95 results about "Auscultation" patented technology

The application discloses a diagnosis data processing method and device and a storage medium, relates to the technical field of data processing, and comprises the following steps: acquiring a heart-lung auscultation sound signal collected by a collection device and a traditional Chinese medicine (TCM) diagnosis standard description received based on an interactive interface; determining a western medicine quantitative diagnosis index according to the heart-lung auscultation sound signal, and correlating a TCM syndrome differentiation type according to the TCM diagnosis standard description and the western medicine quantitative diagnosis index; and generating and outputting a TCM medication recommendation scheme corresponding to a diagnosis result according to the western medicine quantitative diagnosis index and / or the TCM syndrome differentiation type. The application provides strong objective evidence and quantitative reference by differentiating the TCM syndrome differentiation type according to the auscultation sound. When diagnosing and treating diseases, the TCM highly depends on and integrates the auscultation result, and takes the auscultation result as one of key bases for differentiation, prescription selection, treatment effect evaluation and prognosis.

The present invention provides a device (100) and method for measuring and / or monitoring auscultation and other biomedical signals of a body part of a subject, the device (100) comprising: a plurality of sonographic sensors sensitive to surface vibrations-PG sensors (110) configured to measure acoustic activity of the body part, and providing a PG signal (115) indicative of acoustic activity of the body part, the PG sensor (110) being adapted to be arranged on the body part to cover different independent auscultation areas of the body part. The device further comprises at least one other biomedical sensor-BIO sensor (120) configured to independently measure a respective activity of the body part according to the sensor type and to provide at least one BIO signal (125) indicative of the respective activity of the body part. The device further comprises a signal processing unit (160) configured to acquire a signal (115, 125) from each sensor (110, 120) and to collectively perform a signal source specific analysis by combining information of the PG signal (115) with corresponding arrangement information of the PG sensor (110) on the body part and information of the BIO signal (125).

The utility model relates to the technical field of medical instruments, and discloses an adjustable stethoscope which comprises an elastic plate, the two ends of the elastic plate are fixedly connected with mounting cylinders, the two mounting cylinders are arranged in a V shape, one end of each mounting cylinder is fixedly connected with a fixing block, a cavity is formed in each fixing block, and the fixing blocks are fixedly connected with the mounting cylinders. The inner side wall of the cavity is in sliding connection with a pressing rod. According to the adjustable stethoscope, through the arrangement of the mounting cylinder, the pressing rod, the spring, the connecting block, the clamping block and the ear hooks, when the distance between earplugs on the two ear hooks is adjusted, a pressing plate is firstly pressed to drive the pressing rod to move, meanwhile, the spring is compressed to drive the clamping block to move through the connecting block, the pressure of the clamping block on the ear hooks is reduced, and the clamping block is far away from the ear hooks; then the ear hooks can be pulled, under the action of the mounting cylinders, the relative distance between the earplugs on the two ear hooks is changed, the stethoscope can better adapt to the head of each user, and therefore the auscultation comfort level and the sound conduction effect are improved.

1. The name of the design product: pulse pulse sound intelligent auscultation instrument. 2. The use of the design product: an auscultation instrument for detecting pulse and pulse sound respectively or simultaneously and obtaining corresponding pulse data information and pulse sound data information. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: combined state reference drawing. 5. The bottom of the design product is the part that is not easy to see or cannot be seen during use, so the component 1 top view is omitted; the component 2 right view is symmetrical with the component 2 left view, so the component 2 right view is omitted; the component 3 right view is symmetrical with the component 3 left view, so the component 3 right view is omitted.

The utility model discloses an efficient abnormal sound monitoring device for a belt conveyor, which comprises an auscultation optical fiber, and connecting pieces are inserted into two sides of the surface of the auscultation optical fiber. According to the efficient abnormal sound monitoring device for the belt conveyor, through the arrangement of the positioning mechanism, the connecting piece and the auscultation probes, when the device is used, auscultation optical fibers are installed in the connecting piece, then the connecting piece is installed on the surface of an external conveyor, and the auscultation probes installed on the surfaces of the auscultation optical fibers are matched, so that comprehensive coverage can be achieved; the stethoscope is expanded, the traditional manual operation is replaced, the stethoscope probe is used for transmitting data to the industrial optical fiber host and the platform server for data processing, accurate positioning of a fault position can be realized, and finally, when stethoscope optical fibers are disassembled, only a positioning cover on the surface of a connecting piece needs to be unscrewed, so that the stethoscope can be disassembled. The auscultation optical fiber can be taken down from the surface of the conveyor, regular maintenance and replacement by workers are facilitated, and the practicability of the equipment is improved.

