183 results about "Incremental learning algorithm" patented technology

This invention presents a multisensor-connected, AI-enabled telehealth system for assisting healthcare providers with differential diagnosis and patients with early health concern detection. The system comprises a multi-sensor medical device with at least seven sensors, a secure cloud-based platform, and an interactive telehealth module. The device preprocesses and securely transmits patient information to the cloud platform, where an ensemble of deep learning models analyzes the data to generate ranked potential diagnoses with likelihood scores. The telehealth module facilitates communication between providers, patients, and the cloud platform, presenting visualizations and receiving feedback. The system continuously updates and fine-tunes its models using incremental learning algorithms, adapting to new data while retaining previous knowledge. It also generates alerts for providers and patients when deviations from normal physiological patterns are detected, accompanied by explainable AI visualizations.

The invention relates to the technical field of devices for adjusting, controlling or stabilizing power or frequency in a power grid, in particular to a rapid frequency modulation method for a wind turbine generator based on disturbance adaptive compensation, which comprises the following steps of: constructing a dynamic disturbance sensing data set by collecting frequency deviation, a frequency deviation change rate and fan state parameters; a window length and a weight coefficient of a short-time window sliding mean algorithm are dynamically optimized by adopting a genetic algorithm, background noise interference of a power grid is suppressed, and high-precision disturbance characteristics are extracted. And reducing frequency interference of inertia identification by using a reverse test signal. And updating boundary layer parameters of the sliding mode control model through an online incremental learning algorithm, dynamically adjusting the output priority based on the disturbance energy entropy, and eliminating power conflicts. A multi-island genetic algorithm is introduced to optimize a mode switching threshold value, and frequency modulation safe exit is realized in combination with adaptive power ramp rate limitation. According to the method, the frequency response speed and the multi-source cooperation efficiency in the dynamic multi-disturbance and inertia time-varying scene are remarkably improved, and the frequency secondary drop risk is reduced.

The invention discloses an intelligent power grid optimal scheduling method and system based on multivariate energy storage cooperative scheduling, and relates to the technical field of power grid optimal scheduling, and the method comprises the following steps: building a prediction model based on first data, generating prediction data, coupling energy storage characteristic parameters of different types of energy storage equipment with the prediction data, and obtaining a prediction model; establishing a multi-energy collaborative scheduling model; dynamically screening the energy storage scheduling strategy set based on a preset real-time performance evaluation index to generate an optimal strategy subset; according to the optimal strategy subset, performing differentiated charging and discharging control instructions on the energy storage equipment cluster; and collecting second data in the charge and discharge control process, calculating a deviation value between the second data and the prediction data, converting the deviation value into a feature vector, inputting the feature vector into a preset incremental learning algorithm, and optimizing parameters of the multi-energy collaborative scheduling model. Layered screening is implemented in combination with real-time performance evaluation indexes, and it is ensured that the optimal scheduling scheme can be rapidly selected in different time periods and under the uncertain disturbance condition.

The invention provides a tunnel safety-oriented safety step pitch monitoring method and system, and the method comprises the steps: deploying an edge calculation module at a sensor node, carrying out the preprocessing and compression of collected monitoring data, reducing the data transmission amount through data dimension reduction and feature extraction, relieving the data transmission pressure, and improving the data transmission efficiency and real-time performance. An incremental learning algorithm is adopted to carry out online analysis on monitoring data, an anomaly detection model is dynamically updated according to a newly collected data sample, an early warning threshold value is adaptively adjusted, the accuracy and the real-time performance of anomaly recognition are improved, and misinformation and missing report are reduced; a multi-sensor data fusion technology is comprehensively applied, correlation analysis is carried out on sensor data of different types and different positions, the reliability and accuracy of monitoring data are improved through data redundancy and complementation, and comprehensive evaluation of the tunnel construction safety state is achieved.

The invention provides an asset data collection method based on the Internet of Things, and the method comprises the steps: constructing a directed acyclic graph model based on task decomposition and dependency for each node group, determining a task execution sequence and a data transmission mode between the nodes through employing a critical path analysis algorithm, and obtaining a task-oriented node cooperation process; for the data fusion result, dynamically updating a data model and a decision rule of the node by adopting an incremental learning algorithm, and timely discovering abnormal deviation of node data by adopting an anomaly detection algorithm to trigger dynamic adjustment of node marshalling; and constructing a node cooperation incentive mechanism based on the block chain, dynamically adjusting credit values and resource allocation of the nodes according to contribution degrees and task completion quality of the nodes, and constraining and arbitrating cooperation behaviors among the nodes by adopting an intelligent contract technology.

