355results about How to "Achieve noise reduction" patented technology

The invention discloses a sound insulation cabin of a turbine engine. The sound insulation cabin is arranged on the turbine engine in a sleeving mode, and comprises a cabin body, an intake noise reduction unit and a ventilation noise reduction unit; the intake noise reduction unit and the ventilation noise reduction unit are arranged on the cabin body, and the periphery of the cabin body is filledwith sound insulation materials; and the intake noise reduction unit is used for intake noise reduction of the turbine engine, and the ventilation noise reduction unit is used for noise reduction ofa ventilation system of the turbine engine. The sound insulation cabin has the beneficial effects that the intake noise reduction unit is additionally arranged at an air inlet of the turbine engine, and intake noise reduction of the turbine engine is achieved; the ventilation noise reduction unit is additionally arranged in the transmission direction of the turbine engine, and the ventilation andcooling noise reduction for the turbine engine is achieved; the periphery of the cabin body is filled with the sound insulation materials, and the overall noise reduction for the periphery of the turbine engine is achieved.

The invention relates to an SOC estimation method for a series-wound battery pack having an equalization circuit. According to the estimation method, adaptive extended Kalman filtering SOC estimation is carried out on the single batteries with the lowest voltage or the highest voltage in the charge-discharge stage so as to obtain the SOC of the series-wound battery pack. For eliminating influence on the measurement signal from noise, and for analyzing the unstable and sharply-changed voltage and current signals, wavelet transform is performed before the implementation of the adaptive extended Kalman filtering so as to realize denoising and analyzing of the signal; and the condition that the curves of the battery parameters and the open circuit voltage-state of charge (OCV-SOC) are changed along with the changes of temperatures and the changes of the SOC is taken into consideration. By adoption of the estimation method, online updating of the parameters can be performed, so that the SOC estimation precision can be improved; the SOC of the battery pack can be accurately estimated under the premise of ensuring the safety operation of the series-wound battery pack; therefore, the estimation method is applicable to active equalization and passive equalization; and meanwhile, by adoption of the estimation method, the influence from noise can be effectively eliminated, and the voltage and current signals can be effectively analyzed.

The embodiment of the application discloses an under-screen fingerprint module, an electronic device and a fingerprint image processing method. The electronic device comprises a screen and an under-screen fingerprint module arranged in a preset area relative to the screen. The screen is provided with a first polarizer, the fingerprint module under the screen is provided with a second polarizer, and the polarizing directions of the first polarizer and the second polarizer are identical; the first polarizer and the second polarizer are used for filtering the first optical noise, the first optical noise is reflected light, the reflected light is light reflected by the first light through the screen, and the first light is light irradiated in the Z-axis of the screen; the second polarizer is used for filtering the second optical noise, the second optical noise is a direct light ray, and the direct light ray is a second light ray emitted from the emitted light ray, which is reversely irradiated along the Z-axis of the screen. Embodiments of the present application are advantageous in reducing optical noise of fingerprints and improving accuracy and efficiency of fingerprint acquisitionby electronic devices.

The invention relates to the technical field of earphones and in particular relates to an earphone noise reduction method and device, a main earphone, a slave earphone and an earphone noise reductionsystem. The earphone noise reduction method is applied to a main earphone. The main earphone is wirelessly connected to the slave earphone and comprises a first transducer. The slave earphone comprises a second transducer. The main earphone and / or the slave earphone are / is wirelessly connected with an audio source apparatus. The earphone noise reduction method comprises the steps of acquiring a first environmental noise signal collected by the first transducer; receiving, based on wireless communication, a second environmental noise signal collected by the second transducer; generating, according to the first environmental noise signal and the second environmental noise signal, a first noise eliminating signal. Noise reduction of wireless earphones can be achieved. The noise reduction effect is good and the user experience is improved.

