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

191 results about "Noise optimization" patented technology

Big data privacy protection modeling method and system based on federated learning and block chain

The invention discloses a big data privacy protection modeling method and system based on federated learning and a block chain, and relates to the technical field of privacy protection and joint modeling. According to the method, homomorphic encryption, differential privacy, federated learning, secure multi-party computing and block chain technologies are fused, big data privacy protection and joint modeling are realized, encryption and dimensionality reduction are performed on original data through homomorphic encryption and differential privacy, an encrypted training sample of secure privacy is generated, a local model is trained on an encrypted data set through federated learning, and a big data privacy protection result is obtained. The method comprises the following steps: calculating aggregation parameters by using security multiple parties, constructing a verification network in combination with a block chain, ensuring credibility and integrity of model training, and finally, adding noise optimization performance for a global model by using differential privacy, testing generalization ability through cross validation, and determining a deployable privacy protection joint learning model, thereby breaking traditional data islands, promoting cross-mechanism data cooperation, and improving the privacy protection performance. Big data values are released, and data protection regulations and privacy requirements are met.
Owner:TIBET CHENYUN INFORMATION TECH CO LTD

Vibration noise optimization method and system of electric drive assembly

The invention relates to the technical field of vibration noise optimization, in particular to a vibration noise optimization method and system of an electric drive assembly. The method comprises the following steps of collecting multi-working-condition vibration noise of a transmission motor in an electric drive assembly and performing frequency domain conversion to generate vibration noise frequency domain data; on the basis of the data, carrying out gear meshing stress unbalance loading limit calculation, carrying out tooth surface pitting corrosion cycle ductility simulation, and identifying a bearing clearance expansion increment; optimizing the bearing structure according to the bearing clearance expansion incremental data to obtain bearing structure optimization data; performing tooth direction drum shape modification analysis according to the tooth surface pitting corrosion data to obtain modification data; and finally, carrying out anti-vibration strengthening design by combining bearing optimization and tooth direction modification data, generating structural anti-vibration strengthening design data, and sending the structural anti-vibration strengthening design data to a terminal so as to execute structural optimization and reduce the influence of vibration noise. According to the method, the vibration noise optimization technology is optimized, so that the vibration noise optimization technology is more perfect.
Owner:JIAXING UNIV +1

Fault intelligent detection system for power distribution cabinet

The invention discloses an intelligent fault detection system for a power distribution cabinet. The intelligent fault detection system comprises a data collection module, an enhancement processing module, a fault diagnosis module, a repair generation module and an intelligent detection module. The invention belongs to the technical field of fault detection and prediction of power distribution cabinets, and particularly relates to an intelligent fault detection system for a power distribution cabinet, which adopts a fault diagnosis and repair scheme generation method combining frequency difference group and frequency collection data and multi-index data analysis. Fault diagnosis is carried out, and a repair result of a repair scheme is generated, so that powerful data reference and support are provided for fault detection and maintenance of the power distribution cabinet; fault diagnosis is carried out by adopting a bidirectional long-short-term memory model combined with frequency difference grouping noise optimization, and integrated analysis of high-frequency and low-frequency acquired data is effectively combined; and a decision tree regression model method based on data driving is adopted to carry out repair generation, so that the availability and reliability of the system are improved.
Owner:PRIMA ELECTRIC CO LTD

Multi-channel parallel level conversion circuit test system

The invention discloses a multichannel parallel level conversion circuit test system, which relates to the technical field of circuit test and comprises a test host, a multichannel parallel level conversion circuit, a signal source module, a signal acquisition module, a control module and a display module. The test host performs test logic verification on the whole process of the circuit test, the multichannel parallel level conversion circuit serves as a target circuit to be subjected to circuit test, a test signal of the circuit test is generated according to the signal source module, and a test case of the test signal is constructed. The signal acquisition module acquires an output signal of the multichannel parallel level conversion circuit, and generates a circuit tuning output signal after signal gain, signal noise optimization and frequency band filtering, the control module performs circuit testing on a target circuit according to a test case and the circuit tuning output signal, and finally, the control module performs circuit testing on the target circuit according to the test case and the circuit tuning output signal. And the display module visually displays the test result.
Owner:CHENGDU DIANKE RONGXIN TECH CO LTD

