60 results about "Fault injection" patented technology

This invention relates to the field of industrial equipment fault diagnosis, and provides a self-supervised multi-sensor fault diagnosis method and system based on semantic embedding. The method preprocesses raw normal operating condition monitoring data, generates a fault window through single-channel fault injection using temporal semantic embedding, and generates a supervision signal for the fault window. Features are extracted from the training sample window composed of the pure normal operating condition window and the fault window using long-term Transformer branches and short-term CNN branches. The extracted long-term and short-term features are concatenated and mapped to a shared fault feature representation. A fault attribute matrix is ​​constructed, a semantic prototype library is generated, and semantic similarity is calculated. Based on the shared fault feature representation and semantic similarity, a multi-task prediction head is constructed. Based on the multi-task prediction head and the supervision signal, a multi-task loss function is designed to train an end-to-end fault diagnosis model. Post-processing optimization is combined to correct easily misjudged fault results. Online fault diagnosis results are output.

This invention discloses an online editing and parallel execution method and system for vehicle network test cases, relating to the field of vehicle network testing technology. It establishes an online editing environment via a web interface, enabling automatic generation of protocol code and providing testers with a convenient and efficient development experience. Regarding test case execution, it accurately analyzes the dependencies of test cases, uses a topology sorting algorithm to construct a reasonable execution plan, and adaptively switches between sequential and parallel execution modes. Combined with containerization isolation technology, it allocates an independent execution container for each test case, ensuring the isolation and stability of the testing environment. Simultaneously, it initializes a unified test execution context for each test case and establishes a communication connection with the vehicle network bus simulation engine through a standardized interface, achieving standardization and normalization of operations such as message sending and receiving, fault injection, and assertion verification. In variable management, it adopts a copy-on-write mechanism to achieve isolated sharing of project variables, avoiding data crosstalk.

The present application relates to the technical field of power distribution network resilience evaluation, and discloses a power distribution network resilience evaluation verification method, system, device and medium based on multi-dimensional fault injection, which comprises the following steps: constructing a multi-dimensional fault model library; based on a preset test target, selecting a target fault scene from the model library and generating a fault injection strategy; executing the strategy on a hardware-in-the-loop simulation platform, and collecting system operation data in real time; calculating a performance index curve representing the overall power supply level of the power distribution network over time, and quantitatively calculating a plurality of resilience evaluation indexes; based on the resilience evaluation indexes, performing comparative analysis, identifying key scenes that significantly affect the resilience of the power distribution network, and adjusting the fault injection strategy in subsequent tests to realize closed-loop evaluation and verification of the resilience of the power distribution network. The present application not only evaluates the degree of performance loss, but also focuses on recovery speed and recovery efficiency to identify weak links affecting recovery and provide a scientific basis for formulating resilience improvement measures.

A system associated with an enterprise computing environment infrastructure may include a chaos testing tool data store that contains a plurality of electronic records, each record including a chaos engineering fault parameter. A computer processor of a chaos testing tool may receive, from a chaos testing user, injection information associated with an element of the enterprise computing environment infrastructure. The chaos testing tool may then access the chaos engineering fault parameter from the chaos testing tool data store and automatically arrange to inject a chaos engineering fault into operation of the element of the enterprise computing environment infrastructure in accordance with the injection information and the chaos fault parameter. A response of the element of the enterprise computing environment infrastructure may then be measured subsequent to said injection, and the system may output an indication of the measured response to the chaos testing user.

The application provides a path-aware fault processing method for a cloud computing environment, and relates to the technical fields of cloud computing, computer network security and system reliability. The method comprises the following steps: obtaining a real end-to-end network path of target service traffic in a network communication system for cloud computing, and representing the real end-to-end network path as an ordered path sequence; determining a fault type of a target fault to be injected and a target path node corresponding to the target fault in the ordered path sequence based on a preset fault model and the real end-to-end network path, generating a fault specification based on the fault type, the position of the target path node and the fault parameters of the target fault, and controlling the target path node to inject a fault injection primitive corresponding to the target fault; and in the case of injecting the fault injection primitive, performing correlation analysis on running data and the fault injection primitive to generate an influence analysis result of the target fault. The technical scheme of the application improves the accuracy of fault influence analysis.

