55 results about "Support vector machine classifier" patented technology

The invention relates to the technical field of high-voltage circuit breaker fault diagnosis, and discloses a multi-feature optimization fusion high-voltage circuit breaker fault diagnosis method. The method comprises the following steps: adaptively optimizing variational mode decomposition parameters by adopting a particle swarm optimization algorithm, and accurately decomposing an original vibration signal; performing noise dominant and fault feature dominant classification on the intrinsic mode function based on permutation entropy; aiming at the two types of modes, respectively taking signal-to-noise ratio maximization and kurtosis maximization as targets, and implementing differential wavelet threshold denoising; after reconstructing the signal, extracting an energy entropy, a singular value entropy and a power spectrum entropy to form a multi-dimensional feature vector; and inputting the data into a support vector machine classifier subjected to particle swarm optimization hyper-parameter for state diagnosis. According to the invention, through full-chain collaborative optimization, the accuracy and robustness of fault diagnosis in a strong noise environment are significantly improved.

The invention provides a method for measuring surface defects of automobile stamping parts by laser scanning, and belongs to the technical field of part surface defect detection.The method includes the steps that a high-curvature area and a low-curvature area are marked, a self-adaptive viewpoint planning path is constructed based on curvature distribution, dense sampling is adopted in the high-curvature area, and the low-curvature area is marked; a laser scanning device is driven to collect three-dimensional point cloud data, anisotropic thermal diffusion defect enhancement processing is performed on point cloud, a sliding window is adopted to calculate a multi-scale box counting fractal dimension to generate a fractal dimension field distribution diagram, a suspected defect area with the fractal dimension deviating from a normal reference value is identified, and a composite feature vector is extracted; a support vector machine classifier is input to judge a real defect, a defect depth value is corrected by adopting multispectral illumination to measure a bidirectional reflection distribution function parameter and combining with a phase measurement profilometry aiming at the condition of a large incident angle, a defect distribution diagram marked with defect information is generated, and the problem of low surface defect detection precision of a high-curvature area is solved.

The invention discloses a multi-modal data fusion and fault diagnosis method, and belongs to the field of transformer partial discharge fault diagnosis. According to the method, for the problems of false alarm and missing alarm caused by data isolation and lack of effective integration in partial discharge diagnosis of the transformer, acoustic, infrared and visible light multi-mode data are synchronously collected, pixel-level space alignment is carried out based on feature point matching, time sequence synchronization is achieved through hardware trigger signals, and the fault diagnosis accuracy is improved. Multi-level fusion diagnosis of a data layer, a feature layer and a decision-making layer is adopted, including channel superposition to form a fusion diagnosis image, voiceprint features, temperature rise features and arc light or corona features are extracted and input into a feature fusion model to obtain an associated feature vector, decision fusion is performed through a support vector machine classifier and a D-S evidence theory, and a decision-making result is obtained. And outputting a final diagnosis conclusion, thereby realizing accurate and reliable diagnosis of the partial discharge fault of the transformer.

The invention discloses a battery mechanical damage monitoring method and system in the transportation process of an electric vehicle based on acoustic emission spectrum analysis, and the method comprises the steps: carrying out the multi-scale decomposition of an original signal sequence through wavelet transform, separating out a high-frequency transient component and low-frequency background noise, and obtaining a denoised elastic wave signal; calculating time domain features including peak amplitude and duration according to the denoised elastic wave signal, and combining frequency domain features such as a main frequency component to obtain a comprehensive feature vector; if the peak amplitude of the comprehensive feature vector exceeds a preset threshold value, judging that the event is a potential damage event, and extracting a damage related subset from the feature vector to obtain a damage candidate feature; training the damage candidate features through a support vector machine classifier to obtain damage type labels; and aiming at the damage type label fusion transportation environment data, a sliding window is adopted to analyze and track the signal change trend, and the damage evolution degree is determined. According to the invention, accurate identification, classification and dynamic monitoring of transportation damage of the battery pack are realized.

The invention relates to the technical field of optical fiber sensing, in particular to an OTDR event analysis method and system, electronic equipment and a storage medium. The method comprises the following steps: carrying out de-noising processing on an OTDR original curve to obtain an OTDR curve; acquiring a local curve segment corresponding to each sampling point in the OTDR curve, calculating a local slope value and acquiring a jitter degree; setting a compensation value according to the jitter degree, and constructing a dynamic threshold interval corresponding to the local curve segment based on the compensation value and a preset optical fiber loss value; when the local slope value exceeds the dynamic threshold interval, determining a suspected event starting point from the local curve segment; in the OTDR curve, obtaining a suspected event curve segment by combining the suspected event starting point with a preset length; and performing discrete Fourier transform and normalization processing on the suspected event curve segment to obtain a corresponding frequency domain normalization sequence and obtain corresponding statistical characteristics, and inputting the statistical characteristics into a pre-trained support vector machine classifier to obtain an event analysis result. The method and the device are used for improving the accuracy of OTDR event analysis.

