152 results about "Acoustic fingerprint" patented technology

The invention discloses a rescue method and system of a rescue robot for exploration, and relates to the technical field of underground space rescue, and the method comprises the following steps: obtaining multi-path acoustic echo data of a karst cave and motion track data of the robot, and constructing a three-dimensional point cloud model according to the multi-path acoustic echo data and the motion track data of the robot; and identifying unmatched data in the multi-path acoustic echo data and the robot motion trail data, and taking an area where the unmatched data is located as an abnormal area. According to the method, the spatial resolution of signal acquisition is enhanced through the multi-microphone array, robust acoustic fingerprints are extracted in combination with a noise reduction algorithm and short-time Fourier transform, high-confidence human body sound source signals are screened out by using a feature template matching mechanism, accurate extraction and recognition of human body acoustic features in a karst cave complex noise environment are realized, and the accuracy of human body acoustic feature recognition is improved. The problem of misjudgment caused by confusion of sound source features and environmental noise in a traditional method is effectively solved.

The invention provides a multi-language cross-culture communication assisting method and system based on a large model. The method comprises the following steps: receiving a source language audio stream during a call, calling a multi-language sound frequency harmonic modulation feature library to extract fundamental frequency harmonic intensity distribution and tone turning features, and generating a cultural acoustic fingerprint vector; based on the vector, controlling a microphone array phase difference, directionally enhancing a fundamental frequency harmonic component of a speaker and suppressing noise, and outputting a high signal-to-noise ratio spectrogram; analyzing the pronunciation rhythm and tone turning characteristics of the spectrogram, capturing the pitch jump and duration of the syllable boundary, and generating an acoustic culture label; associating the spectrogram with a target semantic library, matching harmonic distribution and a cultural context rule based on a large model, and outputting a cultural interpretation prompt containing an ambiguity resolution suggestion; and generating a calibration result according to the acoustic tag and the semantic prompt, and overlapping the dynamic floating subtitles to the face area of the speaker in the video conference picture. According to the invention, cultural tone ambiguity in multi-language communication is eliminated.

The invention relates to the technical field of power transformer state monitoring, and discloses a main transformer winding temperature rise on-line monitoring method and system, and the method comprises the steps: obtaining the calibration flight time of ultrasonic waves through an acoustic sensor array disposed on the outer wall of an oil tank in a quasi-isothermal state of a transformer; calculating a structure additional time delay which is caused by an internal fixed structure and does not change along with the temperature, and establishing an acoustic fingerprint for the transformer; during on-line monitoring, oil way net propagation time reflecting temperature change of the insulating oil is obtained from on-line flight time measured in real time; and then, based on the net propagation time of the oil way, an acoustic tomography algorithm is adopted to reconstruct internal two-dimensional or three-dimensional temperature field distribution, and the winding hot-spot temperature is finally and accurately calculated in combination with the real-time load current. According to the invention, through the acoustic fingerprint correction technology, the measurement interference of an internal fixed structure is eliminated, and non-intrusive, high-precision and visual online monitoring of the winding hot-spot temperature is realized.

The invention relates to the technical field of fracturing pump truck monitoring, and discloses a fracturing pump truck monitoring system based on acoustic fingerprints and deep learning, and the system comprises a plurality of sensor modules which are used for collecting multi-dimensional operation state data of a fracturing pump truck and comprise sensors used for detecting sound, vibration, temperature, pressure, flow and electrical parameters; the data acquisition and preprocessing module is used for carrying out noise reduction processing and feature extraction on the data; and the anomaly detection module is used for detecting the operation anomaly of the fracturing pump truck based on the acoustic fingerprint model. According to the method, the technology based on acoustic fingerprints and deep learning is adopted, and the fault diagnosis precision and preventive maintenance capability of the fracturing pump truck monitoring system are remarkably improved. Meanwhile, the system can adapt to different environments through data analysis and self-adaptive learning, and the operation efficiency and the response speed are remarkably improved through improved user interaction and data visualization functions.