Programmable frequency divider applied to JESD204B / C

ActiveCN120377897ACounting chain asynchronous pulse countersClosed loop feedbackFlip-flop
The invention relates to a programmable frequency divider applied to JESD204B / C. The programmable frequency divider comprises a prescaler which realizes 1 / 2 / 4 dynamic frequency division through a closed-loop feedback structure; according to the 12-bit main frequency divider, the duty ratio of odd-even frequency division is controlled by a 11-stage asynchronous CML frequency-halving chain and a separation DFF0 module; the frequency dividing ratio N is equal to DIV Nlt; 11: 0gt; 2, the odd number frequency division duty ratio is automatically adjusted to (N + 1) / 2N; the cascade noise optimization comprises the following steps of: resampling by using an input clock fin through a retiming trigger (RetimeDFF1 / 2); according to the pulse generator, the number K of pulses output by a four-stage counter is equal to Pulsecount; 3: 0gt; a decimal value; and the output mode circuit supports three-mode direct connection. According to the programmable frequency divider, the HBT process CML unit and the emitter follower are adopted for buffering; and the high-precision clock synchronization requirements of JESD204B / C systems such as a 5G base station and a millimeter wave radar can be met.
Owner:58TH RES INST OF CETC

Outside-vehicle noise contribution analysis and optimization method and system based on working condition transmission path test

The invention discloses an outside-vehicle noise contribution analysis and optimization method and system based on a working condition transmission path test, and the method comprises the steps: firstly, collecting the near-field noise of each noise source part of a vehicle, and the receiving noise of each receiving point; then, according to the near-field noise corresponding to each noise source component and the receiving noise corresponding to each receiving point, determining a transmissibility function from each noise source component to different receiving points; then, collecting the actual near-field noise of each noise source component under the actual operation condition of the vehicle; and calculating to obtain path synthesis noise from each noise source component to the receiving point by using a transmissibility function from each noise source component to the receiving point. And finally, quantitatively calculating the contribution amount of each noise source component to the noise outside the vehicle through all path synthesis noise obtained through calculation, so as to lock a key contribution component of the noise outside the vehicle, and further carrying out noise optimization on the corresponding component.
Owner:CHONGQING VEHICLE TEST & RES INST CO LTD +1

In-vehicle noise optimization method, device, equipment and medium

The invention provides an in-vehicle noise optimization method and device, equipment and a medium. The method comprises the steps that at least one acoustic package strategy for an electric drive assembly of the vehicle is obtained; on the basis of a virtual acoustic environment created for the electric drive assembly in advance, the sound insulation amount of all the acoustic package strategies for noise generated by the electric drive assembly is determined; according to the data of each acoustic packet strategy on each of at least one preset dimension, determining a target acoustic packet strategy in the at least one acoustic packet strategy, the at least one preset dimension comprising the sound insulation amount; and according to the target acoustic package strategy, performing sound insulation treatment on the electric drive assembly. According to the method and the device, the acoustic package optimization based on the electric drive assembly can be quickly realized under the condition of shortage of resources and periods in the early stage of a project, the efficiency of in-vehicle noise optimization is remarkably improved, and the cost of in-vehicle noise optimization can be remarkably reduced.
Owner:DONGFENG MOTOR GRP

