144 results about "Root cause diagnosis" patented technology

The invention discloses a multi-source information fusion equipment health diagnosis management system, and relates to the technical field of equipment management. Comprising an information acquisition module, a feature perception module, a processing fusion module, an equipment modeling module, an evolution prediction module, a root cause diagnosis module, a cross-domain inspection module, a learning sharing module, a state evaluation module, a collaborative decision-making module, a chain account book module and a visual decision-making module. According to the method, the perspectiveness and the sensitivity of anomaly detection are remarkably improved, noise interference and sampling deviation are reduced, fused data are more stable and have higher physical consistency, differential diagnosis and individual-level prediction are supported, the interpretability of diagnosis and the decision reliability are improved, false alarm and missing alarm are avoided, the early warning reliability is improved, and the method is suitable for popularization and application. And scientific, transparent and traceable health management is realized.

The invention relates to an intelligent operation and maintenance method and apparatus based on a knowledge graph and a large model, and an electronic device. The method comprises the steps of collecting multi-source runtime data of a Kubernetes cluster; constructing a knowledge graph with time dimension based on the resource change event, recording termination time in response to graph relationship failure, recording starting time in response to a newly added relationship and not setting the termination time, and associating the entity with the performance index and the log data; responding to the diagnosis request, scheduling a specialized agent by a coordination agent through multi-agent cooperation to retrieve associated information from multi-source data, and iteratively integrating to generate a structured context; and inputting the generated structured context information into a large model reasoning service to output a fault root cause diagnosis and solution. The technical problems that information dispersion and relevance are weak, root cause positioning is difficult and time-consuming, comprehensive context sensing ability is lacked and expert experience is excessively relied on are solved.

The invention discloses a video monitoring equipment fault real-time detection, root cause diagnosis and closed loop processing method and system. According to the method, by collecting multi-dimensional operation data of equipment, a dynamic weighted health degree model is constructed to realize early-stage accurate discovery of a fault; performing intelligent alarm grading by combining time sequence prediction and health degree change; realizing automatic root cause diagnosis by utilizing topological correlation analysis, log semantic analysis and case similarity matching; and closed loop processing and model self-optimization are realized through a work order system. According to the method, the problems of lagging fault discovery, difficulty in positioning, slow repair and disjunction in assessment in the prior art are effectively solved, and the operation and maintenance efficiency and the service quality are remarkably improved. The abstract drawing is Figure 1.

The invention provides an event root cause intelligent diagnosis method and system for financial service operation risks, and the method comprises the steps: firstly collecting an operation risk event data set which is generated by an operation risk event in a financial service system and contains various information, and then carrying out the feature extraction of the operation risk event data set; the method comprises the following steps: generating an event feature set containing multi-aspect features, constructing a dynamic event association network based on the event feature set, determining nodes and influence intensity parameters, performing causal path weight iterative calculation on the network by using a preset root cause inference rule set, and positioning a root cause node set; and finally, according to the root cause node set, generating a root cause diagnosis result containing the root cause type identifier, the influence path description and the correlation feature contribution degree, thereby improving the accuracy and efficiency of financial service operation risk root cause diagnosis.

The invention relates to the technical field of electronic equipment detection, and discloses an FPC connector quality detection method and system based on multi-modal fusion, and the method comprises the steps: obtaining an original multi-modal data set containing electrical stress, thermal stress and mechanical stress, and carrying out the filtering and time sequence alignment preprocessing, and obtaining a standardized multi-physical field sequence; constructing a three-dimensional space field intensity distribution diagram according to the sequence, and identifying field intensity anomalies by adopting density clustering so as to accurately position potential defects; learning a time sequence evolution mode based on the multi-moment observation value of the defect position to predict the future diffusion trend of the defect; and integrating the diffusion trend, the real-time field intensity and the environment variable to carry out comprehensive modeling and evaluation, and generating a dynamically updated and final quality detection report. According to the method, root cause diagnosis of connector defects, accurate three-dimensional space fault positioning and accurate prediction of future evolution trends can be realized, and the detection precision and predictability are remarkably improved.

