1389 results about "Root mean square" patented technology

The invention relates to the technical field of fault prediction, in particular to a centrifuge fault prediction system based on machine learning, which comprises a data channel synchronization module, a multi-dimensional feature extraction module, a state evolution index construction module, a trend aggregation trajectory recognition module and a fault section recognition module. According to the method, different types of data are synchronously aligned by a multi-channel signal segmentation processing mechanism based on a periodic state, a state evolution sequence is constructed in combination with a unified sampling structure based on a time scale, a state characteristic track is established through a multi-dimensional parameter set, a trend change index is constructed by means of a difference root-mean-square between adjacent states, and the state evolution sequence is analyzed. According to the method, the aggregation section is recognized and the trajectory deviation frequency is counted by utilizing continuous trend mutation, so that dynamic migration of the trajectory boundary and intelligent recognition of the fault section are realized, the boundary failure problem caused by static preset conditions is avoided, and the continuous prediction stability of long-period equipment and the application range under a non-standard working condition are effectively enhanced.

The invention provides a soft rock tunnel surrounding rock parameter dynamic identification method and system based on data driving, and relates to the technical field of underground tunnel mechanical parameter dynamic identification, and the method comprises the steps: obtaining multi-element tunnel surrounding rock parameters, and building a joint probability distribution model of the multi-element surrounding rock parameters based on a Copula theory; performing Monte Carlo simulation, and generating a high-dimensional parameter sample library meeting physical constraints in the parameter constraint space based on the joint probability distribution model; establishing a tunnel three-dimensional numerical model and performing automatic numerical simulation to generate multivariate response data; constructing a Kriging agent model of a Gaussian kernel function based on multivariate response data training, establishing a nonlinear mapping relation between parameter input and deformation output, constructing an inversion objective function by taking the minimum root-mean-square error of multi-measurement-point displacement as an objective, and performing inversion solution by using an adaptive particle swarm optimization algorithm to obtain inversion identification parameters, and a dynamic feedback mechanism is constructed to realize adaptive tracking of the time-varying characteristics of the surrounding rock parameters.

The invention relates to the technical field of electrical performance testing, in particular to a water supply equipment electrical performance detection system based on artificial intelligence, which comprises an electrical parameter acquisition module, an energy efficiency analysis module, an insulation performance evaluation module and a comprehensive diagnosis module. According to the invention, a three-phase voltage and current root-mean-square value is dynamically calculated through a broadband current transformer and a sliding window integration method, a 50Hz fundamental component amplitude is extracted to separate power frequency and high frequency harmonic waves, a continuous period energy efficiency ratio standard deviation triggers an insulation detection threshold value, and a parameter fluctuation and insulation degradation response mechanism is established. Harmonic interference correction synchronous processing energy efficiency ratio and leakage current integration, the detection error being lower than 5%, temperature rise rate linear regression and bearing current threshold value cooperative determination, winding aging cross validation, fault misjudgment rate reduction to 26%, closed-loop detection fusion transient capture, dynamic threshold value triggering and multi-parameter diagnosis, early warning success rate reaching 92%, and positioning response being reduced to 3 seconds.

The invention discloses a microplastic transport simulation and risk identification method based on multi-factor coupling, which comprises the following steps: by coupling a hydrodynamic model and a microplastic transport model, comprehensively considering multiple environmental factors such as tide, water level, runoff, wind speed, wind direction and the like, constructing a wave flow coupling microplastic migration and diffusion model suitable for complex hydrodynamic conditions of a Pearl River estuary; the model is calibrated and verified through measured data, and the precision of the model is evaluated by using indexes such as a Nash efficiency coefficient and a root-mean-square error; in combination with the simulation result and the spatial distribution characteristics of the typical sensitive area, representative sections and stations are selected, and annual-scale micro-plastic concentration change analysis is carried out; and further introducing an ecological risk index to carry out regional ecological risk grade identification, and determining a micro-plastic high-risk area and influence main control factors. The method has high regional adaptability and expansibility, and scientific support and technical reference can be provided for prevention and control of microplastic pollution of estuary and coastal water.