The invention provides an enterprise supply chain financial risk prediction method fusing a dynamic knowledge graph and a graph neural network. The method comprises the steps of multi-source data loading and preprocessing, supply chain knowledge graph construction, financial feature extraction, risk label generation and the like. Aiming at the problems that multi-subject information of core enterprises, suppliers, customers and the like in supply chain data is dispersed and is inconsistent with independent financial data structures, the method solves the problems that manual integration is low in efficiency and prone to errors through automatic data cleaning, entity matching and relation mapping, and a unified and structured enterprise supply chain relation knowledge graph is constructed; the limitation of manually designing network features is overcome by utilizing a graph attention network; an effective feature fusion strategy is designed, and joint feature representation with higher discriminative force is formed; and constructing an end-to-end evaluation framework, training classifiers such as a support vector machine to learn the fusion features, realizing accurate and stable classification of high-risk and low-risk enterprises, and providing probability output to enhance result interpretability and decision support capability.

This invention discloses a clutter discrimination and suppression method based on multiple echo features, comprising: acquiring radar front-end clutter and target echo detection video data and dividing it into several connected regions; extracting multi-dimensional features and labeling prior information for each connected region; using the Relief feature selection algorithm to calculate and filter the weights of the multi-dimensional features, removing redundant features to obtain the optimal feature vector; using this feature vector to train a support vector machine classifier, and obtaining the optimal parameter model through cross-validation; acquiring measured clutter data, extracting corresponding features and inputting them into the model; and determining whether to remove clutter and retain targets based on the output. This invention effectively filters out dynamic clutter spots, avoids false deletion of weak targets, significantly reduces the false alarm rate of the system, and alleviates the computational burden of subsequent track processing.

The invention discloses a steel pipe defect detection method based on artificial intelligence, and belongs to the technical field of pipe detection, and the method comprises the following steps: S1, obtaining original data from a steel pipe surface image, extracting initial features through a convolutional neural network, and generating a first feature set; s2, aiming at the first feature set, adopting an adaptive threshold segmentation algorithm to generate a second feature set; s3, according to the second feature set, performing preliminary division on the defect region through a region growing algorithm to obtain a plurality of defect region images; s4, extracting local texture features of each defect area image, and generating a third feature set corresponding to each defect area image; and S5, for the third feature set, performing defect type classification by adopting a pre-trained support vector machine classifier to obtain a defect type classification result. The steel pipe defect detection method based on artificial intelligence solves the problem that the precision and robustness of current steel pipe surface defect detection are difficult to improve.

This invention discloses a method and system for monitoring mechanical damage to batteries during electric vehicle transportation based on acoustic emission spectrum analysis. The method includes: performing multi-scale decomposition of the original signal sequence using wavelet transform to separate high-frequency transient components and low-frequency background noise, obtaining a denoised elastic wave signal; calculating time-domain features, including peak amplitude and duration, based on the denoised elastic wave signal, and combining this with frequency-domain features such as the dominant frequency component to obtain a comprehensive feature vector; if the peak amplitude of the comprehensive feature vector exceeds a preset threshold, it is judged as a potential damage event, and damage-related subsets are extracted from the feature vector to obtain damage candidate features; training the damage candidate features using a support vector machine classifier to obtain damage type labels; and fusing transportation environment data with the damage type labels, using sliding window analysis to track signal change trends and determine the degree of damage evolution. This invention achieves accurate identification, classification, and dynamic monitoring of battery pack transportation damage.

The application provides an enhanced hyperspectral framework method for storing medicinal plant pest classification, comprising: the framework collects near-infrared hyperspectral images of medicinal plant samples, and constructs a dataset containing healthy level, mild infestation level and severe infestation level through controlled artificial infestation to obtain real spectral data as a basis; the framework adopts a Wasserstein generative adversarial network model with gradient penalty to enhance the real spectral data, generate synthetic spectral data to balance the class distribution and increase the sample diversity, wherein the model ensures the fidelity of the generated data through adversarial training; and the framework applies a convolutional neural network classifier, a support vector machine classifier and a random forest classifier based on the enhanced dataset for pest classification, wherein the convolutional neural network classifier achieves the best performance and realizes the accuracy improvement.

