410 results about "Sound detection" patented technology

The invention provides an abnormal sound detection method based on multi-scale time-frequency feature perception, and relates to the technical field of acoustic detection for industrial machine state monitoring, and the method comprises the steps: inputting an original sound signal, and carrying out the dual-branch feature extraction to generate a time domain coding spectrogram and a logarithmic Mel spectrogram; executing hybrid data enhancement; splicing the enhanced spectrogram and inputting the enhanced spectrogram into a dense encoder for compression modeling; extracting features through a two-stage multi-scale time-frequency sensing network, processing along a time dimension in the first stage, and processing along a frequency dimension in the second stage; inputting the high-order features into a lightweight classifier to output an abnormal score; and comparing the abnormal score with the gamma distribution threshold to judge abnormity. According to the method, the weak anomaly detection rate and the cross-equipment stability are remarkably improved, and the perception and discrimination capability of the model on the multi-scale time-frequency characteristics is effectively enhanced.

A computer-implemented method for training an anomaly detection neural network system comprising an encoder and a decoder is described. The method includes receiving training data comprising a plurality of training examples, each training example including a training audio waveform and a machine identity (ID); processing the training audio waveform to extract training audio features; receiving an environmental noise audio waveform; processing the environmental noise audio waveform to extract noise features; generating augmented features by combining the extracted training audio features and the noise features; processing, using the encoder, the augmented features to generate latent embeddings; processing, using the decoder, the latent embeddings to generate reconstructed audio features; processing, using a convolutional neural network, the augmented features to generate a predicted machine ID probability distribution; and adjusting, through backpropagation, the current values of the parameters of the encoder and the decoder to minimize an objective function.

The invention relates to a glass capillary microscopic flaw detection method and system, and relates to the field of material nondestructive testing, and the method comprises the following steps: collecting a capillary detection signal; when the capillary detection signal is consistent with the detection starting signal, collecting a capillary serial number; determining a sound detection number according to the capillary number; obtaining a standard reaction characteristic based on the capillary serial number and the sound detection serial number; generating and transmitting a corresponding sound wave signal to the capillary tube based on the sound detection number, and collecting sound reaction characteristics; when the sound reaction characteristics are inconsistent with the standard reaction characteristics, controlling vibration auxiliary equipment to apply auxiliary vibration to the capillary tube, and collecting post-vibration sound reaction characteristics; if the post-vibration sound reaction characteristics are inconsistent with the sound reaction characteristics, a capillary tube cleaning prompt is reported; if the after-vibration sound reaction characteristics are consistent with the sound reaction characteristics, capillary tube defect prompts are reported. The method has the effect of improving the detection accuracy of the glass capillary.

An image forming apparatus includes: an image forming unit that forms an image on a recording medium; plural sound detection units that detect a sound of the image forming unit; and a specifying unit that specifies an abnormality of the image forming unit based on information output from the plural sound detection units, in which the specifying unit is provided in a number less than the number of plural sound detection units.

The invention relates to the technical field of industrial equipment fault diagnosis and audio analysis, in particular to a machine abnormal sound detection method and system and a storage medium, and the method comprises the steps: obtaining a to-be-detected sound; preprocessing the to-be-detected sound to obtain a spectrogram of the to-be-detected sound; the spectrogram of the sound to be detected is input into an abnormal sound detection model for recognition, and the abnormal sound detection model comprises a student network, a teacher network and a reconstruction head. According to the embodiment of the invention, the global semantic information and the local detail features of the abnormal sound can be captured at the same time by combining the self-distillation and the mask self-encoder, the accuracy and the stability of abnormal sound detection are remarkably improved, and the method is suitable for abnormal detection scenes of various machine equipment and has relatively strong generalization ability.

A device to perform target sound detection includes a memory including a buffer configured to store audio data. The device includes one or more processors coupled to the memory. The one or more processors are configured to receive the audio data from the buffer. The one or more processors are configured to detect the presence or absence of one or more target non-speech sounds in the audio data. The one or more processors are further configured to generate a user interface signal, to indicate one of the one or more target non-speech sounds has been detected, and provide the user interface signal to an output device. The device further comprises the output device that is configured to output a visual representation associated with the one of the one or more target non-speech sounds has been detected.