Vibration noise optimization method for planet row coaxial speed reducer

The invention relates to the technical field of reducer vibration noise optimization, and discloses a planet row coaxial reducer vibration noise optimization method, which comprises the steps of obtaining initial assembly parameters of a reducer, collecting load measurement signals of planet wheels of the reducer under an order frequency sweeping working condition, converting the load measurement signals into equivalent meshing loads based on a calibration curve, and calculating the equivalent meshing loads according to the equivalent meshing loads. Calculating a load imbalance coefficient according to the equivalent meshing load, and taking a peak value of the load imbalance coefficient as a first evaluation index; shell radial acceleration and sound pressure signals are synchronously collected under the order frequency sweeping working condition, the side-band ratio is calculated, and the peak value of the side-band ratio is taken as a second evaluation index; and performing diagnosis shunting based on the first evaluation index and the second evaluation index, determining an assembly parameter which is adjusted preferentially, executing iterative adjustment, and outputting a final assembly parameter after iteration is completed. According to the method, uniform load unbalance caused by assembly errors and side band amplification caused by geometric eccentricity can be effectively separated and solved, and vibration and noise of the speed reducer are reduced fundamentally.
Owner:JIAXING UNIV +2

Intelligent obstacle identification method and system for unmanned loader and storage medium

The invention discloses an intelligent obstacle recognition method for an unmanned loader, and aims to solve the problems of low obstacle recognition precision, poor real-time performance and insufficient coordination of obstacle avoidance and operation in a complex operation scene. The method comprises the following steps: establishing a multi-source sensing system such as a laser radar and a camera, and realizing data time sequence synchronization, space unification and noise optimization through FPGA hardware; obstacle space and category features are extracted through double-branch parallel detection, and a modal weight fusion result is dynamically distributed in combination with a scene; an improved Hungary algorithm and a classification tracking model are adopted to realize obstacle ID stable association and trajectory tracking, and trajectory prediction is completed based on LSTM and Kalman filtering; and a dynamic avoidance area is constructed, and an obstacle avoidance path is generated through global-local bilevel programming and a safety potential field algorithm and is corrected in real time. The obstacle recognition robustness and real-time performance in a complex environment are improved, and safe and efficient operation of the unmanned loader is guaranteed.
Owner:中铁长安重工有限公司 +1

Propeller design for unmanned aerial vehicle based on aerodynamic performance and noise optimization

The invention discloses an unmanned aerial vehicle propeller design based on aerodynamic performance and noise optimization, and relates to the field of propeller structure design. Aiming at the problem of contradiction between performance and noise optimization design during design of an existing propeller structure, a new design and research thought of the propeller structure for the unmanned aerial vehicle is given, and the propeller structure for the unmanned aerial vehicle which meets aerodynamic performance and is low in aerodynamic noise is designed in a multi-main-microparameter cooperation mode. According to the research thought, the influence effect on the aerodynamic performance and noise of the propeller under different measures can be analyzed, meanwhile, the aerodynamic performance and noise reduction are considered, the design scheme of the propeller for the unmanned aerial vehicle with the maximum take-off thrust, the optimal cruise efficiency and the minimum operation noise is designed under the condition that the service time and the service life of the propeller are guaranteed, and the design method is suitable for popularization and application. The thinking steps are simple and short in time consumption, and basis is provided for subsequent propeller design in the same field.
Owner:HARBIN UNIV OF SCI & TECH

Noise optimization control system for actuating mechanism of sanitation vehicle

The invention discloses a noise optimization control system for an actuating mechanism of a sanitation vehicle, and belongs to the technical field of gas circuit control. The system comprises a hydraulic control loop, a pneumatic control loop and a controller. The hydraulic loop comprises an oil pump, an oil tank, a main reversing valve and an action oil cylinder; working ports A and B of the main reversing valve are respectively communicated with a rodless cavity and a rod cavity of the action oil cylinder; the pneumatic loop comprises an air source, a first reversing valve, a second reversing valve, a reversing air cylinder and a buffering assembly. The air source is communicated with a rodless cavity and a rod cavity of the reversing air cylinder through a first air path and a second air path respectively, a first reversing valve and a second reversing valve are arranged on the two air paths respectively, and the control ends of the two valves are both electrically connected with the controller. The extension and retraction actions of the reversing cylinder control the main reversing valve to switch working ports; in order to slow down the speed that the reversing cylinder pushes a valve rod in the main reversing valve to switch working ports, a first buffering assembly is further arranged on the reversing oil cylinder. According to the invention, the corresponding buffer assembly is additionally arranged, so that the noise optimization control of the actuating mechanism of the sanitation vehicle is realized.
Owner:XUZHOU XUGONG ENVIRONMENTAL TECH CO LTD