The invention provides an agricultural product processing quality traceability monitoring method and system based on edge nodes, and the method comprises the steps: constructing an analytic hierarchy process model through employing the multi-source data of time-space alignment, decomposing an agricultural product processing quality evaluation index into a plurality of sub-indexes, forming an index hierarchical structure, and employing a fuzzy comprehensive evaluation method to obtain a traceability result of the agricultural product processing quality. The importance weight and the satisfaction degree of each sub-index are comprehensively considered, the comprehensive score of each scheme is calculated, and the processing quality of the agricultural products is judged; after the quality problem is processed, key control points and influence factors in the agricultural product processing process are analyzed through data mining, a quality evaluation model and a rule base are dynamically updated by adopting an incremental learning algorithm, and continuous optimization of the model is realized by continuously receiving new data samples and updating model parameters; and the accuracy of agricultural product processing quality evaluation is continuously improved.

The invention relates to the technical field of precise injection molding control, and discloses an injection molding process parameter self-adaptive compensation system which comprises a multi-source sensing module used for collecting mold cavity pressure, melt temperature and screw displacement information in the injection molding process in real time; the data fusion module is used for performing time sequence synchronization, space registration and noise suppression on the multi-source sensing data; the dynamic modeling module is used for constructing a dynamic model of an injection molding process state based on the fused process data and outputting a state estimation value; and the stability analysis module is used for carrying out system stability analysis based on the dynamic model and generating a control compensation strategy. Cooperative control of precise positioning and high-pressure response is realized through a composite driving framework and a dynamic disturbance compensation technology; an incremental learning algorithm and a multi-dimensional quality evaluation system are combined, a process parameter self-evolution mechanism is constructed, material characteristic drift and complex working condition disturbance are effectively dealt with, and closed-loop optimization from process control to quality feedback is formed.

The invention provides an unstructured data automatic processing method and system based on deep learning, and relates to the technical field of data processing, and the method comprises the steps: obtaining unstructured data through an intelligent data collector, building a data feature fingerprint database, constructing a data quality evaluation model through an incremental learning algorithm, and carrying out the data standardization processing; extracting dominant features and recessive features by using a multi-layer cascade network structure and a self-attention mechanism, and constructing a feature association graph and a bidirectional reasoning channel; and performing rule matching and causal reasoning based on the domain knowledge base, and finally realizing automatic structuring of the unstructured data. According to the method, the automation degree and the accuracy of data processing are improved, the manual intervention cost is reduced, and the method has relatively high universality and expandability.

The invention relates to the technical field of new energy vehicle-mounted data processing, and discloses a new energy vehicle vehicle-mounted data processing method and system based on intelligent networking, and the method comprises the steps: collecting and preprocessing data through a multi-source sensor, carrying out the slicing fusion of the data based on time-space correlation, and extracting features through a lightweight convolutional neural network. Constructing an inter-vehicle communication topology model to realize collaborative feature learning, adopting a federal learning framework to train the model and protect privacy, applying a reinforcement learning algorithm to make a decision, establishing a multi-objective optimization model, deploying a dynamic priority scheduling module to manage resources, and optimizing the model based on an incremental learning algorithm. The system covers a plurality of modules such as data acquisition and preprocessing, data dynamic slicing and fusion and the like. According to the method, the data processing efficiency and accuracy are improved, intelligent decision and multi-objective optimization are realized, data privacy is guaranteed, computing resources are reasonably distributed, and the overall performance of the new energy automobile in an intelligent network connection environment is improved.

The invention provides an automatic adjustment method for gold bonding wire production parameters, and relates to the technical field of information, and the method comprises the steps: collecting a new smelting parameter data sample in real time, inputting the data sample into a parameter self-inspection neural network model, obtaining a predicted quality index value, comparing the predicted value with an actually measured quality index, and determining the production parameters of the gold bonding wire. Calculating a prediction error; and an incremental learning algorithm is adopted, online updating and fine tuning are performed on the parameter self-checking neural network model by using the newly collected data sample, and the connection weight of the parameter self-checking neural network model is adjusted according to the prediction error. Real-time self-inspection of parameters in the smelting process and dynamic prediction of quality indexes are achieved, abnormity can be found in time, production parameters can be optimized, and the quality stability and production efficiency of smelted products are effectively improved. Meanwhile, a self-adaptive optimization mechanism of the model ensures continuous improvement of prediction precision, and powerful support is provided for intelligent control of the smelting process.