The invention discloses an artificial intelligence abnormity early warning diagnosis method for industrial equipment operation state monitoring, and belongs to the technical field of industrial equipment intelligent monitoring, and the method comprises the steps: collecting a multi-source heterogeneous signal of industrial equipment, and carrying out the time-frequency dual-domain feature extraction; constructing a multi-scale time window based on the time-frequency features, and executing self-supervised contrast learning by injecting a preset abnormal mode to obtain cross-scale contrast feature representation; constructing a dynamic adjacency matrix according to the comparison features, extracting space-time correlation features through a graph attention network, and determining an abnormal score based on joint evaluation; according to the method, a deep coupling closed-loop cooperative system is formed, multi-dimensional state characterization, adaptive anomaly detection and root cause diagnosis are realized, and the problems of single data source and lack of fault analysis capability in the prior art are effectively solved.

The invention discloses an intelligent automobile interpretable abnormity diagnosis method and system, and relates to the technical field of intelligent traffic. The method comprises the steps of collecting multi-dimensional sensor data based on an intelligent automobile test platform, and constructing a directed causal graph and a causal adjacency matrix which are used for describing a causal relationship between the sensor data; designing a causal constrained graph attention mechanism based on the causal adjacency matrix, and constructing a causal constraint enhanced graph attention anomaly diagnosis model; and based on the directed causal graph and the graph attention anomaly diagnosis model, constructing a hierarchical anomaly diagnosis strategy integrating a feature reconstruction error, a variable causal relationship and a graph attention network weight, positioning an anomaly root cause and identifying a propagation path of the anomaly in the sensor network. According to the invention, the problems of false correlation and lack of exception explanation ability of graph attention network learning in the prior art can be overcome, and reliable exception detection and root cause diagnosis of intelligent automobile multi-sensor data are realized.

The invention provides a vehicle fault root cause diagnosis method, equipment, equipment and a medium, and the method comprises the steps: obtaining a vehicle target fault phenomenon, determining a to-be-detected fault event set based on a preset fault logic relation, constructing an initial scoring matrix, enabling a row vector to correspond to a fault event, enabling a column vector to correspond to the state feature parameters of a plurality of evaluation dimensions, and carrying out the detection of the fault event set; executing the detection task of the highest comprehensive score fault event, obtaining feedback data, updating the initial score matrix parameters based on the feedback data to obtain an updated score matrix, and calculating the comprehensive score of each event based on the updated score matrix again. Iteratively executing the detection task corresponding to the updated highest score event to identify whether the detection event is a fault root cause or not until the fault root cause of the target fault phenomenon is determined; according to the method, through a dynamic priority scheduling mechanism, real-time feedback data is fused in multi-dimensional evaluation, a high-value diagnosis task is executed preferentially, the resource consumption of traditional traversal diagnosis is remarkably reduced, and the fault positioning efficiency is effectively improved.

The invention relates to the technical field of cloud computing, and discloses a log intelligent aggregation and threat traceability analysis method and system for a multi-cloud environment, and the method comprises the following steps: collecting original logs of the multi-cloud environment, injecting a unified service identifier and a cloud platform label, analyzing a heterogeneous log format into structured data, and storing the structured data in a database; sorting and complementing missing log entries according to timestamps; constructing a service dependency graph, quantifying the calling relation weight between services, fusing log semantic features and statistical features, and generating a feature matrix after standardization; according to the method, standardized aggregation of multi-cloud logs is realized through unified service identifiers, the problem of heterogeneous log processing is solved, and the accuracy of complex threat identification and the propagation path verification capability are remarkably improved based on a feature fusion and cascade integration detection mechanism of a service dependency graph; the cross-cloud attack path is accurately positioned in combination with tracing analysis of the service identifier, and root cause diagnosis and security protection in a multi-cloud environment are effectively supported.

The invention belongs to the technical field of aircraft fault diagnosis, and particularly relates to an aircraft fuel control system fault path mining and root cause diagnosis method. The method comprises the following steps: providing a fault propagation-oriented fault root cause diagnostic graph model to realize more interpretable fault source positioning, and backtracking from an alarm node to a fault source based on propagation mechanism information; constructing a variable propagation graph of the aircraft fuel control system in combination with correlation coefficient analysis and a Lingam causal algorithm, and then performing correction based on a system simulation structure in a manual inspection mode so as to establish an interpretable data structure; introducing an edge propagation quantization factor and a path scoring criterion integrating nodes, edges and path lengths to measure the possibility of candidate fault propagation paths; and learning an optimal threshold set of each node in the propagation graph structure by adopting a particle swarm optimization algorithm. The method supports path-level transparent backtracking, improves the accuracy and flexibility of the model, and can excavate a plurality of fault propagation paths.