Image scene conversion method and device, equipment and storage medium

The invention discloses an image scene conversion method and device, equipment and a storage medium. Firstly, an image to be processed and a conversion cue word used for indicating an image scene conversion direction and a specific attribute adjustment requirement can be obtained, the conversion cue word is input into a pre-trained scene noise optimizer, and structured guide noise accurately matched with the cue word is generated through noise optimization processing and used as target noise. Performing vector encoding on the to-be-processed image and the conversion prompt word through an image encoder and a text encoder to obtain an image feature vector and a text feature vector, and performing feature fusion on the image feature vector and the text feature vector by using a cross attention mechanism to generate a fusion vector; and finally, jointly inputting the fusion vector and the target noise into a pre-trained scene conversion model, and performing conditional decoding generation processing to obtain a scene conversion image corresponding to the to-be-processed image. According to the invention, disordered disturbance caused by noise injection is avoided, and drift of the image content in the conversion process is effectively inhibited.
Owner:HANGZHOU WANGDAO HLDG CO LTD

Decimal frequency division all-digital phase-locked loop based on DTC and edge time domain compensation algorithm

The invention relates to a fractional frequency division all-digital phase-locked loop based on a DTC and an edge time domain compensation algorithm, and belongs to the field of radio frequency integrated circuit design. The whole circuit structure comprises a time-to-digital converter (TDC), a digital loop filter (DLF), a digital controlled oscillator (DCO), a programmable frequency divider (MMD), a Sigma-delta modulator and a digital-to-digital converter (DTC). A fractional frequency division function is realized by combining a programmable frequency divider MMD, a Sigma-delta modulator and a digital time converter DTC, a quantization noise optimization circuit is designed mainly by adopting a time domain compensation method, a low fractional spurious effect is realized by combining the DTC, and then signals of fractional frequency division are output and integrated in a phase-locked loop. In a phase-locked loop, a signal output by a Sigma-delta modulator is integrated with a frequency division signal, then a DTC performs time domain compensation according to the signal output by the Sigma-delta modulator, and then transmits the signal to a TDC for phase comparison with a reference signal to control the frequency output of a DCO, so that the high-performance all-digital phase-locked loop circuit with low decimal stray is realized.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

High-accuracy house type image inner contour segmentation method, system and equipment

The invention discloses a high-accuracy house type image inner contour segmentation method, system and device. The method comprises the following steps: carrying out normalization processing (such as data enhancement and noise optimization) on data; detecting a target area based on an improved DETR model, extracting multi-layer features through an optimized encoder and decoder, and generating a bounding box and confidence and category thereof; combining the bounding box with the original image, randomly expanding the bounding box to extract a house area, and reducing watermark and advertisement interference in the image; and on the basis of an improved Mask2Former model, an optimized Transform decoder and an attention mechanism are utilized to generate a segmentation mask and a classification result. According to the method, DETR and Mask2Former models are combined, all functional rooms of the house type image are quickly and accurately segmented, and the blank of a large-scale house type image processing method is filled.
Owner:SOUTH CHINA AGRICULTURAL UNIVERSITY