The invention relates to an InSAR interferogram quality discrimination method based on deep learning, and the method comprises the steps: carrying out the preliminary decomposition of an InSAR interferogram through a multi-scale wavelet transform method, and carrying out the feature extraction, and obtaining a nonlinear feature vector; carrying out deep learning processing on the nonlinear feature vector by adopting a convolutional neural network to obtain interference weight distribution under multi-factor coupling; based on the interference weight distribution, obtaining superposition influence parameters of topographic relief and atmospheric interference, and determining a quantization level of deviation increase; and performing pattern recognition on the quantization level with the increased deviation through a support vector machine classifier to obtain a stable and corresponding quality judgment result. According to the method, the quality judgment accuracy, stability and robustness under the complex terrain and the atmospheric environment are remarkably improved, the reliability of geological disaster early warning is enhanced, and the method has important practical value.

This invention relates to the field of automotive parts processing technology, and discloses an automatic feeding control method and system for an automotive parts electrophoresis line based on multiple sensors. The method includes: acquiring initial multi-source data through a sensor matrix; preprocessing the data to obtain a refined feature vector; acquiring feeding deviation values; if the feeding deviation exceeds a threshold, generating a feeding deviation signal; using a support vector machine classifier to classify and predict the set of deviation signal intensity indicators to obtain a classification result of the deviation factors; mapping the classification result to a control strategy library to match dynamic adaptation rules and obtain feeding parameter correction values; if environmental changes dominate the deviation, calculating a first adjustment coefficient using temperature compensation; performing a secondary calibration of the correction value based on the convergence result to generate a feeding command; updating system parameters and determining whether the deviation has been eliminated; and updating model parameters to obtain updated data acquisition rules. This method can achieve accurate identification and real-time correction of feeding deviations, improving control accuracy.

The application belongs to the technical field of image processing, and particularly relates to a UV ink curing degree detection method and system based on texture analysis, which comprises the following steps: collecting an original gray-scale image of a UV ink surface, constructing a local illumination saturation index positioning mirror reflection dominant area, and combining a texture optical masking coefficient to obtain an adaptive texture recovery gain; performing weighted processing on the gray-scale value and high-frequency component of the original gray-scale image by using the local illumination saturation index and the adaptive texture recovery gain respectively, extracting macroscopic statistics and microscopic structure features of a reconstructed image to construct a multi-dimensional texture feature vector; inputting the multi-dimensional texture feature vector into a support vector machine classifier to obtain a curing state, and generating a control signal according to the curing state. The application improves the extraction effect of weak texture features under strong light interference, and provides technical support for closed-loop control of the curing process.

The present application relates to the technical field of fault detection, and relates to a relay contact fault identification method based on wavelet denoising and a support vector machine, comprising the following steps: S1, constructing a current signal acquisition and double-channel reconstruction circuit: a Rogowski coil is sleeved on an output loop of a relay contact, and a differential voltage signal is inducted and output by the Rogowski coil; S2, respectively adopting a first wavelet base and a second wavelet base to perform multi-scale wavelet decomposition, threshold denoising and wavelet reconstruction on a complete current digital sequence and a transient current digital sequence; S3, extracting time domain statistical features from the complete current digital sequence after denoising, extracting time-frequency energy features from the transient current digital sequence after denoising, and outputting a fault category of the relay contact after classification and decision by a support vector machine classifier. The present application overcomes the inherent contradiction that a single acquisition channel is difficult to simultaneously consider slow-changing contact components and transient disturbance components in terms of dynamic range and denoising strategy.

The invention relates to the technical field of optical detection, in particular to an electronic cigarette shell detection method and system based on machine vision and a storage medium, and the method comprises the steps: 1, setting an image collection environment; 2, carrying out image preprocessing on the original image set; 3, extracting a multi-scale feature vector from the preprocessed image set; step 4, classifying the multi-scale feature vectors by using a pre-trained support vector machine classifier, wherein the support vector machine classifier performs training by collecting electronic cigarette shell image data and manually marking defect types; and step 5, outputting a defect detection result to a production line control system for automatically sorting defective products, and collecting images and feature vector data in the detection process for updating the support vector machine classifier model. And through automatic and accurate machine vision detection, the efficiency of a production line is improved, and the manual detection cost is greatly reduced.