The invention belongs to the field of equipment evaluation, particularly relates to an intelligent evaluation method and system for the operation quality of a flight simulator, and aims to solve the problems of single evaluation dimension, poor real-time performance, low intelligent degree and lack of quantitative standards in the prior art. The method comprises the steps that operation data such as fault time, duration and available time are collected in real time through a sensor network; calculating core indexes such as fault frequency per unit time, accumulated duration and malignant fault rate; dynamically weighting and fusing the indexes to generate a single-machine health index; a correlation model is constructed based on fault space-time correlation between devices, and cluster health scores are output in combination with single machine indexes; when the malignant fault exceeds a threshold value, driving causal inference by utilizing a knowledge graph containing entity causal relationships of fault types, equipment parts and the like, and outputting a root cause diagnosis and maintenance scheme; and acquiring intervened data to update atlas parameters and models to form closed-loop optimization. Multi-dimensional real-time monitoring and diagnosis closed loop of the operation state are realized, and the maintenance efficiency is improved.

The invention relates to a data AI analysis management method and system based on a production element association map. The method comprises the steps that a multi-source heterogeneous production data flow covering the whole industrial production cycle is obtained; constructing a whole-process production element association map through an entity recognition and relationship extraction technology; actual operation indexes of the production nodes are calculated in real time and compared with a reference threshold value, and potential production bottleneck nodes are accurately recognized; upstream associated node data are backtracked, historical data in the same period are combined to be input into the bottleneck root cause diagnosis model, and core influence factors are accurately obtained; generating an optimal scheduling strategy according to the core influence factors and issuing the optimal scheduling strategy to a production execution system; according to the scheme, the multi-source heterogeneous data of the whole period of industrial production can be effectively analyzed and managed, accurate regulation and control of the production process are achieved, and the production efficiency and the product quality are improved.

The invention discloses a health monitoring method and device for industrial equipment. The method comprises the following steps: acquiring a target multi-modal feature vector set; performing time sequence alignment and feature fusion processing on the target multi-modal feature vector set to obtain a target fusion feature vector sequence; inputting the target fusion feature vector sequence into a target equipment health state prediction model for processing to obtain a target equipment collaborative analysis result; obtaining health state prediction data of the target equipment according to the collaborative analysis result of the target equipment; generating a target equipment fault root cause diagnosis report, a target equipment maintenance suggestion and a target risk assessment report; and performing optimization processing on the target equipment health state prediction model according to the target equipment actual operation data, the target equipment fault root cause diagnosis report, the target equipment maintenance suggestion and the target risk assessment report. According to the invention, the fault detection rate of industrial equipment can be improved, the false alarm rate can be reduced, and organic combination of millisecond-level abnormal response and deep historical analysis is realized.

The invention relates to an operation and maintenance alarm root cause positioning method and system fusing a knowledge graph and a large model, and belongs to the technical field of data processing and intelligent operation and maintaining.The method comprises the steps that original alarm data are obtained from a plurality of heterogeneous monitoring sources based on alarm data query service of time period parameters and subjected to cleaning and structural processing, and the original alarm data are obtained; obtaining alarm data to be analyzed; performing unsupervised clustering analysis to realize alarm automatic classification and noise filtering to obtain classified alarms and category labels; extracting corresponding object topological relation information from a pre-constructed knowledge graph; and inputting the classified alarms, category labels and object topological relation information into a large language model, guiding the large language model to perform semantic reasoning through a preset cue word project, and generating a structured diagnosis report containing root cause diagnosis, an influence range and repair suggestions. According to the method, the alarm storm is inhibited, the fault root cause is quickly, accurately and interpretably positioned, and the operation and maintenance efficiency and the system stability are improved.

The invention relates to a multi-protocol compatible ultrasonic radar test method and system. According to the method, protocol configuration is automatically obtained by scanning a radar identification code, communication connection is established, a standardized test process is controlled and executed based on a parameter file to collect response data, and a reconstruction error of the test data is calculated in real time by using an LSTM auto-encoder model to realize anomaly detection and feature extraction. According to the method, a fault source is accurately positioned by combining causal reasoning of a fault knowledge graph, and a diagnosis report containing a solution is finally generated, so that full-process automatic closed loop from protocol adaptive configuration, intelligent anomaly recognition to root cause diagnosis is realized, the efficiency of multi-protocol radar testing and the accuracy of fault diagnosis are remarkably improved, and the fault diagnosis efficiency is improved. The technical defects that a traditional method depends on artificial experience, efficiency is low, and diagnosis results are one-sided are effectively overcome.

