219 results about "Diagnostic algorithms" patented technology

The invention relates to the technical field of motor fault diagnosis, in particular to a motor fault diagnosis algorithm based on multi-sensor fusion, and the algorithm comprises the steps: injecting a step excitation signal into a motor, synchronously collecting the original response waveforms of vibration and current sensors, and calculating the inherent response delay. Establishing a mapping relation library of delay values and current sensor filtering parameters, calling the delay values in real time according to the filtering parameters, performing reverse time offset compensation on a current harmonic signal time sequence, performing time alignment on the two types of data, finally performing cross-domain coupling analysis on the aligned data, extracting vibration pulse peak frequency and current harmonic fluctuation quantity, and determining the vibration pulse peak frequency and the current harmonic fluctuation quantity. Early faults are judged by combining the bearing outer ring fault characteristic frequency band and the load rate dynamic threshold value, graded alarm is generated by tracking characteristics, the problem of fault false judgment and missed judgment caused by sensor data space-time dislocation is solved, and the early fault diagnosis accuracy of the motor is improved.

The invention belongs to the technical field of power monitoring, and discloses a detection method for monitoring the state of a primary and secondary fusion circuit breaker, which comprises the following steps: acquiring state data of the circuit breaker, including electromagnetic waveform data, harmonic response characteristics and temperature distribution gradient; obtaining circuit breaker electric field distribution fingerprints through nonlinear segmented harmonic analysis, constructing a multi-dimensional permeation characteristic matrix, and establishing a micro-scale electrothermal coupling map; performing impedance distortion analysis to obtain a nonlinear region situation table, performing multi-frequency response analysis to obtain a harmonic penetration curve, and constructing a high-frequency harmonic penetration path spectrum; a micro-region diagnosis algorithm is established, nonlinear impedance calibration is carried out, and a multi-level protection instruction sequence is generated; adjusting the operation state of the circuit breaker to obtain a circuit breaker medium steady-state index, and performing risk analysis to obtain a harmonic penetration early warning report; according to the invention, accurate identification and early warning of the abnormal-state area in the circuit breaker are realized, and the safe and stable operation capability of the primary and secondary fusion circuit breaker is improved.

The invention provides a rolling bearing fault diagnosis algorithm based on an improved VMD optimized CNN-GRU neural network. The rolling bearing fault diagnosis algorithm aims at solving the problem that early faults of a rolling bearing are difficult to recognize under complex working conditions. The method comprises the steps of providing an OCSSA algorithm fusing an eagle algorithm and a Cauchy variation strategy, realizing adaptive optimization of VMD parameters, remarkably relieving modal aliasing, and improving signal decomposition precision; according to the method, the CNN-GRU end-to-end deep diagnosis framework is constructed, time-frequency fusion features are automatically extracted, time sequence dependence is modeled, and dependence on artificial features is reduced; the model performance is verified on a CWRU bearing data set, the average recognition accuracy rate reaches 98.67%, compared with a mainstream model, the precision and operation efficiency are obviously improved, and the good generalization ability and engineering application potential are achieved.

The invention discloses a marine low-pressure carbon dioxide tank pressure control method and system, and relates to the technical field of storage tank pressure control, and the method comprises the steps: obtaining real-time pressure data in a low-pressure carbon dioxide tank, and extracting pressure feature data; analyzing the pressure characteristic data by using a pressure diagnosis algorithm, and identifying key factors influencing the pressure stability in the low-pressure carbon dioxide tank; based on the key factors, a pressure regulation and control model is established, pressure parameters of the low-pressure carbon dioxide tank are adjusted in real time, and a control strategy is optimized. According to the method, key factors are analyzed by using a pressure diagnosis algorithm, so that accurate pressure regulation is realized, the stability of the internal pressure of the storage tank is improved by establishing an optimization model and adjusting pressure parameters in real time, the risk of carbon dioxide state change caused by pressure fluctuation is reduced, and the operation safety of a ship is ensured.

The invention belongs to the technical field of battery health detection, and particularly relates to a remote diagnosis and maintenance guiding system for a vehicle battery pack box. The remote diagnosis and maintenance guidance system comprises a data acquisition edge processing module, a multi-mode communication and cache transmission module, a composite fault diagnosis module, a sensor self-calibration and environment compensation module, a cloud big data analysis and model iteration module, a remote maintenance guidance and AR visualization module and a system monitoring module. According to the invention, through multi-mode communication and edge caching, data is ensured not to be lost in an extreme environment; a composite fault is identified through a fusion diagnosis algorithm, and maintenance direction deviation is avoided; according to the invention, a sensor self-calibration and compensation mechanism is provided, false alarms caused by low temperature / high humidity are inhibited, and the accuracy of battery data monitoring is improved.

