803results about "Transformers testing" patented technology

The invention relates to the technical field of transformers, and provides a transformer load capacity prediction method and device, equipment and a storage medium, and the method comprises the steps: obtaining current data, winding temperature data, oil temperature data, environment temperature data and historical load records of a target transformer; calculating a temperature rise correction value based on the winding temperature data and the oil temperature data; after the temperature rise change rate in unit time is calculated through the current data, the environment temperature data and the temperature rise correction value, time sequence matching analysis is carried out on the temperature rise change rate and historical load records, after the load capacity change trend is obtained, comparative analysis is carried out on the load capacity change trend and the historical load records, and a load capacity prediction result is generated. By utilizing collaborative analysis and heat conduction characteristic calculation of multi-source data and comprehensively constructing a time delay interval and a load capacity evaluation method, the precision and applicability of transformer load capacity prediction are improved, and the problem that the prediction precision is insufficient due to the fact that operation data and environment data of the transformer cannot be fully fused during multi-source data processing is solved.

The invention discloses a power transformer arc discharge multi-parameter detection simulation platform and a fault diagnosis method, and relates to the technical field of power system equipment state monitoring and fault diagnosis. The platform comprises a transformer body, a replaceable discharge module, a multi-parameter sensing unit and a signal processing and diagnosis module, and can truly reproduce various typical arc discharge faults of a needle plate, an air gap, a creeping surface, turn-to-turn and the like. The sensing unit is integrated with ultrahigh frequency and ultrasonic sensing probes, high-frequency current and voltage sensors, optical fiber temperature / pressure / strain sensors and the like, so that synchronous acquisition of multi-physical field signals is realized. According to the diagnosis method, through wavelet denoising and multi-dimensional feature extraction, a feature vector of multi-state parameter fusion in the process from partial discharge to arcing is constructed, and accurate classification of fault types is realized by using a support vector machine (SVM) model. The diagnosis method has high accuracy and early warning capability, effectively overcomes the limitation of single parameter diagnosis, and provides reliable technical support for transformer fault research and intelligent operation and maintenance.

Provided are a method for training a transformer fault detection model, a fault diagnosis method, and a related device. The method includes: obtaining an initial voiceprint signal of a transformer and a fault type corresponding to the initial voiceprint signal; preprocessing the initial voiceprint signal to obtain an input signal, and establishing an input signal dataset; performing feature extraction on a first input signal in the training dataset based on a preset feature extraction algorithm to obtain a first voiceprint feature; training an initial detection model based on the first voiceprint feature and a first fault type corresponding to the first input signal to obtain a first training result; determining a loss function based on the first training result and the first fault type; and iteratively adjusting a weight value of the initial detection model until the loss function converges to obtain a fault detection model.

The invention relates to the technical field of transformer detection, and discloses a nondestructive testing optimization method and system for an oil-immersed power transformer, and the method comprises the steps: building a three-dimensional dielectric response coordinate system, and generating a preliminary defect positioning map; aging-dominated and damp-dominated defects are detected and identified through spiral frequency sweep excitation; establishing a temperature gradient excitation scheme based on the defect type to generate a defect degree quantitative evaluation index; designing a sound wave modulation excitation scheme to generate a high-resolution defect characteristic spectrum; constructing a multi-mode intelligent sensor network, and combining a defect development trend prediction model to realize defect evolution prediction and generate a graded early warning signal; according to the method, the whole-process accurate detection of the insulation defect of the transformer from positioning, classification and quantitative evaluation to evolution prediction is realized, and a reliable basis is provided for operation and maintenance.

The invention relates to the technical field of capacitance compensation matching, in particular to a dynamic tuning capacitance compensation matching method and system for a transformer simulation test. The method comprises the following steps: before a test is started, establishing a digital twin model based on parameters of a transformer to be tested, identifying a systematic measurement error source caused by inherent characteristics of a system through simulation, and generating error source correction parameters; in the test period, voltage and current original waveforms containing electrical disturbance in a test loop are obtained in real time through high-frequency synchronous sampling; a mixed disturbance separation model is used, the collected original waveform and the generated error source correction parameters are used as input, and random measurement disturbance components caused by load dynamic changes are calculated and separated in real time; and based on the separated disturbance component, driving a dynamic capacitance compensation module to generate a compensatory electric signal which is equal to the disturbance component in size and opposite to the disturbance component in phase, and injecting the compensatory electric signal into a test loop so as to realize active disturbance cancellation. According to the invention, the measurement precision of the transformer simulation test can be improved.