The invention discloses an audio and video processing method and apparatus of assisted live broadcast. The method comprises the following steps: reading original video streams and original audio streams through an assisted live broadcast audio and video application; processing the original video streams to obtain video streams; processing the original audio streams to obtain audio streams; aligning the timestamps of the video streams and the audio streams to generate an audio and video data packet containing the aligned video streams and the aligned audio streams; connecting cross-process communication channels of the assisted live broadcast audio and video application and a live broadcast application; and transmitting the audio and video data packet to the live broadcast application through the cross-process communication channel. By adoption of the audio and video processing method and apparatus disclosed by the invention, the blockage and crash phenomena in a live broadcast process are avoided to a larger extent, the live broadcast effect is more vivid, and the user experience is improved.

The invention provides an energy-saving control system and control method for a vibrating road roller, and the vibrating road roller. The energy-saving control system for the vibrating road roller comprises an electronically-controlled operation handle, a controller, an electronically-controlled engine, an electronically-controlled running pump, a running module and a running system, wherein the electronically-controlled engine, the electronically-controlled running pump, the running module and the running system are sequentially connected; the controller is connected with the electronically-controlled engine, the electronically-controlled running pump and the electronically-controlled operation handle; and the controller is capable of adjusting the rotational speed of the electronically-controlled engine and the displacement of the electronically-controlled running pump according to the position of the electronically-controlled operation handle. Through the energy-saving control system and control method for the vibrating road roller, and the vibrating road roller, the controller is capable of adjusting the rotational speed of the electronically-controlled engine and the displacement of the electronically-controlled running pump according to the position of the electronically-controlled operation handle, and the electronically-controlled engine is enabled to work at a good rotational speed, so that the purposes of energy saving and noise reduction of the electronically-controlled engine are realized; and meanwhile, the displacement of the electronically-controlled running pump is automatically adjusted through the controller to meet the power need of the whole system, so that the working stability and reliability of the system are ensured.

An embodiment of the invention discloses an audio signal processing method and device. The method comprises steps as follows: to-be-processed audio signals generated in a direct broadcasting process are acquired, and audio frames are extracted from the to-be-processed audio signals; a first probability, a second probability and a third probability are determined according to a transcendental audio model; the first probability is the probability that the audio frame belongs to voice, the second probability is the probability that the audio frame belongs to music, and the third is the probability that the audio frame belongs to noise; if the first probability is smaller than a first threshold or the second probability is smaller than a second threshold and the third probability is larger than a third threshold, the fact that the audio frame contains noise is determined; after the fact that the to-be-processed audio signals contain noise is determined, the audio frame belonging to noise is denoised. The method and the device can be suitable for the application scene of direct broadcasting, denoising of the audio signals is realized, and the quality of the audio signals is improved.

The invention provides a method for eliminating signal online outliers. Firstly, the elimination of outlier energy in signals is finished by performing detection and linear compression on a wavelet function after signal wavelet transformation, and simultaneously, a method for linear elimination of the outliers protects signal characteristics nearby an outlier point and avoids a concussion phenomenon caused by the elimination of the outliers; secondly, aiming at the working characteristics of a micro-machined gyroscope, a method for performing a wavelet noise reduction threshold value calculation by using a virtual outlier concept is put forward to realize the noise reduction of signals of a ship micro-machined gyroscope; and finally, micro-machined gyroscope actually-measured signals containing the outliers and noises are filtered by using the method provided by the invention to ensure that a signal-to-noise ratio higher than that obtained by a universal threshold value noise reduction method is obtained while reducing the concussion nearby the outlier point. The method used for filtering has a small influence on a signal value nearby the outlier point, and the filtering effect is smoother.

