Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

1860results about How to "Improve noise reduction" patented technology

Laser radar signal processing and wind speed estimation method and system based on coherent detection

The invention provides a laser radar signal processing and wind speed estimation method and system based on coherent detection, and relates to the technical field of laser measurement, and the method comprises the steps: obtaining an echo signal and a reference signal of a wind measurement laser radar, carrying out the frequency mixing and filtering processing, generating a difference frequency signal, carrying out the noise reduction and background suppression, and obtaining difference frequency signal data; performing time-frequency analysis according to a window function and resolution of spectrum analysis to generate a Doppler spectrum and a time-frequency spectrum; doppler frequency shift, spectrum width and signal-to-noise ratio are extracted, wind field parameters are estimated, fine correction and adaptive compensation are carried out, a special flow mode is identified, advanced semantic features are extracted, and fine wind field parameters are obtained; constructing a global wind field model, converting adaptive scanning optimization into a Markov decision process, determining an action space and a state space, setting a reward function, combining with a reinforcement learning algorithm to solve and obtain an optimal scanning strategy, performing wind field state prediction, and generating a state prediction report.
Owner:BEIJING XINHONG ENERGY TECHNOLOGY CO LTD

Image deep learning noise reduction method for low-illumination scenes such as night and tunnel

The invention belongs to the technical field of image processing, and particularly relates to an image deep learning noise reduction method for low-illumination scenes such as night and tunnels. The method comprises the following steps: step 1, carrying out nonlinear mapping on a target low-illumination scene image, and then carrying out adaptive enhancement to obtain an intermediate image; 2, performing multi-scale decomposition on the intermediate image by using wavelet transform, and estimating a noise standard deviation on each scale; 3, calculating an adaptive threshold value of each scale and spatial position based on the estimated noise standard deviation and the environment illumination intensity; and a tunnel effect is considered, a tunnel entrance area and a tunnel exit area corresponding to rapid brightness change in the intermediate image are compensated to obtain a compensation image, and the adaptive threshold of each scale space position is applied to the compensation image to obtain a noise reduction image. According to the method, the noise reduction effect and the detail retention capability of the low-illumination image are remarkably improved, and the adaptability of the method is enhanced.
Owner:CHENGDU NUOBIKAN TECH CO LTD

Intelligent glasses audio processing method and system

The invention discloses an intelligent glasses audio processing method and system. The method comprises the following steps: data preparation: collecting source domain data and target domain data; pre-training the model; converting the audio signal into sequence data; an RNN model is constructed and trained; model migration: migrating the pre-trained RNN model to target domain data, and processing noise in the target domain data by using parameters and features of the pre-trained model; intelligent analysis and processing, wherein noise in target domain data is analyzed and processed by using the migrated RNN model; real-time processing and feedback are carried out, audio signals captured by a microphone of the intelligent glasses are analyzed in real time, and a noise reduction strategy is dynamically adjusted to eliminate background noise; and optimizing noise reduction parameters and strategies according to the feedback. By collecting the source domain data and performing model pre-training, the RNN model can identify and process various known noise types and features and quickly adapt to different noise environments, so that the noise reduction effect is improved, and a user can obtain the optimal hearing experience in different noise environments.
Owner:SHENZHEN TIANQU XINGKONG TECH CO LTD

Method and system for detecting temperature of wiring terminal of electric energy meter

The invention relates to the technical field of temperature measurement, in particular to an electric energy meter wiring terminal temperature detection method and system, and the method comprises the steps: obtaining the temperature data and current data of each wiring terminal of each electric energy meter in different time periods within a preset time period, the environment temperature of each electric energy meter, and the structure data of each electric energy meter; determining a heat dissipation condition coefficient of the wiring terminal in the time period; selecting a first time period which simultaneously satisfies a subtraction interval in the current fitting curve of all the wiring terminals of the electric energy meter, and selecting a second time period in which the mean value of the current data of each wiring terminal is the lowest from the first time period; determining an external influence index of the wiring terminal in the time period; calculating the electromagnetic interference intensity of the wiring terminal in the time period; and after parameters of Wiener filtering are set to be electromagnetic interference intensity, temperature data of the wiring terminal in the time period are subjected to noise reduction processing. According to the invention, the noise reduction effect of the temperature detection data is improved, and the authenticity and accuracy of the temperature detection data after noise reduction are further improved.
Owner:海燕接线盒有限公司