The invention relates to the technical field of robot control, in particular to an energy consumption optimization and automatic charging control system for an intelligent pet robot. The system comprises a robot data acquisition module, an energy consumption state evaluation module, an energy efficiency optimization module, an automatic charging scheduling module and a battery health management module which are in communication connection in sequence. The system is driven by multi-dimensional sensing data, energy consumption characteristics are extracted in combination with potential energy field mapping and sparse modeling, and an energy consumption influence map is constructed; joint optimization of the path and the servo strategy is realized by using a quantum behavior particle swarm algorithm; scheduling a charging path through a graph attention network; and the battery health state is dynamically predicted based on an incremental learning algorithm, and the operation efficiency, the cruising ability and the system intelligence of the robot are improved. According to the method, a closed-loop control process is constructed from energy consumption evaluation to energy efficiency optimization, automatic charging and battery health management, good system integration and intelligent response capability are achieved, and the cruising ability and operation stability of the pet robot in a complex application scene are remarkably improved.

The invention provides a financial analysis method and system based on big data, and the method comprises the steps: analyzing the dependency relationship between a non-standard code combination and a fuzzy text mode in a material purchasing scene based on a credible rule library, extracting a new attribute combination feature, and forming an optimization rule feature set if the new attribute combination feature can improve the matching accuracy; performing rule-based key field and attribute set verification matching on the real-time non-standard transaction data according to the optimization rule feature set in combination with a dependency relationship between a non-standard code combination and a fuzzy text mode, and outputting a matched transaction record set; and comparing the difference between the matched transaction record set and the historical manual matching record, extracting and judging whether the newly added non-standard attribute combination is applicable to the non-standard transaction data which is not covered or not after a matching rule is adjusted by adopting an incremental learning algorithm, and if so, forming a dynamic matching table.

The invention provides a classical music cross-modal high-reliability experimental data set construction method for full-scene teaching application, and the method comprises the steps: constructing an original data set through collecting audio, video, music score and other multi-modal data, carrying out the standardization of each modal data through a preprocessing technology, and obtaining a multi-modal data set in a unified format; according to the semantic feature vectors, a knowledge graph is constructed, nodes represent semantic relations between music elements, edges represent semantic relations between the elements, a graph convolutional network is adopted to encode the knowledge graph, and semantic representation of the teaching content is obtained; a virtual reality rendering technology is adopted, multi-modal teaching resources are integrated into an immersive teaching scene, a content sequence is presented in real time, and dynamic teaching experience is obtained; and continuously collecting interaction data of the learner, updating the knowledge graph and the semantic feature vector, and optimizing the cross-modal fusion model by adopting an incremental learning algorithm to obtain a self-adaptive teaching data set.

The invention discloses a water conservancy knowledge graph intelligent question-answering system and method based on a large language model, and relates to the technical field of water conservancy information, and the method comprises the following steps: carrying out the fusion processing of multi-source water conservancy data in advance, constructing a triple knowledge graph containing a water conservancy field entity type and a relation system, and dynamic updating of the knowledge graph is realized through an incremental learning algorithm. According to the method, the defects of a traditional method in semantic understanding are effectively overcome, deep semantic association of professional query can be accurately captured, and answer deviation caused by keyword matching limitation is avoided. Meanwhile, a dynamic updating mechanism of the knowledge graph can integrate new knowledge such as new projects and industry standard updating in real time through an incremental learning algorithm and a time decay function, obsolete out-of-time information synchronously, ensure that a knowledge system of the system is synchronous with development of the water conservancy industry, and solve the problems that a traditional system is high in updating cost and long in period.

A self-adaptive dynamic stratum recognition method based on multi-source drilling parameters comprises the steps that firstly, the drilling rate, the rotating speed and oil pressure parameters are collected through a sensor set, a drilling depth-time curve is constructed, time sequence data are segmented through a sliding window, and filtering, standardization and abnormal value processing are carried out; calculating a mean value, a standard deviation and skewness statistical characteristic of each parameter in the window, and constructing a nine-dimensional characteristic vector in combination with an energy ratio and a covariant coefficient; updating a stratum feature library based on an incremental learning algorithm, and dynamically optimizing a clustering center to realize autonomous evolution; a confidence coefficient threshold value is set according to the statistical characteristics and the clustering distance, and stratum type dual discrimination is completed; by comparing a real-time judgment result with manual sampling data, the generalization of a learning rate parameter optimization model is dynamically adjusted; and outputting a stratum type corresponding to the current drilling depth and a confidence degree evaluation result based on the optimized clustering model. According to the invention, by improving a data processing mechanism and an adaptive decision rule, high-precision and strong-generalization real-time stratum identification is realized.