Systems, methods, and techniques that facilitate application fingerprint generation are provided. One or more embodiments described herein can comprise a computer-implemented method comprising determining, by a device operatively coupled to a processor, fault proneness of one or more microservices regarding one or more fault categories, generating, by the device, an ordered seed set of the one or more microservices based on the determined fault proneness, generating, by the device, an augmented ordered seed set of the one or more microservices based on topological relationships of the one or more microservices and based on the ordered seed set, and building, by the device, a set of one or more patterns of resource constraint faults and a set of one or more patterns of entity experience faults based on the augmented ordered seed set of the one or more microservices.

This invention belongs to the field of elevator technology, specifically relating to a method, equipment, and medium for elevator fault injection based on multiphysics operating mechanisms. It establishes digital models of the main elevator platform system and the isolation door system and defines interfaces. The method includes configuring a data acquisition and control module; initializing the multiphysics parameter set; determining the fault injection point; sending a fault excitation signal to drive co-simulation; collecting state response data; evaluating the fault impact; and generating a report. This method, based on multiphysics coupling mechanisms, achieves accurate simulation of the fault evolution process, quantifies the impact of faults on elevator performance, and accurately locates fault propagation paths. Accurate modeling based on multiphysics mechanisms covers fault injection in core components, and co-simulation realistically reflects fault evolution. It quantitatively assesses the impact of faults on operational performance, clarifies propagation paths, and provides data support for elevator fault diagnosis, preventative maintenance, and control system optimization, thereby improving operational safety and reliability.

The application provides a micro-service architecture-oriented intelligent chaos test method and device, relates to the technical field of software testing, and solves the problems of one-sided fault coverage of traditional tests, rigid strategies, easy triggering of system risks and disconnection with business scenarios. The method comprises the following steps: collecting a service call chain through a distributed tracking technology, and constructing a dynamic dependency graph comprising node importance and link throughput; adopting an LSTM neural network to analyze a business log sequence to identify a business process stage, and establishing a "stage-link-fault" triplet rule; integrating topology features, business stages and real-time operation indexes to construct a state space, and optimizing a fault injection strategy based on a reinforcement learning algorithm and a multi-objective reward function; and limiting the injection intensity and range through a conflict detection and pre-check mechanism. The application is used for reliability verification of a micro-service system, and improves test efficiency and safety.

This invention relates to the field of power system automation testing technology and discloses a fault-tolerant testing method for automated equipment based on an event knowledge graph. The method includes the following steps: extracting entities, relationships, and attributes of fault events from multi-source heterogeneous data, constructing a triplet knowledge representation, eliminating entity ambiguity through semantic alignment technology, and forming a unified fault event knowledge graph; and employing a weighted subgraph traversal algorithm based on the fault event knowledge graph. The aim is to address the problems in existing fault-tolerant testing methods, such as test case generation relying on human experience, difficulty in automatically extracting related event chains from multi-source heterogeneous data to construct scenario-based test cases, lack of temporal logic and physical model constraints in fault injection leading to a disconnect between abnormal message sequences and real fault characteristics, and lack of comprehensive intelligent analysis capabilities for multi-dimensional response signals and a self-evolution mechanism for test knowledge in test result analysis, thus failing to form a continuously learning adaptive intelligent testing system.

To provide a system, computer-implemented method and computer program product for generating training data via reinforcement learning fault-injection.SOLUTION: The method comprises: a step 1102 of accessing a computing application by a device operatively coupled to a processor; and a step 1104 of training, by the device, one or more machine learning models based on responses of the computing application to iterative fault-injections that are determined via reinforcement learning.SELECTED DRAWING: Figure 11

The present application relates to the field of aero-engine simulation technology, more particularly to a semi-physical simulation method and system based on a prediction model.The method comprises: collecting engine test data; identifying a transfer matrix of a state space of the prediction model according to the engine test data, the transfer matrix being used to describe the relationship between an input sequence and an output sequence; calculating matrix coefficients of the prediction model based on the transfer matrix; calculating a predicted value of the output sequence corresponding to the input sequence based on the matrix coefficients and current engine state quantities; and adjusting and updating the operating state of an engine physical system in real time based on the predicted value of the output sequence, so that the engine meets the expected performance.The present application provides high-precision prediction and control for the engine control system by constructing a real-time updated prediction model in combination with actual engine test data.The robustness and adaptability of the control system under fault conditions are enhanced by a fault injection simulation method which simulates various fault types.

