559 results about "Sound detection" patented technology

The invention provides a casting industry abnormal sound detection and grading response method based on voiceprint recognition, and belongs to the technical field of casting industry detection. A high-temperature-resistant microphone array is arranged at an easy-to-leak part of cast aluminum equipment, and three-stage filtering noise reduction and amplitude normalization preprocessing are adopted, so that the problem of poor signal quality caused by noise interference in a complex environment is effectively solved; the characteristics of the molten aluminum leakage sound in different frequency bands and different stages can be captured through variable window long-short time Fourier transform and extended Mel frequency cepstrum coefficient in combination with extraction of an energy change rate and a frequency spectrum gravity center; a Transform-CNN hybrid deep learning model based on an attention mechanism is constructed, and feature screening is optimized through principal component analysis and recursive feature elimination, so that the recognition and generalization ability of the model to the abnormal sound in the casting industry is significantly improved; and meanwhile, graded response measures are made based on the detection result, so that the abnormal conditions of molten aluminum leakage with different severity degrees are processed.

The invention belongs to the technical field of optical fiber sensing, and discloses a high-temperature-resistant and high-pressure-resistant multi-parameter integrated sensor and system based on optical fiber dislocation welding, and the sensor comprises a packaging main body, and the center of the packaging main body is provided with a center hole and a cavity which are used for accommodating a transmission optical fiber. The tail end of the transmission optical fiber is sequentially connected with a temperature detection device and a pressure / sound detection device which are positioned in the cavity; the temperature detection device comprises a fiber bragg grating; the pressure / sound detection device comprises a single-mode fiber, a multimode fiber, a first hollow capillary fiber and a second hollow capillary fiber which are connected in sequence; the axes of the first hollow capillary optical fiber and the second hollow capillary optical fiber are connected in a staggered manner to form an open structure. The pressure / sound-temperature multi-parameter composite in-situ synchronous measurement device realizes composite in-situ synchronous measurement of multiple parameters of pressure / sound-temperature, has the advantages of high temperature resistance, small size and high test precision, and has wide application prospects in the fields of aerospace, petroleum metallurgy, environmental monitoring and the like.

The invention provides a belt conveyor carrier roller fault sound detection method and system, and relates to the field of nondestructive fault detection, and the method comprises the steps: obtaining a time-frequency domain characteristic pattern X of a sound signal; performing feature extraction on the X through a plurality of convolutional layers with different sizes to obtain a multi-scale feature map # imgabs0 #; performing deeper-level fault feature mapping of the spatial dimension and the channel dimension on the # imgabs1 # through a first Ghost module, a deep convolutional layer, a spatial channel collaborative attention module and a second Ghost module in sequence to obtain a high-level semantic feature map # imgabs2 #; inputting # imgabs3 # into a classifier module to obtain a classification result, and completing model training by using a cross entropy loss function and a re-parameterization training method to obtain a fault detection model; and performing short-time Fourier transform on a sound signal to be detected, and inputting the sound signal to the trained fault detection model to obtain a fault diagnosis result. According to the invention, the accuracy and real-time performance of belt conveyor carrier roller fault detection are improved.

The invention relates to the technical field of sound monitoring, in particular to a wild animal sound detection system, method and device based on voiceprint recognition, and the system comprises a multi-mode sound collection module, a voiceprint feature extraction engine, an acoustic fingerprint database, a species recognition decision module and an ecological behavior analysis unit, the multi-mode sound acquisition module integrates an array microphone and an infrasonic wave sensor, and supports full-band environmental acoustic signal acquisition; the voiceprint feature extraction engine extracts animal voiceprint biological features by adopting a self-adaptive frequency band segmentation algorithm; the acoustic fingerprint database stores a multi-species acoustic feature template and an environment interference noise sample; the species identification decision module constructs a voiceprint classification model based on a deep residual network; and the ecological behavior analysis unit generates a wild animal activity mode report through the acoustic event space-time distribution map. Therefore, the problems of serious environmental noise interference, low individual feature discrimination, difficulty and insufficiency in small sample species identification and the like in the prior art are solved.