The invention relates to the technical field of transformers, in particular to a transformer component fault diagnosis method based on machine learning, which comprises the following steps: analyzing medium data acquired by a transformer component, comparing a dielectric loss factor sequence with offset characteristics, training and generating an offset time sequence characteristic set, screening abnormal time periods and aggregating key discharge characteristics, and performing fault diagnosis. And obtaining an abnormal clustering signal group, concluding a trend evolution sequence, performing layered optimization on a path structure, and outputting fault link positioning data. According to the method, various parameters such as dielectric loss, discharge, temperature rise, gas and vibration are integrated, abnormal distribution is actively screened, key node trend change is captured in real time, historical and real-time characteristics in different operation scenes are fused, and efficient analysis of complex link evolution and implicit anomalies is realized. And the fault evolution relationship among the nodes is output in a structured manner, direct application of a diagnosis result in full-link traceability and multi-node trend research and judgment is supported, and the fault diagnosis pertinence and the hidden danger recognition capability are effectively improved.

The invention discloses a column type distribution transformer winding abnormity detection system and detection method. The detection system comprises a frequency response detection instrument, a signal coupling assembly, an impedance matching module and a data processing module. The frequency response detection instrument is used for outputting a frequency sweep excitation signal and collecting a winding response signal; the signal coupling assembly is used for isolating power frequency voltage and filtering low-frequency interference; the impedance matching module is used for adjusting output impedance and input impedance to realize matching with electrical characteristics of different windings; and the data processing module is used for constructing an equivalent detection loop model, completing frequency response simulation calculation and carrying out frequency domain analysis and anomaly identification on an actually measured response curve. According to the invention, electrified state diagnosis of distribution transformer winding structure abnormity (such as deformation and loosening) can be realized.

The invention relates to the field of state monitoring and fault diagnosis of power equipment, in particular to a transformer fault diagnosis method based on a chaos evolutionary optimization algorithm, which comprises the following steps of: 1, acquiring a magnetic flux leakage signal during operation of a transformer; 2, optimizing a parameter modal number K and a penalty factor alpha of variational modal decomposition by using a chaos evolutionary optimization algorithm; 3, performing variational mode decomposition on the magnetic flux leakage signal to obtain an intrinsic mode function component; 4, calculating the envelope entropy of the intrinsic mode function component, and obtaining an effective intrinsic mode function component through screening; 5, extracting the energy entropy and the sample entropy of the effective intrinsic mode function component to form a feature vector; and 6, inputting the feature vector into a pre-trained support vector machine classifier, and outputting a fault type diagnosis result of the transformer. According to the method, the CEO algorithm is combined with the ergodicity of chaotic mapping and the global search capability of the evolutionary algorithm, and the problems that VMD parameters K and alpha are sensitive and depend on experience, and a traditional optimization algorithm is prone to local optimum are effectively solved.

The invention discloses a high-precision transformer fault detection method and system, relates to the technical field of transformer detection, is used for solving the problems of insensitive fault characterization and delayed diagnosis under a light load condition, and judges whether to enter a load judgment mechanism or not by acquiring input side access voltage information and counting low-load accumulated duration. When entering a load discrimination mechanism, detecting the start-stop behavior of a load branch and the temperature rise trend of a winding, calculating a light load index, identifying a light load state, carrying out region division on an iron core, collecting magnetic flux density data, and calculating iron loss balance characteristics aiming at iron loss deviation which is easy to occur under a light load condition; the insulation degradation coefficient is calculated by fusing the oil temperature peak value and the dielectric loss factor, and the abnormal index is generated with the iron loss balance characteristic, so that the early warning of the early hidden fault of the transformer can be realized in a light load scene in which the traditional temperature rise and current indexes are insensitive, and the operation reliability and maintenance efficiency of the transformer in a power distribution system are improved.

Devices methods for triggering alarms and cautions for electrical equipment may include receiving, at edge device, data of an electrical device, including dissolved gas data or electrical data; setting, based on a comparison of a measurement value of the data to an upper rolling window-based threshold or to a lower rolling window-based threshold, a measurement flag for the electrical device; determining a rate-of-change (RoC) of the data; setting a RoC flag for the electrical device based on a comparison of the RoC to a delta RoC-based threshold; determining an acceleration of the data; setting an acceleration flag for the electrical device based on a comparison of the acceleration to a percentile log-ratio change of measurements threshold; and setting one of a no flag, a caution flag or an alarm flag for the electrical device based on the measurement flag, the ROC flag, and the acceleration flag.