The invention discloses an automatic diagnosis algorithm for interpretability-oriented adaptive multi-agent cooperation. The method comprises the following steps: firstly, constructing a bidirectional probability network of symptoms and diseases based on a data set, calculating a disease weight through a pre-diagnosis module, and deciding to enter a Doctor Agent module or a Med-Team Agent module; the Doctor Agent simulates single expert diagnosis and judges whether a patient can be diagnosed or not or continues to inquire related symptoms to assist diagnosis in combination with a medical knowledge base and a bidirectional probability network. The Med-Team Agent is used for simulating consultation of multiple experts, and comprises a Manager Agent and a plurality of Disease Agents which respectively represent an attending physician and a plurality of disease experts. And the Manager Agent dynamically manages a plurality of Disease Agents, selects an appropriate expert to generate related symptoms according to the symptom information of the patient, and finally completes diagnosis. The method is suitable for medical automatic diagnosis tasks, through combination of multi-agent cooperation and bidirectional probability network prompting, the interpretability of diagnosis is improved, and efficient inquiry and accurate diagnosis are achieved.

The invention discloses a transformer substation primary equipment maintenance auxiliary system based on augmented reality, which dynamically associates an equipment three-dimensional model, maintenance regulations and historical maintenance records, and comprises the following steps: firstly, aligning the three-dimensional model of transformer substation primary equipment with physical equipment in real time in a field of view of an AR (Augmented Reality) terminal; the internal structure of the equipment and a highlighted fault area are displayed in a perspective manner, a maintainer can directly see the interior of the equipment and visually check fault points, blind disassembly is avoided, then accurate analysis and fault positioning of the equipment state are realized in combination with a preset intelligent diagnosis algorithm, the abnormal mode of the equipment is quickly identified, the dependence on artificial experience is reduced, the maintenance efficiency is improved, and the maintenance cost is reduced. And finally, according to a specific equipment maintenance type, matching a standardized maintenance regulation, and dynamically superposing maintenance guidance information of corresponding equipment in a view field of the AR terminal, thereby avoiding artificial missing of key steps, improving specific implementation of maintenance work, practically performing the maintenance work according to a standardized operation process, improving maintenance quality, and ensuring comprehensive maintenance.

The invention provides an aviation hydraulic plunger pump fault mode injection simulation hydraulic system and method, and belongs to the field of aerospace. An oil inlet of the aviation hydraulic plunger pump is connected with a fault injector to achieve simulation of various fault modes, and through cooperation of a two-position three-way reversing valve, a related speed regulating valve, an overflow valve, a three-position four-way proportional servo valve and other components, various load conditions and different onboard working conditions can be simulated. In the simulation load branch, a throttling type load, an overflow type load and a throttling-overflow type load can be simulated by adjusting a third proportional speed regulating valve, a second proportional overflow valve and a fourth proportional speed regulating valve; in the reproduction branch of the aircraft wing actuation working condition, an actuation cylinder can be driven by a three-position four-way proportional servo valve to overcome a damping-spring-guide rail load simulation unit, the real working state during wing actuation can be reproduced, and fault reproduction and accurate recognition of an aviation hydraulic plunger pump can be achieved. And the reliability and health state prediction capability of an aviation hydraulic plunger pump fault diagnosis algorithm are improved.

The invention provides a power dispatching data asset full life cycle management method and system. The method comprises the following steps: firstly, collecting power grid real-time operation basic data, calculating a power grid risk grade by means of a power grid risk assessment model, formulating a matching collection strategy according to the grade, and collecting to obtain initial data assets; recognizing and processing abnormal data through a collaborative quality diagnosis algorithm in combination with the real-time state of the power grid, and screening effective data assets; and inputting into a power dispatching decision algorithm, and fusing risks and constraints to generate a power dispatching scheme. And then comprehensively evaluating the scheme by using the data asset utility index, analyzing and determining contribution data assets with remarkable scheduling contribution, and finally dynamically adjusting acquisition and decision algorithm parameters according to an evaluation result and the contribution data assets. According to the invention, full-process collaborative management and control of power dispatching data assets are realized, and the data utilization rate and the scientificity and reliability of dispatching decision are improved.