Active auscultation can be used to determine the characteristics of a user's organs (e.g., lungs or heart). An acoustic or piezoelectric signal (e.g., pulses, tones, and / or broadband pulses) can be projected onto the body or chest of an animal (typically a human). The signal interacts with the body or lungs and, in some cases, may cause resonance within the body / lungs. The resulting signal can be emitted from the body and analyzed to determine, for example, the resonant frequency of the lungs and / or how the sound is absorbed, reflected, or modified by the body. This information can indicate lung characteristics such as lung capacity, the amount of air trapped in the lungs, and / or the presence of COPD.

This invention discloses a multimodal respiratory disease-related data acquisition system and method. The data acquisition system includes a disposable oral-nasal breathing interface, an oral-nasal breath sound acquisition module, a bidirectional flow / differential pressure sensing module, a temperature and humidity auxiliary acquisition module, a chest and back multi-channel auscultation module, a channel auscultation front end, a trimodal respiratory data acquisition box, a mobile terminal annotation module, a clinical label association module, and a local storage module. The data acquisition method is as follows: Step 1, prepare the oral-nasal breathing interface and acoustic coupling patch; Step 2, start the trimodal respiratory data acquisition box; Step 3, the patient performs quiet breathing; Step 4, the patient performs a maximal inhalation followed by a forceful exhalation; Step 5, associate the clinical examination results with the acquired data; Step 6, output risk scores, abnormality prompts, or classification prompts. Beneficial effects: Reduces wind noise interference, allows acoustic signals and lung function data to be acquired at the same time reference, and reduces frictional noise and poor contact.

The invention discloses an internal arteriovenous fistula portable intelligent auscultation instrument for hemodialysis, and relates to the technical field of medical equipment. An alarm, three auscultation result indicating lamps with different colors, an equipment switch and an electric quantity indicating lamp are arranged on the auscultation instrument main machine, an equipment power supply, a control module, a wireless data transmission module and an AI noise recognition chip are arranged in the auscultation instrument main machine, and an auscultation head and a conduction tube are arranged on the outer side of the auscultation instrument main machine. And an auxiliary fixing mechanism is arranged on the stethoscope head. A noise reduction acoustic filter screen is arranged in the auscultation head to accurately filter interference, a signal amplification module at the tail end of a conduction tube amplifies weak blood flow sound, an AI noise recognition chip with a clinical noise spectrum pre-recorded is matched, the internal fistula noise state can be automatically recognized without depending on professional auscultation experience, visual feedback is achieved through a three-color auscultation result indicator lamp, linkage early warning is matched with an alarm, and the internal fistula noise state can be automatically recognized. Common medical care can quickly complete clinical screening, and a patient can also perform self-examination at home, so that the risks of missed judgment and misjudgment are thoroughly avoided.

A multimode stethoscope may provide an auscultatory signal from a patient to a local playback device and to an extended reality (XR) device. The multimode stethoscope may include a signal converter that converts the auscultatory signal to an electric signal carrying the auscultatory signal; an acoustic channel passing the auscultatory signal to an auscultation output port; a chest piece passing the auscultatory signal from the patient to the acoustic channel and to the signal converter; and a first wireless interface wirelessly transmitting the electric signal to the XR device. The auscultation output port may removably attach a stethoscope tube to the acoustic channel. The XR device may display an auscultation position on the patient's body wherein the multimode stethoscope may obtain the auscultatory signal when the chest piece is at the auscultation position. The XR device may store auscultation position data indicating the auscultation position in the patient's profile.

The utility model discloses a sound diagnosis instrument, relates to medical equipment technical field, the sound diagnosis instrument comprises a housing, a lift drive assembly and a bone conduction acquisition head, the housing is provided with an accommodation space, the housing is provided with a guide via hole communicated with the accommodation space; the lifting driving assembly comprises a lifting transmission part and a lifting driving mechanism which are in transmission connection, the lifting driving mechanism is arranged in the containing space, and the lifting transmission part is arranged in the guide through hole in a penetrating mode; the bone conduction collecting head is arranged outside the shell and corresponds to a collecting position used for placing the wrist of a patient, the upper end of the bone conduction collecting head is connected with the lifting transmission part, and the lower end of the bone conduction collecting head is used for abutting against the wrist of the patient so as to collect pulse data of the wrist of the patient; according to the technical scheme, the accuracy of pulse measurement can be improved.