The invention discloses a DVL-assisted SINS robust on-moving initial alignment method. The DVL-assisted SINS robust on-moving initial alignment method comprises the following steps of step (1), acquiring real-time sensor data; step (2), establishing a vector apparent motion parameter equation; step (3), on the basis of establishing the vector apparent motion parameter equation, estimating a parameter matrix through adaptive robust Kalman filtering; step (4), establishing reconfiguration vectors based on estimated parameters; step (5), through an optimal base quaternion attitude determining method, computing the error angle between a determined attitude and a real attitude; step (6), setting an initial alignment moment as M and a real-time data acquiring moment as k, if k=M, outputting an initial alignment result and completing an initial alignment process, and if k<M, determining that the initial alignment process is not completed, and repeating the above steps of (1) to (5) until theinitial alignment process is completed. The DVL-assisted SINS robust on-moving initial alignment method solves the problems of poor alignment precision and divergent alignment processes when system measured noise is abnormal.

The invention discloses a wind power plant short-term wind power prediction method based on VMD-FCM-GRU, and belongs to the technical field of wind power prediction. The method comprises the followingsteps: firstly, obtaining a series of finite stable subsequence components based on a VMD normalized complex wind power time sequence, clustering the subsequence components by using an FCM algorithm,clustering the subsequences with similar fluctuation trends, and superposing the subsequences so as to shorten the training time; and training a GRU neural network for prediction by using the clustered sequences, and superposing and reversely normalizing prediction results of the sub-sequences to obtain a final prediction result. According to the method, in combination with the strong calculationefficiency of the GRU, the VMD-FCM-GRU combined model can realize relatively good prediction precision and relatively short training time, and the precision and speed of short-term wind power prediction can be remarkably improved.

The invention discloses an SAR image noise reduction method based on shear wave coefficient processing and belongs to the technical field of digital image processing. The SAR image noise reduction method based on shear wave coefficient processing comprises the steps of based on the sparsity of converted image shear wave coefficients, firstly establishing a sparse representation model based on the image shear wave coefficients, and then realizing unbiased estimation on sparse representation coefficients in statistical mean sense by use of a Stagewise Orthogonal Matching Pursuit (StOMP) algorithm and reconstructing the sparse-represented shear wave coefficients into a noise-reduced image, making up for the loss of image details due to the partial lost coefficients in sparse representation, performing further iterative denoising on the result of the projection reconstruction of the image in the shear wave function space corresponding to the lost coefficients by use of the capacity of a shear wave function corresponding to the part of coefficients in extracting image edge details in combination with an energy functional-based Total Variation (TV) method, and finally, obtaining a denoised image rich in details; as a result, the speckle noise of the SAR image is suppressed and the detail texture of the image is also maintained; the SAR image noise reduction method based on shear wave coefficient processing can be applied to SAR image noise reduction.

The invention discloses an urban dynamic early warning system and method based on accident risks. Position information and speed information of a vehicle are obtained through a vehicle terminal; driving state information of the vehicle, a traffic flow and road condition information are acquired and analyzed by matching a road section monitoring terminal; various parameters when an accident occurscan be accurately and comprehensively acquired; each parameter is processed through an early warning push terminal; the reason, the high-incidence road section and the accident characteristics of theaccident are obtained through analysis; and thus under certain road condition information, the vehicle running speed interval with the maximum accident occurrence proportion is obtained. After the vehicle enters the high-incidence road section, the speed information and the road condition information of the vehicle are detected in real time; and when the accident characteristics are met, early warning is pushed to remind the driver. After the reason of the accident is analyzed, the noise reduction of the data is realized by removing the accident record corresponding to the accident caused by the human factor, so that the accuracy of the relevance between the driving speed and the road condition state is improved, and the accuracy of early warning is further improved.

The invention relates to an MP3 compressed domain audio self-adaptation noise reduction method. The method is directly used for noise reduction on MP3 compressed domain. Firstly, MDCT coefficient is extracted from MP3 audio data containing noise, and activity detection is carried out on MP3 audio based on MDCT spectrum energy characteristic, so as to distinguish active audio band and mute band. Meanwhile a normal inverse Gaussian (NIG) distribution function is adopted to carry out prior statistic modelling on the MDCT coefficient according to the sparse property of the MDCT coefficient after MDCT coefficient is extracted form MP3 compressed audio data. Then a maximum posterior probability estimator based on NIG prior probability model is designed according to Bayesian theory, so as to obtain corresponding audio band attenuation factor. In the attenuation noise part, the attenuation factor is utilized to attenuate noise of the audio band, and attenuation iteration number is adaptively adjusted according to the attenuation weight of mute band audio, so as to realize noise reduction. Experiment result shows that noise in MP3 audio can be effectively eliminated by adopting the noise reduction algorithm of the invention, signal to noise ratio of compressed audio is improved, and MP3 audio after noise reduction has good quality.