Vibration frequency analysis method and system for pavement compaction

The invention discloses a vibration frequency analysis method for pavement compaction. The method comprises the following steps: collecting a vibration signal; acquiring a local maximum value point and a local minimum value point of the vibration signal; fitting an upper envelope line and a lower envelope line of the vibration signal to obtain an optimized envelope line; the vibration signal is subjected to chaotic mapping to determine the fitness value of each initial component; judging whether the initial value is correct or not, and if yes, updating iteration; if not, iteration is carried out after sine algorithm updating; iterating the optimal solution of the fitness value of the initial component, selecting the optimal k and alpha, determining k and alpha, and performing VMD decomposition; if so, decomposing the vibration signal into a fundamental wave signal and a plurality of harmonic wave signals, performing spectrum analysis on all IMF components obtained by decomposing the vibration signal by applying Hilbert transform, and respectively calculating to obtain the instantaneous frequency and instantaneous amplitude of each IMF component to obtain the Hilbert spectrum of the vibration signal; errors such as spectrum leakage and a fence effect are reduced, and the method has the advantages of being high in adaptability, good in noise reduction performance and the like.
Owner:THE FOURTH CIVIL ENG CO LTD OF CREC SHANGHAI GRP +2

Fault monitoring method and system applied to digital power distribution network

The invention relates to the technical field of power distribution network fault monitoring, in particular to a fault monitoring method and system applied to a digital power distribution network. The method comprises the following steps: firstly, dividing each fault time period from a to-be-filtered time period; according to the difference condition of the fault responsivity of all the monitoring points in each fault time period, obtaining the noise measurement of the digital power distribution network in the to-be-filtered time period; adjusting the smoothing coefficient according to the noise metric, and obtaining the adjusted smoothing coefficient of the digital power distribution network in the to-be-filtered time period; performing filtering processing on the data set in the to-be-filtered time period by using the adjusted smoothing coefficient to obtain a filtered data set; and performing fault detection based on the filtered data set. According to the method, the adjusted smoothing coefficient of the digital power distribution network in the to-be-filtered time period is reasonably set, so that the noise reduction effect is improved, and accurate fault monitoring on the digital power distribution network is guaranteed.
Owner:HAINAN NORMAL UNIV

Nonlinear ultrasonic detection signal noise reduction and feature enhancement method and system

The invention discloses a nonlinear ultrasonic detection signal noise reduction and feature enhancement method and system, and relates to the technical field of nonlinear ultrasonic detection.The method comprises the steps that CEEMDAN decomposition is conducted on detected nonlinear ultrasonic signals of concrete damage, and a plurality of intrinsic mode components IMFs are obtained; classifying and integrating the IMFs obtained by decomposition by using a sample entropy value to obtain a component IN-IMFs after classification and integration; performing variational mode decomposition on the IN-IMFs after classification and integration to obtain a group of intrinsic mode functions IMFs; and dividing the intrinsic mode function IMFs into a training data set and a test data set according to a time step length, inputting the training data set into a gating cycle unit model for training, and outputting a noise reduction and feature enhancement effect result of each IN-IMF. According to the invention, noise interference can be reduced for ultrasonic and nonlinear ultrasonic detection of damage of materials such as rocks and concrete, and nonlinear characteristics of detection signals in nonlinear ultrasonic can be enhanced.
Owner:CHONGQING JIAOTONG UNIV

Multi-mode audio processing method and system based on SOC

The invention relates to the technical field of audio processing, and discloses a multi-mode audio processing method and system based on an SOC. The method comprises the following steps: inputting multiple paths of audio input signals into an ARM processor of an SOC chip for processing, and generating a preprocessed audio data stream; inputting the preprocessed audio data stream into a basic audio processing stream executed by a digital signal processor (DSP) and a multi-modal feature extraction stream executed by an artificial intelligence (AI) accelerator in parallel; performing adaptive noise reduction processing and multi-channel audio signal sound mixing processing in the basic audio processing stream to generate a basic processing feature stream; performing multi-dimensional feature extraction and scene type identification in the multi-modal feature extraction stream to generate a high-level feature stream; according to the method, the processing capability of the SOC chip on different types of audio signals is improved, the continuity and smoothness of the reconstructed audio signals are ensured, and signal distortion is effectively avoided.
Owner:HANK ELECTRONICS

