69 results about "Optimal test" patented technology

The invention relates to the technical field of optical communication, and discloses an optical module adaptive test and rapid convergence method based on reinforcement learning, which can dynamically generate and execute an optimal test sequence for optical modules of different types or states through an off-line trained RL intelligent agent module, avoids redundant steps in a fixed process, and improves the test efficiency. On the premise of ensuring the test coverage, the test time is obviously shortened, and meanwhile, the detection probability of potential defects is improved; through the closed-loop test of the integrated RL intelligent agent module, the test action can be adjusted in real time according to the state of a single optical module, so that the test process can quickly adapt to the individual difference and process fluctuation of the device, the online quick convergence of the test strategy is realized, and the accuracy and stability of the test are guaranteed; and through online iterative optimization of the RL agent module, new data and new changes in the production process can be continuously learned, so that a test strategy is continuously evolved, and the optimal performance is kept for a long time.

The invention discloses a dynamic simulation test verification method and system for a pumped storage unit monitoring system, and the method comprises the steps: building a high-dimensional system state matrix of a pumped storage unit based on the physical parameters and structural features of a hydraulic, mechanical and electrical system of the unit, carrying out the dimension reduction of the high-dimensional system state matrix, and obtaining a dynamic simulation test result of the pumped storage unit; a dynamic simulation model of unit multi-physics field coupling is obtained; constructing a multi-dimensional parameter space based on the parameter sensitivity coefficient and the working condition boundary condition of the dynamic simulation model, and calculating optimal test point distribution through a high-dimensional point flow diameter algorithm to obtain a test scene library; based on the dynamic simulation model and the test scene library, obtaining a real-time monitoring signal sequence conforming to a monitoring system communication protocol; and based on the real-time monitoring signal sequence, signal acquisition, logic judgment and alarm control functions of the monitoring system are tested through an automatic test script, and a performance evaluation result of the monitoring system is obtained. The test comprehensiveness and effectiveness of the pumped storage unit monitoring system are improved.

The invention discloses a flora prediction and petroleum pollution remediation method based on machine learning. The method comprises the following steps: collecting multiple groups of experimental data of a diesel oil pollution sample treated by a microbial agent, extracting environmental factors, microbial community characteristics and target response variables to construct a training data set after missing value processing, abnormal value detection and standardized pretreatment, and importing the data set into a preset machine learning model to obtain a training result; carrying out feature learning, classification training and hyper-parameter optimization by adopting a GridSearchCV method in combination with 10-fold cross validation; evaluating the correlation between a target response variable classification result and the features through a multivariable Pearson's correlation matrix, and constructing an optimal test set; and finally, selecting an optimal prediction model according to a preset index. According to the method, the model training quality is improved through data preprocessing and correlation analysis, efficient flora prediction and algorithm application evaluation are achieved by means of multiple machine learning algorithms, scientific support is provided for petroleum pollution remediation, and remediation accuracy and efficiency are improved.

The invention discloses an intelligent test paper composition and scoring method and system based on a knowledge graph. The method comprises the following steps: S1, constructing a student knowledge graph state sub-graph; s2, constructing a question bank knowledge graph; s3, on the basis of a node embedding modeling method of an improved DeepWalk algorithm, performing joint training and low-dimensional representation learning on knowledge point nodes by utilizing a continuous bag-of-words model of multi-head context aggregation, and constructing a topic adaptation degree scoring index; s4, outputting an optimal test paper scheme set; s5, collecting a current answer record when the student completes the test paper; and S6, extracting a semantic feature vector and a behavior feature vector, constructing a fusion score feature vector, and generating scores of test paper subjective question answers. According to the invention, accurate test paper composition and multi-dimensional subjective question intelligent scoring for individual knowledge states of students are realized, the method is suitable for personalized learning evaluation and teaching feedback scenes in an education evaluation platform, and the method has the advantages of high personalization, fine feedback and automatic scoring.