The invention belongs to the technical field of drainage pipeline detection, and particularly relates to a voiceprint recognition detection method for internal defects of a drainage pipeline, and the method comprises the following steps: S1, collecting sound signals in the pipeline through an acoustic sensor array; s2, preprocessing the collected sound signals, wherein the preprocessing comprises noise filtering, signal enhancement and segmentation processing; s3, extracting time domain, frequency domain and time-frequency domain features of the sound signals, and constructing voiceprint fingerprints; s4, establishing a defect classification model based on the deep neural network, and identifying different types of pipeline defects; s5, carrying out confidence evaluation on the detection result, and determining the position of the defect in the pipeline; s6, outputting a detection result and carrying out graded alarm; according to the method, various defect forms of cracks, blockage, damage and the like of different degrees of the drainage pipeline can be recognized, the recognition accuracy of the internal defects of the drainage pipeline can reach 95% or above through multi-dimensional voiceprint feature extraction and a deep learning algorithm, and continuous monitoring and real-time alarming can be achieved.

The invention relates to the technical field of automatic sorting of agricultural products, in particular to an egg quality intelligent sorting system and method based on multi-modal sensing. The system comprises a multi-mode sensing module, a data processing module and a sorting execution module. The multi-mode sensing module integrates a hyperspectral imaging unit, a voiceprint vibration detection unit and a weight sensing unit, and comprehensively collects egg surface images, vibration frequency and weight data; the data processing module analyzes the image data through deep learning and a data fusion algorithm to detect cracks and blood spots, and fuses multi-modal data to generate features to adapt to characteristic changes of different batches of eggs; the sorting execution module determines the sorting priority according to the fusion features and executes accurate sorting; the system utilizes the synergistic effect of the multi-mode sensing technology to comprehensively evaluate the internal and external quality of eggs, the detection precision is remarkably improved, efficient and intelligent egg sorting is realized, and the automatic sorting technology level of agricultural products is 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.

The invention provides a water heating pipeline pressure self-adaptive regulation and control method and system based on the Internet of Things, and belongs to the technical field of intelligent control of pipelines of the Internet of Things. According to the technical scheme, the method comprises the steps of building a pipeline acoustic sensing network, collecting pipeline external voiceprint signals to generate lightweight feature data, building a voiceprint-pressure mapping model based on the feature data, outputting a real-time pressure value, generating a pipe network state diagram based on the real-time pressure value, generating a pressure regulation and control instruction based on the pipe network state diagram, and achieving pressure self-adaptive regulation. Feedback data is collected according to the regulation and control result, and mapping model parameters are updated. The method has the advantages that the pipeline acoustic sensing network is constructed, edge calculation, depth feature extraction and the parallel neural network are combined, the pressure self-adaptive regulation and control capacity which does not need invasive sensing arrangement and has timeliness and robustness is achieved, meanwhile, a feedback closed loop is formed through a voiceprint-pressure mapping model, and the method is suitable for large-scale popularization and application. And the processing capacity of the system on complex dynamic working conditions is improved.

The invention relates to the technical field of audio processing, in particular to a self-adaptive scene sound effect adjusting method and device and a storage medium, and the method comprises the steps: collecting a mixed audio stream and an original playing audio, and extracting an acoustic fingerprint vector through a pre-trained convolutional neural network; performing acoustic feature deconstruction on the acoustic fingerprint vector to obtain a plurality of acoustic feature components, performing scene recognition judgment according to a preset scene judgment rule based on the plurality of acoustic feature components, and determining an audio playing scene; constructing a time-frequency mask according to the audio playing scene, generating a noise reduction gain matrix based on the time-frequency mask, and performing scene sound field enhancement on the audio playing scene to obtain a sound field optimization matrix; and performing noise reduction and sound effect adjustment on the original playing audio according to the noise reduction gain matrix and the sound field optimization matrix, and outputting the optimized playing audio. According to the invention, sound effect adjustment can be dynamically adapted according to different scenes, and the noise reduction accuracy and the multi-scene sound quality adaptability are improved.

The invention relates to the field of data acquisition, in particular to a multi-sensor array type equipment acoustic fingerprint self-adaptive acquisition device and method, and the device comprises a track which is arranged around a transformer body and is provided with a plurality of acoustic sensors; the controller is responsible for receiving operation state information and environment parameters of the transformer equipment and acquiring the operation state information and the environment parameters through an interface of the transformer equipment monitoring system and the environment monitoring sensor; the controller is provided with a communication module, sends an instruction to the acoustic sensor array through the communication module, and adjusts the layout and parameters of the acoustic sensor; and the server is used for monitoring, analyzing and storing the acoustic fingerprint signals in real time. When the device is used, the layout and parameters of the acoustic sensor are automatically adjusted, so that accurate acquisition of acoustic fingerprint signals of the transformer equipment is realized. Meanwhile, the advanced signal fusion technology is utilized to improve the signal strength and reliability, and more accurate and more reliable data support is provided for state monitoring and fault diagnosis of transformer equipment.