This invention relates to the field of compressor testing and control technology, and more specifically, to a fault simulation testing and control system and method for reciprocating compressors. It addresses the problem that existing reciprocating compressor fault simulation testing and control systems often employ deterministic or simplified excitation methods for valve fault simulation, making it difficult to integrate dynamic operating conditions with real random disturbances, and thus failing to achieve precise and repeatable fault injection based on crankshaft phase. This invention integrates quantum random signals and the compressor operating condition spectrum through a valve quantum fault simulation module. By dynamically adjusting the disturbance and feature ratio through time-varying weights, it generates a high-fidelity, adaptive composite excitation. Based on preset fault types and crankshaft phases, features are injected at specified angles through phase window control, achieving controllable, repeatable, and highly realistic simulation of multiple types and phases of faults.

The present application relates to the technical field of energy storage system, and particularly to a BMS simulation verification method and platform based on fault injection closed-loop joint debugging.A BMS simulation verification method and platform based on fault injection closed-loop joint debugging, the platform comprises the following: a model management layer; a scene generation and scheduling layer; a fault injection layer; a closed-loop joint debugging layer; a result collection and evaluation layer; a report generation and backfilling layer.Compared with the prior art, through the combination of the model library, the scene library and the fault injection library, the virtual BMS is quickly verified under different objects, different working conditions and different fault types; through the closed-loop joint debugging between the battery model, the thermal management model, the actuator model and the communication model, the closeness of the verification result to the real system is improved; through a unified coverage, response quality and protection effect evaluation mechanism, the comparability and screening efficiency between different verification tasks are improved.

This invention discloses an embedded simulation training method for ship propulsion systems based on existing monitoring systems. This method defines four core steps—mode switching and isolation, command acquisition and uplink, simulation calculation, and parameter downlink and drive—and their synergistic effects to construct a stable and secure training data closed loop. This enables highly realistic and zero-risk embedded simulation training using the existing monitoring system's human-machine interface components, without using real propulsion equipment or interfering with the normal operation of the monitoring system. Furthermore, this invention defines a standardized command uplink and parameter downlink mechanism and integrates dynamic fault injection and intelligent evaluation functions, effectively solving the problems of incomplete training coverage, insufficient realism, and evaluation difficulties caused by reliance on advanced platforms and lack of methodological processes in existing technologies.

The embodiment of the application provides a kind of controller test system, the overcurrent protection method of controller test system, belong to test technical field.The system includes the controller to be measured, load module, arbitration module, host computer, control module and power module, wherein: the output end of the controller to be measured outputs first branch current;Arbitration module is arranged between the controller to be measured and load module, is connected with output end and load respectively, and outputs second branch current.Determine arbitration by at least one of first branch current and second branch current, when arbitration result of determination represents that system exists exception, generate control instruction, to make at least one of arbitration module and load module and the controller to be measured disconnected, can realize the real-time monitoring of the controller to be measured, abnormality determination and fast protection, improve the accuracy and reliability of test system, meet the demand of frequent fault injection test scene.

This invention discloses a model- and data-driven fault diagnosis method for deep space exploration spacecraft, belonging to the field of deep space exploration technology. Addressing the shortcomings of traditional methods in model adaptability, data utilization, and fault location, the method constructs a four-layer fusion architecture comprising the entity layer, model layer, data layer, and application layer of the deep space exploration spacecraft system, achieving dynamic integration and interaction between the mechanistic model and multi-source telemetry data. Through a mechanistic-data hybrid model, real-time system state prediction, fault injection simulation, multi-source data comparative analysis, and health status assessment are achieved. A corresponding software prototype has been developed, possessing functions such as fault mode library management, telemetry-simulation data-driven comparison, 3D visualization, and simulation verification of fault handling strategies. This method can effectively assist in the rapid and accurate location and handling decisions of on-orbit faults, improving the safety and reliability of deep space exploration missions.

A model is created of a system to be monitored. Operating states of the monitored system, including steady and transient states, are identified. Faults are injected into the model and the model is used to simulate each of the identified operating states. Results of each simulation are analyzed and used to develop one or more propagation-based fault detection and discrimination strategies that can be used to identify faults in each of the identified operating states. The strategies may further be used to select an optimal set of sensors to assist with fault detection.