The invention discloses a method and a system for detecting the health state of a vehicle battery based on multi-source data analysis, and relates to the technical field of big data analysis, and the method comprises the steps: collecting multi-source data and historical capacity attenuation data of the vehicle battery, carrying out the space-time correlation modeling of the multi-source data, generating a space-time correlation matrix, and carrying out the detection of the health state of the vehicle battery based on the space-time correlation matrix. The method comprises the following steps: extracting key features by adopting an attention mechanism, establishing a capacity fading prediction model based on the key features and historical capacity fading data, calculating a health state index of a current vehicle battery, judging whether the change rate of the health state index exceeds a preset fluctuation range or not, and if the change rate exceeds the preset fluctuation range, judging whether the change rate exceeds the preset fluctuation range. And if not, performing real-time processing on the newly collected multi-source data by adopting an incremental learning algorithm and updating model parameters of the capacity attenuation prediction model. And a reliable basis is provided for battery life prediction, fault diagnosis and maintenance decision making.

The invention discloses a lithium battery recession track dynamic prediction system based on deep learning, and the system comprises a data collection module which is used for collecting the related data of a lithium battery; the feature extraction module is used for performing multi-dimensional feature fusion on the related data of the lithium battery, obtaining a fusion feature vector and sending the fusion feature vector to the trajectory prediction module; the trajectory prediction module is used for receiving the fusion feature vector, inputting the fusion feature vector into a prediction model, and performing decline trajectory prediction on the lithium battery through the prediction model; the updating module is used for dynamically updating prediction model parameters by utilizing an incremental learning algorithm; and the visualization module is used for carrying out dynamic mapping based on decline trajectory prediction and lithium battery related parameters, and generating an interactive decline trajectory thermodynamic cloud picture and a residual service life probability distribution curved surface. According to the method, the residual service life probability distribution is output by capturing the nonlinear dynamic change and the long and short term dependency relationship in the lithium battery recession process, and quantitative analysis of prediction uncertainty is realized.

The invention relates to the technical field of construction site safety, and discloses an engineering construction dangerous area intelligent identification method and system based on a generative large model, and the method comprises the steps: obtaining the real-time monitoring data of each area of a construction site and the record of a safety event, and constructing an incidence matrix of the safety event and the monitoring data; for the incidence matrix, obtaining an incidence mode and rule between the security event and the monitoring data, and determining a key monitoring data set influencing the security level; and performing back test verification on the security level and the management and control measures regularly, and performing iterative optimization on setting of the security level by adopting an incremental learning algorithm by comparing and analyzing related data and actual effect data of the management and control measures under the historical security level. According to the invention, intelligentization and automation of construction site safety management are realized, the risk of safety accidents is effectively reduced, and the safety management efficiency and accuracy are improved.

The invention relates to the technical field of numerically-controlled machine tool diagnosis, and discloses a numerically-controlled machine tool fault diagnosis system based on machine learning. The system comprises a multi-source sensing data acquisition module for acquiring multi-dimensional sensing data such as vibration spectrum, spindle current waveform, temperature distribution, servo motor encoder feedback and the like; the operation feature coding module receives the multi-dimensional sensing data, extracts time domain statistical features and frequency domain energy distribution features, and generates a multi-source feature coding result; the incremental learning analysis module dynamically updates the feature weight through an incremental learning algorithm, and constructs an incremental training data set; the genetic optimization module optimizes the network structure and hyper-parameter configuration of the fault diagnosis model according to the incremental training data set, and generates optimized network structure parameters; and the integrated diagnosis decision module receives the current operation state data and the optimized network structure parameters, fuses diagnosis results of a plurality of base classifiers through an integrated learning algorithm, and outputs fault type classification signals.

