814 results about "Transformer windings" patented technology

The invention relates to the technical field of power transformer state monitoring, and discloses a main transformer winding temperature rise on-line monitoring method and system, and the method comprises the steps: obtaining the calibration flight time of ultrasonic waves through an acoustic sensor array disposed on the outer wall of an oil tank in a quasi-isothermal state of a transformer; calculating a structure additional time delay which is caused by an internal fixed structure and does not change along with the temperature, and establishing an acoustic fingerprint for the transformer; during on-line monitoring, oil way net propagation time reflecting temperature change of the insulating oil is obtained from on-line flight time measured in real time; and then, based on the net propagation time of the oil way, an acoustic tomography algorithm is adopted to reconstruct internal two-dimensional or three-dimensional temperature field distribution, and the winding hot-spot temperature is finally and accurately calculated in combination with the real-time load current. According to the invention, through the acoustic fingerprint correction technology, the measurement interference of an internal fixed structure is eliminated, and non-intrusive, high-precision and visual online monitoring of the winding hot-spot temperature is realized.

The invention provides a forward-flyback full-circulation path high-capacity efficient equalization topology and a control method, and relates to the technical field of battery equalization management, and the method comprises the steps that only one multi-winding transformer is needed, and each battery pack corresponds to one transformer winding; the number of primary windings of the transformers is not increased along with the increase of the number of the batteries, and the number of the transformers is not increased along with the increase of the number of the battery packs; adjacent batteries share one pair of MOSFETs, so that nearly 50% of MOSFETs can be reduced; in addition, the equalizer provided by the invention can realize total energy flow paths between any batteries, between any battery monomer and a battery pack, between any battery packs and between any battery pack and the whole energy storage system, and can be flexibly applied to various conditions. Compared with an existing equalization topology, the equalizer provided by the invention is smaller in size and lower in cost, can select and match an equalization mode, and can be applied to a large-scale energy storage system.

The invention provides a transformer winding state detection method based on temperature characteristics. The method comprises the following steps: (1) collecting operation data; (2) preprocessing the operation data; (3) taking the normalized transformer load current, the normalized active power, the normalized top oil temperature, the normalized ambient temperature and the normalized oil flow speed as input data, taking the normalized winding hot-spot temperature as output data, and constructing a data set; (4) establishing a VSN-TKAN-GRN deep learning network parallel computing model of the transformer winding hot-spot temperature considering the multi-head attention mechanism; (5) predicting the hot-spot temperature of the transformer winding based on a VSN-TKAN-GRN deep learning network parallel computing model; and (6) calculating the average relative error percentage of the transformer winding hot-spot temperature prediction result and the actual measurement result, and judging the winding state according to the change of the average relative error percentage. According to the method, the state of the transformer winding in operation can be efficiently and accurately judged, so that effective transformer operation and maintenance measures can be taken in time, and large faults are avoided.

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 discloses a reclosing locking method and system based on winding hot-spot temperature fitting, and relates to the technical field of power transformer dynamic stability assessment, and the method comprises the steps: determining a target transformer, collecting parameters, building a winding current calculation model, calculating steady-state and short-circuit current waveforms, and carrying out the winding temperature rise test of the transformer, the method comprises the following steps: measuring a steady-state temperature rise value, constructing and correcting an electromagnetic heat flow coupling model, generating steady-state and transient-state temperature field data of a winding, constructing a target function of a winding hot-spot temperature, fitting simulation data by utilizing an optimization algorithm, obtaining a fitting function, calculating a winding stress value under a short-circuit working condition in real time, and comparing the winding stress value with a dynamically adjusted stress limit value, so as to obtain a winding stress value. Alarm and locking reclosing are triggered according to the result, and intelligent protection of the transformer is achieved. According to the invention, through accurate parameter acquisition, model establishment, temperature field simulation, hot-spot temperature fitting and stress calculation, real-time monitoring and intelligent protection of the transformer winding under the short-circuit working condition are realized.