The invention discloses a low-altitude atmosphere three-dimensional wind field inversion method based on wind profile radar vertical observation, relates to the technical field of three-dimensional wind field inversion, and aims to solve the problem of poor inversion effect caused by inaccurate model parameters in the wind field inversion process. The difference between simulation data and actual observation data is evaluated from multiple angles, a comprehensive optimization basis is provided, parameter calculation optimization is performed by adopting a particle swarm optimization method, the method has the characteristics of high convergence speed and high global search capability, is suitable for optimization of complex problems, and is used for confirming model requirements according to a wind field inversion rule. The model is selected by combining the evaluation result of the model library, it is ensured that the selected model has high pertinence and applicability, the prediction precision and reliability of the model are improved, model initialization is conducted through wind field fusion data, data information of multiple sources is fully fused, and the comprehensiveness and accuracy of the data are improved.

The invention provides an underwater image enhancement quality evaluation method based on quality perception domain adaptation. The method comprises the following steps: S1, acquiring a plurality of original underwater images to generate a training set and a test set; s2, constructing an underwater image enhancement quality evaluation network by using a deep learning framework; s3, training the underwater image enhancement quality evaluation network by using the training set, calculating a root-mean-square error between a prediction quality score and a label corresponding to each first enhancement image, and obtaining network loss in combination with binary cross entropy loss; s4, repeating the step S3 for multiple rounds to obtain an underwater image enhancement quality evaluation network model; and S5, testing each second enhanced image in the test set by using the underwater image enhancement quality evaluation network model to obtain a corresponding predicted quality score as an underwater image enhancement quality evaluation result. The method has the beneficial effects that the quality of the underwater enhanced image can be efficiently and accurately predicted.

Aspects of this disclosure relate to symbol based envelope tracking. A voltage modulator circuit can generate an output bias voltage that tracks a root mean square symbol power of a radio frequency signal. A crest factor reduction circuit in a signal path that provides the radio frequency signal can adjust a crest factor reduction threshold such that the crest factor reduction threshold corresponds to the output bias voltage.

The invention discloses a wind profile radar radial speed quality control and horizontal wind field inversion method. According to the method, through the steps of multi-mode detection splicing, signal-to-noise ratio threshold value quality control, beam consistency inspection, horizontal wind component inversion, space and time continuity inspection and the like, the quality control process of the wind field data is optimized, the precision of the horizontal wind field data is remarkably improved, and particularly, the root-mean-square error and deviation in high-level data are remarkably reduced. The core innovation comprises a mode splicing strategy based on sounding data comparison, dynamic signal-to-noise ratio threshold calculation, threshold setting of beam consistency check and a wind component compensation algorithm when a vertical beam is missing. Through experimental verification, compared with a traditional wind profile radar data processing method, the wind profile radar data processing method has remarkable advantages in data accuracy and stability.

The invention relates to the technical field of trajectory tracking control of piezoelectric motion tables, and discloses a trajectory tracking control method and device for a piezoelectric console, and the method comprises the steps: constructing an initial dynamic model of a piezoelectric motion table based on an asymmetric Bouc-Wen hysteresis model, and obtaining a to-be-identified parameter set; based on the root-mean-square error between the actual output displacement of the piezoelectric motion platform at the plurality of sampling time points and the predicted output displacement of the initial dynamical model, constructing a self-adaptation function of the parameter set to be identified; identifying and acquiring a target model parameter set by using a multi-modal Bayesian gradient optimization algorithm and taking the value convergence of the self-adaption function as an optimization target to obtain a target dynamic model; based on the target dynamic model, constructing a hysteresis state observer, and obtaining feed-forward compensation voltage; constructing a self-adaptive fuzzy PID feedback controller, and obtaining a feedback control voltage; and summing the feedforward compensation voltage and the feedback control voltage to generate a driving voltage so as to drive the piezoelectric motion table to perform trajectory tracking.