The invention discloses a construction and updating method of an electric power knowledge graph, a product and a storage medium, and relates to the technical field of electric power system management. The method comprises the following steps: acquiring an original power data set in a power system; preprocessing the original power data set to obtain a target power data set; according to the target power data set, an initial power knowledge graph is constructed, the initial power knowledge graph comprises a basic framework and a graph database, the basic framework is used for representing the architecture of power knowledge contained in the power system, and the graph database is used for storing and querying the power knowledge based on a graph structure; and updating the initial power knowledge graph based on an incremental learning algorithm to obtain a target power knowledge graph. The technical problem that safe and stable operation of a power system is affected due to the fact that an isolated database and a manual analysis method are adopted for power dispatching information management in the prior art is large in error and low in efficiency is solved.

The invention discloses an equipment digital twin model updating method and system, a terminal and a medium. The method comprises the following steps: collecting data of a plurality of positions of equipment; for any data acquisition point on the equipment, the monitoring frequency is dynamically adjusted according to the change sensitivity index of the monitoring data; preprocessing the collected data; according to the processed data, updating a digital twin model of the equipment; when the model is updated, the allocation of computing resources is dynamically adjusted according to the change trend of the data; and updating the part, influenced by the physical entity change, in the model by adopting an incremental learning algorithm. The method has the advantages that the updating efficiency of the equipment digital twin model can be improved, the real-time performance and reliability of a digital twin system are remarkably improved, and powerful support is provided for safe operation, maintenance and management of large equipment.

The invention relates to a thermal power plant fault early warning and diagnosis method based on a nebula system, and the method comprises the steps: collecting the multi-dimensional operation time sequence data of a thermal power plant, carrying out the feature extraction and lexical element processing of the multi-dimensional operation time sequence data through an encoder, and obtaining a unified equipment state lexical element sequence; based on the equipment state lexical element sequence, constructing a dynamic star map representing the operation state of the whole power plant; inputting the dynamic star map into a space-time fusion backbone network; the space-time fusion backbone network performs iterative processing on the dynamic star map and generates a health degree attenuation trajectory; when the slope of the health degree attenuation trajectory exceeds a preset threshold value, dynamic early warning and system diagnosis are triggered, and a natural language diagnosis report containing a causal reasoning chain is generated; new multi-dimensional operation time sequence data are collected in real time, and an incremental learning algorithm is used to update the encoder and the space-time fusion backbone network online; compared with the prior art, the system can continuously adapt to working condition changes and has high self-optimization capacity.

The invention relates to the technical field of injection mold monitoring, and discloses an injection mold cavity state monitoring method, system, equipment and medium, the injection mold cavity state monitoring method comprises the following steps: multiple sensors collect mold state data in real time, and the mold state data are preprocessed and fused to generate a comprehensive data set; training a machine learning model based on historical samples, and updating model parameters in real time through an incremental learning algorithm; analyzing current data by adopting dynamic fuzzy logic reasoning, and outputting a state evaluation result; real-time data and results are uploaded to the cloud for deep analysis and distributed storage; a user feedback mechanism is integrated, and model parameters and a fuzzy inference rule base are optimized. According to the method, model parameters are updated in real time through an incremental learning algorithm, a multi-parameter nonlinear coupling relation is analyzed in combination with dynamic fuzzy logic reasoning, and based on cloud collaboration and a user feedback closed-loop mechanism, self-adaptive monitoring and continuous optimization of the injection mold state are achieved, and the anomaly detection precision and the system robustness are improved.

The invention relates to the technical field of large models, in particular to an urban intelligent collaborative decision-making system and method based on a large model, and the system comprises a multi-source heterogeneous data fusion perception layer, a deep learning cognitive engine, a self-adaptive regulation and control decision-making layer and a system efficiency optimization and safety guarantee system. The method has the advantages that multi-modal data of a traffic camera, a geomagnetic sensor, a vehicle-mounted terminal and the like are integrated, space-time correlation characteristics are extracted by using a multi-layer attention mechanism of a large model, and traffic flow prediction and signal timing optimization linkage regulation and control are realized in combination with an incremental learning algorithm. Compared with the prior art, the platform solves the problems that a traditional method is poor in dynamic adaptability to a complex road network and low in prediction precision, the passing efficiency of the urban road network can be improved by 15%-22%, and the abnormal congestion response time is shortened to be within 3 minutes.

The invention provides a process abnormity early warning method and system in a process industry process, and belongs to the technical field of process abnormity early warning, and the method comprises the steps of data acquisition, modeling, model training, incremental learning, third prediction, difference value calculation, judgment, alarm and the like. The system comprises a data acquisition module, a modeling module, a model training module, an incremental learning module, a third prediction module, a difference value calculation module, a judgment module and an alarm module. According to the method, from the perspective of process related parameters, changes of various factors are adapted through the incremental learning algorithm, that is, new knowledge can be learned based on new data, and accurate prediction of process abnormal phenomena is realized.