Echo cancellation algorithm

The invention discloses an echo cancellation algorithm, which comprises the following steps: S1, introducing a DNSMOS tool to screen high-quality data, and carrying out noise reduction preprocessing on data with relatively low MOS score; s2, adopting a progressive training method; s3, an alignment module based on a cross attention mechanism is adopted, and local features are extracted through depth one-dimensional convolution to improve the performance of the alignment module; s4, generating an echo time delay label by adopting an automatic labeling method; s5, calculating relative delay probability distribution; s6, improving the echo cancellation capability in a complex environment by adopting a knowledge distillation algorithm; s7, performing joint processing through delay alignment and filter coefficient estimation, and compressing the feature dimension through affine transformation to obtain a filter coefficient; s8, using an SI-SNR loss function and a PLCPA-ASYM loss function to optimize the output signal quality of the noise reduction model; and S9, introducing an audio state detection function. According to the method, the traditional signal processing and deep learning technologies are combined, an improved echo cancellation algorithm is provided, and the method has high precision, strong generalization and complex environment adaptability.
Owner:SHANGHAI SHENGHAN INFORMATION TECH CO LTD

Sound insulation cover, sound insulation cover assembly and energy storage cabinet

The utility model relates to a soundproof cover, a soundproof cover assembly and an energy storage cabinet, the soundproof cover comprises a cover body and at least one separator, the cover body is internally provided with a cavity, a first opening and a second opening, the first opening and the second opening are communicated with the cavity, the at least one separator is arranged in the cavity and divides the cavity into a plurality of sub-runners, one end of each sub-runner is communicated with the first opening, and the other end of each sub-runner is communicated with the second opening. The cover body is provided with a first arrangement area, the first arrangement area is located on the cavity wall of the cavity, and / or the first arrangement area is arranged in the cover body and communicated with the cavity, the partition piece is provided with a second arrangement area, the second arrangement area is located on the outer surface of the partition piece, and / or the second arrangement area is located on the outer surface of the partition piece. The second arrangement area is arranged in the partition piece and communicates with the cavity, and the first arrangement area and the second arrangement area are both used for arranging the noise reduction piece. Thus, the noise reduction part can make contact with airflow in the flow channel and absorb sound waves (medium-high-low-frequency sound waves) of the airflow, the noise reduction effect is achieved accordingly, the contact area of the airflow and the noise reduction part is large, and the noise reduction effect of the sound insulation cover is improved.
Owner:BYD CO LTD

OCT image intelligent classification processing method and system based on deep learning

The invention discloses an OCT image intelligent classification processing method and system based on deep learning, and the method comprises the steps: obtaining an OCT image of a target object, and carrying out the noise reduction of the OCT image; extracting an original ROI region from the OCT image after noise reduction, and performing data bias field correction processing on the original ROI region to obtain a target ROI region; performing local feature extraction on each type of features in the target ROI region, and performing feature dimension reduction on the extracted local features of each type of features by using a PCA algorithm to generate target features; and inputting the target features into a trained OCT image classification model to generate a classification result. The ROI with high quality is obtained through image noise reduction and correction processing, local features of each feature are extracted, multi-fusion feature classification is input into the OCT image classification model, and OCT image classification can be completed rapidly and accurately.
Owner:CHINA JAPAN FRIENDSHIP HOSPITAL

Generator device and control method thereof

The invention relates to the technical field of wind power generation control, in particular to a generator device and a control method thereof. The method comprises the following steps of performing real-time monitoring on noise frequency, amplitude and phase when a generator device operates, and generating a noise characteristic data set; extracting the main frequency and phase characteristics of a noise source from the noise characteristic data set, and performing reverse analysis on the data to generate reverse sound wave signal data opposite to the phase of the noise source; and the reverse sound wave generating device transmits the reverse sound wave signal data to the generator device, outputs reverse sound waves through a broadband loudspeaker, superposes the reverse sound waves and original noise in the space, and monitors the noise after noise reduction in real time to obtain noise reduction effect feedback data. According to the invention, noise characteristics are monitored in real time, matched reverse sound wave signals are extracted and reversely generated, reverse sound wave characteristics are dynamically adjusted, closed-loop adaptive control is formed, and efficient and stable noise reduction of a generator device is realized.
Owner:HAIYANG DANQING NEW ENERGY TECHNOLOGY CO LTD

Automobile road noise active control method and device based on Elman neural network