The embodiment of the invention discloses an insulation aging early warning method and device for a medium-high frequency transformer and a medium, and relates to the technical field of transformers, and the method comprises the steps: collecting a multiband light intensity distribution signal of a target resin region in the transformer according to a preset collection frequency through a preset multispectral distributed optical fiber sensing array; the insulation state of the target resin area is predicted through a pre-constructed neural network identification model and a multi-spectral distributed optical fiber sensing array, and the predicted insulation state health degree of the target resin area is determined; acquiring real-time environment parameters of the target resin area, dynamically correcting a preset early-warning discharge threshold according to the real-time environment parameters, and determining a current early-warning dynamic discharge threshold; and extracting a plurality of current light intensity parameters in the multiband light intensity distribution signal, predicting an insulation state health degree and a current early warning dynamic discharge threshold through the plurality of current light intensity parameters, and performing insulation defect early warning on the insulation state of the target resin area.

The invention provides an on-line monitoring system and method for the grounding current of a transformer iron core, and belongs to the field of data processing, and the system comprises a magnetic adsorption type dual-channel current sensor which is used for synchronously collecting a transformer iron core grounding current channel signal and a transformer clamp grounding current channel signal; the self-adaptive signal preprocessing module is used for carrying out self-adaptive differential processing through a self-adaptive differential coefficient and carrying out variable gain adjustment and self-adaptive filtering; the multi-dimensional feature extraction module is used for performing multi-dimensional signal feature extraction on the purified grounding current signal to obtain a multi-dimensional feature parameter set; the feature fusion module is used for performing constraint fusion on the multi-dimensional feature parameter set based on the corrected iron core eddy current loss physical model, and generating a comprehensive health evaluation index through an adaptive weight adjustment mechanism; and the intelligent diagnosis module is used for carrying out transformer iron core fault type identification, health state evaluation and trend prediction according to the comprehensive health evaluation index and the multi-dimensional characteristic parameter set to obtain a transformer iron core state monitoring result.

The invention discloses a transformer health state determination method, system and device and a storage medium, and belongs to the technical field of transformers, and the method comprises the steps: carrying out the temperature detection of a key part of a transformer through a temperature sensor, and obtaining a temperature parameter set; performing stress measurement on the stress concentration area of the transformer to obtain a stress parameter set; inputting the temperature parameter set into an insulation thermal aging model to obtain a thermal aging damage index; performing damage evaluation on the stress parameter set through a Miner rule to obtain a mechanical fatigue damage index; and determining a health state value of the transformer based on the thermal aging damage index and the mechanical fatigue damage index. According to the method, the influence of the temperature on the insulation life is quantified based on the insulation thermal aging model constructed based on the Arrhenius equation, and the mechanical fatigue damage index is accumulated in combination with the Miner rule, so that the health state value of the transformer can be accurately estimated, the accuracy of transformer health state evaluation is improved, and the accident risk of a power system is reduced.

The invention discloses a fault prediction method and system for a transformer, and belongs to the technical field of transformer state monitoring and fault prediction. The technical problems that an existing transformer fault prediction method is low in accuracy due to single data modality, insufficient in model generalization ability due to scarcity of real fault data, lack of an adaptive mechanism and the like are solved. According to the technical principle, gas concentration, vibration spectrum, temperature, sound and thermal imaging data are collected through a multi-mode sensor array deployed on a transformer site; a multi-head attention mechanism is adopted in the edge calculation unit to realize multi-source data fusion, and fault prediction is carried out through an LSTM-Attention hybrid model; multi-node model parameters are aggregated through federal learning at the cloud, and model adaptive optimization is realized in combination with reinforcement learning. According to the system, the prediction accuracy is improved, the delay is reduced, training data is expanded by five times through the generative adversarial network, distributed deployment and privacy protection are supported, and an efficient transformer state early warning solution is provided for an intelligent power grid.

The invention discloses a transformer fault diagnosis method and system based on a random forest algorithm, and the method comprises the steps: collecting transformer historical fault data, preprocessing the collected transformer historical fault data, and constructing historical sample data; the method comprises the following steps: collecting real-time operation data of a transformer and preprocessing the real-time operation data to obtain a multi-dimensional feature vector; constructing a training sample set by using the historical sample data, and training a random forest model containing T decision trees by using the training sample set; and inputting the multi-dimensional feature vector into the trained random forest model for diagnosis, outputting a fault diagnosis type, dynamically optimizing the random forest model according to the change condition of the real-time operation data, adjusting the branch decision tree, and restarting branch decision tree training. According to the method, high-precision fault diagnosis and quick response can be realized, the decision reliability is greatly improved, the maintenance cost is reduced, the feature data dimension is reduced, and the sensitivity of fault detection and analysis is improved.