The invention discloses a heart sound signal acquisition and automatic classification method based on deep learning, and aims to solve the problems that wireless transmission time delay of heart sound signals is high, weak pathological features are difficult to extract and classification accuracy is low. The method comprises the following steps: acquiring signals of four auscultation areas by using a high-fidelity wireless digital stethoscope; high-speed and low-delay transmission of medical-level signals is realized by utilizing a star flash transmission module and combining predictive coding and Huffman coding compression mechanisms; in the preprocessing stage, self-adaptive wavelet denoising based on signal energy entropy is adopted, a multi-resolution fusion feature extraction strategy is provided, the problem of time-frequency resolution tradeoff is solved through narrow window and wide window dual-channel parallel processing, and transient positioning features and pathological frequency domain textures are captured at the same time; the classification model adopts a multi-scale parallel convolution structure and is matched with a recurrent neural network and an attention mechanism, so that the problem that transient and continuous heart sound features are difficult to consider at the same time in a single scale is solved. According to the method, the accuracy and robustness of heart sound classification are remarkably improved.

The invention discloses a cardiac mechanical signal processing method and device based on wavelet reconstruction. The method comprises the following steps: performing trend removal and frequency band extraction on an original SCG signal, and reserving main mechanical energy components corresponding to a heart sound event; then wavelet decomposition and main scale reconstruction are carried out, and time domain features of key components such as S1 and S2 structures similar to PCG signals are strengthened, so that heart sound-like signals which are similar to PCG in form and clear in rhythm are generated. Compared with an original SCG signal, the heart sound-like signal obtained through reconstruction is remarkably improved in the aspects of rhythm definition, form consistency and peak stability. And further performing rhythm analysis on the reconstructed signal, introducing physiological constraints, and screening to obtain a cardiac trigger point sequence, thereby realizing high-precision cardiac recognition. The device can be integrated with medical image equipment and wearable equipment, and the functions of heart sound gating, synchronous triggering or auscultation auxiliary analysis and the like are achieved.

The utility model relates to the technical field of medical equipment, in particular to an auscultation device for children, which comprises a chest device, the chest device is clamped on a stethoscope fixing seat, a clamping seat is slidably connected onto the stethoscope fixing seat, a pull rod is rotatably connected onto the clamping seat, one end of the pull rod is rotatably connected onto a connecting seat, and the other end of the pull rod is rotatably connected onto the connecting seat. The connecting base is connected to the supporting rod in a sliding mode, a sliding rod is arranged at one end of the connecting base, and a cylindrical button is detachably connected to the sliding rod. According to the stethoscope fixing seat, the movable seats on the two sides can be close to each other, the clamping seats on the movable seats can be close to each other, when a chest device is placed between the clamping seats on the two sides, the clamping seats can clamp and fix the chest device, the chest device can be rapidly installed on the stethoscope fixing seat, the chest device does not need to be independently placed in a pocket, and therefore medical staff can conveniently use the stethoscope fixing seat. And the stethoscope is also prevented from moving randomly.

The invention discloses a collaborative auscultation method, system and device and a storage medium, and relates to the technical field of intelligent medical treatment and auxiliary diagnosis, and the method comprises the steps that an AI auscultation doctor end receives a control instruction input by a user through an image user interface, and sends the control instruction to a doctor seeing end; the doctor seeing end collects sound vibration data of an auscultation area based on the instruction and sends the collected sound vibration data to the AI auscultation doctor end; when the AI auscultation doctor end receives sound vibration data, the data are input into the auscultation analysis decision network model for analysis and reasoning, and an AI auscultation conclusion is generated. According to the method, auscultation is carried out through sound vibration data, cardiopulmonary physiological information can be comprehensively captured, and the abnormal feature detection rate and diagnosis accuracy are improved; meanwhile, in combination with an AI auscultation conclusion output by the auscultation analysis decision network model, auscultation decision is assisted, remote auscultation defects are overcome, efficiency and accuracy are improved, and medical resource pressure is relieved.