The invention provides a crop variety classification method, device and equipment based on single nucleotide polymorphism, and relates to the technical field of crop analys.The method comprises the steps that gene sequencing is conducted on target crop samples for the target crop samples, and high-confidence-coefficient gene sequence data corresponding to the target crop samples are obtained; determining a target map corresponding to the target crop sample based on the high-confidence gene sequence data; inputting the target map into a convolutional neural network model to obtain a map vector corresponding to a target crop sample output by the convolutional neural network model; and inputting the atlas vector into a support vector machine classifier to obtain an identification result of the target crop sample output by the support vector machine classifier. According to the technical scheme, the gene sequence of the crop sample is converted into the map form, the difference between crop varieties can be visually recognized, high-efficiency and high-precision crop variety classification can be carried out without depending on professionals, and the cost is saved to a large extent.

The invention discloses a fault detection method for oil gas recovery processing equipment by a compression condensation membrane separation method, and relates to the technical field of oil gas recovery processing, which comprises the following steps of: 1, continuously collecting multi-parameter data during operation of the oil gas recovery processing equipment through a plurality of sensors, the multi-parameter data at least comprise power supply voltage, temperature, pressure, flow, liquid level and vibration acceleration; and step 2, inputting the acquired multi-parameter data into a fault detection system. According to the method and the device, the multi-parameter state estimation is carried out based on the extended Kalman filtering algorithm, and the Mahalanobis distance of the residual error is calculated, so that the early and accurate detection of the abnormal operation of the equipment is realized; in combination with a support vector machine classifier, multiple fault types can be quickly distinguished; and on the basis of a finite-state machine model, corresponding optimization strategies such as nonlinear PID adjustment and model prediction control or safety interlocking protection measures are automatically executed according to different fault types, so that the accuracy and the real-time performance of fault detection and the automation level of the system are remarkably improved.

The application relates to an improved oil and gas pipeline information-physical fusion system leakage detection method of a 1DCNN, which comprises the following steps: acquiring oil and gas pipeline data through a sound wave sensor in an oil and gas pipeline information-physical fusion system and uploading the data to a system cloud; constructing a one-dimensional convolutional neural network (1DCNN) pipeline leakage detection model by adjusting a network structure and parameters; constructing a 1DCNN-TSNE-SVM model, extracting features of each layer of the 1DCNN network, performing feature fusion, performing dimension reduction on the features through a TSNE algorithm, and performing classification and identification through a support vector machine (SVM) classifier optimized through a particle swarm optimization (PSO) algorithm; downloading various pipeline signals from the system cloud to construct training samples and test samples, training and testing the model, and monitoring pipeline abnormal conditions in real time. The application can accurately find pipeline leakage and timely alarm, thereby reducing economic losses.

The invention discloses a social fraud early warning method and system based on voice emotion mutation detection, and the method comprises the steps: carrying out the preprocessing of a voice signal collected in real time, and extracting an initial acoustic feature through a Mel-frequency cepstrum coefficient method; calculating rhythm features through the acoustic feature vectors in combination with speech speed and pause indexes, and analyzing changes in a time window to obtain a dynamic feature sequence fusing acoustics and rhythm; inputting the dynamic feature sequence into a long-short-term memory network for time sequence modeling to obtain an emotion dynamic change trend vector; comparing the emotion dynamic change trend vector with a preset normal emotion baseline to obtain a preliminary abnormal emotion tag; verifying the preliminary abnormal emotion label in combination with dialogue context semantic features, and processing joint input of the label and semantics by adopting a support vector machine classifier to obtain a fraud risk score; and inputting the fraud risk score into a decision module, and when the score is higher than a warning threshold, triggering an early warning signal to obtain a fraud abnormity confirmation result.

The invention provides a malicious communication behavior detection method and system in encrypted traffic, and belongs to the technical field of network security. The method comprises the following steps: acquiring historical encrypted traffic, screening normal communication traffic samples, and constructing a normal communication behavior model; and training the model by using a support vector machine classifier. And then collecting a real-time encrypted traffic data packet sequence, extracting a feature vector set, inputting the feature vector set into the trained classification model, quantifying the deviation degree with a normal communication sample, screening out abnormal traffic exceeding a preset threshold value, and forming an abnormal traffic set. Key abnormal indexes such as the data packet sending and receiving rate difference ratio and the data packet size standard deviation are determined based on the set, and if any index exceeds the standard, the malicious communication behavior is judged. In this way, high-concealment malicious behaviors can be accurately recognized without decryption, normal communication and malicious communication are effectively distinguished, and zero-trust chain collapse is avoided.