The invention discloses a test paper generation method and system, and belongs to the technical field of intelligent education, and the method comprises the steps: obtaining student answer records, question-knowledge point mapping, a test question bank and knowledge text information, and constructing a knowledge point graph; constructing a student-question-knowledge three-layer heterogeneous graph, and predicting the answering performance of the students on the test paper; taking the answer expression as environment feedback input of reinforcement learning, taking a question set of the current test paper as a state, replacing questions in the test paper or keeping the questions as an action, determining a comprehensive reward value of the test paper in each dimension by constructing a multi-target reward function, and generating an optimal test paper through iterative optimization by taking maximization of the comprehensive reward value as a target; on the basis of the adjacency relation in the knowledge point graph, candidate test questions are selected from a test question bank to form a candidate sub-question set, and multiple sets of parallel test papers equivalent to the optimal test paper are generated through an equivalent question replacement strategy. Through the method, more efficient, reasonable and fair parallel test paper generation can be realized.

The present application relates to the technical field of power battery health state evaluation and abnormality identification, and particularly relates to a remote health state analysis and abnormality identification method for an electric bicycle battery, which comprises: applying a small signal active excitation under an admitted working condition and synchronously collecting to form an opportunity diagnosis excitation data window; developing time-frequency coupling modeling, including equivalent impedance, harmonic and intermodulation fingerprint, Koopman operator modeling and entropy coefficient difference, and generating a multi-domain response package, a physical invariant vector and an uncertainty matrix by constructing a spectral measure geometry distance with an optimal transmission; gating and layering standardization according to the geometry distance and consistency score, obtaining a health state estimation record and an abnormal event set by using a shape-constrained health mapping model; combining the mapping Jacobian and the dual potential, generating a next-period opportunity diagnosis excitation plan by using D-optimal test design and updating the population health manifold, so as to realize remote health evaluation and early abnormality identification across environments and devices and with traceability.

The invention discloses a multi-target test selection method and system under a test uncertainty condition based on E domination guidance. The method comprises the following steps of: firstly, explicitly modeling uncertainty in a test process by using a detection probability matrix and a false alarm probability matrix; secondly, establishing a multi-objective optimization model which takes the minimum test cost, the minimum missing report rate and the minimum false alarm rate as objectives and takes the fault detection rate and the fault isolation rate as constraints; introducing an E domination relation fused with the preference of a decision maker to improve a traditional Pareto domination criterion; on the basis, designing an E-GPSO algorithm fusing a genetic algorithm and particle swarm optimization to perform iterative search, and dynamically maintaining a non-inferior solution set by adopting an external file based on an E domination criterion; and finally, outputting an optimal test scheme set meeting the constraint and the preference. According to the method, the test cost and the diagnosis reliability can be effectively coordinated and optimized, the decision space is remarkably reduced, and the efficiency and the quality of testability design are improved.

The invention belongs to the field of integrated circuit testing, and discloses a Shmoo testing method and device and a storage medium. The method comprises the steps of determining to-be-optimized Shmoo test parameters of an integrated circuit and defining a search range; an optimization objective function is established, an initial test parameter set is generated, and initial test or simulation is executed to obtain initial fitness data; executing an iterative loop of the grey wolf optimization algorithm, calculating a fitness value of a current test parameter set in each iteration, identifying an optimal test parameter, a suboptimal test parameter and a third optimal test parameter, and updating an algorithm control parameter; updating other test parameters according to the position information of the three test parameters, and carrying out boundary processing on the updated test parameters to keep the test parameters in a predefined search range; and when the termination condition is met, outputting the optimal test parameter as an optimal Shmoo test parameter combination, thereby determining the performance boundary of the integrated circuit or generating a Shmoo graph, and realizing more comprehensive and accurate Shmoo test.