The invention discloses an automobile road noise active control method and device based on an Elman neural network. The method comprises the following steps: acquiring vibration acceleration data and in-vehicle noise data when a vehicle runs; the vibration acceleration data and the in-vehicle noise data are used for training an Elman neural network; taking a predicted noise signal output by the Elman neural network as a reference signal, and inputting the reference signal into a filter to obtain a filtered signal; playing the filtering signal in the target noise reduction area, and synchronously collecting residual noise as an error signal; adjusting the weight parameter of the filter through the error signal, and processing the reference signal through the filter with the updated weight parameter to obtain an updated filtering signal; the steps of generating the error signal and updating the weight parameter are repeatedly executed until the average noise reduction amount in the vehicle is lower than a preset condition, and a final filtering signal is obtained; and playing the final filtering signal to counteract the noise in the vehicle. According to the invention, the acoustic feedback problem and the noise transmission time delay problem caused by directly using the noise signal as the reference signal can be avoided.
Owner:WUHAN YUCHEN ELECTRONIC TECHNOLOGY CO LTD

Photovoltaic window, photovoltaic power generation building and photovoltaic power generation method

The invention belongs to the technical field of photovoltaic power generation, and particularly relates to a photovoltaic window, a photovoltaic power generation building and a photovoltaic power generation method. A photovoltaic window comprises photovoltaic glass and further comprises a vacuum glass assembly, a door and window edge covering structure and a ventilation flow channel, the vacuum glass assembly and the photovoltaic glass are arranged in parallel, and the door and window edge covering structure surrounds the edges of the vacuum glass assembly and the photovoltaic glass for packaging. The ventilation flow channel is a gap between the vacuum glass assembly and the photovoltaic glass; more than two automatic ventilation parts are arranged on one side, close to the photovoltaic glass, of the door and window edge covering structure, and when the automatic ventilation parts are opened, the ventilation flow channel is communicated with the outside; and when the automatic ventilation part is closed, the ventilation flow channel is separated from the outside. According to the invention, high-efficiency photovoltaic power generation can be carried out under the condition of unmanned supervision.
Owner:HEFEI UNIV OF TECH

Voice activity detection method and headphone

The invention provides a voice activity detection method and a headset, and relates to the field of noise reduction. The voice activity detection method comprises the steps that multiple microphone voice signals corresponding to the same frame of voice are acquired, one frame of the multiple microphone voice signals comprises a forward voice signal and a backward voice signal corresponding to the same frame of voice, the forward voice signal is a voice signal in a preset user voice transmission direction, and the backward voice signal is a voice signal in a preset user voice transmission direction; the backward voice signal is a voice signal in a direction opposite to a preset user voice transmission direction; calculating the correlation of the forward voice signal and the backward voice signal and a first energy ratio; and determining the type of the multi-path microphone voice signal based on the correlation and the first energy ratio, wherein the type of the multi-path microphone voice signal is a voice frame or a noise frame. The method can effectively improve the detection accuracy of voice activity detection.
Owner:BESTECHNIC SHANGHAI CO LTD

Silencing device for generator set container and generator set container

The silencer for the generator set container comprises a metal cavity, a first connecting device with an opening is arranged at one end of the cavity, and the first connecting device is connected with a smoke exhaust pipeline of a generator set. A second connecting device with an opening and a smoke exhaust pipeline connected with the second connecting device are arranged at the other end of the cavity; more than three partition plates for dividing the chamber of the cavity into a plurality of sub-chambers are sequentially arranged between the side close to the first connecting device and the side close to the second connecting device along the length direction of the cavity. The projections of the holes in every two adjacent partition plates in the length direction of the cavity are crossed or not overlapped; the sum of the areas of all the open holes in the rear partition plate in the smoke discharging direction is larger than or equal to the sum of the areas of all the open holes in the front partition plate; the silencing device is excellent in noise reduction performance and can meet the requirements of the diesel generating set with high power and high noise.
Owner:SHENZHEN DONGTAI MECHANICAL & ELECTRICAL EQUIPMENT CO LTD