The invention relates to a line fault reason intelligent identification method based on a recording waveform image, and the method comprises the steps: carrying out the feature extraction of a fault waveform image through employing a scale invariant feature transform (SIFT) feature extraction method, and mining key feature information in the fault waveform image; a clustering method (K-means) is utilized to classify similar feature descriptors according to clusters to form a visual dictionary, and on this basis, an image pyramid technology is utilized to realize multi-scale feature fusion of image vectors; and a support vector machine (SVM) classifier is introduced, and vectorized image features are utilized to carry out accurate identification on fault causes. The line fault reason identification model constructed by the invention can effectively predict various power grid line fault reasons, and improves the accuracy and timeliness of fault reason identification; good robustness is shown in an actual case test, and generalization performance and stability of the model are ensured through cross validation and monitoring of model performance indexes; and powerful support is provided for fault diagnosis and maintenance of a power system.

The present application relates to the technical field of machine vision, in particular to a multi-angle license plate image automatic recognition processing system and method, electronic equipment and storage medium, the method comprising: acquiring multi-angle license plate images, using an adaptive threshold segmentation algorithm to perform binary processing on the images and extract license plate contours; using perspective transformation to correct license plate contour images at different angles; extracting local binary pattern features and HSV color histogram features of the corrected license plate contour images, using a support vector machine (SVM) classifier to cut the license plate character regions, correcting the cutting results according to the license plate character arrangement rules to obtain accurate character cutting images, building a multi-layer convolutional neural network, inputting the cut character images into the network for recognition and classification, and mapping and outputting license plate number information. The present application comprehensively utilizes image processing, machine learning and deep learning technologies, and comprehensively improves the accuracy and robustness of license plate recognition, and has a broad application prospect.

The application relates to a method for monitoring the state of health of a battery of an uninterruptible power supply, comprising: collecting an infrared image and basic attribute data of the battery of the uninterruptible power supply; performing wavelet packet transformation on voltage and current data in the basic attribute data to generate a time domain graph, and fusing the infrared image; inputting the fused image and the basic attribute data into a bypass free attention classifier and a support vector machine classifier based on active learning for training, and outputting classification results; inputting the classification results of the bypass free attention classifier and the support vector machine classifier based on active learning into a multi-modal fusion classifier for fusion prediction; testing the multi-modal fusion classifier with a test set, taking the multi-modal fusion classifier meeting performance requirements as a real-time battery state of health monitoring deployment model configured by the uninterruptible power supply; obtaining a final battery state of health prediction, and also providing an uninterruptible power supply battery state of health monitoring system using the above method.

The application provides a fine blanking equipment monitoring method and system based on fiber grating sensing and machine learning, and relates to the field of fine blanking equipment monitoring.The method steps include laying fiber grating sensors on the slider of a fine blanking machine, and collecting strain data of the slider in real time;preprocessing the strain data to remove noise and nonlinear trends in the strain data;based on minimum value point detection, splitting the strain data from multi-stroke data into single-stroke data, dividing each single-stroke data into data of four stages of fast forward, detection, fine blanking, and fast reverse, and saving to an array;calculating time domain feature parameters of the data in each stage of the array, setting classification labels for the four stages respectively, and constructing a training data set;training a support vector machine classifier based on the training data set to obtain a stage recognition model;and building a visual interface to display real-time data monitoring data of the stage recognition model and perform fault early warning.

The invention discloses a respiratory virus inactivation data-driven modeling prediction control method, which relates to the technical field of biological medicine, and comprises the following steps: acquiring initial virus characteristic data from a virus surface structure database through molecular dynamics simulation, and processing to obtain a structure change matrix of viruses under different inactivation conditions; performing feature extraction on virus characteristics and antibody binding sites by adopting a support vector machine classifier according to the structure change matrix, and determining a potential unexpected interaction site set; according to the respiratory virus inactivation data-driven modeling prediction control method, the scientificity and stability of inactivation process parameter determination are effectively improved, the safety risk caused by improper inactivation conditions is reduced, the process optimization period is shortened, the experiment cost is reduced, the good immune effectiveness is maintained while the virus inactivation safety is guaranteed, and the method is suitable for popularization and application. Therefore, the practical application requirements in vaccine research and development and virus prevention and control can be better met.