The present invention relates to the technical field of transformer fault detection. Disclosed is a transformer early fault diagnosis method based on the difference between virtual and actual winding leakage magnetic field waveforms, comprising: collecting leakage magnetic field information of a non-ideal winding structure transformer by means of fiber-optic magnetic field sensors; decomposing a winding of the non-ideal winding structure transformer into a plurality of regular windings; superposing leakage magnetic fields at the ends of a plurality of regular windings to obtain a non-ideal winding end leakage magnetic field; calculating a leakage flux matrix leakage inductance parameter and a leakage magnetic field output matrix parameter on the basis of the non-ideal winding end leakage magnetic field; establishing a circuit-leakage magnetic field multi-state digital model corresponding to the transformer; and using the difference between an actual transformer leakage magnetic field waveform and a digital transformer model virtual leakage magnetic field waveform as a fault characteristic quantity, completing threshold calculation and early fault sensitivity verification, forming a waveform difference-based early fault diagnosis criterion, and determining a fault position. The present invention can achieve quick and sensitive diagnosis of early faults of transformer windings and improves device operating reliability.

The invention discloses a transformer noise suppression method, system, equipment and medium, and the method comprises the steps: collecting the winding temperature, iron core temperature, cooling system working condition, load current and other operation parameters of a transformer in real time, constructing a multi-physical field coupling model covering electromagnetic, thermal and mechanical characteristics, and providing basic data for noise analysis; based on a heat conduction equation and a vibration acoustics theory, a mapping relation between a heat dissipation state and a transformer noise source is established, and dynamic influences of heat dissipation on noise amplitude and frequency are quantified; through combination of finite element simulation and a thermal network model, winding / iron core deformation caused by temperature change is analyzed, then a modulation rule of deformation on noise radiation characteristics is derived, and a heat dissipation state-physical deformation-noise characteristic transfer function is constructed; and based on the transfer function, dynamically adjusting operation parameters of the transformer by adopting a model predictive control and adaptive filtering technology, and minimizing noise output on the premise of ensuring heat dissipation efficiency.

The invention discloses a simple winding mold for an oil-immersed power transformer, and particularly relates to the technical field of transformer winding, the simple winding mold comprises a center ring, a supporting assembly is arranged on the center ring, the supporting assembly comprises a supporting cylinder arranged at the top end of a dislocation cavity, and a plurality of base plates are distributed on the outer side of the supporting cylinder. Through corresponding cooperative use of the structures, radial inward pressure during wire winding can be resisted, the collapse or bulging phenomenon caused by tension compression of the inner layer of the coil can be avoided, more uniform outer side support can be provided, and the circular retentivity of the section of the coil can be remarkably improved; and segmented and layered support of the coil is realized. According to the structure, the supporting range can be flexibly adjusted according to the thickness of the coil, a datum plate is matched for positioning the position of the wire, the phenomenon that the wire slides off and is not evenly stacked when the wide coil or multiple layers are wound is effectively avoided, and the overall compactness and the radial mechanical strength of the coil can be greatly improved by combining the winding tension and the pre-pressing technology.

The embodiment of the invention discloses a waveform identification and correction method and system for winding deformation diagnosis, and relates to the technical field of transformer winding monitoring, and the method comprises the steps: synchronously collecting voltage and current signals, and carrying out the preprocessing; performing waveform disturbance type identification on the preprocessed signal, and dividing the disturbance type into harmonic dominant disturbance, voltage sag disturbance or compound disturbance, and harmonic dominant disturbance, voltage sag disturbance or compound disturbance; dynamically selecting a corresponding waveform processing path according to a waveform disturbance type identification result; processing the signal by adopting the selected waveform processing path so as to correct and reconstruct the signal and obtain compensated voltage and current waveform data; by constructing a disturbance identification and path adaptive processing mechanism, the problems of processing lag and compensation distortion of a general algorithm during dynamic signal disturbance are solved, the identification precision is improved, and real-time error correction is realized.

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 provides an optimized winding method and system for a high-frequency transformer winding. A comprehensive parameter database based on current density distribution data of a high-frequency switching power supply is established, the axial temperature of a winding layer is collected in real time in combination with a self-calibration multi-axis winding device, and tension and interlayer gap compensation parameters are generated through temperature gradient feedback. The tension parameter drives the machine to adjust the winding tightness, and the gap parameter optimizes the heat dissipation channel. And synchronously fusing the current distortion data of the LLC resonant topology and an electromagnetic field simulation result, and generating a resonant frequency adjustment signal to suppress abnormal high-frequency current distribution. And dynamic matching of winding tightness, current distribution and heat dissipation requirements is realized through cooperative control. According to the system, electromagnetic, mechanical and thermal field multi-dimensional linkage is adopted, the skin effect and hot spot concentration are reduced, the temperature rise gradient is balanced, and the high-frequency working condition stability is enhanced. According to the technical scheme, through electromagnetic, mechanical and thermal field cooperative regulation and control, the temperature rise peak value of the high-frequency winding is greatly reduced, and the efficiency is greatly improved.