The invention provides an embedded space security analysis method and device, electronic equipment and a storage medium, and belongs to the technical field of network security, and the method comprises the steps: obtaining a target vector set based on a knowledge base of a to-be-tested RAG system; clustering the target vector set to obtain a topic cluster set, and for each topic cluster in the topic cluster set, calculating a vector center point of the topic cluster; generating a rejection set based on the vector center points of all topic clusters; determining an initial load document and an initial trigger query, and taking the initial load document and the initial trigger query as an initial test combination; based on the rejection set, performing iterative updating on the initial test combination through a greedy coordinate gradient algorithm to obtain an optimal test combination; and taking the optimal test combination as a test sample of the RAG system to obtain a test result, and obtaining a security analysis result based on the test result. According to the invention, the accuracy of RAG system security analysis can be improved.

The invention discloses a thermal out-of-focus compensation method and device, computer equipment and a storage medium, and the method comprises the steps: collecting a plurality of temperature values of at least one heating position of a projection device in sampling time, and obtaining target temperature data; according to the target temperature data and a preset focal length compensation model, obtaining an optimal current focusing position currently corresponding to a focusing motor of the projection device; the focal length compensation model is obtained by training based on test temperature data and a corresponding optimal test focusing position; acquiring a focal length compensation value of a focusing motor according to the optimal current focusing position; and adjusting the focusing position of the focusing motor according to the focal length compensation value. According to the method, through the established focal length compensation model, the real-time optimal focusing position of the focusing motor can be accurately predicted, meanwhile, the temperature change is monitored in real time, preventive fine adjustment is carried out before defocusing, the defocusing problem caused by the temperature change is effectively solved, and rapid and accurate self-adaptive focusing control is achieved.

The application discloses a system function test method, device, equipment and medium, and relates to the field of system test. The method comprises the following steps: acquiring a function description interface from a preset automatic script, and sending the function description interface to a matching bus; determining function information of a function to be tested in the function description interface by using the matching bus, and matching an optimal interface from all current tool description interfaces based on the function information and matching information defined in a preset function set; testing the function to be tested by using an automatic test tool corresponding to the optimal interface, and returning a test result to the automatic script. In this way, the method in the application can automatically match the optimal test tool to test the function to be tested of the system to be tested without manual packaging and adaptation of the tool, greatly reduces the time for selecting and packaging and adapting the test tool in the function test, and further improves the system test efficiency.

A system and method for sampling a flight envelope of an air vehicle under test. The method includes obtaining engineering models of the vehicle to identify how the vehicle behaves, obtaining empirical models through test data, and obtaining historical models of similar legacy aircraft. The method further includes ensembling the models into an integrated model and assessing the ensemble uncertainty at any particular test point, for a variety of aircraft conditions, to determine model reliability. The method includes determining the optimal order of test points based on local model uncertainty, testing the air vehicle at a point, revising the integrated model with that data and reassessing the uncertainty, and determining if a stop testing condition has been met, in which case the testing series is closed. The last calibrated integrated model could then be used to generate trusted data for any remaining required test using a certification by analysis method.

This invention belongs to the field of structural static testing technology, and discloses a method, equipment, medium, and terminal for controlling static deformation measurement errors. Under a given load mode, the static deformation of a structure is approximately expressed as a linear combination of a few contributing modes. The influence of structural parameter changes on static deformation is reflected in the changes in the contributing mode combination coefficients. The problem of monitoring structural static deformation is transformed into the problem of measuring the contributing mode combination coefficients. The measurement error of the contributing mode combination coefficients becomes the decisive factor in the static deformation measurement error. Based on the characteristic that the larger the contributing mode combination coefficient, the smaller the upper bound of the estimation error tends to be, the optimal test load corresponding to each contributing mode of the load to be measured is found sequentially. Then, the static test is carried out on the structure using the optimal test load. Finally, the static deformation of the load to be measured is calculated by indirect measurement, thereby realizing the control of the measurement error of the static deformation of the load to be measured.