Image generation method and device, equipment and storage medium

The invention provides an image generation method and device, equipment and a storage medium, and the method is applied to the field of computer images, and comprises the steps: obtaining a style reference image of a to-be-processed image if the style guide type of the to-be-processed image is an image guide type, determining a target image style corresponding to the style reference image based on the content feature and the style feature of the style reference image; if the style guide type is an instruction guide type, obtaining a guide text instruction of the to-be-processed image, and determining a target image style corresponding to the guide text instruction based on text feature information of the guide text instruction; adding random noise to the to-be-processed image to generate a noise image; and generating a noise optimization parameter for the noise image based on the target image style, and calling the noise optimization parameter to carry out iterative denoising on the noise image to generate a target style image. Therefore, the precision and efficiency of style migration are improved, and the detail fidelity and style consistency of the target style image are enhanced at the same time.
Owner:JILIN UNIVERSITY

Audio noise reduction method, system and device based on AI model and storage medium

The invention discloses an audio noise reduction method, system and device based on an AI model and a storage medium, and relates to the technical field of voice noise reduction, and the method comprises the steps: receiving a live video stream, and segmenting the live video stream into image frame data and audio stream data; the image frame data and the audio stream data are input to a preset scene recognition model, the recognition result of the current scene is obtained, and the preset scene recognition model comprises a character recognition sub-model, a voice recognition sub-model and a classification output module; and determining and executing a current noise reduction strategy according to the identification result to obtain an audio output signal, the current noise reduction strategy being a human voice enhancement strategy, an ambient sound enhancement strategy or a fusion enhancement strategy. According to the invention, scene recognition is carried out in a multi-modal fusion mode, different noise reduction strategies are adaptively executed according to the scene recognition result, noise optimization can be carried out for different scenes, and the audio output effect is improved.
Owner:NANJING PUTIAN TELEGE INTELLIGENT BUILDING

Vehicle noise optimization method and device, vehicle and storage medium

The invention relates to a vehicle noise optimization method and device, a vehicle and a storage medium, and relates to the technical field of computers. The method comprises the following steps: acquiring a noise exceeding value of a target part of a vehicle; the noise exceeding value is a difference value between a noise value generated by the target part and a reference noise value corresponding to the target part in the vehicle driving process; determining target equivalent static stiffness corresponding to the noise exceeding value of the target part; the noise generated by the target part with the target equivalent static stiffness is lower than a reference noise value corresponding to the target part; and determining an optimization scheme of the target part of the vehicle based on the target equivalent static stiffness. Therefore, the structure of the target part can be optimized based on the optimization scheme, so that the noise generated by the target part in the vehicle driving process is reduced.
Owner:CHONGQING CHANGAN AUTOMOBILE CO LTD

Vehicle cooperative positioning method based on robust adaptive high-order volume Kalman filtering

The invention discloses a vehicle cooperative positioning method based on robust adaptive high-order volume Kalman filtering, belongs to the technical field of cooperative navigation, is used for processing cooperative navigation data, and comprises the following steps: establishing a system model according to GNSS / UWB tight coupling integration; carrying out nonlinear updating by utilizing a five-order volume rule; a fading factor is derived based on a strong tracking theory, and correction of a prior state covariance is realized; on the basis that a linear regression model approximates a non-linear measurement model, a Huber function is used for reconstructing measurement noise, so that the influence of non-Gaussian noise is inhibited; and optimizing measurement updating of a filtering algorithm according to the corrected priori state covariance and measurement noise. According to the method, good relative positioning performance can be realized under the condition that the system has model errors and non-Gaussian noise interference, and the precision and robustness of vehicle cooperative positioning are improved.
Owner:LIAONING TECHNICAL UNIVERSITY +1

Method for testing noise and vibration of refrigeration fan of refrigerator

The invention provides a method for testing noise and vibration of a refrigeration fan of a refrigerator, relates to the field of vibration testing of refrigerators, and aims to solve the problem that the real noise performance of the fan in a complex environment in the refrigerator cannot be reflected in the current noise testing of the fan of the air-cooled refrigerator. The actual installation states of a fan, an air duct and a box body are reserved to eliminate single body test deviation, vibration and noise data are synchronously collected, time domain and frequency domain analysis is covered, vibration-noise causal relation tracing is achieved, the coupling frequency band and energy distribution of vibration and noise are quantified through time domain and frequency domain conjoint analysis, and therefore the noise source and the coupling frequency band are positioned, and the noise quality is improved. And targeted optimization is facilitated, and the noise optimization efficiency and the optimized noise control effect are improved.
Owner:QINGDAO WANBAO COMPRESSOR