The utility model relates to a kind of multifunctional physical examination apparatus, including Y-shaped sound guide pipe (1), auscultation ear piece (2), chest piece (3), the auscultation ear piece (2) symmetry is set in the two branch ends of Y-shaped sound guide pipe (1), the chest piece (3) is set in the main stem end of Y-shaped sound guide pipe (1), the chest piece (3) back detachably provided with light source (4) and timer (5), the main stem side wall of Y-shaped sound guide pipe (1) is provided with scale mark layer (6) and pupil table (7), the main stem of Y-shaped sound guide pipe (1) still be provided with sensory tester (8), percussion hammer subassembly (9). Compared with prior art, the utility model is simple in structure, convenient to carry and take, and is conducive to improving the work efficiency of medical staff to carry out physical examination.

The invention discloses a traditional Chinese medicine diagnosis question and answer based on deep learning, and relates to the technical field of traditional Chinese medicine, and the method comprises the steps: remotely obtaining tongue condition information, pulse condition information, complexion diagnosis information and auscultation information of a patient; the color and state of the patient can be remotely observed; the disease condition of the patient is obtained through language communication; wherein the disease conditions of the patient comprise consciousness symptoms, the incidence process, the treatment course, the daily life, the plain physique, the past medical history and the family medical history; constructing a diagnosis and treatment knowledge graph by analyzing related traditional Chinese medicine literatures and medical case contents; wherein the medical case content comprises the disease condition, tongue condition information, pulse condition information, complexion diagnosis information and auscultation information of the patient; and in combination with syndrome type classification of a traditional Chinese medicine theory, analyzing the constructed disease condition knowledge graph by using a deep learning model so as to intelligently classify and diagnose the disease condition of the patient.

This invention discloses an automatic auscultation and sputum expectoration integrated machine, including a sputum expectorator, a base plate, a left backrest, and a right backrest. A guide rod is provided on the top front side of the vertical base plate along the left-right direction. The tops of both the left and right backrests slide in conjunction with the guide rod, and the bottoms of both the left and right backrests slide in conjunction with the front side of the base plate. Both the left and right backrests have grooves for the movement of the treatment heads. The two treatment heads of the sputum expectorator are respectively mounted on left and right treatment head drive mechanisms. The left auscultation mechanism is used to auscultate the rales in the left lung, and the right auscultation mechanism is used to auscultate the rales in the right lung, thereby determining the specific location of sputum in the lungs. The base plate also has treatment head drive mechanisms that respectively percuss the left and right sides of the patient's back. The treatment head drive mechanisms drive the treatment heads to percuss the patient's back, accurately percussing the stethoscope to determine the lung location of the sputum, and the vibration loosens the sputum to facilitate coughing.

The application relates to the technical field of medical devices, and discloses a portable arteriovenous fistula auscultation terminal and an auscultation system, which comprises a body box, a control box fixedly installed at the middle of the upper end face of the body box, installation boxes fixedly installed at the front and rear end faces of the body box, limit rods slidingly installed at the front and rear sides of the lower end face of the body box, and a sticking pad fixedly installed at the lower end face of the limit rod. The auscultation system further comprises a supporting mechanism arranged at the left and right side walls of the body box, an adjusting mechanism arranged at the inner cavities of the body box, an adsorption mechanism arranged at the left and right side walls of the body box, and a buffer mechanism. The distance between the two supporting rods can be adjusted through the adjusting mechanism, so that the device is suitable for users with different body sizes. Through the arrangement of the supporting mechanism and the adsorption mechanism, the whole device can be stably placed on a table top, so that the stability of the device during use is improved.

Computer software, a computer system (212) and a corresponding method for assessing health of a heart valve of a heart of a subject (202) are disclosed. A plurality of murmur-grade values are received, wherein each murmur-grade value is associated with a different respective auscultation position (102, 104, 106, 108). The plurality of murmur-grade values are input to a first trained software model (304), implemented by the computer software. The first trained software model (304) is operated to generate a value indicative of health of the heart valve. The value indicative of health of the heart valve is output from the first trained software model (304).