The application relates to the technical field of chip intelligent testing, in particular to an amplitude modulation signal source scheme intelligent generation system based on vector simulation gating, which comprises a data acquisition module used for acquiring a response characteristic vector of a chip to be tested; a state inference module used for inferring an underlying state vector based on the response characteristic vector and a preset probability agent model; a risk calculation module used for calculating an uncertainty index based on the underlying state vector and a preset risk weight coefficient; a risk judgment module used for judging the risk level of the chip to be tested according to the uncertainty index and a preset risk threshold; a resource allocation module used for allocating a calculation time budget according to the risk level; a scheme generation module used for determining an optimal test scheme from a preset candidate scheme library within the calculation time budget; and a test execution module used for executing the optimal test scheme; and the application avoids wasting unnecessary time on a large number of healthy chips and significantly improves resource utilization efficiency.

The invention provides an automatic connection detection method compatible with multi-category metering equipment, and the method comprises the following steps: S1, forming a multi-dimensional feature vector of the metering equipment based on a multi-modal sensor; s2, constructing a multivariate interaction state tensor based on the multi-dimensional feature vector, obtaining the relative performance of the metering equipment in different feature spaces from multiple dimensions, generating a comprehensive response measure, minimizing the state error of the metering equipment, and obtaining an optimal strategy vector; and S3, converting the optimal strategy vector into a feature control code through feature mapping, matching the feature control code with a preset test process library to obtain an optimal test scheme of the current metering equipment, generating a nested structure vector of control logic, and controlling joint selection and test process execution. According to the invention, through fusion of the multi-modal information, the multi-dimensional features of the metering equipment can be fully extracted, and accurate distinguishing of different types of metering equipment is realized, so that the accuracy of identification and connection of the metering equipment is effectively improved.

The present application relates to the technical field of intelligent operation and maintenance, in particular to a rail transit low-voltage device adaptive testing and predictive diagnosis method and system. By applying electrical excitation and mechanical vibration stress to the device to be tested and collecting multi-dimensional time series data, then using a waveform analysis model to extract deep features to identify early faults, using a sequence prediction model to analyze the performance degradation trend, and based on this, dynamically generating an adaptive optimal test path through a reinforcement learning model. Finally, with the help of a domain knowledge graph, correlation reasoning is performed to generate a comprehensive diagnostic report containing fault root causes and maintenance recommendations. The present application deeply integrates artificial intelligence into the testing process, realizes the transition from passive measurement to active cognition, significantly improves the depth, efficiency and intelligence level of testing, and provides forward-looking and accurate protection for the reliability of rail transit low-voltage devices.

The invention relates to the technical field of software testing, in particular to a test case recommendation method, system and equipment. The method comprises the following steps: comparing a to-be-tested version code of a target application with a previous version code to obtain a difference code; inputting the difference code into a trained AI model to indicate the AI model to output an optimal test case suitable for the difference code according to the difference code and a pre-constructed knowledge base; wherein the knowledge base is obtained in the following mode: obtaining coverage rate data obtained based on the target test case, taking the target test case as a historical test case, associating the target test case with the corresponding coverage rate data, and storing the target test case in the knowledge base. Therefore, the problems that in the prior art, the test case maintenance cost is high, and the designed test case code coverage rate is low can be effectively solved.

The invention discloses a receiving sensitivity testing method and system based on a Bluetooth HCI command and conduction isolation, and relates to the technical field of wireless communication testing. The method comprises the following steps: constructing an electromagnetic shielding test environment, and carrying out system calibration in the test environment to obtain a power calibration value and an inherent loss value; measuring background noise power of each channel, and determining an optimal test channel and a power compensation factor in combination with a reference noise threshold; according to the Bluetooth communication protocol physical layer parameters and the target packet error rate, determining the number of theoretical transmitted data packets, and calculating a judgment threshold of the number of successfully received data packets; searching a critical attenuation value, iteratively adjusting the attenuation value of the programmable attenuator according to a judgment threshold value, and adjusting an attenuation step value according to the change rate of the number of successfully received data packets; and calculating the final receiving sensitivity based on the power calibration value, the inherent loss value, the critical attenuation value and the power compensation factor. By optimizing electromagnetic shielding, channel selection and three-stage scanning, the accuracy of receiving sensitivity testing is improved.