Aspects of this disclosure relate to symbol based envelope tracking. A voltage modulator circuit can generate an output bias voltage that tracks a root mean square symbol power of a radio frequency signal. A digital predistortion system in a signal path that provides the radio frequency signal can adjust a digital predistortion based on a symbol based envelope tracking state.

The invention relates to the technical field of belt conveyor carrier roller fault monitoring, and discloses a belt conveyor carrier roller fault distributed optical fiber monitoring system which comprises a double-light-source DAS system, optical fiber information acquisition, filtering preprocessing, time domain analysis, time-frequency domain analysis, phase analysis, multi-mode feature fusion, fault classification and fault position and grade output. By building a dual-light-source polarization diversity DAS system and combining an adaptive filtering preprocessing technology, high signal-to-noise ratio acquisition and noise reduction processing of vibration signals are realized, dual-light-source orthogonal polarization state transmission effectively suppresses polarization fading, wavelet packet denoising and variable-step LMS filtering collaboratively filter environmental noise and pulse interference, and the noise reduction performance of the vibration signals is improved. Meanwhile, the application of the dynamic weighted root-mean-square value and the continuous wavelet transform ensures the accurate capture of the time domain energy characteristic and the frequency domain time-varying characteristic, and lays a reliable foundation for the multi-modal characteristic fusion.

The invention provides a sea surface height abnormal data downscaling method based on deep learning, and relates to the technical field of data processing, and the method specifically comprises the following steps: preprocessing data including AVISO data, SWOT data and key auxiliary variables; an enhanced super-resolution generative adversarial network ESRGAN is constructed, a high-resolution feature map is generated, and the ESRGAN comprises a generative network and a discrimination network; using a plurality of loss function combinations to optimize the performance of the generative network and the discriminant network, including adversarial loss, perception loss and pixel loss; and evaluating the pixel-level error and the spatial detail consistency output by the ESRGAN by adopting a root-mean-square error and a structural similarity index respectively. According to the technical scheme, the problems that in the prior art, a data downscaling method is limited in applicability and generalization ability, and is difficult to adapt to fusion requirements of different regions and multi-source data are solved.

The invention discloses a visible light and infrared fusion target detection method and system for an all-time unmanned aerial vehicle scene, and belongs to the technical field of unmanned aerial vehicle aviation and intelligent image processing. The method comprises the following steps: analyzing an original visible light image to calculate average brightness and root-mean-square contrast, and quantifying scene illumination conditions; distortion correction and registration are carried out on the original image; a parallel backbone network is adopted to extract visible light and infrared twinborn feature maps, the number of channels allocated to two modal features is dynamically adjusted through 1 * 1 convolution according to illumination condition parameters, and then a dual-light fusion network containing a gated convolution block is utilized to perform weighted fusion; and target prediction is carried out through the progressive feature pyramid network. Through an illumination adaptive fusion strategy and targeted data enhancement, the precision and robustness of target detection in a complex all-day scene are significantly improved, and the method is suitable for real-time target detection tasks of the unmanned aerial vehicle.

The invention provides a fuse slow fusing fault detection method based on phase voltage correlation characteristics. The method comprises the following steps: acquiring three-phase phase voltages of a plurality of nodes at the upstream and the middle and downstream of a line, performing normalization and sliding window processing on the acquired phase voltages, and inputting the phase voltages into a neural network model for training; the fuse anomaly detection method based on the neural network is constructed according to the characteristic that phase voltage may slightly drop when the fuse is slowly fused and by combining priori knowledge of voltage regular change of each node of a line, and a phase voltage reconstruction value is updated in real time by mining nonlinear characteristics among voltage data of each node through the neural network. And finally, according to whether the root-mean-square error between the actual value and the reconstruction value of the phase voltage exceeds an adaptive threshold value, identifying that the fuse is abnormal. Example results show that the method can effectively identify the slow fusing process of the fuse, and a foundation is laid for reliable operation of a protection system and improvement of operation and maintenance efficiency.