A computer-implemented method when executed by data processing hardware causes the data processing hardware to perform operations. The operations include maneuvering, autonomously, a vehicle along a test track, monitoring, via at least one audio sensor, audio data from the vehicle during the maneuvering of the vehicle along the test track, and monitoring, via a monitoring system disposed along the test track, monitoring data of the vehicle along the test track. The operations also include executing, based on the monitored audio data, a sound detection function of an autonomous test algorithm, detecting, via the sound detection function, an error noise, categorizing, via a categorization function of the autonomous test algorithm, the detected error noise, identifying, based on the categorized error noise, a maintenance station and executing, in response to the identified maintenance station and categorized error noise, a spontaneous path planning function of the autonomous test algorithm.

A machine abnormal sound detection method based on feature enhanced dynamic graph convolution belongs to the field of machine abnormal sound detection, and comprises the following steps: firstly, generating a time-frequency spectrum feature representation for an original audio signal of a machine through a feature extractor; the method comprises the following steps: extracting multi-scale features by using an FE module through 1D-FFT, multi-scale trend period decomposition and a Token-Transform structure to obtain an enhanced feature spectrogram; sDA-GCN and DCA-GCN network structures are used, shared features and dynamic differences between devices are mined based on an enhanced feature spectrum, and feature differences under domain offset are reduced; through a coarse-grained label classifier, a fine-grained label classifier and a domain classifier, in combination with GRL and CORAL losses, fine-grained alignment of the feature space is realized; a three-stage training strategy is used, and the model is optimized through perception consistency pre-training, unsupervised contrast classification learning and reconstruction error-based anomaly detection. According to the invention, high-performance anomaly detection is realized.

The invention relates to the technical field of vehicle fault diagnosis, and particularly discloses a vehicle steering system abnormal sound real-time detection method. A differential mechanism turning abnormal sound detection and avoidance scheme in the prior art has defects and mainly depends on gasket surface treatment, the effect has timeliness, real-time monitoring cannot be achieved, the abnormal sound problem cannot be thoroughly avoided, and long-term noise, vibration, sound vibration roughness performance and driving comfort of a vehicle are affected. The method aims at solving the problems, data preprocessing and feature extraction are carried out by collecting the vehicle running state and acoustic data, and an abnormal sound detection model is constructed and trained based on the processed feature data. By integrating the multi-source sensor data and the advanced machine learning model, the abnormal sound of the vehicle steering system can be accurately detected in real time, the noise, vibration and sound vibration roughness performance and driving comfort of the vehicle are effectively improved, predictive maintenance is supported, and therefore the overall reliability and safety of the vehicle are improved.

The invention discloses an abnormal sound detection method based on multiple tasks, and belongs to the technical field of sound detection, and the method comprises the steps: obtaining a to-be-detected sound signal; preprocessing the sound signal to be detected; wherein the preprocessing process at least comprises the steps of performing data enhancement on a sound signal to be detected, and generating a target Log-Mel spectrogram; inputting a sound signal to be detected and the target Log-Mel spectrogram into the trained multi-task learning network, and outputting a multi-modal feature and a classification abnormal value; inputting the multi-modal features into a trained Gaussian mixture model to generate an abnormal score; and performing anomaly judgment on the sound signal to be detected based on the anomaly score and the classification anomaly value. Through collaborative design of a multi-task learning framework and multi-modal feature fusion, the problems that a traditional anomaly detection method is weak in generalization ability and high in false alarm rate in a complex industrial environment are solved, and high-precision and high-robustness abnormal sound detection is achieved.

The application relates to the technical field of acoustic signal processing. A three-dimensional sound event accurate identification and positioning method based on AI and a multi-microphone array is provided, which comprises the following steps: acquiring a multi-channel sound signal; performing frame windowing processing on the multi-channel sound signal to obtain time-frequency domain information; generating mel feature information; performing time-space joint feature extraction to generate an initial event category and a three-dimensional direction code; generating multi-angle virtual sound field data by combining the attenuation relationship between the sound source direction and the microphone angle through a simulation algorithm; inputting the real-time collected multi-channel sound signal into an optimized three-dimensional sound detection model for reasoning, and outputting an optimized event category and a three-dimensional direction code; performing dynamic calibration to generate a real-time calibrated three-dimensional sound detection model, so as to solve the problems of insufficient multi-dimensional distribution characteristic capturing capability of a three-dimensional sound field, limited model generalization capability caused by single data training and static environment assumption, and insufficient real-time adaptability under dynamic noise interference and long-term performance attenuation.

