35 results about "Diagnostic reasoning" patented technology

In the method and system for automated data diagnosis, a relational data base is formed of attributes characterizing an entity. The framework computes optimal diagnosis for a diagnostic inference problem which separates the desirable attributes from the undesirable attributes. The user of the system is permitted to specify certain parameters based on which the system computes a set of optimal or near optimal association rules between the attributes of a specific process, product, or other entity. The system and method of the present invention considers the simplicity of conditions in addition to support and confidence when ordering them, contributes the notion of tight conditions and semi-equivalence to remove redundant rules, uses the concept of the top fringes which allows near optimal conditions to be found, in addition to optimal conditions. Numeric as well as non-numeric attributes can be analyzed.

A method for distributed diagnostic reasoning is provided. The method includes establishing a computing node monitoring the operation of a component of a complex system and populating at least one of a processor and the memory of the computing node with one or more standardized executable application modules (SEAMs) and a workflow service. The method further includes creating a configuration file in combination with several SEAMS to create a distributed diagnostic reasoner (DDR) associated with the component. The method also comprises installing the configuration file in the computing node for execution by the processor; and initializing the one or more SEAMS, the configuration file and the workflow service, wherein the workflow service facilitates data flow between the one or more SEAMS and the static data associated with a fault condition resident in the configuration file.

The invention discloses a time-varying reliability evaluation method for a mechanical system based on a dynamic Bayesian network. The time-varying reliability of mechanical systems is calculated by using the Sterling information update formula and Monte Carlo simulation. Beneficial effects of the invention: Bayesian network provides a graphical representation method of knowledge, which can describe the causal probability relationship between node variables in a directed graphical manner, which can be used for uncertainty knowledge expression, causal reasoning and diagnostic reasoning Wait. The reasoning of the Bayesian network can effectively identify the weak links of the system reliability; its graphical display makes the relationship between the components in the mechanical system more intuitive and clear, and the dynamic Bayesian network technology is applied to the time-varying reliability of the mechanical system Evaluation, analysis of the multi-state and failure correlation of the mechanical system, to improve the theoretical support for improving the performance and reliability of the mechanical system.

The invention discloses a data-driven self-adaptive multi-layer flow model equipment diagnosis method, which combines the better accuracy based on the data-driven method and the better interpretability based on the multi-layer flow model method, and overcomes the traditional The fixed abnormal alarm threshold in the multilayer flow model method is easy to cause missing alarms, which leads to wrong diagnosis results. Based on the data-driven equipment status classification and identification results, the abnormal alarm threshold of the multi-layer flow model is adaptively adjusted, and the current equipment status is further confirmed through the multi-layer flow model anomaly detection and diagnostic reasoning to enhance the reliability of equipment fault diagnosis. The equipment diagnosis method has important scientific research value and engineering application value.

The invention discloses an embedded real-time diagnosis inference algorithm testing system of an airplane. The system comprises a master control device, a data simulation device and an embedded target machine; the master control device registers a diagnosis inference algorithm to be verified, integrates the registered diagnosis inference algorithm to be verified in the embedded target machine, and emits a fault generation instruction to generate fault data; the data simulation device generates corresponding fault data according to the fault generation instruction emitted by the master control device; the embedded target machine runs the diagnosis inference algorithm to be verified to carry out inference caculation the fault data, and sends a calculation result to the master control device; and the master control device analyzes the calculation result, and evaluate performance of the diagnosis inference algorithm to be verified. According to the invention, the difficulty in verifying the diagnosis inference algorithm in real time in the prior art is overcome.

The invention discloses an embedded-type real-time diagnostic reasoning algorithm experiment method for an airplane. The embedded-type real-time diagnosis reasoning algorithm experiment method is as follows: a master control device registers a to-be-verified diagnostic reasoning algorithm; the master control device integrates the registered to-be-verified diagnostic reasoning algorithm into an embedded-type target machine; a data simulation device starts a fault simulation model to generate corresponding simulation fault data according to a simulation fault instruction of generating simulation fault data from the master control device; the embedded-type target machine utilizes the to-be-verified diagnostic reasoning algorithm to perform reasoning calculation on the simulation fault data and sends the calculation result to the master control device; and the master control device evaluates the performance of the to-be-verified diagnostic reasoning algorithm through analyzing the calculation result. The embedded-type real-time diagnostic reasoning algorithm experiment method can be used for solving the difficulty of verifying the real-time diagnostic reasoning algorithm on the airplane in the prior art.

The invention discloses an overhead power transmission line running state assessment method based on a bidirectional Bayesian network. The method can be used for conducting a real-time assessment on the running state of an overhead power transmission line. According to the method, a Bayesian network structure for the assessment of the running state of the power transmission line is constructed with various factors which influence the running state of the power transmission line serving as a condition attribute set and the running state of the line serving as a decision attribute, a conditional probability table is obtained according to sample training, and by utilizing the bidirectional reasoning technology dedicated to the Bayesian network, the running state of the line can be judged by means of causal reasoning, and the hidden danger of the state can also be recognized by means of diagnostic reasoning; when an assessment error exists, a self-feedback system can be used for conducting early warning and correction, an assessment database, the network structure and parameters can be modified dynamically in real time so as to be adapted to an update, and therefore healthy running of the power transmission line is truly guaranteed.

The invention discloses a method for diagnosing a compressor-associated failure based on a Bayesian network. Based on a three-layer Bayesian diagnosis network of working condition operation, failure and symptom, a simple and intuitive graphic mode is used for expatiating the complicated causality and conditional relation between the failure, the reason and the symptom thereof, performing diagnostic reasoning under a finite, incomplete and uncertain information condition and completely describing the probability of the system failure, so qualitative information and quantitative information canbe integrated, the function of fully utilizing multi-source information is realized, and the testing sample size for performing the failure diagnosis is reduced by fully utilizing the priori information and historical information of a specific diagnosis object; and the accuracy and the efficiency for the failure diagnosis can be greatly improved by establishing a proper Bayesian diagnosis networkand determining a rational prior probability.