A detection device for detecting a quality of ultra-long pile foundation of deep foundation pit support structure is provided, and includes a plurality of sound detection pipes which are parallel to each other and are vertically arranged on a reinforcement cage of a pile foundation. The plurality of sound detection pipes are paired, two sound detection pipes in each pair of the plurality of sound detection pipes are arranged opposite to each other, and ends of the plurality of sound detection pipes are connected to each other through connecting brackets; and a sound wave transmitter and a sound wave transducer are respectively arranged in the two sound detection pipes and are connected with the sound wave detector arranged outside the pile foundation through cables.

Provided in the present invention are an abnormal-sound detection method and system based on diffusion denoising for an air conditioner outdoor unit. The method comprises: acquiring normal operation sound data of an air conditioner outdoor unit and interference sound data in an environment where air conditioner detection is performed; pre-processing the sound data to obtain respective time-frequency features; training a Gaussian mixture model on the basis of the time-frequency feature of the interference sound data, obtaining the data distribution thereof to perform random sampling, and superimposing, onto the time-frequency feature of normal sound data of an air conditioner, sound data sampled from the data distribution, so as to obtain fifth sound data and a corresponding sampling step label; training a neural network model by means of the normal operation sound data of the air conditioner outdoor unit and the fifth sound data, so as to obtain a trained anti-interference abnormal-sound detection model for an air conditioner outdoor unit; and acquiring operation sound data to be subjected to detection of the air conditioner, pre-processing same, and then inputting same into the trained abnormal-sound detection model for an air conditioner, so as to determine whether an operation sound of the air conditioner is abnormal. The present application improves the anti-interference performance of a detection algorithm and the air conditioner outdoor unit detection efficiency, thereby reducing the labor cost.

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.

The invention relates to the technical field of identity recognition, in particular to a multi-modal data fusion identity authentication and security monitoring system based on deep learning. Comprising an identity authentication module, a real-time analysis module and a remote control module, and the identity authentication module is used for collecting face images, sound and behavior pattern multi-modal data of a user, performing multi-modal data fusion and outputting identity authentication data of the user; the real-time analysis module is used for respectively collecting real-time video data and audio data, fusing the picture detection data and the sound detection data and outputting real-time abnormal behavior data; the remote control module is used for storing the identity authentication data and the real-time abnormal behavior data and transmitting the data in a remote access mode; through the above mode, the identification precision is improved during analysis, and the interference of environmental factors is reduced, so that the safety of the whole identity authentication system and the user experience are improved.

The present application provides a self-supervised machine abnormal sound detection method based on a dual-path WaveNet, including: Step 1: Use WaveNet in the frequency-domain path to model the frequency information of each time frame of the input sound signal and extract frequency-domain features; Step 2: The time-domain path takes the output of the frequency-domain path as input, transposes it, and models the time dimension; Step 3: The outputs of the frequency-domain path and the time-domain path are further fused through a two-dimensional convolutional layer to generate a one-dimensional embedding vector; Step 4: Adopt a self-supervised strategy to construct a classification task using metadata to train the model; Step 5: For the trained model, in the detection stage, determine whether it is normal according to the abnormal score of the model test sample. The dual-path design of the present application realizes the comprehensive modeling of the time-frequency spectrogram, not only retains the local details of the time and frequency dimensions, but also can effectively capture the frequency-domain harmonic information and the time-domain dynamic characteristics, and solves the problem of insufficient modeling of complex features in the time-frequency spectrogram.