The invention discloses a hydropower station on-duty emergency processing method, system, equipment and medium based on a knowledge graph, and belongs to the technical field of hydropower station emergency processing, and the method comprises the steps: collecting the operation parameter data and historical fault information of a hydropower station, and carrying out the digital processing; based on a natural language processing and artificial intelligence training technology, constructing a knowledge graph including fault types, cause analysis and emergency disposal measures; establishing an intelligent fault diagnosis algorithm based on a knowledge graph, and carrying out fault identification and positioning on the operation data of the hydropower station; performing classification and priority ranking on the faults according to the identified fault result, and matching a corresponding processing flow; and according to the fault classification information, an emergency plan is started, a control instruction is executed to complete emergency processing operation, and recording is carried out. According to the invention, real-time sensing of the operation state of the hydropower station, accurate fault identification and priority classification are realized, and the response speed and processing accuracy of the hydropower station to emergencies are effectively improved.

The present invention discloses a method for analyzing power equipment faults based on multi-source data fusion, the method comprising: data collection and storage; data processing; fault diagnosis; integrating multi-source data fusion with a deep learning fault diagnosis algorithm, and optimizing the execution efficiency of the algorithm. The present invention uses multi-source data fusion and deep learning to monitor and warn of power equipment status and faults in real time, and provides corresponding maintenance suggestions and measures according to the type and degree of the fault. It can be applied to the operation and maintenance of power systems, as well as other intelligent management systems that require power equipment information. Its high efficiency and intelligence can greatly improve the operating efficiency and safety of power equipment, and reduce maintenance costs and risks.

The invention relates to an end-edge-cloud full-link intelligent fault diagnosis platform based on a virtual rack, and the platform comprises a virtual rack system which is used for carrying out the dynamic modeling and fault type modeling of a tested system or part, and simulating the response characteristics of the tested system or part under a set boundary condition and a fault state, converting the response characteristic into an electrical signal; the edge calculation system is used for carrying out preprocessing and feature extraction on the collected electric signals; a user of the cloud intelligent fault early warning system carries out fault diagnosis, reliability analysis or residual life estimation according to the features extracted by the edge computing system. According to the platform, an end-edge-cloud full-link technology is verified based on a virtual rack model, so that the experiment cost can be remarkably reduced, and the early-stage test and deployment efficiency of a diagnosis algorithm can be improved; a modularized structure is adopted, algorithms and models in the modules can be modified and replaced according to actual needs, communication modes among the modules can be configured according to needs, and the system has good expandability and adaptability.

The invention provides a robot fault data generation method and system based on sample simulation transfer learning, and the method comprises the steps: evaluating the similarity between experiment action curves of two robots through KL divergence based on source domain data and target domain data, selecting a next action most likely to enable the motion response curves of the two robots to be similar for each current pose; a system transformation network is constructed and trained, fault sample currents obtained by an experimental robot are all converted into fault samples of a target robot based on the trained system transformation network, and a virtual fault data set of a target domain is generated to train a fault diagnosis algorithm. Aiming at the difficulty that a fault sample cannot be prepared for a deployed normal fault-free robot in the field of industrial robots, sample data can be obtained for a robot which is in service but has no fault sample by utilizing abundant healthy samples, so that any fault diagnosis algorithm is supported.

The invention discloses a state monitoring method for a two-way liquid cooling energy storage system, and belongs to the field of energy storage system monitoring. According to the method, the problem that the system state is difficult to accurately monitor in real time in the prior art is solved, the detailed operation state of the system can be mastered in real time through comprehensive data acquisition, the data quality is improved through filtering, denoising and normalization operation in the data processing link, a foundation can be laid for subsequent accurate evaluation, and the system reliability is improved. Potential faults can be found in time through state evaluation and abnormal early warning links, fault positions and reasons are accurately positioned in combination with a fault diagnosis algorithm, the maintenance time is effectively shortened, fault risks are reduced, system operation parameters are automatically adjusted according to evaluation and diagnosis results in an operation optimization link, and the system reliability is improved. And the cooling liquid flow, the temperature and the battery charging and discharging strategy are optimized, so that efficient and safe operation of the two-way liquid cooling energy storage system is guaranteed.