The invention discloses a test failure root cause diagnosis method, which relates to the technical field of electric digital data processing, and is characterized in that after a test failure signal is captured, comprehensive analysis is carried out in combination with multi-source log information of a test case and test environment configuration data, so that the influence of environment configuration on a test is fully considered, and information in a log is fully mined; according to the method, a more accurate diagnosis result is obtained, and a corresponding solution is matched according to a test failure root cause to solve the problem of test failure, so that the problems of low efficiency and high misjudgment probability of manual analysis, neglect of the influence of a test environment on the test failure, difficulty in identifying implicit connection between texts in a log and difficulty in testing failure in the prior art can be solved. Therefore, the technical problem that the obtained analysis result is difficult to be used for accurate root cause diagnosis is solved, the diagnosis efficiency of test failure root causes is improved, the diagnosis precision is improved, and the overall test period is shortened.

The invention discloses a remote fault diagnosis method and system for a mixing plant, and the method comprises the steps: constructing a digital twin body, obtaining a multi-modal sensing signal of each operation part, and forming a multi-modal joint feature vector representing a multi-source operation state; importing the feature vector into a digital twinborn body for physical constraint correction, and establishing a time sequence causal network by taking a key component of the mixing plant as a node according to the corrected feature vector; acquiring real-time monitoring data of a target mixing plant, acquiring abnormal probability distribution through residual modeling, and performing root cause inference in combination with a time sequence causal network to generate root cause diagnosis information; the operation situation data of the associated mixing plant is gathered based on the cloud platform, and cross-site early fault diagnosis and early warning are realized by using a federal learning mechanism; and constructing a mixing station cluster network, performing operation health evaluation on each station, performing station adaptation analysis in combination with a current mixing task, and generating mixing station selection recommendation information so as to improve the operation and maintenance efficiency and the production stability.

The invention discloses a positioning end PPP-RTK real-time precision product monitoring method and device, and belongs to the technical field of satellite navigation and positioning. The method comprises the steps that a PPP-RTK positioning result and a post precision coordinate reference value are acquired in real time, ENU direction positioning deviation is calculated, three types of parameters including satellite geometric configuration, product precision and data timeliness are fused to generate a credibility index C, and an alarm threshold value is dynamically adjusted according to the credibility index C; establishing a positioning precision database to support rapid query and analysis; making a multi-level alarm rule for positioning continuity and precision overrun, and presetting a diagnosis item mapping relation; and after the alarm is triggered, data recording, root cause diagnosis and information output are automatically executed, so that full-process automation from abnormal sensing to root cause definite diagnosis is realized. According to the invention, the reliability, the stability and the operation and maintenance efficiency of the PPP-RTK positioning service are remarkably improved through an evaluation-prediction-diagnosis three-layer intelligent closed-loop system.

A method may obtain a failure propagation model, wherein the failure propagation model comprises: a model representation of a plurality of hardware components, a set of hardware failure probabilities; and a logic that maps signals to the hardware components. A method may receive an alert signal from the aircraft. A method may map the alert signal to the plurality of hardware components. A method may perform a root-cause diagnosis of the alert signal that has been mapped to the plurality of hardware components comprising: determining via the failure propagation model, one or more combinations of hardware failures associated with the alert signal; and determining a probability of occurrence associated with the combinations of hardware failures. A method may display a report that includes combinations of hardware failures associated with the alert signal and the probability of occurrence associated with the combinations of hardware failures.

The invention relates to an AI-driven intelligent work reporting method, system and device and a medium. The method comprises the steps of collecting original operation data of production equipment and performing anomaly detection to generate a standardized anomaly event stream; carrying out unified representation on the abnormal event and the production context thereof, and generating a space-time aligned feature sequence; calculating causal intensity between abnormal events based on a preset model and constructing a dynamic time sequence causal graph; back diffusion iteration is carried out by simulating abnormal influence to trace root cause nodes, and a root cause score sorting vector is generated; positioning a key root cause and tracing a propagation path of the key root cause, analyzing backlog data for root cause types such as network interruption, and performing compensation work reporting; and finally, optimizing causal intensity model parameters by utilizing artificial feedback. The method overcomes the defects that in the prior art, abnormal events are analyzed in an isolated mode, and causes and effects cannot be correlated, intelligent root cause diagnosis and work report data self-correction of a complex abnormal chain can be achieved, and therefore production data reliability and operation and maintenance efficiency are improved.