Noise reduction device for air source heat pump unit

The utility model discloses a noise reduction device for an air source heat pump unit, which belongs to the technical field of air source heat pump units and is characterized in that effective dispersion is carried out through a breathable mesh plate, primary noise reduction treatment is carried out on airflow through a noise reduction plate, and low-frequency noise reduction treatment is carried out on noise in the airflow again through low-frequency sound-absorbing cotton. The noise reduction device for the air source heat pump unit comprises a unit body, a condenser is arranged on the unit body, air guide barrels with cooling fans are symmetrically arranged at the top of the unit body, a cooling air barrel is installed at the top of the unit body, an air guide cavity is formed in the cooling air barrel, and a ventilation mesh plate is installed at the middle section of the air guide cavity. A noise reduction plate is installed on the inner side edge of the heat dissipation air cylinder and corresponds to the position between the two breathable mesh plates, an air outlet is formed in one end of the air guide cavity, and a plurality of pieces of low-frequency sound absorption cotton are installed at the position, corresponding to the air outlet, of the heat dissipation air cylinder.
Owner:HAINING PUJIN NEW ENERGY TECH CO LTD

Voice denoising method and device under low signal-to-noise ratio

The invention provides a voice denoising method and device under a low signal-to-noise ratio, and relates to the technical field of voice denoising. The method comprises the following steps: recording audio through a microphone, and obtaining pure voice data; preprocessing the pure voice data to obtain training voice data; according to the U-net network structure and the Transform model structure, constructing a to-be-trained TFDense-Net voice denoising model, and according to the to-be-trained TFDense-Net voice denoising model; based on a multi-spectrum discriminator, according to the training voice data, an Adam optimizer is used to carry out adversarial iteration training on a to-be-trained TFDense-Net voice denoising model, and the TFDense-Net voice denoising model is obtained; the method comprises the following steps: acquiring voice data to be denoised through a microphone in a low signal-to-noise ratio environment; and inputting the voice data to be denoised into the TFDense-Net voice denoising model to obtain denoised voice data. The invention relates to a high-efficiency and clear voice denoising method under a low signal-to-noise ratio, which combines an improved dense block and a video converter.
Owner:BEIJING LANGUAGE AND CULTURE UNIVERSITY

Photovoltaic DC fault arc signal noise reduction method and device

The invention provides a photovoltaic direct current fault arc signal noise reduction method and device, and relates to the technical field of photovoltaic direct current fault arc diagnosis. The method comprises the following steps: decomposing a photovoltaic DC fault arc signal based on an IMGO-ICEEMDAN decomposition method to obtain a photovoltaic DC fault arc intrinsic mode component; calculating a multivariate intrinsic mode index, and dividing the photovoltaic DC fault arc intrinsic mode component into a high-frequency noise component, a low-frequency signal component and a noisy signal component according to the multivariate intrinsic mode index; performing noise reduction on the noisy signal component through the improved wavelet threshold to obtain an improved wavelet threshold noise reduction signal; and reconstructing the low-frequency signal component and the improved wavelet threshold noise reduction signal to obtain a noise reduction signal. According to the noise reduction method, the noise reduction effect of the fault arc signal is effectively improved while the key characteristics of the photovoltaic direct current fault arc signal are reserved, and the fault arc recognition accuracy can be remarkably improved.
Owner:UNIV OF SCI & TECH BEIJING

Electronic device for reducing wind noise and its application

The present invention provides an electronic device for reducing wind noise and its application. The raw materials of the porous block material include zeolite, adhesive and dispersant. The present invention also provides an electronic device comprising the above-mentioned porous block material. The present invention further provides an electronic device for reducing wind noise, including a body, an arc cover and a PCB board, the two ends of the body are respectively connected to the PCB board and the arc cover, the body is provided with an inner sound channel along the central axis, the arc cover is provided with an outer sound channel, the outer sound channel is in a windmill-shaped structure as a whole, including a central cavity and a plurality of branch channels, the branch channels are radially arranged around the central cavity, and each branch channel is a streamlined arc structure. The present invention further provides the application of the above-mentioned electronic device in an electronic device with a microphone. The electronic device provided by the present invention can effectively reduce wind noise and significantly improve the call quality of communication equipment.
Owner:SSI NEW MATERIAL (ZHENJIANG) CO LTD

Active noise control method based on reference signal weighting

The invention relates to an active noise control method based on reference signal weighting, and the method comprises the following steps: 1, obtaining a reference signal x (n) and an error signal e (n) needed by a system, x (n) = [x (n), x (n-1),..., x (n-L + 1)] T, and n is a positive real number and represents a time sequence; the error signal e (n) is a signal obtained by offsetting a desired signal d (n) of the area to be muffled and a secondary sound source signal; a second step of generating a secondary sound source signal through the collected signal, and performing weight updating on an adaptive filter which is composed of four parts, namely a secondary sound source signal generation module, a reference signal secondary path filtering module, a reference signal weighting module and an adaptive filter weight updating module; and step 3, evaluating and adjusting the active noise control method based on reference signal weighting by adopting the average noise reduction amount.
Owner:TIANJIN UNIV