Multi-source data fusion method and system based on data analysis

The invention discloses a multi-source data fusion method and system based on data analysis, and relates to the technical field of electric digital data processing. The multi-source data fusion method based on data analysis comprises the following steps of performing fusion real-time analysis; performing dynamic fusion adaptive analysis; and interactive fusion validity analysis. According to the method, real-time analysis is carried out through real-time fusion data, whether sampling sensing frequency optimization is carried out or not is judged, then dynamic adaptability analysis is carried out according to sensing fusion data, whether sensing fusion parameter optimization is carried out or not is judged, finally interaction effectiveness analysis is carried out, and whether interaction fusion noise optimization is carried out or not is judged. Therefore, the reliability of the corresponding fire-fighting information dynamic fusion of the fire-fighting facilities in the transformer substation in the communication process of the internet of things is improved, and the problem that the reliability of the corresponding fire-fighting information dynamic fusion of the fire-fighting facilities in the transformer substation in the communication process of the internet of things is not high in the prior art is solved.
Owner:GUANGZHOU POWER SUPPLY BUREAU GUANGDONG POWER GRID CO LTD

Power self-service terminal voice intention recognition system based on background noise optimization

The invention relates to the technical field of voice recognition, in particular to an electric power self-service terminal voice intention recognition system based on background noise optimization. The system comprises a voice interaction noise optimization module, a scene voice transcription analysis module, a scene voice intention recognition module and a recognition confidence iterative optimization module, a voice interaction original data set during voice interaction between the power self-service terminal and a user can be collected, and noise optimization is carried out to generate a target voice interaction data set; performing voice transcription analysis based on the target voice interaction data set, and generating a text transcription result; performing keyword semantic matching calculation on the text transcription result and an intention recognition knowledge base to obtain an intention recognition result of the user; and calculating a comprehensive recognition confidence coefficient based on the intention recognition result, if the comprehensive recognition confidence coefficient is lower than a set threshold value, performing secondary noise optimization on the voice interaction original data set and re-executing the judgment step, and if not, outputting the intention recognition result of the user. According to the invention, the accuracy of terminal speech recognition and intention recognition can be improved.
Owner:STATE GRID TIANJIN ELECTRIC POWER COMPANY

Sheet metal structure radiation noise optimization method, computer device and storage medium

The invention provides a sheet metal structure radiation noise optimization method, a computer device and a storage medium, and the method comprises the steps: building an acoustic model of a target sheet metal structure, carrying out the simulation analysis of the radiation noise of the target sheet metal structure, and taking a plate of which the acoustic contribution proportion is greater than a first threshold value as a target optimization plate; obtaining the modal contribution of each modal to acoustics under the peak frequency of the target optimization plate, superposing the modal contribution proportions from high to low to obtain the sum of the modal contribution proportions, and forming a modal shape variable group by all the modals when the sum of the modal contribution proportions is greater than or equal to a second threshold value; according to the modal shape variable group, determining a structural shape parameterized model of the target optimization plate by taking the participation factor of each modal shape as a design variable; and selecting a modification area of the target optimization plate, and performing structure optimization by using a preset algorithm to obtain a final optimization structure of the target optimization plate. According to the invention, the noise optimization effect and optimization efficiency of the sheet metal structure can be improved.
Owner:GREE ELECTRIC APPLIANCE INC OF ZHUHAI