The invention belongs to the technical field of medical instruments, and particularly relates to a head-mounted stethoscope for heart disease monitoring, which is used for daily physical examination work and application to a heart rehabilitation path after a cardiac pacemaker is implanted, and comprises a U-shaped frame, and a U-shaped groove is formed in the U-shaped frame. By arranging the mounting rings and the sound boxes in the earmuffs, when the device is used, the earmuffs can be worn on the ears, the sound receiving heads are placed in a manner of being attached to the thoracic cavity of a patient, the sound receiving heads are used for receiving heart sounds of the patient, heart sound data are transmitted to the control host through the wires, and then the control host plays the heart sounds through the sound boxes; the U-shaped frame is arranged on the U-shaped frame, damage to external auditory canal mucous membranes caused by long-time auscultation work is effectively reduced, meanwhile, the holographic glasses are arranged to be connected with the U-shaped frame, the holographic glasses are connected with the control host, and therefore heart sound data are converted into beating images through the control host, visualization is achieved, and the auscultation effect and the auscultation efficiency are effectively improved.

The invention relates to the technical field of wireless audio transmission, and discloses an audio sharing loudspeaker device matched with a heart sound stethoscope for teaching. The device comprises a parameter acquisition unit, a calibration unit, a clock unit, a distribution unit, a decoding unit, a feedback unit and an evaluation unit, wherein the parameter acquisition unit acquires environmental data and generates audio adjustment parameters; the calibration unit calibrates the teaching audio signal according to the audio adjustment parameter; the clock unit extracts time stamp information from the calibrated audio signal flow and realizes clock synchronization; the distribution unit generates and pushes multiple paths of audio distribution streams based on time synchronization, and monitors transmission interference and processes data packet loss at the same time; the decoding unit decodes the audio signal stream and adjusts the volume; the feedback unit collects audio playing effect feedback data and optimizes transmission; the evaluation unit evaluates audio distribution quality and reasonably switches channels. According to the invention, the problems of asynchronous playing and unstable sound quality in multi-terminal audio teaching are solved, and the synchronism and teaching quality of heart sound auscultation teaching are improved.

The invention discloses a condition detection method of a stethoscope, electronic equipment, a medium and a product, and relates to the technical field of intelligent equipment.The condition detection method of the stethoscope comprises the steps that contact information between a coverage area of a receiver and the receiver is obtained through a sensor group, and the contact information comprises contact values of different positions on the receiver and the coverage area; generating a contact condition between the receiver and the coverage area based on each contact value in the contact information; the contact condition is output, and the contact condition comprises point locations representing sufficient contact and / or insufficient contact. The contact condition between the receiver and the coverage area is automatically generated and output, so that a user of the stethoscope can adjust the position or posture of the receiver in real time according to the contact condition, dependence on personal experience of a doctor is effectively reduced, and objective guarantee is provided for high-quality auscultation sound.

The invention provides a heart sound classification method and device and a computer readable storage medium. The method comprises the following steps: acquiring a heart sound signal by an auscultation part; the data processor performs segment processing on the heart sound signals through the sliding window to obtain segment signals; the data processor converts the segmented signals from a time domain to a frequency domain to generate a segmented spectrogram; the data processor inputs the segmented spectrogram into a trained deep learning model to obtain a classification result, the deep learning model takes a residual convolutional neural network as a basic network architecture and comprises an attention mechanism module, and the attention mechanism module is used for enhancing attention to key features in the segmented spectrogram; and the communicator uploads the classification result to a back-end server and / or a personal terminal. According to the heart sound classification method provided by the invention, the heart sound classification precision of the deep learning model is improved, and the generalization ability and adaptability to heart sound signals are enhanced.

The utility model relates to the technical field of medical instruments, and discloses a swallowing stethoscope which comprises a stethoscope head and a terminal device, the stethoscope head is attached to the lower jaw and the neck of a human body to be used for collecting swallowing signals, and the terminal device is connected with the stethoscope head to be used for displaying the swallowing signals. The stethoscope head comprises an inflation cavity and an inflation pump connected with the inflation cavity, one side of the inflation cavity is provided with a resonance membrane attached to the lower jaw and the neck of the human body, the resonance membrane is a flexible electrode film capable of collecting electromyographic signals, and a sound sensor is arranged in the inflation cavity; a processor which is connected with the sound sensor and the resonance membrane and is used for processing sound signals and electromyographic signals is arranged on the listening head; the terminal device is connected with the processor. The swallowing stethoscope provided by the utility model can efficiently capture sound information of swallowing and breathing and activity signals of swallowing actions, and data are directly transmitted to terminal equipment, so that a doctor can check and analyze auscultation results anytime and anywhere, and the convenience and efficiency of diagnosis are improved.