This application discloses a fault injection method, a test case distribution method, and related apparatus. The fault injection method includes: acquiring test cases, wherein the test cases instruct a fault simulation device to execute a corresponding fault; executing the test cases to inject a fault into the hardware device under test; receiving an error code, wherein the error code is generated by a fault detection device on the hardware under test based on a test signal generated by the fault; and determining that fault injection is successful when the error code matches a preset result. Using the method of this application, fully automated fault injection is achieved through a fault simulation device. Compared to manual fault debugging in traditional hardware testing, this method offers higher testing efficiency and significantly reduces labor costs.

The application relates to a multi-processor module fault injection test device, and belongs to the technical fields of network communication, redundancy management and system test. The application can simulate all potential faults of processor modules and verify the performance of hot backup switching between the processor modules; a test equipment node sends a fault injection test case number to a tested equipment node, the tested equipment node executes a test script file with the corresponding number, can obtain all expected test intermediate running results of the tested equipment node in time, and can statistically calculate fault test coverage in real time; when the number of processor modules in the system is increased or reduced, the test code does not need to be modified, the system expansion is supported, and the system expansion has good adaptability.

The application provides a program instruction vulnerability evaluation method based on bit-level cloning, comprising the following steps: loading a target program to be evaluated as an input into an evaluation system; the evaluation system analyzes dynamic instruction groups of the program, determines clonable bit positions of each dynamic instruction group, including clonable SDC bit positions and clonable non-SDC bit positions; performing fine-grained bit-level cloning and fault injection on the clonable bit positions and other bit positions respectively to determine SDC vulnerability of each dynamic instruction. The application has the beneficial effects that: through the combination of bit-level cloning and fault injection, repeated operations are reduced, cost is lowered, bit-level accurate analysis is realized, differentiated evaluation of complex programs is supported, and quantitative basis is provided for high-reliability software design.

The present application relates to the technical field of artificial intelligence, and is applied to the financial insurance scene, and particularly relates to a performance anomaly simulation method, device, equipment and medium, wherein the fault injection configuration parameters corresponding to a target fault scene in a storage system are acquired, the fault injection configuration parameters include fault type parameters and fault control parameters, a preset hook function is used to capture I / O requests associated with a block device, the I / O requests carry read / write type identifiers, whether the I / O requests belong to the type of faults to be injected is determined based on the read / write type identifiers and the fault type parameters, if yes, the fault injection operation is performed on the I / O requests meeting the conditions based on the fault control parameters, so as to complete the performance anomaly simulation. It can be seen that, in the present application, the fault injection configuration parameters are acquired and the I / O requests are captured, whether to inject faults is dynamically determined based on the read / write type identifiers and the fault type parameters, and the fine fault injection operation is performed, so that the accuracy of the performance anomaly simulation is improved, and the stringent requirements of the financial industry on the performance anomaly test of the storage system are met.

This utility model discloses a pressure scanning valve with real-time fault injection simulation function. The top of the middle frame is connected to the upper cover, and the bottom of the middle frame is connected to the bottom cover. Multiple pressure sensor assemblies are arranged through the top of the upper cover, which also has a power supply interface, a communication interface, a simulation test interface, a network port, and multiple temperature measurement interfaces. The circuit board assembly is housed within the cavity formed by the middle frame and the bottom cover. The pressure sensor assemblies, temperature measurement interfaces, power supply interface, communication interface, simulation test interface, and network port are all connected to the circuit board assembly via cables. This utility model, through optimized structural design and functional integration, enables real-time simulation of various fault scenarios when the pressure scanning valve is used in an automated control system. This improves the fault diagnosis and handling capabilities of the pressure scanning valve and the automated control system working together, enhancing the overall reliability and stability of the system in complex application scenarios such as aerospace and industrial automation. It has significant technical advantages and engineering practical value.

The application discloses a kind of bus performance test method and system for electronic system, it is related to computer technology field, the method includes: constructing multi-protocol adaptive test excitation model;Simulate complex extreme operating environment stress;Perform cross-layer synchronous data acquisition of physical layer, protocol layer and application layer;Establish cross-layer fault diagnosis model;Quantify bus health status and generate evaluation report.The system includes modular protocol analysis engine, multi-physical field environment simulation unit, three-layer synchronous acquisition module, fault injection unit and multi-protocol hybrid topology support module.The present application aims to solve the problems of lack of real extreme operating environment factors in the prior art, poor protocol adaptation capability, lack of cross-layer fault diagnosis and inability to quantify health status, and can achieve high-fidelity full-dimension testing, multi-protocol adaptive switching and intelligent health assessment, significantly improving the correlation of test results and actual service status and the whole life cycle support capability of electronic systems.