Noise source determination method and device

The embodiment of the invention provides a noise source determination method and device, and belongs to the field of mechanical equipment optimization. The method comprises the following steps: carrying out noise contribution analysis on a plurality of components of the mechanical equipment, and determining main noise source components; constructing a finite element structure model of the mechanical equipment; noise excitation is conducted on the finite element structure model to obtain noise response information, corresponding to the main noise source component, of the finite element structure model, and the noise response information comprises noise peak values under different excitation frequencies; performing equivalent radiation sound power analysis on a finite element structure model corresponding to the main noise source component according to the noise response information to obtain a first analysis result; and determining a noise main contribution position of the main noise source component according to the first analysis result and the noise peak values under different excitation frequencies. Through the method, the noise source can accurately determine the specific position on the single component, and the noise optimization of the mechanical equipment is more targeted.
Owner:ZOOMLION HEAVY MASCH CO LTD

Gear modification method for reducing gear noise

The invention belongs to the technical field of new energy automobile noise optimization, and particularly relates to a gear modification method for reducing gear noise, which comprises the following steps: S1, constructing a gear transmission system model; s2, simulating gear transmission performance under different load conditions and extracting key parameters; s3, shaping parameters to be optimized are set; s4, performing optimization calculation on each to-be-optimized modification parameter by taking reduction of a transmission error and improvement of a gear contact area as targets; in the optimization calculation process, according to a preset weight distribution strategy, weight proportions are set for different operation conditions and used for representing priorities of all the operation conditions; and S5, adjusting the numerical value of the modification parameter in the optimization result in the step S4, so that the transmission error curve is in a sine or cosine trend under all operation conditions. According to the method, smoothing of a transmission error curve, optimization of tooth surface contact performance and uniformization of edge load distribution can be achieved within the full working condition range, gear meshing noise is remarkably reduced, and the noise quality of a whole vehicle is improved.
Owner:CHONGQING TSINGSHAN IND

Noise optimization control method, device and equipment when rotor is captured and storage medium

The application relates to a noise optimization control method, device and equipment for rotor capture and a storage medium, and relates to the fan technical field, and particularly relates to a noise optimization control method, device and equipment for rotor capture and a storage medium, which comprises the following steps: obtaining a starting instruction issued by a fan; outputting first voltage data through voltage detection and comparison by using the starting instruction issued by the fan; determining the motion state of the fan at present by using the first voltage data; and obtaining the related results of noise optimization control of single-resistance sampling during rotor capture by using the determination result of the motion state of the fan at present and executing the corresponding motion mode. Through voltage detection and comparison, the first voltage data is outputted, the motion state of the fan at present is determined by using the first voltage data, and the corresponding motion mode is executed, so that single-resistance sampling realizes noiseless starting during rotor capture.
Owner:西安安凡达智能电机有限公司

Urban design noise optimization method and system based on artificial intelligence

The invention discloses a city design noise optimization method and system based on artificial intelligence, and the method comprises the steps: carrying out the preprocessing of building form and noise measurement data, and constructing a basic data set after noise simulation verification; a three-dimensional city model and a measuring point network are generated through a layered parameterization framework, the structural noise level is calculated, real-time verification is carried out in combination with planning constraints, and a structural design space, noise basic data and feasibility guarantee are provided; a two-stage multi-layer perceptron network is constructed, local building group acoustic influence and a global city noise mode are processed respectively, and high-precision noise prediction is achieved through training; and deploying a large language model as an optimization agent, and outputting an optimal scheme through multiple rounds of iterative optimization and evaluation. Compared with the prior art, the method has the advantages that the noise prediction precision is effectively improved, a structured design space is provided for parametric modeling, the feasibility is guaranteed through real-time verification, efficient iteration is achieved through large language model optimization, and compared with a traditional method, the efficiency is remarkably improved, and the labor cost is reduced.
Owner:TSINGHUA SHENZHEN INTERNATIONAL GRADUATE SCHOOL

Noise optimization method and device for indoor fan, air conditioner and storage medium