The invention discloses an ultrasonic signal processing method based on an auto-encoder. The method includes preprocessing an ultrasound signal, and then superposing samples of the ultrasonic signals,establishing and classifying a sample library of the ultrasonic signals, compressing and decompressing the ultrasonic A scanning signals through an automatic encoder established through a neural network, obtaining related weights and bias variables of the feature functions based on deep learning, and performing noise reduction processing on subsequent ultrasonic signals by taking the related weights and bias variables as noise reduction parameters. The method is good in signal noise reduction screening compatibility, small in operand and low in calculation cost, and the feature extraction accuracy of the noise reduction auto-encoder is improved.

The invention provides a virtual outlier noise reduction method of micro-inertial device signals, which comprises the following steps: (1) for continuous signals with noise, intercepting fixed-length data quantity to be recorded as a sequence A; (2) carrying out symmetric extension on the sequence A to finish wavelet decomposition; (3) averaging wavelet functions after sequence decomposition, and computing signal variance; (4) computing the outlier, and eliminating a threshold; (5) carrying out noise reduction treatment on the wavelet functions by utilizing the computed threshold T; (6) repeating step (2) to step (5) until the number of the decomposed layers reaches the set value; (7) finishing reconstruction of the signals by utilizing the treated wavelet functions, and realizing noise reduction treatment on the signals at the intercepted section; and (8) repeating step (1) to step (7) to realize continuous noise reduction of the signals. When filtering the measured signals of a micro-mechanical gyroscope with the outlier and noise by aopting the method of the invention, oscillation near an outlier point is reduced, and a signal-to-noise ratio which is higher than that acquired by the universal threshold noise reduction method can be acquired.

The invention discloses an electric oil-free main air compressor, and belongs to the technical field of air compressors. The electric oil-free main air compressor comprises a fan, an air compressor body, a motor, a cooler, dampers, water drainage electromagnetic valves, a pull rod and a housing. The cooler comprise a middle cooler body and a rear cooler body. At least four dampers are mounted on a fan support and a motor support correspondingly, and are connected with an automobile body. The water drainage electromagnetic valves are mounted at the lower end of the middle cooler body and the lower end of the rear cooler body. The pull rod enables the motor support and the air compressor body to be connected and locked. A damping material layer is arranged in the housing, and the air compressor body is composed of a main shell and a compression cylinder assembly. A bent axle is arranged in the main shell, and the compression cylinder assembly is in an X shape and is composed of at least one high-pressure cylinder assembly and at least two low-pressure cylinder assemblies. According to the electric oil-free main air compressor, the potential hazards of oil leaking and mixing of the air compressor are avoided through air cooling, and the maintaining cost is lowered; the compression cylinder assembly forms reasonable air flow direction, and the maximum cooling efficiency is achieved; damping materials are coated on the housing, and noise is lowered.

The invention relates to a particle damping rubber vibration isolator of an engine. According to the technical scheme, the upper end face and the lower end face of vibration isolation rubber (3) are in vulcanizing bonding with a corresponding upper connecting plate (2) and a corresponding lower connecting plate (4), a lower connecting bolt (5) is fixed onto the lower plane of the lower connecting plate (4), an upper connecting bolt (1) is fixed onto the upper plane of the upper connecting plate (2) and a damping rod (7) is fixed onto the lower plane of the upper connecting plate (2). The upper connecting bolt (1), the upper connecting plate (2), the vibration isolation rubber (3), the lower connecting plate (4), the lower connecting bolt (5) and the damping rod (7) are coaxially connected. The vibration isolation rubber (3) is a hollow cylinder, the hollow part of the hollow cylinder forms a closed damping cavity (8) with the upper connecting plate (2) and the lower connecting plate (4), particle damping materials (6) are placed in the damping cavity (8) and the particle damping materials (6) occupy 50-85% of the volume of the damping cavity (8). The particle damping rubber vibration isolator of the engine is simple and reliable in structure, convenient to manufacture and low in cost, has the dynamic characteristics of low-frequency high dynamic stiffness and large damping and also has the dynamic characteristics of high-frequency low dynamic stiffness and small damping.