The embodiment of the invention relates to the technical field of transformer fault detection, and discloses a transformer winding fault detection method and system based on frequency response and a medium, and the method comprises the steps: determining the equivalent inductance and equivalent capacitance of a transformer winding; and calculating a first-order grounding coefficient of driving point admittance by using the peak frequency and the valley frequency when the neutral point is grounded, and calculating a first-order open-circuit coefficient by using the peak frequency and the valley frequency when the neutral point is open-circuit. A first difference function is constructed through the equivalent inductance, the scaling rate and the first-order grounding coefficient, and a second difference function is constructed through the equivalent capacitance and the first-order open circuit coefficient. And fault detection of the transformer winding is carried out according to a comparison condition between fluctuation of the first difference function and the second difference function and a preset threshold value, and early sensitive detection is realized.

The invention belongs to the technical field of transformers, and particularly relates to a transformer winding deformation accumulation evaluation system and method, and the system comprises a data collection module, a damage calculation module, a self-adaptive correction module and an early warning output module. Wherein the data acquisition module is used for acquiring an input signal of transformer winding deformation and preprocessing the input signal; the damage calculation module is used for performing real-time calculation on the input signal after the budgeting; the self-adaptive correction module is used for dynamically correcting the real-time calculation result of the input signal after the budgeting and calculating a damage value caused by short-circuit current impact in real time; and the early warning output module is used for carrying out early warning on the dynamically corrected deformation degree of the transformer winding and providing decision support. The accumulated deformation degree of the transformer winding can be accurately evaluated, maintenance can be carried out in time, transformer damage accidents are effectively avoided, and the method is suitable for health state on-line monitoring of power transformers, converter transformers and high-frequency switching power supply transformers.

The invention discloses a fluorescent optical fiber temperature measuring device for a transformer winding. The fluorescent optical fiber temperature measuring device comprises an optical fiber temperature sensor, a control and interaction unit, a transmission and switching unit, a flange fixing unit and a protection unit, through the complete system design of the optical fiber temperature sensor, the control and interaction unit, the transmission and switching unit, the flange fixing unit and the protection unit, a whole-process closed loop from temperature sensing and signal transmission to data processing and alarm control is realized. The optical fiber temperature sensor is in direct contact with a winding hot spot, temperature measurement is performed based on the fluorescence decay time principle, the problems that a traditional indirect calculation method is large in error and an electrical sensor is poor in anti-interference performance are solved, system integration is achieved, and monitoring is more accurate. The optical fiber temperature sensor adopts a polyimide optical fiber core and a polytetrafluoroethylene sheath, has no metal part, is resistant to high pressure, and is completely immune to EMI / RFI; a signal isolation unit of the control and interaction unit further blocks external interference and ensures stable work in a strong electromagnetic environment.

The embodiment of the invention discloses a transformer winding overheating fault diagnosis method, and relates to the technical field of power equipment state monitoring, and the method comprises the steps: building a temperature field model of a target transformer under a normal working condition and a plurality of preset winding overheating fault working conditions through a finite element simulation method, and obtaining a temperature field model of the target transformer based on a simulation result; calculating to obtain a group of fault temperature rise critical values corresponding to the positions of the winding sections; when the transformer runs on line, actual measurement temperature rise data of a plurality of positions on the surface of a box body of the transformer are obtained, and the actual measurement temperature rise data are compared with a fault temperature rise critical value so as to locate a winding section where an overheating fault occurs; for the fault section, solving an actual overheating temperature rise value of the fault section through an inversion calculation method by utilizing a preset transformer equivalent thermal circuit model and combining the actually measured top layer oil temperature and bottom layer oil temperature data; high-precision simulation is arranged offline, an efficient algorithm is used online, the diagnosis precision and efficiency are both considered, the accuracy is high, and the practicability is high.

The invention relates to a strain monitoring system and method for a transformer winding. The strain monitoring system comprises the transformer winding and a strain monitoring device. The strain monitoring device comprises a fiber bragg grating array which is arranged on a transformer winding and is used for capturing strain signals of the transformer winding; the signal processor is connected with the fiber grating array and is used for receiving and processing the strain signal to generate an electric signal; the data analysis unit is connected with the signal processor, and the data analysis unit is used for receiving and analyzing the electric signal to obtain strain information of the transformer winding; and the wireless transmission unit is connected with the data analysis unit and is used for wirelessly transmitting the strain information to a monitoring center. According to the invention, the fiber grating array is arranged on the transformer winding, and the fiber grating array transmits the strain information through the optical signal, so that the electromagnetic noise is suppressed and the monitoring accuracy is improved by using the characteristic that the fiber is not interfered by the strong electromagnetic environment of the transformer.