The invention relates to the field of breath sound monitoring, and discloses a tracheal intubation device and a breath sound monitoring system.The tracheal intubation device comprises a tracheal catheter used for being inserted into an airway of a patient; the first sound detection piece is an optical fiber sound sensor, the first sound detection piece is installed on the tracheal catheter, the first sound detection piece is used for detecting breathing sound wave information in the airway of a patient, and the first sound detection piece is used for being in communication connection with the monitoring host so as to transmit the detected breathing sound wave information to the monitoring host. Therefore, the first sound detection piece is installed on the tracheal catheter, the first sound detection piece can be directly located in the internal environment of the airway of the patient, the accuracy of monitoring breathing sound and sound wave information of the patient through the tracheal intubation device can be improved, and the first sound detection piece transmits the breathing sound and sound wave information to the monitoring host in real time; the medical staff can monitor the breathing condition of the patient in real time through the monitoring host, find out abnormal breathing of the patient in time and carry out treatment.

The invention relates to the technical field of audio signal processing. The invention provides a method, system and device for predicting pulmonary nodules through sound and a storage medium. The method comprises the following steps: in a quiet test environment, directionally collecting a sound signal of a patient through an audio sensor; wherein the sound signals comprise breath sounds, cough sounds, vowels and sentences; performing noise reduction processing on the collected sound signals to obtain a noise reduction data set; extracting multi-dimensional voiceprint features from the noise reduction data set, and constructing a sound feature matrix; and performing multi-modal fusion analysis on the sound feature matrix and clinical data of the patient, inputting the sound feature matrix and the clinical data into a sound prediction model optimized by a focus loss function, and outputting a pulmonary nodule risk prediction result and a visual diagnosis report. The problems that the misdiagnosis and missed diagnosis rate is high, the radiation risk is large and the equipment dependence is strong when the pulmonary nodules are examined by the existing iconography, and the characteristic analysis is single, the noise immunity is poor and the screening accuracy is insufficient in the sound detection technology are solved.

To provide a technique for detecting abnormal sound having a relatively small amplitude in a rotating body such as a motor.SOLUTION: A rotating body inspection device includes a frequency spectrum generation unit, a cepstrum generation unit, an order cepstrum generation unit, and an abnormal sound detection unit. The frequency spectrum generation unit generates a frequency spectrum for each measurement section in time series from vibration data that is data of vibration for each rotation speed of the rotating body. The cepstrum generation unit generates a cepstrum from the frequency spectrum for each measurement section. The order cepstrum generation unit generates an order cepstrum that is data obtained by converting a quefrency of the cepstrum into an order for each measurement section. The abnormal sound detection unit detects abnormal sound of the rotating body based on the order cepstrum for each measurement section.SELECTED DRAWING: Figure 2

The invention discloses a machine abnormal sound detection method based on enhanced self-coding reconstruction and probability modeling, and aims to solve the problem that in an existing unsupervised machine abnormal sound detection method based on a generative adversarial network, the time-frequency feature reconstruction result of machine operation sound is too smooth, so that the machine abnormal sound detection capability is insufficient. According to the method, time-frequency feature extraction is carried out on collected machine operation sound signals, modeling is carried out on machine operation sound time-frequency feature distribution under a normal working condition in combination with a probability statistical model, and the time-frequency features of the machine operation sound under the normal working condition are reconstructed and learned by using an auto-encoder of a structure enhancement mechanism. The method realizes unsupervised machine abnormal working condition determination by combining the reconstruction error and the probability determination result, can improve the determination stability and robustness of abnormal sound detection, reduces the model complexity, and is suitable for application scenarios such as industrial equipment operation state monitoring and fault early warning.