The invention relates to a movable plant wall, in particular to a special movable plant wall for an external building wall, and aims to solve the problems that heat island phenomena in cities are caused and urban air pollution is increasingly serious due to small floor areas of greenbelts because of limited space of urban building groups and the greenbelts and central greenbelts are further from residential areas. A scheme I and a scheme II are included, the similarity between the schemes is that each of the schemes comprises a fixed frame, a plant planting wall assembly and a plurality of guide devices, the fixed frame is fixedly connected onto the external building wall, the plant planting wall assembly is arranged in the fixed frame and is in sliding fit with the fixed frame, the plurality of guide devices are arranged on the fixed frame, and the plant planting wall assembly is connected with an indoor wall through the plurality of guide devices; the difference between the schemes is that structures of the plant planting wall assemblies are different; a resident can irrigate plants through water guide plates in the scheme I, and the plant planting wall assembly can collect rainwater automatically and irrigation can be realized without watching in the scheme II. The movable plant wall system is applied to building groups.

The invention discloses an image noise reduction method based on an image block prior estimation mixed framework, and specifically relates to prior estimation of image blocks, and an image noise reduction method. The prior estimation involves classifying the image blocks through detecting image structures and performing image noise reduction on the classified image blocks according to different image results by using an image block expected logarithm likelihood estimation and an image block coupling-three-dimensional filtering method. According to the invention, by use of the image noise reduction method based on the image block prior estimation mixed framework, noise reduction can be realized relevantly according to different image block structures, and experiment results show that the method, compared to other noise reduction methods, has the advantage of better-robustness noise reduction.

The invention discloses a shakeproof part of a compressor pipeline, a compressor assembly and an air conditioner. The shakeproof part comprises a body and shearing thickening fluid contained in the body; a containing cavity arranged in a seal manner is formed in the body, the containing cavity is filled with the shearing thickening fluid, and the body is used for being attached to the side wall of the compressor pipeline so as to relieve vibration of the compressor pipeline. According to the technical scheme, the shearing thickening fluid is injected into the body, on the basis of the damping self adaptation of the shearing thickening fluid, under the different vibration frequencies, the damping and the self-adaptation vibration state can be changed, absorbing of the vibration energy is achieved, vibration is effectively relieved, and noise reduction is achieved.

The invention belongs to the technical field of noise reduction, and discloses a sound absorbing device. The sound absorbing device comprises a sound absorbing unit body, and the sound absorbing unitbody comprises a porous sound absorbing device and a resonant sound absorbing device; the porous sound absorbing device comprises a porous sound absorbing layer, and a tube cavity is formed in the porous sound absorbing layer; the resonant sound absorbing device comprises a resonant tube and a sound absorbing tube; the resonant tube is mounted in the tube cavity in a matched mode; and a through hole is formed in the top of the resonant tube, the sound absorbing tube is mounted in the through hole in a matched mode, and both the two ends, in the resonant tube, of the sound absorbing tube are open. The sound absorbing device is provided with the porous sound absorbing device and the resonant sound absorbing device, thus a parallel sound absorbing structure is formed, and the overall sound absorbing performance to low, medium and high frequency wide band sound waves is good; and the sound absorbing performance can be improved within the limited thickness.