The invention relates to the technical field of underwater static target object detection and processing, in particular to an unmanned cross-domain positioning and acoustic fingerprint processing method and system for an underwater static target. Comprising the following steps: performing wide-area scanning on a task sea area, and scheduling an AUV and unmanned aerial vehicle cluster to a target area after discovering a suspicious target; the unmanned aerial vehicle cluster receives an acoustic signal of the AUV and transmits the acoustic signal to the cooperative resolving center in combination with self-positioning data so as to provide accurate coordinate guidance for the AUV; the AUV sails to a target area, parallel processing map construction and accurate positioning, target identification and dual-mode fingerprint generation are carried out, and a target task package is packaged; the ROV receives and analyzes the task packet, autonomously plans a path and sails to a target area, a sonar is started to collect data and generate real-time feature fingerprints, and the real-time feature fingerprints are matched with fingerprints in the task packet; and after matching succeeds, a specific job task is autonomously executed. According to the invention, a complete automatic solution is provided for scenes such as deep and far sea detection, emergency salvage, pipeline maintenance and the like.

The invention discloses a transformer fault detection method and device, a medium and equipment, and relates to the technical field of computers. Historical voiceprint data of a transformer are firstly acquired as sample data, fault types of the sample data are marked, then composite multi-scale dispersion entropies of the sample data are extracted, the composite multi-scale dispersion entropies are input to an encoder of a Transformer model to obtain predicted fault types, and the predicted fault types are optimized by taking minimization of deviation between a real fault type and the predicted fault types as an optimization target. And training an encoder of the Transform model to obtain a fault detection model, and finally extracting a composite multi-scale dispersion entropy corresponding to voiceprint data of a to-be-detected transformer, and inputting the composite multi-scale dispersion entropy into the fault detection model to perform fault feature extraction so as to determine the fault type of the to-be-detected transformer. According to the method, the time domain features of the voiceprint data of the transformer are reflected by adopting the composite multi-scale dispersion entropy, so that the fault features can be extracted from the voiceprint data more comprehensively, and the fault detection accuracy is improved.

The invention relates to the technical field of bag type dust collector filter bag abrasion detection, in particular to a filter bag damage non-contact detection method and system based on acoustic array positioning. The method comprises the following steps: arranging an acoustic sensor array in an air purification chamber of the dust remover, and collecting acoustic signals in real time; after band-pass filtering is carried out on the signals, feature vectors of the signals are extracted and matched with a pre-established acoustic fingerprint database, so that a filter bag damage event is recognized; after identification, based on the time difference of arrival of the signal to at least three sensors in the array, combining the coordinates of the sensors and the sound velocity, and utilizing a TDOA positioning algorithm to calculate the space coordinates of the damaged sound source; and finally, matching the coordinates with a pre-stored filter bag coordinate mapping table, determining the number of a specific damaged filter bag, and performing visual highlight marking on a pattern board plane layout of an application layer terminal. The online, real-time, automatic and accurate positioning of the damaged filter bag is realized, the problem that the prior art can only give an alarm but cannot position is solved, and the operation and maintenance efficiency and safety are improved.

The invention relates to a vehicle health dynamic monitoring method and system based on acoustic fingerprints, and belongs to the field of vehicle safety. The method comprises the following steps: capturing voiceprint transmission delay inequality and sensing baseline spacing, calculating a sound source azimuth angle, and positioning an abnormal sound source coordinate; triggering an active voiceprint acquisition protocol based on the abnormal sound source coordinate, acquiring an original abnormal sound signal, and performing environmental noise suppression to obtain a pure signal with a high signal-to-noise ratio; starting an acoustic fingerprint hierarchical scanning protocol, decomposing the high-signal-to-noise-ratio pure signal into fine sub-bands, extracting a key monitoring frequency band, and obtaining a frequency band attention index based on the key monitoring frequency band; and when the frequency band attention index exceeds a preset threshold range, outputting a troubleshooting instruction and generating a reverse sound wave signal and a vibration hedging amplitude. According to the invention, high-precision acoustic space perception and adaptive noise suppression optimization are realized, and dynamic monitoring of vehicle health is effectively carried out.