The invention relates to the technical field of data analysis, in particular to a data and knowledge combined driven intelligent decision-making method and system.The method includes the steps that multi-source heterogeneous data and knowledge base concepts are unified into a structured graph structure through multi-dimensional feature extraction and multi-head attention fusion context prompt, and a structured semantic basis is provided for intelligent decision-making; by combining data-driven mining and knowledge prior constraints, the accuracy and robustness of causal reasoning are improved, and the reliability of root cause diagnosis is ensured; a root cause path is searched and enumerated in a reverse breadth-first manner by taking an abnormal entity as a starting point, so that rapid and traceable abnormality positioning is realized, and a user is assisted to focus a high-probability root cause; through modular assembly and full-link element traceability, while the analysis threshold is reduced, decision full-link transparency is realized, and the auditing requirement of a high-risk scene is met; by automatically converting natural language requirements into executable scripts, the decision-making efficiency of non-technical users is improved.

The invention discloses an automatic fault detection and diagnosis system and method based on an artificial intelligence optimization operation system and a function library, and belongs to the technical field of intelligent building and industrial equipment operation and maintenance. The system comprises a data acquisition and preprocessing layer, a fault detection layer, a fault diagnosis layer, an intelligent recommendation layer and a visual display layer. The method comprises the following steps: collecting equipment data in real time and preprocessing; performing anomaly detection and performance trend analysis in combination with statistical process control and a machine learning algorithm; performing root cause diagnosis by using a Bayesian reasoning model; classifying faults according to an energy performance type, a controllability type and a thermal comfort correlation type, and evaluating priorities through a multi-dimensional weighted scoring model; and intelligently generating a solution and updating the knowledge base. According to the method, whole-process automation from early warning, diagnosis, classification to recommendation is achieved, the equipment reliability, the energy efficiency and the operation and maintenance intelligent level are improved, and the method is suitable for application scenes such as artificial intelligence middleware and computer visual and auditory software.

The invention relates to the technical field of vehicle energy consumption analysis, and discloses a vehicle energy consumption closed-loop analysis method based on big data, which comprises the following steps: data acquisition and scene recognition, clustering and reference calculation, anomaly recognition, and hierarchical root cause diagnosis on vehicles with abnormal energy consumption, comprising macroscopic state comparison and microcosmic operation parameter comparison, and if no suitable vehicles with normal energy consumption in the same track exist, self historical comparison analysis is carried out; and improvement and tracking verification: based on the diagnosis result, generating improvement measures and implementing the improvement measures, and performing multi-dimensional effect tracking verification on the vehicle after the improvement measures are implemented. The invention further discloses a vehicle energy consumption closed-loop analysis system based on the big data. According to the vehicle energy consumption closed-loop analysis method and system based on the big data, the problems of reference static state, low diagnosis efficiency and flow splitting in the prior art are effectively solved.

The invention provides an injection molding quality problem traceability analysis method, which comprises the following steps of: acquiring a surface image and process parameters of a molded product, extracting defect characteristics through methods of image enhancement, edge detection, region segmentation and the like, and fusing the defect characteristics with normalized process parameter data to obtain an injection molding quality problem traceability analysis result; constructing a multi-modal knowledge graph containing entity nodes and causal relationship edges; further introducing implicit causal edges and path diversity scores to realize dynamic sorting and root cause identification of defect causal paths; the system supports knowledge increment updating and scoring model reinforcement learning under actual production feedback, so that the root cause diagnosis accuracy and the system adaptive capacity are continuously optimized, and the automation, accuracy and knowledge evolution efficiency of injection molding defect analysis in a complex scene are improved.

The invention relates to the technical field of digital twinning, in particular to a digital twinning dynamic updating and virtual-real mapping optimization method for a complex scene, which comprises the following steps of: establishing a bidirectional value function of virtual and physical spaces, searching a cooperative Nash equilibrium solution through multi-round game theory iteration, and realizing cooperative Pareto optimization of a virtual-real system under constraints; an anomaly detection incremental learning and elastic weight consolidation mechanism is introduced, and causal discovery and anti-factual reasoning are combined to realize root cause diagnosis and interpretable decision intervention. According to the complex scene-oriented digital twinborn dynamic updating and virtual-real mapping optimization method, an isolation forest is adopted to isolate abnormal samples through random segmentation, and a variational auto-encoder is combined to learn low-dimensional latent space representation, so that the problem of novel abnormal missing detection is solved, and an elastic weight consolidation mechanism is introduced to avoid disastrous forgetting; a variable causal relationship is mined from observation data based on a PC algorithm, and anti-fact root cause diagnosis is realized by taking a structural causal model and do-calculation as a framework.