The invention relates to the field of noise reduction and discloses an active noise reduction device for a motor of an electric or hybrid electric vehicle. The active noise reduction device comprises a noise reduction shell and a controller. A motor body is sleeved with the noise reduction shell, and a gap is arranged between the noise reduction shell and the motor body. A plurality of horns are evenly distributed on the inner wall of the noise reduction shell. The controller is connected with the horns and is used for driving the horns to generate sound waves in order to offset the noise, wherein the sound waves are opposite to the noise generated by the motor in phase and identical to the noise generated by the motor in amplitude. The horns are HI-FI horns. An opening of the noise reduction shell faces one end of the output shaft of the motor body, and the opening is shaped like an inwards contracted frustum. The active noise reduction device can be used for processing the high-speed noise of the motor of the electric or hybrid electric vehicle, and therefore good finished vehicle NVH performance can be achieved.

An embodiment of the invention provides an audio noise reduction method and device. The method comprises the following steps: obtaining an audio signal to be processed and carrying out filtering processing on the audio signal to generate a noise reduction control signal same in value and opposite in phase with the audio signal; when detecting that signal amplitude at some time point of the noise reduction control signal meets an amplitude limit starting threshold value, starting an amplitude limiter, and carrying out attenuation processing on the signal amplitude corresponding to a time point after the time point, wherein since one condition under which howling occurs is that the signal amplitude reaches a certain value, by reducing the signal amplitude corresponding to the time point after the first time point, the howling occurrence condition can be damaged, and occurrence of the howling can be prevented; and at last, outputting the noise reduction control signal obtained after attenuation processing, and carrying out superposition on the noise reduction control signal obtained after attenuation processing and the noise signal to realize noise reduction of the audio signal to be processed.

The invention relates to a low-rank characteristic-based frequency modulation sequence matrix noise reduction and target detection method. The method includes the following steps that: received signals of L periods are continuously obtained, and the received signals are down-converted to a base band, and beat signals of L periods can be obtained; discrete sampling is performed on the beat signals, so that an L-row and N-column matrix S can be obtained; based on two sets of random sampling, nuclear norm optimization solution is performed obtained matrixes respectively, and a noise reduction result S' can be obtained; N<FFT>-point FFT is performed on each row of the matrix S', so that a matrix SR can be obtained; N<FFT>-point FFT is performed on each column of the matrix SR, so that a matrix SRD can be obtained; and two-dimensional average unit-ordered statistics constant false alarm rate detection is performed on the matrix SRD, and the distance and speed of a target are extracted. According to the method of the invention, nuclear norm optimization solution can be performed on the matrixes through utilizing a matrix filling theory according to the low-rank characteristics of signals, and therefore, noise reduction of the two-dimensional matrix can be realized, and a signal to noise ratio can be improved effectively; and based on the two-dimensional average unit-ordered statistics constant false alarm rate detection, noise estimation in Doppler domain can be improved, and problems existing multi-target detection can be solved.

The invention discloses a weapon bay noise suppression device based on environment gas jet. The weapon bay noise suppression device is installed at an opening of a weapon bay (11) and comprises a plenum chamber (2) which is connected along an airflow direction and is provided with a small opening and a large cavity, and a jet flow opening cover (4) provided with a jet flow outlet (6), wherein the jet flow outlet (6) with long and thin rectangular cross section is positioned at the front edge of the weapon bay (11). The weapon bay noise suppression device is installed inside the weapon bay, environment gas is utilized as an air source, the intensity of noise in the bay when the weapon bay is started is reduced by spraying gas flow to the opening of the weapon bay, the aerodynamic configuration of an aircraft cannot be damaged, also high-pressure air source does not need to be additionally supplied, the service life is long, and stable and reliable effects are achieved.

The invention discloses a multi-sensor video fusion and de-noising method and device. The method comprises the steps of converting the input video frame to a frequency domain, and separately generating a low-frequency sub-band coefficient and a high-frequency sub-band coefficient; separately fusing the low-frequency sub-band coefficient and the high-frequency sub-band coefficient; and performing inverse transformation on the fused low-frequency sub-band coefficient and high-frequency sub-band coefficient to obtain fused video. Therefore, the multi-sensor video fusion and de-noising method and device can realize multi-sensor video trans-scale fusion and de-noising by video frame decomposition based on three-dimensional shearlet transformation, high-frequency coefficient fusion strategy based on 3D PCNN (Pulse Coupled Neural Network) and low-frequency coefficient fusion strategy based on remarkable 3D PCNN.