The invention provides an Internet of Vehicles broadcast frame radio frequency fingerprint identification method based on LMMSE channel estimation. The method comprises the following steps: obtaining subcarrier data in a resource grid based on an obtained signal of a physical side link broadcast channel; performing root-mean-square delay expansion and channel autocorrelation matrix construction based on the subcarrier data, and combining priori signal-to-noise ratio regularization and time domain windowing operation to obtain a channel estimation value; initial radio frequency fingerprint features are obtained through the channel equalization and the channel estimation value, and the improved neural network and the initial radio frequency fingerprint features are utilized to carry out classification identification on the Internet of Vehicles equipment. Influences of noise and channels on fingerprints are effectively considered, and the purpose of extracting fingerprints of different devices in a complex environment more accurately is achieved.

The invention relates to a rainfall nowcasting method based on U-KAN grading loss weighting and frequency self-adaption, which comprises the following steps: (1) carrying out quality control and screening on a radar puzzle, and establishing a data set; (2) dividing a training set, a verification set and a test set, and standardizing; (3) constructing a U-KAN model, selecting training parameters and inputting data: combining a traditional Unet structure with a KAN network to construct the U-KAN model; then performing model training to obtain a prediction result; the prediction result is restored to the original magnitude through destandardization; (4) introducing a loss function based on a root-mean-square error and grade weighting in a model training stage, and performing post-processing on model output by adopting a frequency deviation correction method; (5) integrating and averaging the forecast products processed by the two complementary strategies, and recording the forecast products as U-KANE; and (6) predicting a rainfall result in the next three hours by using radar echo data in the past one hour, and outputting a rainfall short-term and imminent forecast result by the U-KANE.

The invention provides a slope displacement monitoring method and system based on reinforcement learning and enhanced Kalman filtering, and the method comprises the steps: carrying out the preprocessing of displacement data collected by Beidou, and carrying out the abnormal value elimination, missing value interpolation and time consistency inspection; establishing a Kalman filtering model containing displacement and speed state vectors, and initializing a process noise covariance matrix Q and an observation noise covariance matrix R as initial filtering parameters; q and R matrixes are dynamically optimized through a PPO reinforcement learning algorithm, and parameter self-adaptive adjustment is achieved; carrying out displacement trend analysis on the filtered output data, marking abnormal trend data by adopting a statistical test and trend inflection point recognition algorithm, and feeding back a root-mean-square error of the abnormal trend data to a PPO algorithm to carry out parameter readjustment; data stage changes are analyzed based on a sliding window technology, independent experience playback buffer areas are set for data in different stages in PPO, and associated updating of filtering parameters is achieved. According to the invention, the precision and reliability of slope displacement monitoring are improved.

The invention relates to the technical field of electroencephalogram signal processing, and provides a brain-computer AI glasses electroencephalogram signal multi-dimensional quality dynamic detection method, which comprises the following steps: preprocessing collected electroencephalogram signals; performing task frequency band component analysis on the channel signals subjected to the matrix rank analysis, and calculating a power proportion of a target frequency band; performing maximum gradient analysis on the channel signal, and calculating the maximum gradient value of the channel signal; performing root-mean-square analysis on the channel signal, and calculating a root-mean-square value of the channel signal; performing fluctuation amplitude analysis on the channel signal, and calculating a peak-to-peak value of the channel signal; performing brain hemisphere symmetry analysis on the left and right homologous channel signals, calculating the correlation and mean square error of the channel signals, and setting a dynamic threshold according to the frequency band of the channel signals; obtaining an electrode impedance value, and mapping the electrode impedance value into an impedance score through a preset exponential attenuation function; the final quality score of the channel is obtained, and dynamic detection and real-time score updating of the electroencephalogram signal quality are achieved.