The invention provides an acoustic modal test method and device, electronic equipment and a storage medium, and the method comprises the steps: controlling at least one sound source device to output a preset audio signal at the same time; acquiring response signals detected by the plurality of sensors; the plurality of sensors are used for respectively executing sound detection at a plurality of detection positions in a compartment area; establishing a geometric model based on the audio signal, the detection position and a response signal detected by the sensor; and analyzing the geometric model to obtain an acoustic modal test result. According to the embodiment of the invention, the acoustic modal test result measured by the method is beneficial to improving the riding experience of passengers.

The invention relates to an intelligent AI information processing method and system, and relates to the technical field of information processing, and the method comprises the steps: collecting sound detection information and image detection information; updating the sound detection information through a preset sound processing method; obtaining a detection text according to the sound detection information; identifying a detection field from the detection text; identifying the marked image field through the image detection information; and combining the detection field, the marked image field and the image detection information to obtain final uploading information, and uploading and storing the final uploading information. The information processing method and device have the effect of improving the information processing accuracy.

Presented herein are system and methods for an indoor camera that can detect an audio event. The system can include an indoor camera, a control panel, and one or more processors coupled with non-transitory memory. The indoor camera can monitor an indoor environment. The indoor camera can capture audio data and visual data. The visual data can include images and / or videos. The indoor camera can detect, by analyzing audio data captured by the indoor camera, an audio event. The indoor camera can classify the audio event into a type of audio event. The indoor camera can transmit a message to the control panel, wherein the message indicates a type of the audio event. The control panel can receive messages and / or notifications from the indoor camera. The control panel can activate an alarm upon receiving the message having a particular type of audio event.

The application relates to a control method and an AI self-closing valve, and relates to the technical field of self-closing valves, which comprises the following steps: collecting a surrounding image of a gas stove; collecting a gas stove image when the surrounding image contains a preset human feature; recognizing an actual gas flow through the gas stove image; obtaining electromagnetic operation parameters in response to the actual gas flow; taking a valve flap of a gas outlet of a self-closing valve as a detection valve flap; controlling the electromagnetic device to operate at the electromagnetic operation parameters, and collecting a detection position of the detection valve flap and sound detection information; obtaining a foreign matter type and a foreign matter position based on the sound detection information; updating the electromagnetic operation parameters in combination with the foreign matter type, the foreign matter position and the detection position; and controlling preset electromagnetic devices to drive the detection valve flap to slide at the electromagnetic operation parameters. The application has the effect of improving the safety of gas use.

The invention relates to the technical field of green plant building, and discloses a self-adaptive noise reduction type green new energy low-carbon plant and a using method.The self-adaptive noise reduction type green new energy low-carbon plant comprises an outer wall arranged on the outer side of an inner wall, a sound insulation space is formed between the outer wall and the inner wall, and supporting columns are installed for supporting; first reflecting plates are rotationally arranged on the inner walls of the two sides of the inner wall, sound detection probes are arranged on the first reflecting plates, and an adjusting mechanism comprising a first rotating plate, a second rotating plate and an electromagnet is arranged between the first reflecting plates and the inner wall of the inner wall; an opening is formed in the top of the inner wall, a second reflecting plate is slidably mounted in the opening, and linkage mechanisms comprising rotating shafts and telescopic mechanisms are arranged on two sides of the second reflecting plate; the lower ends of the two second reflecting plates are connected with partition plates, and compartments are formed between the partition plates and the inner wall. In the invention, the noise centralized processing area is constructed through the sound insulation space and the honeycomb layer, an additional sound insulation cover is not needed, and the equipment flexibility is improved; the angle of the first reflecting plate is adjusted through the detection probe and the adjusting mechanism, the position of the second reflecting plate is synchronously adjusted through the linkage mechanism, noise is reflected into the sound insulation space to be absorbed, energy consumption is reduced, and carbon emission is reduced.