Method and device for optimizing noise of indoor fan, air conditioner and storage medium

The invention provides a method and device for optimizing noise of an indoor fan, an air conditioner and a storage medium, operation parameters and scene information of the air conditioner are obtained, a to-be-used rotating speed relation is determined from pre-stored corresponding relations of parameters and rotating speed relations on the basis of the operation parameters, and the to-be-used rotating speed relation comprises the corresponding relation of information and rotating speed; and determining a target rotating speed based on the scene information and the corresponding relation between the information and the rotating speed, and adjusting the rotating speed of the indoor fan based on the target rotating speed to optimize the noise. Through the mode, the corresponding target rotating speed can be determined according to different operating parameters and scene information, so that the noise is optimized, the noise can be reduced under the condition that the structure of the air conditioner does not need to be changed, and the noise reduction effect can be improved.
Owner:QINGDAO HAIER AIR CONDITIONER GENERAL CORP LTD +3

Method for reducing noise of multiple microphone cores of microphone

The invention discloses a multi-microphone-core noise reduction method for a microphone, and the method comprises the steps: obtaining a multi-channel sound signal through a plurality of microphone cores of the microphone, and transmitting the sound signal to a beam forming system; the beam forming system can output processed multi-channel sound signals and transmit the processed multi-channel sound signals to the filtering control system and the self-adaptive noise elimination system. The filtering control system can output processed multichannel sound signals and transmit the processed multichannel sound signals to the self-adaptive noise elimination system and the single-channel noise reduction system; the adaptive noise elimination system can convert multi-channel sound signals into single-channel sound signals and transmit the single-channel sound signals to the single-channel noise reduction system, background noise can be effectively suppressed through technical means of beam forming, filtering control, adaptive noise elimination and the like, voice signal definition and quality are improved, and the noise reduction effect is improved. And the requirements of modern communication and audio processing equipment are met.
Owner:FUJIAN ZHENHONG ELECTRONIC TECH CO LTD

Escalator fault diagnosis method based on multi-sensor data input

The invention discloses an escalator fault diagnosis method based on multi-sensor data input. The escalator fault diagnosis method comprises the four steps of escalator original data collection, data preprocessing, fault data set setting, escalator fault recognition and cloud model updating. According to the data preprocessing, escalator signal data are filtered through an improved wavelet threshold noise reduction method; the quality of escalator signal data is improved; the fault data set is set by fusing fault data of all parts and all types of the escalator, full utilization of the fault data of the escalator is achieved, and the richness of fault category signals is improved. According to fault identification, multi-sensor data is input into a CNN-GRU network, and the CNN-GRU network extracts features in the input data and obtains a final identification result. According to cloud model updating, the CNN-GRU model is optimized by using CFOA, a network model with the optimal CNN-GRU is constructed, the recognition precision is high, the generalization performance is good, and the method can be widely applied to the field of escalator fault diagnosis.
Owner:HUNAN UNIV OF SCI & TECH

Rotor assembly and motor using same

The invention discloses a rotor assembly and a motor using the rotor assembly, and the rotor assembly comprises a rotor injection molding body which is internally provided with a hollow cavity penetrating through the two axial ends of the rotor injection molding body; an output shaft is integrally formed at one axial side end of the rotor injection molding body through injection molding; a shaft hole used for being connected with a rotor supporting shaft in a matched mode is formed between the output shaft and the hollow cavity in a penetrating mode. A magnet ring injection-molded on the outer peripheral side of the rotor injection-molded body; the fixing plug is suitable for being inserted into the hollow cavity from the end, away from the output shaft, of the rotor injection molding body. A through hole which is coaxially communicated and matched with the shaft hole is formed in the fixing plug; wherein the hollow cavity and / or the fixed plug are at least provided with a section of suspension interval which is not completely contacted with the outer wall surface of the rotor support shaft.
Owner:JIANGSU LEILI MOTOR