The invention relates to the technical field of motor control, in particular to a control and parameter intelligent optimization method for an anti-impact high-precision PMSM (permanent magnet synchronous motor) feeding servo system, which comprises the following steps of: S1, establishing a physical structure and a dynamic model of a PMSM driving feeding system; s2, designing a variable gain fractional order super-spiral sliding mode controller VGFSTSMC, realizing finite time convergence of position tracking errors by dynamically adjusting and controlling gain coefficients, and inhibiting system jitter; s3, designing an adaptive sliding mode disturbance observer ASMDO, and estimating and compensating unknown disturbance in real time through adaptive gain adjustment and an integral sliding mode surface; s4, identifying a system Stribeck friction model based on a least square method, and inputting the system Stribeck friction model as a friction feedforward compensation FFC to a current loop to reduce the disturbance uncertainty of the system; s5, dynamically adjusting and optimizing control parameters of the VGFSTSMC and the ASMDO by adopting an optimization algorithm so as to minimize a root-mean-square value RMSE of a position tracking error and a maximum instantaneous error; and S6, VGFSTSMC, ASMDO and FFC are combined with an optimization algorithm, and the PMSM is driven to realize high-precision position control.

A method for removing tube wave interference from optical fiber acoustic wave sensing seismic data, including: acquiring seismic wavefield data which contains a tube wave and is collected by an optical fiber acoustic wave sensing instrument; calculating a root-mean-square amplitude of the waveform data cut on the seismic trace as an amplitude normalization factor; performing normalization processing on the amplitude value; performing de-tail mean filtering processing on the normalized amplitude value along the travel time of the tube wave, to obtain a predicted amplitude value; performing tube wave interference removal processing on each seismic trace, and performing inverse normalization processing to obtain the seismic wavefield data without tube wave interference. The method effectively suppresses the tube wave interference in the optical fiber acoustic wave sensing seismic data. An apparatus for removing tube wave interference from optical fiber acoustic wave sensing seismic data, and a computer device are further provided.

The invention discloses a monitoring and early warning method for wind-induced abnormal vibration of a cable-stayed bridge cable, and the method comprises the steps: calculating an energy concentration coefficient R according to a vibration intensity peak value P1st corresponding to a first large peak value and a vibration intensity peak value P2nd corresponding to a second large peak value; adding the energy concentration coefficient R into the array {R} to obtain an array {R} of bmin, and calculating the acceleration root mean square of the vibration acceleration data of the inhaul cable bmin according to the vibration acceleration data of the inhaul cable bmin; if k continuous energy concentration coefficients R in the array {R} of bmin exceed the early warning lower limit value and the acceleration root mean square exceeds the acceleration RMS upper limit threshold value, an early warning signal is sent out. The method has universality and effectiveness in identifying the second large vibration intensity peak value of different stay cable spectrograms, a bridge management and maintenance unit can conveniently know the abnormal vibration condition of the stay cable in time and maintain the stay cable, the service life of the stay cable is prolonged, and a guarantee is provided for safe operation of a bridge.

The invention discloses a self-adaptive threshold SAMP reconstruction method for a power quality disturbance signal. According to the method, a compression observation value is obtained by constructing a random Gaussian observation matrix, and sparse representation is carried out on an original signal by using discrete Fourier transform. In the iterative reconstruction process, the spectrum amplitude difference is introduced for the first time to serve as an adaptive termination basis, and automatic adaptation of different noise levels and different disturbance characteristics is achieved in combination with a dynamic threshold update function. According to the method, the problems of traditional SAMP sparseness overestimation and redundant iteration are effectively avoided, and the calculation load is remarkably reduced. Compared with an OMP method, an original SAMP method and the like, the method has the advantages that the number of iterations can be reduced by 30%-60%, the reconstruction signal-to-noise ratio is increased by 2-5 dB, the root-mean-square error is reduced by 10%-25%, higher robustness and real-time performance are achieved in power quality disturbance signal reconstruction, and the method is quite suitable for scenes such as compressed sampling, edge calculation and high-speed signal reconstruction in a power quality monitoring system.