A heart-lung stop prediction device includes: right and left sound detection sections for detecting sounds generated by heartbeat fluctuation at right and left corneal wind sites, respectively, and detecting sounds generated by breathing fluctuation at the right and left corneal wind sites, respectively; a calculation section for calculating a stress index of a mammal based on the sounds generated by heartbeat fluctuation and the sounds generated by breathing fluctuation detected by the right and left sound detection sections; a prediction section for predicting a heart-lung stop period of the mammal based on the stress index calculated by the calculation section; and a notification section for notifying the heart-lung stop period predicted by the prediction section.

This allows for the assurance of good call quality across multiple frequency bands without the need for tuning for each individual frequency band. [Solution] This is an acoustic signal processing device that transmits a signal in a predetermined frequency band, the receiving frequency band, acquired via a communication device that performs voice communication, to a sound generating unit via a receiving-side signal path to produce sound from the sound generating unit, and acquires voice input via a sound detection sensor via a transmitting-side signal path and outputs it to the communication device. It comprises a band detection unit that detects whether the receiving frequency band is a narrowband first frequency band or a second frequency band wider than the first frequency band, based on a reference signal transmitted through the receiving-side signal path, and a band-specific countermeasure unit that takes countermeasures according to the frequency band detected by the band detection unit.

The application provides a pop sound detection method, comprising: obtaining an audio file and a corresponding recording file; calculating a first energy value corresponding to the audio file and a second energy value corresponding to the recording file by using Fourier transform; and determining that the audio file has a pop sound if a difference between the first energy value and the second energy value at the same time exceeds a set threshold. The application does not need manual listening to the audio file to detect the pop sound, and realizes automatic detection of the pop sound phenomenon of the audio file. On this basis, a corresponding pop sound detection report can be generated to further help users identify and repair the pop sound fault. The application also provides a pop sound detection system, a computer readable storage medium and an electronic device, which have the above beneficial effects.

The present invention provides a generative model-based method and system for detecting abnormal sounds from an air conditioner outdoor unit. The method comprises obtaining normal operating sound data of the air conditioner outdoor unit and interference sound data from the air conditioner detection environment; preprocessing the sound data to obtain time-frequency features; training a Gaussian mixture model based on the time-frequency features of the interference sound data to obtain its data distribution, which is then used for random sampling. The sampled sound data is then superimposed on the time-frequency features of the normal air conditioner sound data to obtain fifth sound data and corresponding sampling step labels. A neural network model is trained using the normal operating sound data and the fifth sound data to obtain a trained anti-interference abnormal sound detection model for the air conditioner outdoor unit; obtaining the air conditioner operating sound data to be tested, preprocessing it, and inputting it into the trained abnormal sound detection model to determine whether the air conditioner operating sound is abnormal. The present invention improves the anti-interference performance of the detection algorithm and the efficiency of air conditioner outdoor unit detection, thereby reducing labor costs.

Sensor and / or sound detection device with: a sensing device (10) with a sensitive surface (12) which is designed such that a change in at least one physical quantity and / or at least one chemical concentration at the sensitive surface (12) causes a change in a sensor signal output by or tapped from the sensing device (10); wherein at least one access channel (18) in the sensor and / or sound detection device is designed such that, at least as long as the at least one access channel (18) is open, air and / or at least one gas can be transferred through the at least one access channel (18) between a spatial environment of the sensor and / or sound detection device and the sensitive surface (12); characterized by at least one at least partially water-impermeable membrane (20) with an inner membrane surface (20a) oriented towards the at least one associated access channel (18), wherein at least one contact surface (22) of the respective membrane (20) located on the respective inner membrane surface (20a) is pressed against at least one associated membrane contact surface (24) on the at least one associated access channel (18) by deformation of the respective membrane (20) when a membrane outer surface (20b) of the respective membrane (20) or a cover layer (40) located on the respective membrane outer surface (20b) is wetted with at least a minimum quantity of liquid, such that the at least one associated access channel (18) is sealed liquid-tight, wherein the at least one membrane (20) is designed such that, if the respective membrane outer surface (20b) or cover layer (40) is not wetted,the respective membrane (20) is in its initial position and the at least one associated access channel (18) is kept open via at least one open intermediate gap between the at least one contact surface (22) of the respective membrane (20) in its initial position and the at least one associated membrane contact surface (24) on the at least one associated access channel (18).