The invention relates to the technical field of power equipment monitoring, and particularly discloses a transformer voiceprint fault recognition method fusing multi-scale fractal dimensions and permutation entropy, and the method comprises the steps: obtaining a voiceprint data set of a transformer; based on the voiceprint data set, determining the frequency domain feature of the multi-scale fractal dimension of the voiceprint signal and the time domain feature of the multi-scale permutation entropy of the voiceprint signal; fusing the frequency domain features of the multi-scale fractal dimensions and the time domain features of the multi-scale permutation entropy of the same scale, and constructing a feature matrix with equivalent frequency alignment; classifying the fused feature matrix by adopting a multi-binary classification support vector machine classifier to obtain a recognition result of the typical fault of the transformer; according to the method, the complexity characteristics of the voiceprint signal under multiple scales and multiple dimensions can be fully mined, the identification degree of multiple types of fault characteristics is improved, and the method has high precision performance in multiple types of fault identification, has better robustness and cross-domain generalization ability, and has better stability and reliability in a complex environment.

The invention provides a pig feed fermentation process state analysis method based on image recognition, and the method comprises the steps: collecting a plurality of frames of fermentation images, generating a morphological enhancement image through illumination normalization and semantic segmentation, and extracting spatial features through a convolutional neural network; then, a dynamic manifold space is constructed by utilizing a self-organizing neural network, and embedding from high-dimensional features to low-dimensional manifolds and typical feature dynamic modeling are realized; tangent vector differential is calculated in a manifold space to obtain dynamic characteristics such as speed and acceleration, dynamic weighting is carried out through a time gating fusion unit, and the characteristic time sequence sensing capacity is improved. And finally, a fermentation stage label and trend prediction confidence are output through a support vector machine classifier, fermentation process state intelligent analysis and collection frequency adaptive adjustment are realized, the precision and timeliness of fermentation process form identification are improved, and the method has relatively high robustness and automation level.

The invention relates to the field of artificial intelligence, in particular to a bearing fault diagnosis model training method, a bearing fault diagnosis method, a bearing fault diagnosis device, bearing fault diagnosis equipment and a medium, and the method comprises the steps: extracting multi-dimensional training motion features of a training vibration signal, including a time domain feature, a frequency domain feature and a time-frequency domain feature, the time-frequency domain features are obtained through complementary global local mean decomposition, and CELMD adaptively processes non-stationary signals through local mean decomposition; redundant features in multi-dimensional training motion features are removed, correlation between the features is eliminated, key information is reserved, feature dimensions are reduced, calculation complexity of follow-up model training is reduced, and meanwhile the overfitting problem is avoided. And performing model training on a vector machine classifier according to the training fusion features and the corresponding fault category labels to obtain a bearing fault diagnosis model, so that the model can accurately identify the bearing fault type, and the classification accuracy is remarkably improved.

This application provides an intelligent sorting and targeted dismantling method for lithium battery recycling. By applying a specific frequency pulse voltage to waste lithium batteries, electrochemical response data is collected. Impedance spectrum features are extracted using a convolutional neural network, and a support vector machine classifier is used to classify the health status into multiple categories, generating classification labels. Then, based on remaining capacity and cycle life estimates, the sorting batch sequence is optimized, and finally, control commands are sent to automated conveying equipment to achieve automated sorting. This application significantly improves classification accuracy and processing efficiency, and reduces the risk of misjudgment.

The invention discloses a default electricity consumption intelligent monitoring method and system for a special line of centrifugal pump irrigation and drainage equipment, and the method comprises the steps: obtaining real-time electric quantity data and a power signal from the special line of the centrifugal pump irrigation and drainage equipment, extracting a periodic sharp wave crest feature in the power signal, and obtaining a wave crest frequency jitter index; according to the wave crest frequency jitter index, normal fluctuation and abnormal fluctuation are distinguished by comparing the wave crest frequency jitter index with historical normal operation data of the centrifugal pump irrigation and drainage equipment so as to judge the boundary of default electricity utilization, and meanwhile, a support vector machine classifier is adopted to carry out cavitation event identification on the power signal. Determining that the centrifugal pump irrigation and drainage equipment has an impeller cavitation process; and obtaining a preset electric quantity consumption reference value database corresponding to different cavitation strength, and performing query matching in the electric quantity consumption reference value database through the cavitation strength estimation value to obtain an electric quantity consumption reference value corresponding to the cavitation strength estimation value. According to the method, the accuracy of operation efficiency monitoring and default power consumption identification of the centrifugal pump irrigation and drainage equipment is remarkably improved, and stable operation of the equipment and power consumption compliance are guaranteed.