The invention discloses a generative image forgery detection method based on attention guidance and incremental learning, and the method comprises the steps: constructing an end-to-end detection model which comprises a multi-modal feature coding module, an A-DTG module, an incremental learning module and a classification module; the A-DTG module generates a domain label by using a self-attention mechanism and a multi-modal attention fusion technology; the incremental learning module is combined with an online incremental learning algorithm, knowledge distillation and a transfer learning technology to realize real-time updating of the model; and optimizing model training through a classification loss function, a distillation loss function and a total loss function. The method effectively solves the problems that in the prior art, the detection capacity of a novel forgery technology is insufficient, multi-modal data processing is weak, and a model cannot be updated in real time, and can remarkably improve the accuracy, generalization and timeliness of image forgery detection in the scenes of news media, judicial evidence obtaining, social media and the like.

The invention provides an intelligent orchard expert knowledge base construction method and system based on machine learning, and the method comprises the following steps: collecting and preprocessing the related data of an orchard, and obtaining an initial knowledge base; constructing a knowledge representation model by adopting an ontology construction method based on the initial knowledge base, and obtaining standardized knowledge representation based on the knowledge representation model; based on the standardized knowledge representation, adopting machine learning reasoning to obtain a knowledge reasoning chain; based on the knowledge reasoning chain, learning a new planting case and expert feedback by adopting an incremental learning algorithm, and automatically updating the initial knowledge base to obtain an expert knowledge base; and based on the expert knowledge base, adopting a machine learning algorithm to obtain an orchard management decision, and completing construction of the intelligent orchard expert knowledge base based on machine learning. The intelligent level of orchard management can be remarkably improved, and powerful support is provided for precise planting.

This invention presents a multisensor-connected, AI-enabled telehealth system for assisting healthcare providers with differential diagnosis and patients with early health concern detection. The system comprises a multi-sensor medical device with at least seven sensors, a secure cloud-based platform, and an interactive telehealth module. The device preprocesses and securely transmits patient information to the cloud platform, where an ensemble of deep learning models analyzes the data to generate ranked potential diagnoses with likelihood scores. The telehealth module facilitates communication between providers, patients, and the cloud platform, presenting visualizations and receiving feedback. The system continuously updates and fine-tunes its models using incremental learning algorithms, adapting to new data while retaining previous knowledge. It also generates alerts for providers and patients when deviations from normal physiological patterns are detected, accompanied by explainable AI visualizations.

The invention discloses a concrete filled steel tube service life prediction method and system based on machine learning. According to the method, sensor data, external environment data, unmanned aerial vehicle images and satellite remote sensing data are collected to serve as original data and real-time monitoring data, fusion, denoising, normalization and missing value filling are conducted on the original data, and a feature matrix is generated. And training the feature matrix by using a machine learning model to obtain an initial life prediction model, and continuously receiving real-time data through an incremental learning algorithm for dynamic updating to obtain a dynamically optimized life prediction model. According to the structure aging characteristics, life prediction is divided into an initial aging stage, a middle-term damage stage and an advanced-age stage, and accurate prediction is carried out by applying customized models. And finally, integrating the prediction result to an intelligent decision support platform, and displaying the prediction result, the structure health state and the maintenance suggestion through a visual tool. The precision and real-time performance of service life prediction of the concrete-filled steel tube structure are remarkably improved, and the method has a wide application prospect.

The invention relates to the technical field of intelligent detection, in particular to a cage guide anomaly detection method based on audio signal analysis, which comprises the following steps: S1, acquiring audio signals of equipment in different running states in real time; s2, the collected audio signals are preprocessed, and audio features related to the running state of the cage guide are extracted; s3, establishing a dynamic feature change model; s4, applying the dynamic feature change model established in the S3 to analysis of real-time audio signals, and judging whether abnormity occurs or not; and S5, if the audio signal is judged to be abnormal in the step S4, carrying out classification processing on the abnormal signal through a pre-trained classification model. According to the method, the dynamic feature change model and the incremental learning algorithm are combined, real-time and accurate analysis of the audio signals of the cage guide system is achieved, and various abnormal types can be effectively recognized and automatically classified.