The invention provides an intelligent project task scheduling method and system based on a knowledge graph, and relates to the technical field of project data process.The method comprises the steps that firstly, a manufacturing event knowledge graph is constructed, a typical time sequence problem link is solidified, and a multi-channel similarity evaluation model aligned with real shutdown, risk and resource occupation performance is trained; when a new target abnormal project task appears, candidate links with reasonable structures are screened in the atlas, comprehensive similarity is calculated and sorted, all candidate problem links are screened out, and main root cause types and alternative root cause types of the target abnormal project task are automatically selected based on comprehensive similarity scores; therefore, the processing strategy corresponding to the target abnormal project task is scheduled, systematic errors introduced by the simple vector distance are remarkably reduced on the two aspects of root cause diagnosis and task scheduling, and the accuracy and the performability of the scheduling processing strategy are improved.

This invention discloses a multi-source information fusion-based equipment health diagnosis and management system, relating to the field of equipment management technology. It includes: an information acquisition module, a feature perception module, a processing and fusion module, an equipment modeling module, an evolution prediction module, a root cause diagnosis module, a cross-domain testing module, a learning and sharing module, a status assessment module, a collaborative decision-making module, a chain ledger module, and a visual decision-making module. This invention significantly improves the foresight and sensitivity of anomaly detection, reduces noise interference and sampling bias, makes the fused data more stable and physically consistent, supports differentiated diagnosis and individual-level prediction, improves the interpretability of diagnosis and the credibility of decision-making, avoids false alarms and missed alarms, enhances the reliability of early warnings, and achieves scientific, transparent, and traceable health management.

The present invention discloses a method for predictive maintenance of transmission equipment, which relates to the technical field of transmission equipment maintenance and is applied to a roller conveying system for flexible materials. The method is characterized in that it includes the following steps: S1, placing position triggers at each key transition node of the roller conveyor to collect the timestamps of the materials passing through the detection points in real time, and generating a unique number and a corresponding time series relationship for each material; S2, calculating the standard material passing time based on the theoretical beat cycle, and subtracting the actual time from the standard cycle to construct a beat offset set to reflect the conveying beat deviation of the materials between adjacent detection points. The present invention realizes early warning and intelligent regulation of flexible material conveying rhythm disorders through beat offset modeling, abnormal cluster identification and root cause diagnosis, and dynamically adjusts the compression bandwidth and drive delay when the risk of disorder occurs, effectively alleviating the risk of accumulation, and improving system stability, automation level and operating efficiency.

The embodiment of the invention discloses an abnormal root cause analysis method and device, equipment, a storage medium and a product. The method comprises the steps that a root cause positioning request is obtained, the root cause positioning request comprises an abnormal event needing abnormal root cause analysis, an audit log of a database instance corresponding to the abnormal event in a target time period is pulled, root cause analysis is conducted on the audit log from at least one dimension, and at least one candidate template is obtained, and based on the at least one candidate template, generating an abnormal root cause analysis result of the abnormal event, the abnormal root cause analysis result comprising a root cause template or a root cause transaction related to the abnormal event. Therefore, the root cause analysis is carried out on the audit log of the database instance corresponding to the abnormal event in the target time period from one or more dimensions, so that the root cause diagnosis granularity can be refined, and a more accurate abnormal root cause analysis result is generated.

The invention relates to the technical field of industrial process monitoring and fault diagnosis, and discloses an alarm AI application system based on industrial data, and the system comprises a data access and preprocessing module which is used for collecting and preprocessing the industrial data so as to generate a standardized state vector sequence; the offline model construction module is used for performing offline training and solidifying a physical channel model and a data channel model for subsequent diagnosis; the real-time diagnosis and alarm module is used for loading the model, calculating physical and mode residual errors in parallel and executing root cause diagnosis so as to generate a quantized causal score; and the diagnosis result output module is used for triggering an alarm according to the residual error and the causal score and outputting an explanatory report containing root cause positioning. According to the method, the two-channel residual error model is constructed, and the dynamic Jacobian matrix is utilized to drive the dynamic causal graph network, so that the alarm accuracy and the root cause diagnosis reliability are obviously improved.