The invention discloses a transformer winding deformation diagnosis software system based on frequency domain transfer function analysis, relates to the technical field of transformer winding deformation diagnosis, and is used for realizing accurate online diagnosis of winding deformation. The frequency response data quality control module performs fast Fourier transform and adaptive filtering on the original frequency response signal uploaded by the distributed detection terminal to generate a transfer function data set of which the signal-to-noise ratio reaches the standard; the transfer function multi-dimensional analysis module performs longitudinal deviation and transverse consistency analysis on the data set, identifies resonant frequency deviation, amplitude change and quality factor drift, and generates a deformation suspicious degree index; the deformation trend prediction module calculates a change trend slope based on a historical suspicious degree sequence and identifies a sensitive frequency band; and the fault mode identification module carries out spectrum refinement analysis on the sensitive frequency band, matches the sensitive frequency band with a typical fault feature library, and outputs a fault type and confidence evaluation. Multi-terminal synchronous monitoring, dynamic prediction and intelligent fault identification are realized, and technical support is provided for predictive maintenance of the transformer.

The invention relates to a power transformer partial discharge source positioning method based on a learning vector quantization network model, and belongs to the technical field of power equipment detection, and the method comprises the following steps: S1, measuring voltage frequency responses of a transformer winding at different tapping positions; s2, obtaining an approximate fitting voltage transfer function through a vector fitting VF technology; s3, establishing a transformer segment winding transfer function SWTF library; s4, calculating a partial discharge PD reference signal; s5, constructing a learning vector quantization LVQ network model, and taking the marked partial discharge reference signals as a training set to train the LVQ network model; s6, injecting a partial discharge test pulse into the randomly selected winding tap connection, and taking the obtained response as a partial discharge test signal; and S7, inputting a partial discharge test signal into the trained LVQ network model, and testing the classification performance of the model.

The invention discloses a preparation method and application of a high-thermal-conductivity polyimide-based paint film for a transformer winding, and relates to a preparation method and application of a polyimide-based paint film. The invention aims to solve the problem of poor heat-conducting property of the existing polyimide dielectric material. The method comprises the following steps: 1, preparing boron nitride nanosheet powder; 2, modifying the surface of the boron nitride nanosheet powder; 3, adding diamine and the boron nitride nanosheet subjected to surface modification into an aprotic polar solvent; 4, adding dianhydride; and 5, carrying out gradient heating to carry out imidization. The heat conductivity coefficient of the high-heat-conductivity polyimide-based paint film for the transformer winding reaches 0.35 W / (m.K) and is improved by 183% compared with that of a pure polyimide material, and meanwhile the high-heat-conductivity polyimide-based paint film has high insulation performance and is used for preparing high-heat-conductivity and high-insulation electrical insulation devices; the electrical insulation device comprises but is not limited to a high-power density motor, a transformer enameled wire and a high-frequency power transformer.

The invention provides an electrical equipment remote monitoring and fault diagnosis system based on the Internet of Things. According to the method, a multi-source heterogeneous sensor network adopts a self-adaptive acquisition strategy, an edge computing node calculates a signal entropy value in real time, when a chaotic signal is found to be abnormal, the acquisition frequency is automatically improved, Beidou grid code space labeling is started, an attention mechanism of an LSTM-CNN hybrid network is combined, power frequency interference and environmental noise are separated, a standardized vector is output, and the accuracy of the chaotic signal is improved. The problem that a traditional filtering algorithm is prone to losing fault features is solved, a cloud server constructs an equipment part fault graph model through a graph neural network, an improved message passing algorithm is used for analyzing a node coupling relation, and a three-dimensional model of equipment and a signal propagation path inverse calculation method are combined. Accurate positioning of hidden faults such as transformer winding turn-to-turn short circuit is achieved, the real-time state of equipment is dynamically mapped through the digital twin, three-dimensional visual maintenance guidance is generated through the maintenance knowledge graph on the basis of monitoring evidences, and the maintenance decision-making efficiency is remarkably improved.