The invention relates to a transformer abnormal sound source positioning method and system, and belongs to the technical field of power equipment state evaluation, and the method comprises the steps: constructing a Bayesian neural network embedded with a voiceprint physical mechanism, and enabling a sound wave propagation equation to serve as a physical constraint to be embedded into the Bayesian neural network; reconstructing the voiceprint signal by adopting a compressed sensing technology to obtain a reconstructed voiceprint field; designing a multi-task objective function including data fitting, physical constraint and positioning loss, and optimizing data fitting, physical constraint and positioning precision to obtain a trained Bayesian neural network; based on a gradient sound source inversion positioning algorithm and the trained Bayesian neural network, sparse regularization is combined to obtain a prediction result of accurate positioning; and a prediction result is visualized to a three-dimensional model of the transformer, and the position of an abnormal sound source is visually displayed. According to the method, the limitation of a traditional method in a complex environment is overcome, and high-precision and high-robustness transformer abnormal sound source positioning is realized.

The invention discloses an SMD (Surface Mount Device) device dispensing quality detection method and related equipment. The method comprises the following steps: acquiring an acoustic signal generated by a colloid material in a dispensing process; performing time-frequency domain transformation on the acoustic signal, and extracting an acoustic feature vector representing physical characteristics of the colloid; matching the acoustic feature vector with a preset acoustic fingerprint database to obtain a matching result; based on the matching result, performing multi-time scale trend analysis on the acoustic characteristic change of continuous multiple times of dispensing to obtain a trend analysis result; and matching with a preset abnormal mode library according to the trend analysis result, determining the abnormal type and the abnormal degree of the colloid material, and obtaining a dispensing quality prediction result. According to the technical scheme, the dispensing quality can be predicted in real time through acoustic feature analysis in the dispensing process, special detection time does not need to be additionally arranged after the dispensing procedure is completed, the production efficiency is remarkably improved, meanwhile, potential quality problems can be found in advance, the rework rate is reduced, and the product yield is improved.

The invention discloses a cable fault voiceprint monitoring method and system based on deep learning, and the method comprises the steps: obtaining sound data during the operation of a cable, carrying out the preprocessing, obtaining voiceprint data, carrying out the feature extraction through Mel-frequency cepstrum sparsity, replacing the last layer of a ResNet model with a new full-connection layer, and carrying out the detection of the voiceprint data. The number of neurons of the ResNet model is matched with the number of cable fault types needing to be classified, so that the ResNet model originally used for an image recognition task is completely suitable for voiceprint monitoring, the step of image conversion is not needed any more, robustness in a complex environment is improved, assistance of other models is not needed any more, and the calculated amount and the scheme complexity are reduced.

The invention relates to the technical field of intelligent control of double-drum washing machines, and discloses an intelligent control system of an energy-saving double-drum washing machine, which comprises a hardware execution unit used for providing multi-mode sensing, accurate liquid management, mechanical execution and energy recovery functions; the control processing unit is used for processing the received data, operating an algorithm and coordinating the operation of each component of the system; the cooperative control software module runs on the main control board and comprises an acoustic fingerprint identification and fault diagnosis module and an intelligent fluid precise counterweight and cooling module; an AI-driven collaborative decision and adaptive optimization module; the invention discloses a micro heat pump energy recovery and precise temperature control linkage module. By means of the high-sensitivity acoustic array sensor and the acoustic fingerprint recognition and fault diagnosis module, clothes imbalance is recognized, point-to-point liquid balance weight is achieved by means of the micro-fluidic spraying valve array, the optimal dehydration cooperative scheduling strategy is generated, water and electricity resources are greatly saved, and the dehydration efficiency is improved.

A system, product and method comprising: capturing, by two or more microphones of a separate device physically separate from a hearable device of a user, a noisy audio signal from an environment of the user, wherein a plurality of people is present in the environment, the hearable device is used for providing audio output to the user; processing the noisy audio signal, thereby obtaining an enhanced audio signal, said processing comprises applying speech separation on the noisy audio signal to obtain a separate speech segment of a person of the plurality of people, wherein the speech separation utilizes an acoustic fingerprint of the person for extracting the separate speech segment of the person; and outputting the enhanced audio signal to the user via the at least one hearable device.