The invention provides a noise optimization method and device of an indoor draught fan, an air conditioner and a storage medium. The noise optimization method of the indoor draught fan comprises the steps that a sound signal corresponding to the indoor draught fan is obtained, an amplitude mean value within a preset duration is obtained based on the sound signal, and the amplitude mean value serves as a to-be-processed amplitude value; and under the condition that the amplitude to be processed does not meet the amplitude condition obtained in advance, the rotating speed of the indoor fan is adjusted, and the sound signal corresponding to the indoor fan is obtained again till the amplitude to be processed meets the amplitude condition, so that noise optimization is achieved. In this way, the flexibility of noise optimization can be improved, the accuracy of noise optimization can be improved, the noise optimization effect of the indoor fan can be improved, and the use experience of a user is improved.
Owner:QINGDAO HAIER AIR CONDITIONER GENERAL CORP LTD +3

A traffic classification method and system based on smooth noise data enhancement

The present invention discloses a traffic classification method and system based on smooth noise data enhancement. The method comprises the following steps: a noise generation module generates unified normalized noise and converts the normalized noise into characteristic noise; a noise optimization module optimizes the noise shape through a gradient-based algorithm and optimizes the noise scale through an improved Bayesian optimizer; a data enhancement module generates optimized smooth noise based on the optimized noise shape and noise scale, and adds the optimized smooth noise to benign and malicious samples, respectively, to obtain enhanced new samples; an integrated learning module uses the enhanced samples as pseudo-malicious samples to train a traffic classifier, collects the results of traffic classifiers trained under multiple sets of noise scales, and combines the classification results using an improved Boosting algorithm to obtain the final classification result. The method effectively optimizes the classification boundary of the traffic classifier, improves the recall rate of the traffic classifier for unknown types of malicious traffic, and enhances the generalization of the classification results.
Owner:WUHAN UNIV

Noise-optimized ducted propeller

The invention relates to a ducted propeller (1) and to an aircraft having a ducted propeller according to the invention. The ducted propeller (1) has a stator (10) which comprises a central element (12) extending along a longitudinal axis (x). The stator (10) further has a housing (13) which is arranged around the central element (12), wherein the central element (12) is connected to the housing (13) via at least one first web (11a) and at least one second web (11b). A rotor (20) having a plurality of rotor blades (21) is arranged on the central element (12) of the stator (10).According to the invention, a first web (11a) is arranged offset from a second web (11b) axially along the longitudinal axis (x) by a defined distance (d), wherein the distance (d) is selected such that a first sound wave (4a) generated at the first web (11a) due to the air flow is 180° out of phase with a second sound wave (4b) generated at the second web (11b) due to the air flow and identical to the first sound wave (4a).
Owner:DR ING H C F PORSCHE AG

A variable flux leakage permanent magnet synchronous motor considering multiple operating conditions and its low vibration and noise optimization design method

The present invention discloses a variable-leakage permanent magnet synchronous motor and its low-vibration-noise optimization design method that considers multiple operating conditions. The method comprises the following steps: obtaining a variable permanent magnet leakage flux through the magnetic circuit distribution of the permanent magnet motor; adjusting the amount of permanent magnet leakage flux to meet the motor's requirements for torque, speed regulation range, and low vibration and noise when the motor is in different operating conditions; constructing a regional leakage flux structure to achieve controllable leakage flux and provide the motor's initial structure; analyzing the electromagnetic vibration characteristics of the variable-leakage permanent magnet synchronous motor under different operating conditions to obtain relevant data on performance such as the lowest non-zero-order electromagnetic force; evaluating the degree to which key motor parameters affect electromagnetic performance and the performance requirements of the motor under different operating conditions; and performing comprehensive optimization using a multi-objective genetic algorithm to determine the final size of the motor. The present invention enables the motor to achieve wide speed regulation and high torque performance while suppressing the motor's vibration and noise under different operating conditions.
Owner:JIANGSU UNIV