The subject matter of the present invention includes a fully automatic, early detection fire suppression method. The fire suppression method implements MEMS technology combined with artificial intelligence (AI) and machine learning (ML). The fire suppression method includes real-time monitoring, fire detection sensors, and diagnostics algorithms. A uniquely integrated application of technologies provides for distinguishing between safe and dangerously destructive fire events and the instantaneous extinguishing of a dangerous fire at its inception.

A system and method for distinguishing the type of seizures in a human patient, such as an epileptic seizure (ES), or a functional or dissociative seizure (FDS). The system and method use a diagnostic analytical platform that gets heart rate variability (HRV) analytical metrics from a ECG and uses an analytical diagnostic algorithm to determine if an ES or FDS has occurred in the patient. The diagnostic analytical platform can create a model for distinguishing that a predetermined type of seizure has occurred from the HRV analytical metrics.

The invention discloses a power equipment maintenance operation virtual simulation system and training method, and the system comprises a virtual simulation platform which is used for loading a power equipment virtual environment and a maintenance task; the data acquisition module is used for acquiring operation data in real time; the intelligent fault diagnosis module is used for dynamically generating a fault scene according to the operation data and optimizing a fault simulation and diagnosis algorithm through machine learning; the feedback module is used for providing operation feedback for students in real time according to the operation data; the data analysis platform is used for analyzing the operation data and generating a personalized training scheme; the training cost is greatly reduced, and the risk of equipment damage caused by misoperation is reduced. Meanwhile, the repeatability of the virtual environment enables the trainee to practice repeatedly until the trainee masters various skills skillfully, thereby remarkably improving the training efficiency and quality.

The invention discloses a circuit breaker fault diagnosis method based on global-local feature extraction. Comprising the following steps: 1, collecting vibration signals of a circuit breaker in a normal working condition and a fault state as original data; 2, extracting original time domains and frequency domains of the vibration signals of the circuit breaker operating mechanism in different states and time-frequency characteristics of a generalized S transformation matrix, and regarding the original time domains and frequency domains as global characteristics; 3, extracting local features of the vibration signals by using a texture feature extraction mode of matching a local binary pattern with a gray-level co-occurrence matrix; 4, further screening the features by using maximum correlation and minimum redundancy to obtain a feature set; and 5, in combination with a kernel extreme learning machine classifier and GL-mRMR feature extraction, obtaining a GL-mRMR-KELM model applied to circuit breaker vibration data classification. The method is used for fault diagnosis of a high-voltage circuit breaker, and solves the technical problems of low universality and poor accuracy under small samples in a current operating mechanism state diagnosis algorithm.

The invention discloses a few-sample epidemic disease image diagnosis algorithm based on comparative learning and a DS evidence theory. The algorithm comprises the following steps: S1, data set preparation: collecting chicken images of normal chickens without epidemic disease tags as a pre-training data set; collecting an epidemic disease image of an abnormal chicken with an epidemic disease tag as a training data set; epidemic disease labels corresponding to the epidemic disease images are label sets; s2, pre-training: performing comparative learning through a query encoder and a momentum encoder based on a MoCoV2 comparative learning framework to obtain a trained query encoder; s3, training: constructing a classification model, carrying out refined training through the training data set, and carrying out supervised learning through the label set to obtain a trained classification model; s4, diagnosis result fusion: inputting a plurality of to-be-diagnosed images into the trained classification model to obtain probability distribution of epidemic disease categories corresponding to the to-be-diagnosed images; and based on the DS evidence theory and the probability distribution, obtaining the prediction probability of the epidemic disease category of the to-be-diagnosed chicken.

The invention discloses a fault positioning method, device and system for an information communication system. According to the method, firstly, operation data of an information communication system are collected, and on the basis, various algorithms in a fault diagnosis algorithm library are applied to analyze the data, so that system faults are accurately diagnosed. The fault diagnosis algorithms are obtained through continuous learning and optimization of a self-learning module, and can adapt to system changes and improve diagnosis accuracy. According to a diagnosis result, the system accurately matches a fault position, and effective positioning of the fault is realized. The fault positioning method not only improves the diagnosis efficiency and quality, but also ensures the high reliability and stability of the information communication system, greatly optimizes the operation and maintenance process of the system, ensures the continuity and safety of the communication service, and greatly improves the reliability and reliability of the information communication system through the implementation of the method. The method is of great significance in guaranteeing healthy operation of an information communication system and improving service quality.