The invention discloses a visual detection system and method for a TBM wall back grouting effect, and belongs to the technical field of tunnel detection, and the system comprises an acoustic signal transmitting matrix, an acoustic energy sensing matrix, a tunnel half-section synchronous lifting device, a data processing center, a core scheduling unit, a holographic data processing unit and a holographic intelligent analysis unit, the tunnel half-section synchronous lifting device comprises a tunnel half-section synchronous lifting track, a transmitting base, a sensing base, a transmitting sensing partition plate and a transmitting sensing fixing plate. According to the method, grouting attribute information of a to-be-detected area is obtained through a root-mean-square value, a longitudinal wave energy dissipation value, longitudinal wave sending and receiving time difference and a wave velocity value, a three-dimensional information model of a tunnel section is built through a holographic data processing unit based on the information, and difference data and a difference area are presented through a holographic intelligent analysis unit; therefore, visualization processing of the tunnel grouting information is achieved, and the accuracy of TBM wall back grouting effect detection is improved.

The invention provides a rolling bearing digital twinning dynamic evolution method and system based on continuous learning, and belongs to the technical field of bearing life prediction. The method comprises the following steps: processing a bearing monitoring signal through short-time Fourier transform to generate standardized time-frequency data; constructing health indexes based on the index degeneration function and dividing health levels; training a life prediction model by using the extended LSTM network and taking the time-frequency data as input; real-time data is collected through a fixed time window to predict the life, and when the root-mean-square error of a predicted value and an actual value exceeds the limit, the edge device is triggered to upload new data; evaluating parameter importance in combination with a Fisher information matrix, and dynamically adjusting a regularization intensity updating model; and monitoring the data standard deviation in real time, triggering shutdown when the data standard deviation exceeds the limit, otherwise, predicting the remaining life by updating the model, and stopping when the remaining life reaches the threshold value. According to the method, dynamic evolution of the digital twin model is realized through continuous learning, and the industrial equipment state monitoring and predictive maintenance capability is effectively improved.

The invention provides a vibration reduction buffering and posture self-adaptive adjusting method in wind turbine generator cabin transportation, and relates to the technical field of wind turbine generator transportation, which comprises the following steps: collecting transportation vibration time sequence data, after wavelet denoising and normalization processing, adopting synchronous compression decomposition and nonlinear cross-scale feature mapping to extract a dominant frequency component, and then extracting the dominant frequency component; synchronously calculating time domain parameters (a root mean square value, a peak factor and a waveform factor) and frequency domain parameters (a frequency centroid and bandwidth energy distribution); inputting the multi-dimensional features into a graph convolutional neural network to realize vibration mode classification, constructing an attitude optimization model based on a classification result, performing cooperative solution through a multi-agent depth deterministic strategy gradient algorithm, and outputting an optimal attitude adjustment parameter; after the adjustment is implemented, new vibration data are collected to update network parameters, and closed-loop control of vibration feature recognition and attitude optimization is formed. Transportation vibration impact is effectively reduced, and the transportation stability and safety of wind power equipment are improved.

The invention provides a combustion device CO2 emission concentration prediction method based on a CNN-LSTM model, and the method comprises the following steps: screening an input variable data set according to a correlation coefficient between each input variable and the CO2 emission concentration; performing data conversion processing; constructing a CNN-LSTM model as an initial prediction model, inputting the training set into the initial prediction model for training until the average absolute error loss is less than 5%, and storing the model as a training model; changing hyper-parameters of the initial prediction model, performing multiple times of training, and selecting a training model with the minimum root mean square error and the maximum decision coefficient as a final prediction model; and inputting the relevant characteristic variable parameters of the current time step into the final prediction model to obtain a CO2 emission concentration prediction value of the next time step. The CO2 emission concentration of the combustion device can be accurately predicted in real time.