The invention discloses a machine abnormal sound detection method and system based on a dynamic attention mechanism, and the method comprises the steps: constructing a feature extraction network and a detection network, extracting the frequency domain-time domain features of machine audio in the feature extraction network through a log-Mel spectrogram and an improved WaveNet and TgramNet network, obtaining a feature fusion spectrogram, and carrying out the detection of the abnormal sound of a machine. A mobile FaceNet network and a detection network of an OCBAM dynamic attention mechanism are included, machine audio is obtained, data labeling of a specific machine type and a working state is carried out on the machine audio, a feature extraction network is used for carrying out feature extraction on a machine audio data set, a detection model is trained, and the detection model is used for detecting abnormal sound. According to the invention, the problem of difficulty in machine abnormal sound detection in a complex industrial environment is solved, the safety and efficiency of industrial production can be effectively improved, the production process and quality control are optimized, and the downtime and maintenance cost of equipment are reduced.

The invention is suitable for the technical field of butterfly valve control, and particularly relates to a butterfly valve rapid cut-off control method and a butterfly valve. Wherein the position information comprises a first position and a second position, the first position is used for reflecting the position of a first sound detection device arranged at the upstream of the butterfly valve, and the second position is used for reflecting the position of a second sound detection device arranged at the downstream of the butterfly valve; acquiring sound information according to the position information; analyzing according to the sound information to obtain a change graph; wherein the change pattern is used for reflecting a sound pattern formed by impact of the fluid on the pipeline in the process that the fluid flows from the first position to the second position; analyzing according to the change graph and the sound information to obtain closing information; wherein the closing information is used for indicating the closing time of the butterfly valve. According to the butterfly valve quick cut-off control method, noise in the pipeline can be reduced, and damage to the butterfly valve and the pipeline due to pressure shock waves is reduced.

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 provides a machine equipment abnormal sound detection method, a medium, equipment and a product, and relates to the technical field of abnormal sound detection, and the method comprises the steps: carrying out the data enhancement processing of an original audio during the operation of machine equipment, and dividing the original audio into a source domain sample and a target domain sample; the waveform features of the enhanced audio are converted into FFT spectrogram features, amplitude spectrogram features and logarithmic Mel spectrogram features; constructing three networks, extracting three embedded features, and then connecting; based on the splicing features of the source domain samples, obtaining a plurality of clustering centers of each category of samples in the source domain through clustering, and taking the minimum value of cosine distances between the source domain samples and all the clustering centers as the similarity score of the source domain; and based on the splicing features of the target domain samples, taking the minimum value of the cosine distance between the target domain samples and the sample mean value as the similarity score of the target domain, and taking the smaller value of the two similarity scores as an abnormal score. The method can effectively cope with the situation of domain generalization.

An unsupervised industrial abnormal sound detection method combining self-supervised learning and a Gaussian mixture model (GMM) is provided to deal with intelligent industrial equipment monitoring challenges. Traditional diagnosis depends on manpower or rules, various faults are difficult to process, and data are uneven. According to the method, TinyCRNN and GMM are used, audio is processed into a Mel spectrogram through Librosa, normal sound features are extracted through self-supervision, then abnormity is identified through GMM clustering analysis, and performance is evaluated through AUC and the like. According to the method, dependence on labeled data is reduced, the problem of data scarcity is solved, detection accuracy and robustness are improved, the application potential in industrial fault detection is large, and especially the advantage on unknown faults is remarkable.

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 discloses a transformer fault sound detection and early warning method, and belongs to the technical field of transformer detection, and the method comprises the steps: collecting the working sound data of a transformer in a fixed time period, including frequency, amplitude and duration; according to the working sound data of the transformer, analysis is carried out based on a pre-trained fault sound detection model, a fault type is output, and fault early warning is carried out; wherein a layered attention mechanism, residual connection and a Mish activation function are introduced to improve the time delay neural network, and the fault sound detection model is constructed based on the improved time delay neural network and a large language model. According to the invention, the problem that the fault type of the transformer cannot be accurately and timely identified and automatic early warning cannot be carried out in the prior art is solved.

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.

The invention relates to the field of acoustic signal processing, and discloses an industrial equipment abnormal sound data expansion method based on an improved generative adversarial network, and the method comprises the steps: constructing an improved generative adversarial network I-WaveGAN model; the I-WaveGAN model is trained, and a trained model is obtained; and generating the abnormal sound audio data of the industrial equipment by using the trained model. The method has the beneficial effects that high-fidelity modeling of audio features of industrial equipment is realized, the quality, diversity and discrimination of data expansion are remarkably improved, the modeling problem caused by abnormal sample deficiency is effectively relieved, and an efficient, stable and generalizable training data enhancement method is provided for an abnormal sound detection system.