The invention discloses a transformer internal multi-parameter information fusion discharge diagnosis and evaluation method, and relates to the technical field of power equipment state monitoring and fault diagnosis. According to the method, eight types of sensors are deployed in a transformer, and electrical, mechanical, thermotechnical and insulating multi-physical-field parameters are cooperatively collected; thirdly, performing three-stage preprocessing of abnormal value elimination, standardization and differential noise suppression on the data; then 12 types of fault features are extracted; carrying out feature layer fusion by adopting a dynamic weight distribution method based on AHP-working condition correction, and constructing a fusion feature vector; performing decision-making layer fusion through a five-layer fuzzy logic-neural network hybrid model, and outputting a fault probability and a fault type; and finally, dividing five fault levels according to the fault probability and outputting specific processing suggestions. According to the method, multi-parameter adaptive fusion and high-precision diagnosis are realized, the accuracy is high, the average time delay is low, and the problems of incomplete fault coverage and poor working condition adaptability of a traditional method are effectively solved.

The invention provides a rapid detection and diagnosis method and system for a short-circuit fault of a transformer winding, and relates to the technical field of transformers, and the method comprises the steps: collecting the electrical parameters of the transformer winding, calculating equivalent impedance, building a transfer function model and an equivalent impedance model, and extracting a frequency domain fault characteristic quantity and a short-circuit force characteristic; and constructing a characteristic quantity judgment matrix to obtain a weight coefficient, carrying out multi-source information fusion by utilizing a D-S evidence theory, and realizing fault diagnosis by combining fuzzy comprehensive evaluation. The method can accurately identify the short-circuit fault type of the transformer winding, and improves the reliability and accuracy of fault diagnosis.

The invention discloses a transformer monitoring method and system based on a multi-dimensional signal, and relates to the technical field of transformer monitoring, and the method comprises the steps: obtaining the multi-dimensional signal and working condition parameters of a transformer, carrying out the time domain feature extraction of the multi-dimensional signal, obtaining a corresponding time domain correlation feature, carrying out the frequency domain feature extraction of the multi-dimensional signal, obtaining a corresponding frequency domain correlation feature, and carrying out the time domain feature extraction of the multi-dimensional signal; fault analysis is carried out according to the working condition parameters and the frequency domain correlation characteristics, and a corresponding initial fault detection result and an electromagnetic coupling residual value are obtained; and if so, carrying out fuzzy evaluation on the time domain correlation feature, the frequency domain correlation feature, the electromagnetic coupling residual value and the multi-dimensional signal based on a pre-trained fault detection model to obtain a corresponding fault monitoring result. The technical problems that a traditional transformer monitoring method mainly depends on electrical signal analysis, but key parameters such as oil temperature are not included in a monitoring system, so that potential fault hidden dangers cannot be found in time, and the operation reliability of the transformer is reduced are solved.

The embodiment of the invention provides a power transformer fault identification method and device, equipment and a medium. The method comprises the following steps: acquiring a multi-source mechanical wave signal in an operating environment of the power transformer, and performing short-time Fourier transform on the multi-source mechanical wave signal to obtain a multi-channel time domain matrix in the same time domain; determining a comprehensive feature corresponding to the multi-channel time domain matrix based on a multi-level feature weighting strategy, and determining a global association feature of the multi-channel time domain matrix based on the comprehensive feature; determining a pseudo tag of the global association feature through a preset semi-supervised learning model, and determining a fault category tag corresponding to the global association feature based on the pseudo tag and a real tag of the global association feature; and determining a fault category corresponding to the power transformer based on the fault category label. The method is used for achieving the effects of improving the real-time performance, accuracy and robustness of power transformer fault identification in a complex environment, further improving the operation reliability of the power transformer and guaranteeing the safety of a power grid.