The invention discloses a soil water content inversion method based on improved combination roughness, and relates to the field of remote sensing, and the method comprises the steps: synchronously obtaining a Sentinel-1 radar image and a Sentinel-2 optical image, and extracting different polarization backscattering coefficients, local incident angles and normalized water body indexes through preprocessing; the method comprises the following steps: generating a bare soil simulation backscattering coefficient data set, removing vegetation scattering contribution by using a water cloud model, obtaining a real bare soil backscattering coefficient, constructing a training set and a verification set containing actually measured soil water content, constructing a lookup table based on double models, and calculating the water content of the bare soil by minimizing a root-mean-square error between simulation and the real backscattering coefficient. Global search is carried out in a preset parameter space to determine an optimal earth surface root mean square height and a correlation length, a novel polynomial combination roughness is constructed, a physical correlation between the roughness and a backscattering coefficient is established, a dual-polarization empirical equation set is constructed, and simultaneous solution is carried out after parameters are optimized according to a criterion; according to the method, a more reasonable inversion result of the soil water content in a large range can be obtained.

The invention discloses a method and a device for evaluating the measurement uncertainty of an automatic verification line of an electric energy meter, and the method comprises the steps: analyzing each uncertainty source according to the structure of the to-be-evaluated automatic verification line of the electric energy meter and the environment condition of the to-be-evaluated automatic verification line of the electric energy meter, so as to determine each uncertainty component for evaluation; the same installation type standard electric energy meter is adopted to carry out a measurement experiment, data measured by the installation type standard electric energy meter is used as a reference value, and a relative error between the data measured by the installation type standard electric energy meter and data displayed by a working standard meter is used as a basic error of the automatic verification line of the electric energy meter. Calculating the value of each uncertainty component; taking the root mean square of the value of each uncertainty component as the synthesis standard uncertainty of the electric energy meter automatic verification line; and multiplying the synthesis standard uncertainty by a set confidence factor to obtain an evaluation result of the expansion uncertainty of the automatic verification line of the electric energy meter. According to the method, the measurement uncertainty can be evaluated more comprehensively and accurately.

The invention discloses a TR assembly gold wire bonding process parameter prediction method based on a multilayer perceptron neural network, and belongs to the technical field of microwave device intelligent manufacturing. According to the method, an intelligent mapping model of gold wire bonding geometric parameters and radio frequency performance is constructed by fusing a multi-layer perceptron neural network and parameterized electromagnetic simulation. The method specifically comprises the following steps: generating 45 groups of samples in a process parameter space by adopting Latin hypercube sampling; obtaining an S parameter data set through batch processing electromagnetic simulation; box-Cox conversion and normalization preprocessing are carried out on the data; the method comprises the following steps: constructing an MLP neural network model of a 3-32-16-2 structure, and determining hyper-parameters by using Bayesian optimization; and after training is completed, rapid reverse mapping from target performance to process parameters is realized. According to the method, the number of traditional tests is reduced from more than 200 to 45, the predicted root-mean-square error of S21 is smaller than or equal to 0.12 dB, the determination coefficient is larger than or equal to 0.96, and the parameter backstepping time lt is obtained; according to the method, full-process automation from simulation, training, optimization to production and issuing is realized, and the development efficiency of the TR component is remarkably improved.

The invention discloses a turning signal noise reduction method based on an improved wavelet threshold, and the method comprises the steps: carrying out the multi-layer wavelet decomposition of a noise-containing turning signal, obtaining the low-frequency and high-frequency wavelet coefficients of each layer, and processing the high-frequency wavelet coefficients of each layer through an improved threshold function, thereby achieving the noise reduction of the turning signal. And reconstructing a signal through wavelet inverse transformation of the processed wavelet coefficient to realize denoising. The optimal number of decomposition layers required by a sampling signal is determined according to noise power, and finally, an optimal wavelet basis is determined by taking a signal-to-noise ratio, a mean square error and the like as evaluation indexes. By means of the improved wavelet threshold function, on one hand, the signal denoising effect can be achieved, and on the other hand, the situation that details are damaged due to excessive noise reduction can be avoided. Experimental data show that the improved threshold function effectively suppresses random errors, the signal-to-noise ratio is improved, the root-mean-square error is reduced, and the denoising effect is good.