The invention relates to a pump-valve compound control hydraulic system for a full-hydraulic straightener, and belongs to the technical field of electro-hydraulic servo of full-hydraulic straighteners. The pump-valve compound control hydraulic system is characterized in that based on the variable frequency electronic technology, a variable frequency motor and a variable pump are used for replacing a common three-phase asynchronous motor and a constant displacement pump, the novel pump-valve compound control hydraulic system is provided by fusing respective advantages of pump control and valve control and combining energy accumulator units, by means of the variable rotating speed and variable displacement compound control, comprehensive indicators of the hydraulic system are increased greatly, noise reduction, high efficiency and energy conservation of the hydraulic system are achieved to the greatest extent, energy can be saved by 20-60%, and efficiency can be improved by 5-30%; by embedding the pressure conversion gain and position conversion gain, triplex control over the position, the flow and the pressure is achieved, the response speed of the hydraulic servo system is increased, and the intelligence degree of the hydraulic servo system is improved.

The invention discloses a noise reduction method of weak labeling data based on regularized label propagation, which comprises the following steps: 1, obtaining a required weak labeling sample data set from a crowdsourcing data platform; 2, constructing a local neighborhood structure for that weakly labeled image sample data; 3, solving the sample nearest neighbor weighted similarity matrix of thelocal neighborhood structure; 4. Constructing a noise reduction model based on system state consistency for local neighborhood structure under weak supervision; 5, solving that noise reduction modelbased on the regularize label propagation method, and achieving the noise reduction of the weakly labeled sample data set. By constructing a local neighborhood structure of weak labeling data, Considering the whole weak labeling sample data set as a system, a denoising method of weak labeling data is proposed from the viewpoint of system consistency, which realizes the denoising of weak labeling data, optimizes the labeling quality of sample data set, and does not require manual experience or expert intervention in the denoising process, effectively improves the denoising accuracy and reducesthe efficiency.

The invention discloses an oil-electricity hybrid power vehicle energy management control system which comprises a fuel oil power generation set, a traction converter, a power battery and a traction motor, wherein the traction converter comprises an AC / DC (Alternative Current / Direct Current) module, a DC / AC electronic switch, a support capacitor and a DCU (Deceleration Control Unit) controller; the fuel oil power generation set is connected with the traction motor and auxiliary equipment through the AC / DC module and the DC / AC electronic switch; the fuel oil power generation set is controlled through an excitation driving module; the power battery is connected with the AC / DC module and the DC / AC electronic switch respectively; both ends of the power battery are connected with the support capacitor in parallel; brake resistors are connected in parallel with both ends of the power battery. The working time of a fuel engine is greatly shortened, in addition, the fuel engine mainly works ata rated power or an economical operation range, both the traction demand of a vehicle can be met, and the oil consumption and the operation cost can be greatly reduced, waste gas emission and noise can be reduced, and the purposes of energy conservation, emission reduction and noise reduction can be achieved.

Disclosed is a rolling bearing early fault feature extraction method. The invention provides a rolling bearing early fault feature method based on sparse optimization, and the method comprises a first step of acquiring acceleration signals of a rolling bearing as signals to be analyzed; a second step of establishing a sparse optimization function of the signals to be analyzed, and solving for period impact components in the signals to be analyzed; and a third step of conducting an envelope demodulation analysis of the period impact components to obtain the fault feature frequency. The invention makes use of the prior knowledge that the rolling bearing fault signals have sparsity, does not need the coefficient sparsity under dictionary transform based on fault signals, and avoids the problem of diagnostic errors caused by the selection of an inappropriate dictionary.