The application provides an inertial platform fault injection and testing method based on redundancy technology, aiming at an inertial platform accelerometer height measurement and altimeter combined error feedback compensation height measurement system adopting redundancy technology, four faults of platform noise interference fault, platform large interference torque fault signal, altimeter noise fault and altitude redundancy error feedback fault, adopting a time injection function mode, combining an inertial platform mechanical motion model, a direct current torque motor model and a gyroscope measurement model established by a transfer function method, organically combining the above faults and signals into a closed loop closed system, effectively simulating the altitude measurement output signal of the redundancy technology based on the fault state, thereby realizing the fault injection simulation of the inertial platform system and realizing the equivalent function of the testing system.

This invention relates to the field of aero-engine control, and more specifically, to a single-event upset (SWE) system testing method and system. The SWE testing method proposed in this invention specifically includes the following steps: establishing a physical communication link between a test device and a device under test (DUT); the test device parses a test input file from the DUT to build an address space model; the test input file includes a user interface description, object code, and C language source code header files; the test device sends a fault injection command to the DUT using a bus-interactive communication method; the DUT receives the fault injection command, selects a corresponding injection method, and performs fault injection to conduct a SWE fault test; the test device records the injection results and generates a test output file. This invention achieves accurate injection of SWE faults using a software approach, significantly reducing testing costs and time.

The present application relates to a kind of machine learning code library memory fault injection vulnerability detection methods based on bit flip, comprising the following steps: S1, add extension function to programmable compiler, insert detection instruction to sensitive code in machine learning code library, to detect the code point position at risk with dynamic analysis method;S2, using machine learning model and data set under actual application scenario, collect running data, calculate and find risk sensitive code point position, i.e. the imbalance degree of sensitive instruction is calculated and analyzed, determine the risk sensitive instruction set vulnerable to memory fault injection vulnerability;S3, by injecting bit flip into actual memory hardware, obtain the fault injection vulnerability distribution profile of actual memory hardware;S4, match piece by piece, obtain vulnerability sensitive instruction set.The beneficial effect is to reduce or remove the risk and harm caused by tampering machine learning code library, ensure the security and integrity of machine learning model.

This invention discloses a fault assessment model construction method, device, terminal equipment, and storage medium, as well as a power inspection route optimization method, belonging to the field of power system operation and maintenance. The method comprises: simulating a digital twin model of the target power inspection scenario based on the grid topology data and the basic equipment parameters of each operating device in the target power inspection scenario; using a historical environmental perception dataset as the environmental condition input for a fault injection engine, driving the digital twin model to perform fault scenario simulation through the fault injection engine, generating original historical equipment operation data for each operating device; iteratively training a preset neural network model based on the original historical equipment operation data and the historical environmental perception dataset, and using the trained neural network model as the fault assessment model for the power inspection scenario. By implementing this application, the problem of existing power inspection routes not considering the fault risk status of operating equipment can be solved.

The application relates to the technical field of intelligent charging and discloses a charging pile test simulation system, which can input real-time test operation contents or / and test data contents, such as fault injection operations or / and fault recovery operations and real-time charging contents concerned by users, based on an interactive unit, so that the test depth and abnormal coverage capability are enhanced; a BMS data generation and sending module constructed based on a model unit can dynamically generate BMS demand data according to a pre-constructed virtual battery model in combination with a charging request instruction, so that not only is a closed-loop simulation interaction of the whole charging process realized, but also the dynamic characteristics of a charging battery can be maintained in the charging simulation process, the charging pile test provides strong tool support, and the simulation capability is weak, the function is single, and the operation is complex.

This invention discloses a semi-physical method and apparatus for fault diagnosis and fault-tolerant control of combined engines, belonging to the field of aerospace engineering technology. The method includes: a real-time simulator generating virtual data; the simulator injecting programmable faults and reconstructing fault channel data by weighted fusion according to a formula based on spatial neighborhood relationships; and a controller acquiring multi-source data and calculating based on the PCA algorithm. T2 Fault detection is performed using SPE statistics, the fault source is located through contribution values, and fault-tolerant control commands are generated within 20ms to achieve closed-loop control. The device includes a simulator, simulator, controller, test management system, and communication bus for performing the above steps. This invention achieves high-fidelity fault injection, hard real-time calculation and diagnosis, and multi-level fault-tolerant control closed-loop verification from sensor to system level, providing an efficient testing platform for combined engine health management.