The invention discloses an analysis method and system for energy conservation and loss reduction of transformers, and the method comprises the steps: collecting the standby state data of a transformer group, recognizing a high-loss unit, and predicting the parameter drift trend of the high-loss unit; acquiring an electromagnetic impact strength signal in a working state; the parameter drift trend and the electromagnetic impact strength signal are fused, and the collaborative imbalance risk is evaluated; and according to a risk assessment result and a risk cause, dynamic voltage regulation and load balancing optimization are adaptively executed. The cross-working-condition correlation analysis and closed-loop control are carried out on the transformer group serving as the power supply core, so that the standby no-load loss can be effectively reduced, the equipment aging can be delayed, the operation cost can be reduced, the long-term stability and reliability of the power supply system can be ensured, and the method can be widely applied to the industrial fields of pulsed electric fields, precision manufacturing and the like.

The invention provides a real-time monitoring method and system for a power transformer, and relates to the technical field of intelligent monitoring, and the method comprises the steps: carrying out the noise removal and time synchronization of original data through wavelet transform, and carrying out the recognition and elimination of abnormal data through an isolation forest algorithm, and obtaining the preprocessed data; key features are extracted from the preprocessed data, a weighted average method is adopted for fusion, and a comprehensive state index is generated; based on the comprehensive state index, using a fault classification model constructed based on a deep neural network to identify a fault type, using a long short-term memory network to analyze and predict the future state of the transformer, and calculating a transformer health score according to the comprehensive state index and the future state of the transformer; and according to the transformer health score, setting multi-level alarm thresholds for real-time alarm, and generating a maintenance suggestion in combination with the fault type. According to the invention, the accuracy of fault early warning is improved.

The invention relates to the technical field of control systems, and particularly discloses an intelligent control system for an insulation test of a marine dry-type transformer. The system comprises a high-voltage test power supply module, a multi-mode sensing acquisition module, an insulation state evaluation module, a self-adaptive boost decision module and a test process control module, and evaluates an insulation state and dynamically decides a boost rate and a holding strategy by acquiring voltage, leakage current, partial discharge and temperature data in real time. Intelligent control and safety protection in the insulation test process are achieved, potential insulation damage is effectively avoided, and diagnosis precision is improved.

The invention relates to a fault detection method and device of a converter transformer, computer equipment and a medium. The method comprises the steps of obtaining a vibration time-domain waveform signal and a current time-domain waveform signal of a winding of the converter transformer in a preset time period, determining vibration frequency response data of the winding according to the vibration time-domain waveform signal and the current time-domain waveform signal, and determining the current time-domain waveform signal of the winding according to the vibration frequency response data and preset reference vibration frequency response data. And determining a fault detection result of the winding. By adopting the method, the timeliness of fault detection of the converter transformer can be improved.

The invention discloses a transformer insulating sleeve fault diagnosis method and device and electronic equipment. The method comprises the following steps: acquiring an infrared image and a visible light image of a to-be-detected insulating pipe sleeve in a transformer; respectively carrying out feature extraction on the infrared image and the visible light image by adopting a scale invariant feature transformation method to obtain an infrared feature point set and a visible light feature point set; performing feature fusion based on the infrared feature point set and the visible light feature point set to obtain a target fusion image; multiple features in the target fusion image are extracted, and the multiple features at least comprise a thermal image temperature feature, a texture feature and a shape feature; and obtaining a thermal fault diagnosis result of the to-be-detected insulating sleeve by adopting a pre-trained insulating sleeve fault diagnosis model based on the multiple characteristics. According to the invention, the technical problem of low potential thermal fault diagnosis accuracy of the transformer insulating sleeve in the prior art is solved.

The invention belongs to the field of transformer pile head recognition, and particularly relates to a distribution transformer pile head automatic recognition system which comprises a data integration module, a data processing module, a system control module, a waveform parameter calculation module, an excitation circuit analysis module, an equivalent inductance conversion module and a looseness recognition algorithm module. According to the scheme, the high-cost limitation of a traditional vibration sensor or 3D modeling is broken through, and remote monitoring of looseness of the transformer pile head can be achieved through equivalent excitation inductance conversion and waveform similarity analysis without additional hardware transformation based on voltage and current data collected by an existing digital platform (a resource middle platform, a marketing middle platform and the like) of a power grid. Compared with the traditional scheme in the industry, the method has the advantages that the hardware transformation cost is reduced by more than 70%, the problem of missing inspection of manual inspection is avoided, the average recognition time of the pile head loosening fault is shortened to be within 15 minutes from 4 hours of traditional manual inspection, the monitoring efficiency is remarkably improved, and non-intrusive and low-cost accurate sensing of the state of the transformer is realized.