The invention relates to the technical field of mechanical equipment fault diagnosis, and discloses a contact ball bearing loss degree identification method and system. The method comprises the following steps: synchronously acquiring multi-modal data during bearing operation, including an image sequence acquired by a high-resolution industrial camera and a voiceprint signal acquired by an array microphone, pre-processing the data, constructing a multi-modal feature fusion network, and fusing features by adopting a cross-modal attention mechanism to obtain a multi-modal feature fusion network; and constructing a loss evaluation model based on improved Transform to process the spatial-temporal characteristics, and finally outputting a bearing loss degree grade. According to the method, complementarity of multi-modal data is effectively utilized, accuracy of feature expression and accuracy of loss degree identification are improved, support is provided for maintenance and management of equipment, and the method has the advantages of being high in identification accuracy, high in reliability, good in practicability and the like.

The invention relates to the technical field of building construction, and discloses an attached vibrator vibration parameter matching decision-making system, which comprises a perception execution dual-mode vibrator network, a vibration acoustic fingerprint generation and analysis module, a fingerprint evolution time sequence inference module and a multi-target dynamic decision-making engine, generating a vibration acoustic fingerprint formed by multi-dimensional physical characteristics according to the response signal; the method comprises the following steps: constructing a fingerprint evolution sequential sequence, comparing the fingerprint evolution sequential sequence with a reference database, deducing the performance of a concrete material on line, and further calling a mapping function matched with the performance to evaluate a real-time compactness state; and finally, based on the evaluated compactness, the multi-target dynamic decision engine adopts a model prediction control strategy to generate an optimal dynamic operation instruction for each vibrator node. Closed-loop self-adaptive control of detection, evaluation, decision making and execution is constructed, the optimal vibration parameters can be matched in real time, the vibration quality and uniformity of concrete are remarkably improved, energy consumption is reduced, and dependence on artificial experience is reduced.

The invention belongs to the technical field of battery fault recognition, and provides a battery early fault recognition method and system based on acoustic fingerprints, and the method comprises the steps: collecting an output signal of a piezoelectric sensor on the surface of a battery at a high-frequency sampling rate, removing background noise in a mode of combining a time domain spectral subtraction method with a statistical threshold, and dynamically updating noise spectrum estimation; performing parallel calculation on short-time Fourier transform, continuous wavelet transform and Mel-frequency cepstral coefficients to form a feature tensor; learning a low-dimensional fingerprint vector through a sparse auto-encoder, wherein a loss function comprises a reconstruction error term and a sparse constraint term; and a mahalanobis distance or a single-class support vector machine is used to measure a deviation degree between the fingerprint vector and the health fingerprint database, a fault confidence coefficient is output, and when the confidence coefficient exceeds a preset threshold value, early fault early warning is triggered. According to the method, characterization processing can be carried out on the acoustic data of the battery within milliseconds, the fault confidence coefficient is given, and high-sensitivity detection, easy migration, early warning and real-time performance are achieved.

The invention relates to a hydraulic turbine set operation system and method based on digital twinning, and the system comprises a hydraulic turbine set top cover, the hydraulic turbine set top cover is provided with a plurality of groups of voiceprint collection arrays, and each group of voiceprint collection array comprises a plurality of voiceprint collectors which are arranged in the vertical direction at fixed intervals. The voiceprint collector is used for collecting original voiceprint data of different positions on the top cover of the hydraulic turbine set and sending the collected original voiceprint data to the data center. After receiving the original voiceprint data, the data center preprocesses the original voiceprint data, establishes a digital twinning reference model based on a mapping relation between real-time working condition parameters and voiceprint signal features through a digital twinning technology, and constructs an expected feature vector based on a voiceprint collector position compensation vector and a mapping matrix; and adjusting the difference vector by using the correction factor. The system adopts a plurality of directions and a plurality of voiceprint collectors configured in each direction, and the voiceprint collection accuracy is high in an extreme water flow state.

This invention relates to the field of audio processing technology, specifically to an adaptive scene sound effect adjustment method, device, and storage medium. The method includes: acquiring a mixed audio stream and the original playback audio; extracting an acoustic fingerprint vector using a pre-trained convolutional neural network; deconstructing the acoustic fingerprint vector to obtain multiple acoustic feature components; based on these components, identifying and determining the audio playback scene according to preset scene determination rules; constructing a time-frequency mask based on the audio playback scene; generating a noise reduction gain matrix based on the mask; simultaneously enhancing the sound field of the audio playback scene to obtain a sound field optimization matrix; and performing noise reduction and sound effect adjustment on the original playback audio based on the noise reduction gain matrix and the sound field optimization matrix, outputting the optimized playback audio. This invention can dynamically adapt sound effect adjustment according to different scenes, improve noise reduction accuracy, and enhance multi-scene sound quality adaptability.