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 motor manufacturing, and provides a motor abnormal sound detection method and device, and the method comprises the steps: obtaining a source vibration signal after a motor operates at a steady speed; determining a steady-speed vibration signal section of a motor steady-speed operation interval and a tail-speed vibration signal section of a tail-speed operation interval in the source vibration signal; based on the steady-speed vibration signal segment, determining all frequency multiplications of the steady-speed operation interval; and determining vibration characteristics at each frequency multiplication position in the tail speed vibration signal section, and judging that abnormal sound exists in the motor under the condition that the characteristic value of the vibration characteristic at any frequency multiplication position exceeds a characteristic threshold value. Because the abnormal sound of the motor is caused by the resonance characteristic at the frequency doubling position of the motor vibration signal, the abnormal sound of the motor can be accurately detected by detecting the number of order lines and / or resonance energy at the frequency doubling position of the tail speed vibration signal section of the motor tail speed operation interval, and the detection result has good consistency.

The utility model discloses a system for detecting abnormal sound of an engine by an engine pedestal, which belongs to the technical field of engines, and comprises a microphone, a sound sensor, an engine working parameter detection sensor and a channel acquisition case which are arranged on the engine, the microphone is used for detecting the sound of the engine moving part; the microphone and the sound sensor are respectively connected to the channel acquisition case through data lines, the engine working parameter detection sensor is connected to an engine pedestal through a data line, and the channel acquisition case is connected to the engine pedestal through a Can signal line; the engine pedestal comprises a main controller, a sound detection feedback unit is integrated in the main controller, and the sound detection feedback unit is used for processing detection data of a microphone, a sound sensor and an engine working parameter detection sensor and giving engine abnormal sound feedback. The system can timely judge the abnormal sound of the engine from the outside of a test room and stop the rack and the engine, and accurately recognize the part with the abnormal sound at the same time.

Systems and methods for utilizing microphone array information for acoustic modeling are disclosed. Audio data may be received from a device having a microphone array configuration. Microphone configuration data may also be received that indicates the configuration of the microphone array. The microphone configuration data may be utilized as an input vector to an acoustic model, along with the audio data, to generate phoneme data. Additionally, the microphone configuration data may be utilized to train and / or generate acoustic models, select an acoustic model to perform speech recognition with, and / or to improve trigger sound detection.

The utility model relates to an intelligent auxiliary glasses system for a deaf-mute. The intelligent auxiliary glasses system comprises a central control module, a sign language detection module, a voice playing module, an environment detection module, a sound detection module, a display module and a vibration module, the central control module is connected with the sign language detection module, the voice playing module, the environment detection module, the sound detection module, the display module and the vibration module. The intelligent auxiliary glasses system provided by the utility model has comprehensive functions, and can fully consider the safety problem of deaf-mute people going out.

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 and device, equipment and a storage medium, and the method comprises the steps: carrying out the feature extraction of a two-dimensional feature representation of a target detection audio through a feature capture unit in a target detection model, and obtaining a to-be-detected audio feature of the target detection audio, the feature capture unit is composed of a plurality of feature extraction modules and at least one compression excitation module, and each feature extraction module is composed of a plurality of densely connected time delay neural network layers; inputting the to-be-detected audio features into a detection classification unit in a target detection model for abnormal sound detection to obtain an audio category of the target detection audio; and obtaining an audio detection result of the target detection audio according to the audio category of the target detection audio. By means of the mode, modeling optimization is conducted on the time sequence features, a multi-granularity context sensing mechanism is established, time-frequency domain feature enhancement is enhanced, the detection precision and robustness of the model are remarkably improved, and meanwhile generalization of the model is greatly enhanced.

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.