The invention discloses a historical building repairing method and system based on multi-source data fusion and AI diagnosis, and belongs to the technical field of historic building repairing. According to the method, the multi-source data of the historical building are integrated, the digital twinborn model of the historical building is constructed, defect identification and state evaluation are performed on the digital twinborn model based on the AI diagnosis algorithm, the repairing scheme of the historical building is generated, the repairing effect is fed back in real time through the digital twinborn model, the multi-source data cover full dimensions, and the repairing efficiency is improved. The model restores details of building components and can simulate structural deformation under the load effect and material attenuation caused by the environment, real-time data mapping enables the model to synchronously reflect the state of a solid building, defect danger coefficients are calculated through multi-parameter fusion, the types and positions of defects such as structural deformation and material degradation can be automatically recognized for generation of differentiated repairing schemes, and the method has the advantages of being high in practicability and easy to popularize. Hidden defects are prevented from being missed in manual detection, risk quantification is achieved by combining defect danger coefficients with weight distribution, and the generated scheme better fits the actual defect condition of historical buildings.

According to the coal mill health monitoring, fault early warning and fault diagnosis method and device, comprehensive monitoring of the running state of the coal mill and early fault early warning are achieved through combination of multi-parameter real-time monitoring and an intelligent diagnosis algorithm, various parameters such as vibration, temperature and pressure are collected, and the coal mill health monitoring, fault early warning and fault diagnosis method and device are obtained through spectral analysis and rule judgment. Various fault types such as oil system faults, bearing faults and grinding piece faults are accurately recognized, targeted processing suggestions are provided, and the operation reliability and maintenance efficiency of the coal mill are remarkably improved.

The invention provides a safety redundancy control method, system and device for a combined magnetic field six-phase motor and a medium thereof, and the method comprises the following steps: 1, monitoring the operation state of the combined magnetic field six-phase motor in real time in a multi-dimensional manner, and obtaining the real-time operation parameters of the combined magnetic field six-phase motor; according to the invention, through multi-dimensional real-time monitoring of the operation state of the motor and an advanced intelligent diagnosis algorithm, more accurate and faster fault diagnosis is realized, and the reliability and safety of the motor are greatly improved; the redundancy strategy is dynamically selected according to the fault condition and the motor operation state, so that the fault-tolerant capability is improved, and the influence of the fault on the motor performance is reduced; through the adaptive optimization control strategy, it is ensured that the motor always keeps the optimal output performance and safety under the fault condition, the usability and adaptability of the motor are improved, the system can continuously improve the performance of the system and adapt to different working environments and fault conditions, and stronger vitality and competitiveness are achieved.

The present invention discloses a system for predicting a health condition using a single-lead electrocardiogram device, the system including: a single-lead electrocardiogram measurement unit (110) provided with two electrodes, and configured to obtain asynchronous electrocardiogram data by measuring electrocardiograms for at least two electrical axes at different times; and a prediction unit (120) configured to predict the presence / absence of a disease and the degree of the disease from the asynchronous electrocardiogram data input from the single-lead electrocardiogram measurement unit (110) through a diagnostic algorithm (121) previously constructed by being trained on a plurality of standard electrocardiogram datasets in which standard lead electrocardiograms measured for the same electrical axes are matched to the presence / absence of diseases and degrees of the diseases corresponding to the standard lead electrocardiograms.

The invention discloses an intelligent diagnosis report generation system for an electrochemical energy storage lithium iron phosphate battery, and relates to the technical field of battery management, and the system comprises a traditional integrated hardware platform which is used for collecting real-time operation data monitored by a sensor; the intelligent diagnosis algorithm module is used for scoring the consistency, reliability and safety of the system, and performing integration in a weighted average mode according to the consistency, reliability and safety scores to obtain a comprehensive health score of the system; and the diagnosis report generation module is used for obtaining a system health comprehensive score by summarizing the scores of the ten key indexes, and presenting an index diagnosis level according to the system health comprehensive score. According to the method, the problems of inaccurate battery health assessment, low efficiency of fault diagnosis and inaccurate safety state assessment are solved, and the operation performance and safety of the energy storage system are enhanced while the user experience is improved through display in the form of a diagnosis report.