The embodiments of the present application provide a stethoscope device and a stethoscope system. The stethoscope device includes at least a support and a stethoscope assembly. The support includes a device storage portion. The stethoscope assembly is connected to the support. The stethoscope assembly includes a pickup, a sound transmission tube, and a microphone docking piece. The sound transmission tube connects the pickup and the microphone docking piece. The microphone docking piece includes a sound outlet. The sound outlet is connected to the device storage portion. The stethoscope device of the embodiments of the present application can help reduce the user's auscultation burden and workload, and is not likely to cause adverse effects on the user's hearing.

The invention discloses a system and method for combining an auscultation instrument and a human body structure model, and aims to improve the precision and efficiency of medical auscultation. The system comprises an auscultation instrument module, a human body structure model module, a data fusion and display module and other core parts. The auscultation instrument module is responsible for collecting sound signals and shooting auscultation part images through a camera. The human body structure model module is used for accurately positioning auscultation parts based on a high-precision 3D model; and the data fusion and display module deeply fuses the sound, the image and the model, and provides visual comprehensive audio-visual materials for medical staff. In addition, the system can further expand a vibration acquisition module, a temperature acquisition module, a percussion module and the like, and diagnosis information is further enriched. Through deep analysis of sound signals, vibration signals and position correlation, the system can assist medical staff in identifying abnormal features, provide a preliminary diagnosis basis, support auscultation position guidance and other functions, and significantly improve scientificity and accuracy of clinical decisions.

The invention relates to the technical field of blood pressure monitoring, in particular to a blood pressure monitoring method and device based on infrasound auscultation. The method comprises the following steps: acquiring an auscultation signal and carrying out band-pass filtering processing on the auscultation signal to obtain an infrasound auscultation signal after band-pass filtering; performing homomorphic filtering processing on the infrasound auscultation signal after band-pass filtering to obtain a homomorphic envelope, determining a maximum value point of the homomorphic envelope, and setting a time region, determining a maximum value point, a first minimum value point located on the left side of the maximum value point and a second minimum value point located on the right side of the maximum value point on the infrasound auscultation signal after band-pass filtering based on the time region; and obtaining a time difference value between the maximum value point and the minimum value point I in the same time region, and calculating the diastolic pressure based on the time difference value. By means of the mode, the diastolic pressure, the systolic pressure and the heart rate can be easily, conveniently and rapidly obtained, and the accuracy of the obtained diastolic pressure, the systolic pressure and the heart rate is high.

The present application relates to the technical field of teaching training, in particular to a four-step palpation and fetal heart auscultation training method and system with adjustable fetal position; the method of the present application involves basic training and advanced training; the basic training adjusts the fetal position in a fixed order, and the single step is qualified to be locked or unqualified to be reset; the operation process is standardized, the accumulated deviation of the position and posture is eliminated; the four-step palpation is step-by-step practical operation and instant error correction, which conforms to the clinical standard; the data of the fetal position adjustment, palpation and auscultation are quantified and weighted, the operation ability is scientifically evaluated, and the pain points of the lack of standardization and the unscientific evaluation in the traditional training are solved; the advanced training constructs a dynamic fetal position model based on the clinical labor data, simulates the progressive change of the fetal position in the labor, fills in the blank of the dynamic scene, adjusts the position and posture without pre-warning, disposes the error in stages, strengthens the dynamic judgment and emergency ability of the trainee, trains in different difficulty gradients, generates a node evaluation report, and realizes the ability advancement from the basic standardization to the clinical practice.

1. Name of the product in this design: Stethoscope. 2. Purpose of this design: For doctors to listen to patients' auscultation. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model.

The invention relates to a method for diagnosing deformation of a casing of an axial flow fan. The method comprises the following steps: (1) acquiring multi-source data; (2) vibration signal processing and spectrum analysis; (3) sound signal feature extraction: carrying out frequency domain analysis on the auscultation signal, extracting sound pressure level and frequency distribution features, judging a through-flow non-uniform region in combination with a vibration spectrum, and positioning a high-risk position of case deformation; (4) detecting the structure state of the casing; and (5) comprehensive diagnosis and fault positioning: if the following conditions are met at the same time, determining that the casing is deformed. The method has the advantages that (1) multi-dimensional fusion diagnosis: vibration, acoustics and structure detection data are combined, and the diagnosis accuracy is improved; and (2) quantitative analysis: realizing deformation degree grading and the like through quantitative indexes such as a frequency spectrum proportion and gap deviation.