The invention discloses a transformer winding loose fault feature extraction method based on chaos theory and an ephemeral optimization K-means algorithm. The method comprises the following steps: step 1: setting measuring points on a transformer box, obtaining vibration signals of each measuring point, and selecting a measuring point D with the largest vibration amplitude as the optimal measuring point; step 2: calculating the maximum Lyapunov exponent of the vibration signal collected by the measuring point D, and judging its chaotic characteristics; step 3: calculating the correlation dimension and Kolmogorov entropy of the vibration signal with chaotic characteristics as the chaotic characteristics of the transformer winding loose fault; step 4: reconstructing the vibration signal in phase space to obtain a phase space trajectory; step 5: optimizing the initial cluster centers of the K-means algorithm by using the ephemeral optimization algorithm, clustering the phase space trajectory, and finally calculating the sum of the cluster center moments and the radial vector offset of the obtained K cluster centers as the geometric characteristics of the transformer winding loose fault; and step 6: comparing the chaotic characteristics and geometric characteristics of the abnormal state of the transformer winding with reference values ​​to achieve accurate identification.

A calculation method for a transformer winding considering a frequency-dependent loss, comprising: according to simulation requirements, defining key parameters calculated by using a finite-difference time-domain (FDTD) algorithm; constructing an equivalent flat wire model in an FDTD grid; calculating frequency-dependent internal impedance per unit length of a flat wire; and on the basis of a vector fitting method and a time-domain convolution calculation method, substituting the frequency-dependent internal impedance into a time-domain equation of the FDTD algorithm for updating and iterative solving, so as to obtain an electromagnetic field calculation result. In the present invention, on the basis of the vector fitting method and time-domain convolution calculation, the impact of the frequency-dependent characteristics of an electromagnetic field distributed in a conductor on an electromagnetic transient process is accurately considered during the FDTD time-domain solving, so that the calculation accuracy and efficiency of conventional FDTD algorithms and even conventional cross-scale modeling techniques can be significantly improved, thereby carrying out the targeted electromagnetic transient analysis on the reliability, safety, and predictability of transformers, and achieving the early detection of potential faults and defects, or formulating targeted maintenance plans and repair schemes.

The invention discloses a winding laminated structure design method and device for optimizing high-frequency copper loss of a planar transformer. The method comprises the steps that 1, parameters of a to-be-optimized planar transformer winding are determined; 2, a lamination combination is arranged for the windings, the number of copper layers corresponding to the windings and the number of turns of the windings in the copper layers are determined, and the copper layers have no sequential relation; 3, the current amplitude and phase of each copper layer in the lamination combination are calculated, the currents of the copper layers are sequentially connected in a vector mode on a complex plane according to an optimal path, a local optimal lamination structure is obtained, and the optimal path judgment basis is that after the current vectors of the copper layers are connected end to end, the sum of squares of the distances from the end points of all the vectors to the original point is minimum; 4, calculating the copper loss of the local optimal laminated structure based on a preset high-frequency copper loss analysis model; step 5, setting different lamination combinations for the windings, and repeating the step 3 and the step 4 until all possible combinations are traversed; and step 6, comparing the local optimal laminated structure copper loss corresponding to all combinations, and selecting the copper loss with the minimum copper loss as the global optimum. According to the method, high-frequency skin and proximity loss can be effectively inhibited, and high-frequency copper loss is reduced.

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 discloses a transformer winding temperature and strain double-parameter monitoring method, system and device and a medium, and relates to the technical field of transformer monitoring, and the method comprises the steps: arranging a temperature sensing unit and a strain sensing unit on an optical fiber; a first reflection spectrum signal and a second reflection spectrum signal of the transformer winding are obtained and demodulated, and a first temperature signal of the transformer winding and a mixed signal containing a second strain signal and a second temperature signal are obtained; and taking the first temperature signal as compensation, and decoupling the mixed signal to obtain a second strain signal of the transformer winding. The fiber bragg grating technology is adopted, a plurality of sensors are inscribed on one optical fiber, synchronous measurement of temperature and strain is achieved, and strain data are compensated through winding temperature changes. According to the invention, the defects that only a single physical quantity can be monitored and the strain measurement accuracy is influenced by the temperature in the prior art are overcome, and accurate, convenient and efficient monitoring of the temperature strain of the transformer winding is realized in combination with online monitoring software.