The invention belongs to the technical field of wind power blade lightning protection, and discloses a lightning protection system fault diagnosis method, which is characterized in that a data sound card collector is arranged at the root of a blade and is used for collecting sound signals in a blade cavity, converting the collected sound signals into digital signals, and sending the digital signals to a server; the fault monitoring, fault early warning and diagnosis module monitors the lightning protection system in real time by using the digital signal through a deep learning fault diagnosis algorithm; meanwhile, a current loop is arranged at the blade root and used for collecting lightning current, the state of a down lead of the lightning protection system in the service period of the blade is judged by assisting a fault monitoring, early warning and diagnosis module by comparing the lightning current with existing actual lightning current data, and finally the real-time state of the lightning protection system is responded to through an upper computer. The fault monitoring, early warning and diagnosis system can monitor the state of the lightning protection system in the service period in real time, can repair or replace the down lead fractured due to mechanical stress generated by deformation in time, improves the reliability of the lightning protection system, and reduces the risk of lightning protection failure.

The invention relates to the technical field of train safety monitoring, and discloses a multifunctional train safety monitoring system based on a fiber bragg grating, comprising a sensing module used for adopting a fiber bragg grating sensor technology; the integration module is used for quickly integrating and summarizing multi-source heterogeneous data from a plurality of sensors; the intelligent preprocessing module is used for carrying out primary processing on the collected original data by applying an algorithm; the deep analysis module is used for data analysis and a machine learning technology; the accurate diagnosis module is used for combining a fault diagnosis algorithm and a knowledge base; and the real-time early warning module is used for early warning according to the diagnosis result. The sensing module is reasonably arranged at key parts of a train by means of the fiber grating sensor technology, physical parameters are accurately collected, the reliability of a data source is guaranteed, the integrated module receives, converts and integrates multi-source heterogeneous data, the data are managed orderly, the integrated module and the integrated module cooperate with each other, the data quality is improved, management and calling are more efficient, and stable operation of the monitoring system is facilitated.

A method and system for diagnosing an idiopathic psychosis patient and improving treatment targeting for that patient. Cognitive performance is measured on the patient. Pro- and anti-saccade signals are measured on the patient. Motor inhibition is measured on the patient. EEG signals are measured on the patient. Principal components analysis is applied to the measured signals and scales to determine the most significant features. The patient is evaluating on at least 11 dimensions of neuro-cognitive performance. A trained numerical taxonomy approach is used to classify the patient as belonging to a B-SNP psychosis Biotype and the patient's condition is categorized based on the classified Biotype. The B-SNIP psychosis Biotype is used to implement targeted treatment for an individual patient. The diagnostic algorithm is continuously re-trained using new cases and new laboratory tests to improve precision of B-SNIP psychosis Biotypes diagnosis and the accuracy of selecting treatments for individual patients.

The invention relates to the field of electric reactor fault diagnosis, in particular to an electric reactor mechanical fault diagnosis method based on parameter adaptive optimization, which comprises the following steps: preprocessing vibration signals generated when an electric reactor has a mechanical fault through a wavelet threshold denoising method, extracting vibration signal characteristics through Fourier transform and wavelet packet transform, and calculating the mechanical fault of the electric reactor according to the vibration signal characteristics; according to the method, the high-voltage electric reactor is subjected to fault diagnosis, screening is carried out through a random forest method, fault diagnosis is mainly carried out through a convolutional neural network-Transform hybrid model (CNN-Transform), and accurate diagnosis of the fault of the high-voltage electric reactor is realized by utilizing the local and structured feature extraction capability of the CNN model and the global context and long-distance dependency relationship establishment capability of the Transform model. And an improved dung beetle optimization algorithm (MDBO) is introduced, internal parameters of the hybrid model are dynamically adjusted, parameter adaptive optimization is realized, and the diagnosis accuracy is improved.

The invention relates to the technical field of induced draft fan bearing seats, and discloses an induced draft fan high-temperature-resistant bearing seat structure and thermal state monitoring algorithm integrated system which comprises a bearing seat body. Four corner areas of the bearing seat body are respectively provided with a fixing hole used for being fixed with a base, and the center of the bearing seat body is provided with a circular bearing mounting hole; according to the induced draft fan high-temperature-resistant bearing seat structure and thermal state monitoring algorithm integrated system, the annular liquid storage cavity structure provides an optimal measurement point for the temperature sensor while actively dissipating heat, high unification of the heat dissipation efficiency and accurate monitoring is achieved, and secondly, through time sequence correlation analysis of temperature and vibration signals, a multi-parameter fusion diagnosis algorithm is used for diagnosing the heat dissipation efficiency of the bearing seat structure and the thermal state monitoring algorithm. In addition, localization processing is combined with the self-adaptive learning function, the anti-interference performance and long-term stability of the system are enhanced, and meanwhile the maintenance process is simplified through remote parameter configuration.