The invention discloses a voiceprint and stress wave multi-mode identification method for a fan blade icing state, and the method comprises the steps: constructing a quantum Mel filter group, and converting a voiceprint signal of the fan blade icing state into a quantum state code; quantum convolution feature extraction operation is carried out on the quantum state code, and the quantum state code is converted into a classic feature vector according to a quantum convolution feature extraction result; constructing an icing state classification model, and inputting the classic feature vector into the icing state classification model for processing; by constructing the icing state classification model, the voiceprint and the stress wave in the icing state of the fan can be considered, and an efficient and accurate method is provided for icing detection of the wind driven generator blade.

The invention relates to the field of digital information transmission, and discloses a safe box encryption method based on voice and voiceprint recognition, which comprises the following steps of: synchronously acquiring environmental acoustic fingerprints of a user terminal and a safe box, and combining a voiceprint transient entropy characteristic extracted by a voice signal and a physical layer modulation characteristic of a wireless channel during sound production; and constructing a triple physical layer verification mechanism to cooperatively generate a one-time session key. According to the method, the voiceprint biological characteristics and the channel environment characteristics are deeply coupled, qualitative change from pure data protection to interaction process authenticity verification is realized, meanwhile, the context constraint of key negotiation is enhanced by using the space-time anchoring effect of the environmental acoustic fingerprints, and the transmission security in a near-field voice interaction scene is remarkably improved.

The invention discloses a voiceprint detection method for internal abnormity of a wind driven generator blade, and relates to the technical field of electrical equipment fault detection. According to the voiceprint detection method for the internal abnormity of the wind driven generator blade, the problems of data diversity and fault sample scarcity are solved through a unique mode of implementing corresponding diagnosis for different working condition information in the wind driven generator and an abnormity diagnosis mode based on an auto-encoder. The voiceprint detection method for the internal abnormity of the wind driven generator blade is used for efficiently and accurately detecting the internal abnormity of the wind driven generator blade.

The application relates to the technical field of aluminum processing supervision, in particular to a generation method of an aluminum leakage judgment model, an aluminum leakage detection method and equipment, which comprises the following steps: acquiring a first acoustic fingerprint signal and noise power spectral density under a casting state without aluminum leakage; acquiring a second acoustic fingerprint signal and environmental sound power spectral density under the casting state with aluminum leakage; calculating a noise suppression gain function; acquiring a training acoustic fingerprint signal and extracting casting acoustic fingerprint features based on the noise suppression gain function; classifying the casting acoustic fingerprint features to acquire non-aluminum leakage feature labels and aluminum leakage feature labels, and training to obtain an aluminum leakage judgment model; collecting real-time acoustic fingerprint signals under the casting state and obtaining real-time acoustic fingerprint features; inputting the real-time acoustic fingerprint features into the aluminum leakage judgment model and waiting for output judgment results; if the judgment results correspond to the aluminum leakage feature labels, it is determined that aluminum leakage is determined and alarm information is output. The application is used for improving aluminum leakage detection effects in a multi-noise environment.

The application provides a pipeline leakage detection method based on multi-modal feature fusion, and relates to the field of pipeline leakage detection. The pipeline leakage detection method based on multi-modal feature fusion comprises the following steps: acquiring an acoustic signal in a pipeline, determining an acoustic fingerprint energy spectrum in the pipeline based on the acoustic signal; acquiring a thermal image in the pipeline, determining a thermal diffusion gradient in the pipeline based on the thermal image; acquiring a pressure signal in the pipeline, determining a fluctuation entropy in the pipeline based on the pressure signal; using a confidence function, respectively mapping the acoustic fingerprint energy spectrum, the thermal diffusion gradient and the fluctuation entropy into confidence values; fusing the confidence values corresponding to the acoustic fingerprint energy spectrum, the confidence values corresponding to the thermal diffusion gradient and the confidence values corresponding to the fluctuation entropy, and determining a detection result of whether the pipeline leaks. Through the above method, the false positive rate of pipeline leakage detection is reduced.