The invention provides a motor abnormal sound detection method and device, and the method comprises the steps: collecting a sound pressure signal and a rotating speed signal of the operation of a motor, carrying out the synchronous processing of the sound pressure signal and the rotating speed signal, obtaining a synchronous original signal, carrying out the feature extraction of the synchronous original signal, and obtaining a feature vector; the feature vector comprises at least one feature component of a rotating speed deviation coefficient, a frequency band energy ratio, a dominant frequency and harmonic relation index and an amplitude attenuation rate, calculating an abnormal sound risk index by using the feature vector, determining an abnormal sound judgment threshold through a dynamic threshold updating strategy, and determining the abnormal sound by comparing the abnormal sound risk index with the abnormal sound judgment threshold. And outputting a motor abnormal sound detection result. According to the motor abnormal sound detection method provided by the embodiment of the invention, the sound pressure signal and the rotating speed signal are synchronously acquired, the multi-dimensional feature vector is extracted, the abnormal sound risk index is calculated, and self-adaptive judgment is performed based on the dynamic threshold strategy, so that an automatic abnormal sound recognition process based on multi-source signal fusion is realized, and the motor abnormal sound detection efficiency is improved.

The invention discloses a method and a system for detecting mobile phone noise through sound recorded by a mute box. Belongs to the field of audio signal processing. The method comprises the following steps: S1, placing a to-be-tested mobile phone in a mute box, exciting an audio input device or an audio output device of the mobile phone through a preset audio signal, and respectively collecting corresponding audio data; s2, storing the collected audio data as an audio file with a unique identifier; s3, reading audio signal data in the audio file, and performing data standardization and validity verification; s4, extracting time domain features and frequency domain features based on the standardized audio signal data; s5, according to the time domain features and the frequency domain features, whether the audio signals conform to a preset noise feature mode is judged, and if yes, it is judged that noise exists in the mobile phone to be detected; otherwise, determining that no noise exists. According to the invention, the accuracy, consistency and automation level of mobile phone recovery quality inspection can be improved.

The embodiment of the invention provides a noise evaluation method for a steering system, a vehicle and a storage medium, and the method comprises the steps: obtaining a vibration signal of the steering system in a vehicle steering process; analyzing the vibration signal to obtain vibration data corresponding to noise generated by the steering system and acoustic characteristics of the noise; determining a sound pressure level of the steering system based on the vibration data and a preset mapping relation; and evaluating the noise based on the sound pressure level and the acoustic characteristics to obtain a noise evaluation index. The technical problem that the accuracy of abnormal sound detection of the steering system is low in the prior art is solved.

The utility model discloses a kind of infant intelligence care camera, including shell, main control circuit board, camera module and wireless communication module. Main control circuit board is equipped with sound detection circuit module, temperature and humidity signal processing circuit and image processing circuit, respectively with microphone, temperature and humidity sensor and camera module electrical connection, for monitoring the sound characteristics of infant, environmental temperature and humidity parameters and activity state. Image processing circuit can detect whether target object in image crosses the boundary of preset safety fence area. When system detects abnormal condition, alarm indicating device issues alarm and sends corresponding abnormal information to external mobile terminal through wireless communication module. Realize the intelligent monitoring of infant, improve the security and convenience of care.

The utility model relates to the technical field of automobile part detection, and provides abnormal sound detection equipment which comprises a rack, a main shaft, a first tool assembly and a second tool assembly. Wherein the main shaft is mounted on the rack and can rotate around the axis of the main shaft relative to the rack; the first tool assembly comprises a first toggle clamp and a base, the base is installed on the main shaft and can rotate along with the main shaft, and the first toggle clamp is installed on the base; the second tool assembly comprises a second tool A and a second tool B, the second tool A is detachably mounted on the rack and used for fixing an AB column mounting part of the vehicle door limiter, the second tool B can be fixed to the base through the first toggle clamp, and the second tool B is used for fixing a door metal plate mounting part of the vehicle door limiter. Thus, detachable connection between the second tool assembly and the rack is achieved through the first tool assembly, and the abnormal sound detection equipment can be suitable for to-be-detected objects of various models by replacing the second tool assembly.