Silencing body, server silencer and server

The silencing body comprises a first wall and a second wall which are arranged in a spaced mode, at least one partition plate is connected between the first wall and the second wall so that at least one sound cavity can be formed between the first wall and the second wall, and an opening penetrating through the wall thickness is formed in the part, corresponding to the sound cavity, of one of the first wall and the second wall; when the number of the sound cavities is at least two, the structures and the sizes of all the sound cavities are the same, and all the sound cavities correspond to the preset target frequency, so that the noise elimination body can perform noise elimination and noise reduction on the noise of the target frequency; wherein when the size parameter of the sound cavity is determined, the target frequency of the noise absorbed by the sound cavity is acquired; determining a frequency correction coefficient; obtaining a correction frequency according to the frequency correction coefficient and the target frequency; and designing size parameters of the acoustic cavity according to the correction frequency. The silencing body corresponds to the target frequency to be eliminated, the silencing and noise reduction effect is good, and the silencing body can be modularized easily.
Owner:INSPUR SUZHOU INTELLIGENT TECH CO LTD

Active noise reduction method for OWS earphone, electronic equipment and readable storage medium

The invention relates to an OWS earphone active noise reduction method, electronic equipment and a readable storage medium. The method comprises the following steps: acquiring a noise signal through a microphone; analyzing the noise signal, and when the volume of the noise signal is greater than a preset volume threshold value, generating a noise reduction sound wave opposite to the phase of the noise signal through an electroacoustic transducer to eliminate noise; analyzing the noise signal to determine an environmental scene; when the OWS earphone is in a commuting scene, determining the phase and frequency of a noise reduction sound wave according to a noise signal collected by the microphone; calculating a noise reduction evaluation index in the commuting scene, and adjusting the phase and frequency of a noise reduction sound wave according to the noise reduction evaluation index to maintain an optimal noise reduction effect; different noise reduction modes are set according to common application scenes of the earphone, feedback can be made according to noise reduction requirements of different application scenes, the use experience of a user is not affected while the noise reduction effect is generated, and meanwhile the optimal noise reduction effect is kept through the noise reduction evaluation index.
Owner:RISUNTEK INC

Video noise reduction method and device, computer equipment and medium

The embodiment of the invention discloses a video noise reduction method and device, computer equipment and a medium, and the method comprises the steps: obtaining a target video, and traversing image frames in the target video; when the current image frame of the target video is traversed, acquiring motion information of pixel movement between the current image frame and an adjacent image frame of the current image frame, and determining a pixel-level weight map for the current image frame based on the motion information; performing noise reduction processing on the current image frame by using the pixel-level weight map of the current image frame to obtain a noise-reduced image frame of the current image frame; obtaining a noise reduction image frame of each image frame in the target video, and generating a noise reduction video of the target video based on the noise reduction image frame of each image frame in the target video; the video quality can be improved.
Owner:SHUXING TECH (BEIJING) CO LTD

Optical coherence imaging noise reduction method, device, equipment and medium

The invention discloses an optical coherence imaging noise reduction method and device, equipment and a medium, and the method comprises the following steps: obtaining a B-scan image, and constructing a training set; training an image noise reduction model based on the deep neural network by adopting the training set; obtaining a to-be-denoised B-scan image, inputting the to-be-denoised B-scan image into the trained image denoising model for denoising, and outputting a reconstructed B-scan image; wherein the image noise reduction model comprises an encoder and a decoder, and the encoder takes a B-scan image with noise as input to obtain a potential representation of the B-scan image with noise; and the decoder takes the potential representation of the B-scan with noise as input, and outputs a reconstructed B-scan noise reduction image. According to the method, the image noise reduction model is constructed through the deep neural network, the B-scan image is subjected to noise reduction, the clear B-scan image is effectively obtained, and the method has the advantages of being excellent in noise reduction effect and high in speed. The method can be widely applied to the technical field of image imaging noise reduction.
Owner:SOUTH CHINA UNIV OF TECH +1

Silicone rubber material and preparation method thereof

PendingCN119081414AAdapt to the needs of useCompensate for reduced tear strengthRubber materialPolymer science
The invention discloses a silicone rubber material and a preparation method thereof, and belongs to the technical field of organic polymer materials, and the silicone rubber material comprises the following components in parts by mass: 100-200 parts of methyl vinyl silicone rubber-based rubber, 2-20 parts of an aerogel noise reduction filler, 2-40 parts of a reinforcing filler, 3-5 parts of hydrogen-containing silicone oil, 0.05-5 parts of a catalyst, and 0.05-1 part of an inhibitor. The noise reduction effect of the silicone rubber material is improved.
Owner:GOERTEK INC