The invention relates to the technical field of power equipment state detection, in particular to a transformer winding state detection method, system and equipment based on dynamic frequency band adaptation and a storage medium. Collecting full-band frequency response data of the healthy reference winding, and performing adaptive adjustment on a preset basic frequency band based on the peak-valley distribution density to obtain a reference target frequency band matched with the frequency spectrum characteristics of the winding; generating a reference polar coordinate feature map through a phase-amplitude mapping rule, and extracting pattern texture features to construct a reference feature library; collecting detected winding data and taking the reference target frequency band as a detection frequency band to generate a detected polar coordinate feature map; a multi-dimensional evaluation result is obtained through graph space similarity comparison and feature difference quantification in combination with amplitude anomaly recognition; and outputting a normal, slight fault or serious fault state judgment result of the tested winding based on the preset evaluation threshold interval and the working condition adaptation correction rule. The problems that in the prior art, frequency band division is fixed, and threshold values lack working condition adaptation are solved.

The invention provides a transformer abnormity monitoring method and system based on artificial intelligence, relates to the technical field of transformer state monitoring, and solves the technical problems of poor scene adaptability, multi-source data isolation and weak early warning in the prior art. The method comprises the following steps: acquiring real-time data and historical data of a transformer; preprocessing the real-time data through a preprocessing algorithm to obtain standard data; constructing an AI anomaly monitoring model based on historical data; wherein the AI anomaly monitoring model comprises a dynamic baseline module, an anomaly detection module and an anomaly classification module; and inputting the standard data into the AI anomaly monitoring model to generate an anomaly alarm. The method is used in the transformer abnormity monitoring process.

The invention belongs to the technical field of power protection, and particularly relates to a station transformer grounding current synchronous synthesis method and system, and the method comprises the steps: carrying out the grouping according to the number of a station transformer, synchronously collecting the grounding branch current of each station transformer to obtain an original signal, carrying out the double identification, and carrying out the homologous copying; generating two paths of independent signals of frequency detection and phase calibration; frequency detection signals are grouped according to double identifications, the independent actual frequency of each station transformer is obtained after frequency detection processing, and a same-frequency sine dynamic reference signal is generated based on the independent actual frequency; performing phase alignment and compensation on the phase calibration signal and the corresponding reference signal according to the double identifiers to obtain a calibrated signal; according to the method, the phase calibration reference of each station transformer is completely matched with the actual frequency of the station transformer, the reason of phase reference dislocation caused by frequency fluctuation is eliminated from the source, and the accuracy of synthesizing the total grounding current in the station is improved.

The invention discloses a fusion filtering method, system, equipment and medium for power transformer winding state monitoring, and belongs to the technical field of power equipment state monitoring, and the method comprises the steps: obtaining an original state monitoring signal of a transformer winding; performing multi-scale decomposition on the original state monitoring signal by adopting self-adaptive wavelet transform; an improved particle filter is embedded, and a suggested distribution function of relative entropy optimization and a dynamic weight updating mechanism are combined; the filtered sub-signals are reconstructed through inverse wavelet transformation; weight parameters are adjusted in a self-adaptive mode; and outputting the key state parameters for transformer winding health assessment. Under the complex electromagnetic environment and the dynamic load fluctuation working condition, the signal-to-noise ratio of the state data of the transformer winding can be remarkably improved, the comprehensive accuracy rate of state evaluation is improved, and reliable data support is provided for health management and preventive maintenance of the transformer winding. And the operation reliability of the transformer and the intelligent level of state evaluation can be obviously improved.

The invention relates to the technical field of power equipment monitoring, in particular to a movable transformer operation monitoring method and device, a medium and equipment. The method comprises the following steps: acquiring an ultrasonic signal generated in the movable transformer in a monitoring period; performing fast Fourier transform on the ultrasonic signals, and extracting spectrum features of the ultrasonic signals; inputting the frequency spectrum characteristics into a partial discharge prediction model to obtain a predicted partial discharge result of the movable transformer at a first future time point corresponding to the monitoring period; acquiring monitoring data of the movable transformer in the monitoring period based on the predicted partial discharge result; inputting the monitoring data into a temperature prediction model to obtain a predicted hot spot temperature of the movable transformer at a second future time point corresponding to the monitoring period; and performing heat dissipation processing and risk early warning on the movable transformer based on the predicted partial discharge result and the predicted hot spot temperature. According to the invention, accurate prediction of partial discharge and thermal runaway of the movable transformer is realized.