas cut monitoring method. According to the monitoring method, nonlinear dynamic characteristics of ultrasonic signals are extracted through multi-scale fuzzy divergence entropy, and a gas content value is obtained based on inversion of a support vector machine model subjected to sample training, so that quantitative monitoring and early warning of tiny changes of the gas content are realized; compared with an existing deepwater drilling gas cut monitoring method, the method has the remarkable advantages in the aspects of monitoring precision, dynamic response characteristics, noise interference resistance and the like, and accurate recognition and real-time quantitative monitoring of early weak gas cut signals can be achieved. A deepwater drilling gas cut monitoring method comprises the following steps that ultrasonic echo signals of gas-liquid two-phase flow are collected; extracting a multi-scale fuzzy divergence entropy value in the ultrasonic echo signal; and inputting a feature vector in the multi-scale fuzzy divergence entropy into the trained support vector machine classification model to obtain a gas content recognition result.

The invention relates to the technical field of data processing, in particular to a mining area geological information comprehensive analysis method and system based on data integration, and the method comprises the steps: obtaining and preprocessing multi-source geological data, carrying out the feature correlation analysis and normalization, and obtaining a standardized data set; classifying the magnetic anomaly and gravity anomaly data through a support vector machine to generate a fluid dynamic classification result; performing interpolation processing on the classification result to generate continuous fluid dynamic data, and analyzing the speed and direction change of the fluid to generate a permeability distribution diagram; extracting an abnormal region according to the dynamic change trend, matching the abnormal region with historical data, marking geological abnormal points and generating an abnormal distribution diagram; according to the geological flow monitoring report, the underground water body type or the change of the oil-gas mixing proportion is judged, a pressure fluctuation mode is recognized, and a refined geological abnormal point distribution diagram is generated. According to the invention, mining area resource management and potential risk early warning can be effectively supported.

The invention provides a hyperspectrum-based citrus leaf lesion diagnosis system and a hyperspectrum-based citrus leaf lesion diagnosis method, and the hyperspectrum-based citrus leaf lesion diagnosis system and the hyperspectrum-based citrus leaf lesion diagnosis method disclosed by the invention have the advantages that on the basis of analyzing hyperspectral imaging data of citrus leaves without diseases, lack of nutrients, black spots and yellow shoot; three parameters of yellow wave band reflectivity, infrared wave band slope and inflection point wavelength are used as characteristic quantities, and classification of four types of blades is realized by applying a support vector machine (RBF-SVM) classification model based on a Gaussian radial basis kernel function. The method solves the problems that when citrus tree disease information is detected through a field detection method at present, long-time observation with eyes is needed, subjective judgment of observers is depended, and misjudgment is likely to be caused; according to the present invention, the problem that the citrus tree disease information detection by using the chemical detection method needs the special person to detect by using the professional equipment so as not to accurately and rapidly detect each production stage of the citrus tree can be solved, and the citrus leaf disease can be rapidly and accurately diagnosed.

The application discloses a kind of intelligent detection methods for weld defects of stainless steel composite straight welded pipe, belong to nondestructive intelligent detection technical field.The method includes: establishing longitudinal space coordinate axis mapped with the length direction of weld;Synchronous acquisition of phased array ultrasonic fan-shaped scanning reflected echo signal and pulse eddy current induced eddy current attenuation curve, respectively extract interface reflection peak amplitude and decay time constant;Equivalent thickness of coating is calculated using decay time constant, and after comparing with nominal thickness, the receiving gain of phased array ultrasonic is dynamically adjusted, and the acoustic characteristics after compensation are output;The compensated acoustic characteristics and electromagnetic attenuation characteristics are input into the fusion judgment model to identify the defect category and spatial position.The application calibrates ultrasonic gain in real time through pulse eddy current, eliminates heterogeneous interface acoustic impedance mismatch interference, combines multimodal characteristics and support vector machine classification, realizes weld defect detection in full thickness range, reduces false defect alarm rate, and is suitable for online automatic detection.

The invention provides a rotating machine fault diagnosis method based on divergence entropy and a frequency domain Gramer angle field, and belongs to the field of rotating machine fault diagnosis. Rotating machine fault vibration signals are obtained, the divergence entropy value of an intrinsic mode component of an original signal is calculated under the condition that the global complexity of original information is considered, and the frequency domain Gramer angle field is calculated; taking the intrinsic mode component corresponding to the minimum divergence entropy as a signal noise reduction result; and calculating a frequency domain Greem angle field of the intrinsic mode component corresponding to the minimum divergence entropy, extracting a direction gradient matrix for support vector machine classification, and showing high accuracy of rotating machine fault diagnosis through a comparison result of a prediction class and a real class. According to the method, the divergence entropy and the frequency domain Gramer angle field are combined to carry out rotating machine fault diagnosis, and a diagnosis result with high accuracy can be provided for the rotating machine fault.

This invention discloses a radar target classification method and apparatus based on time-frequency feature fusion. In this method, radar echo signals are acquired and preprocessed to obtain multiple frames of target signals. Based on pre-defined micro-Doppler physical models for different target types, time-frequency analysis is performed on the multiple frames of target signals to extract multi-dimensional feature vectors containing micro-Doppler features. Target types include pedestrians, motorcycles, cars, and buses. Variance analysis is used to select features from the multi-dimensional feature vectors, retaining a pre-defined number of key features with the strongest discriminative power to form optimized feature vectors. The optimized feature vectors are then input into a pre-trained support vector machine classification model to obtain the target classification result. This invention achieves accurate and rapid identification of millimeter-wave radar targets through precise micro-Doppler physical modeling and multi-dimensional feature fusion, improving the accuracy and robustness of target classification in complex environments.

The present application belongs to the technical field of gas invasion monitoring of deepwater oil and gas field drilling, and particularly relates to a deepwater drilling gas invasion monitoring method. The monitoring method extracts the nonlinear dynamic characteristics of ultrasonic signals through multi-scale fuzzy divergence entropy, and obtains the gas holdup value based on the support vector machine model trained by samples, thereby realizing quantitative monitoring and early warning of the small change of gas holdup. Compared with the existing deepwater drilling gas invasion monitoring method, the present method has significant advantages in monitoring accuracy, dynamic response characteristics and anti-noise interference performance, and can realize accurate identification and real-time quantitative monitoring of early weak gas invasion signal. A deepwater drilling gas invasion monitoring method comprises the following steps: collecting ultrasonic echo signals of gas-liquid two-phase flow; extracting multi-scale fuzzy divergence entropy values in the ultrasonic echo signals; inputting the feature vectors in the multi-scale fuzzy divergence entropy values into the trained support vector machine classification model to obtain the gas holdup recognition result.