The invention relates to the field of battery management systems, and particularly discloses a battery equalization-alternating current self-heating integrated topology based on electromagnetic induction and a control method, the topology comprises a battery pack, a switch array, a multi-winding transformer, a signal acquisition and processing module, a control unit and a driving circuit, energy balance in the battery modules and among the modules is realized through the multi-winding transformer, and the same transformer winding is utilized to generate alternating current at low frequency to realize self-heating of the battery; the control method is based on battery voltage and temperature information, balancing and heating modes are dynamically switched, and flexible control over the heating rate and the balancing speed is achieved by adjusting PWM parameters. The system is high in integration level, does not need an external power supply, is high in expansibility, and is suitable for efficient thermal management and state equalization of various lithium ion battery systems in a low-temperature environment.

The invention provides an ultrasonic de-noising method and system based on an SGF-ASO optimization algorithm, and belongs to the technical field of electrical equipment state monitoring and fault diagnosis, and the method comprises the steps: collecting and preprocessing an ultrasonic echo signal of a transformer winding; sGF analysis is carried out on the preprocessed ultrasonic echo signal, a multi-scale frequency spectrum is generated, spatial gradient features are extracted, and a fusion frequency spectrum gradient map is generated through cross-scale fusion; constructing an oil temperature adaptive ASO constraint model to carry out adaptive sparse optimization on the multi-scale frequency spectrum; and performing inverse short-time Fourier transform on each scale frequency spectrum in the optimized multi-scale frequency spectrum to obtain a multi-scale time domain signal set, and fusing the time domain signal set to output a de-noised ultrasonic echo signal. According to the invention, the structure retention capability of ultrasonic signals in a high-temperature complex environment is enhanced, and high-fidelity noise reduction and oil temperature adaptive processing are realized through a multi-scale gradient guided sparse optimization mechanism.

The invention discloses single-shaft winding equipment for coil production for transformer manufacturing, and relates to the technical field of transformer winding equipment. Comprising a supporting plate, the supporting plate is fixedly installed at the top of a platform, a through hole is formed in the top of the supporting plate, a sliding block is slidably connected into the through hole, and a guiding piece is fixedly connected to the bottom of the sliding block. According to the single-shaft winding equipment for coil production for transformer manufacturing, wires are limited through the rolling wheels on the two sides, it can be ensured that the wires are arranged according to a preset path in the winding process, the conditions that the wires are crossed or overlapped or staggered or the like are prevented, coil winding is more uniform and compact, the quality and performance of the coils are improved, and the production efficiency of the coils is improved. And meanwhile, when the tension of the wire is not uniform in the pay-off process, the roller can properly tension or loosen the wire through contact and friction with the wire, so that the tension of the wire is kept in a proper range, and the winding quality of a coil is prevented from being influenced by too large or too small tension.

The invention discloses a transformer mechanical fault diagnosis method and device and a storage medium, and belongs to the technical field of deep learning, and the method comprises the steps: obtaining a to-be-diagnosed vibration signal of the surface of a transformer box body, and obtaining a corresponding to-be-diagnosed mode component; inputting the modal component to be diagnosed into a pre-trained fault diagnosis model to obtain a fault diagnosis result; the fault diagnosis model training method comprises the steps of obtaining a training sample set; wherein the training sample set comprises a historical modal component and a fault category label corresponding to the historical modal component; the training sample set is input into a pre-constructed fault diagnosis model, a trained fault diagnosis model is obtained, an encoding module of the fault diagnosis model carries out time-frequency domain feature extraction and time-frequency domain attention weighting on the input data to obtain time-frequency domain fusion features, and the time-frequency domain fusion features are input into the fault diagnosis model; spatial topological features are obtained through image feature extraction and image attention weighting, step-by-step feature re-calibration is carried out on time-frequency domain fusion features, and the fault diagnosis accuracy is remarkably improved.

The invention provides horizontal winding equipment for a transformer coil, which belongs to the technical field of transformer winding equipment and comprises a winding machine, a linear driving unit and a connecting unit. Wherein the connecting unit is provided with a supporting arm, one end of the supporting arm is connected to the connecting unit, the supporting arm is arranged to be capable of swinging in the direction perpendicular to a main shaft of the winding machine, the supporting arm is provided with a belt wheel set, the belt wheel set is connected with a rubber belt, and the rotating direction of the rubber belt is consistent with the winding direction. And the rubber belt can be pulled by the linear driving unit and moves along with a wire arranging path. By arranging the rubber belt capable of synchronously moving along with winding, during winding, the side face of the rubber belt exerts certain pressure on the side face of the coil, winding is tighter, the contact area of the rubber belt and the side face of the coil is large, pressure can be evenly exerted on the side face of the coil in the winding state, and the winding efficiency is improved. And insulation layer damage caused by pressure concentration is avoided.