The invention relates to the technical field of voice customer service testing, in particular to an automatic testing method for a voice customer service system, which comprises the following steps of: acquiring multi-source data, and performing standardized preprocessing to form a standardized data set; constructing a multi-dimensional quantitative model, determining a core dimension classification rule and a test index standard, and performing iterative optimization through a multi-dimensional test configuration particle swarm intelligent optimization model to generate an optimal test configuration scheme; through a full-link test, collecting test data and extracting a core index, generating a system performance level and an optimization direction through a comprehensive evaluation model, and forming decision support data; constructing an abnormal root cause positioning model to mine an index association link, and positioning a system abnormal core cause; and integrating whole-process data to construct a traceable evaluation system, and outputting a quantitative evaluation result and optimized data. According to the scheme, the testing accuracy and efficiency of the intelligent voice interaction system are effectively improved.

This disclosure provides a method and system for large-scale model-assisted logic function simulation and verification for hardware design, relating to the fields of artificial intelligence and hardware design technology. The method includes: performing logical perception analysis on hardware design specifications to generate a structured design analysis report; based on the design analysis report and design specifications, using a generator agent to initially generate a testbench, obtaining an initial test platform and a reference design under test set; simulating the initial test platform and the reference design under test set, and verifying the initial test platform using a consensus verification mechanism based on confidence levels; iteratively refining the test platform using a corrector agent based on a structured reflection report to obtain the final optimal test platform; and automatically generating a retrieval knowledge base precisely aligned with hardware semantics using a reflexive domain knowledge mining method, achieving fully automated construction of the hardware domain knowledge base. This disclosure achieves fully automated system-level hardware design testbench generation and verification.

The present application relates to the technical field of pre-diagnosis and health management, and specifically discloses a transmission performance test method for 100GNRZ direct modulation long-distance transmission optical signals, comprising the following steps: S1: configuring parameters of an OTN device, pre-setting test points, obtaining data received by the test points, calculating bit error rate and packet loss rate and selecting optimal test points; S2: setting rotating speed gears, adjusting according to the rotating speed gears, obtaining bit error rate and packet loss rate, obtaining the limit rotating speed of a polarization scrambler based on the bit error rate and packet loss rate of the optimal test points; S3: setting the rotating speed of the polarization scrambler to zero, making the rotating speed between two rotating speed gears cyclically jump, obtaining the jump interval at the end, and analyzing based on the limit rotating speed and the jump interval. Through the analysis of the bit error rate and the packet loss rate, the performance model of the device is constructed, so that the OTN device can always maintain an efficient and stable data transmission state in a complex and variable actual network environment.

The embodiment of the invention relates to an optimal test case selection method based on the multi-dimensional correlation degree of test cases. Methods, systems, and non-transitory processor-readable storage media for selecting systems for test relevance are provided herein. An example method includes executing a plurality of test cases on a system. A test relevance selection system analyzes relevance between executed test cases by checking results of execution of a plurality of test cases to create a test case set relevance degree matrix. The test correlation selection system selects a subset of the plurality of test cases based on the test case set correlation degree matrix for execution on the test system to optimize the test coverage of the plurality of test cases.

The invention provides a self-adaptive power control method for phased-array antenna testing, which can solve the problems that the input power is difficult to dynamically determine, the testing safety is insufficient and the precision is restricted by the signal-to-noise ratio due to inconsistent channel gains, temperature drift and frequency point difference in the phased-array antenna testing. The method comprises the following steps: presetting a maximum input power threshold value and a minimum signal-to-noise ratio threshold value; excitation is started from absolute low initial power; detecting the input power in real time through a feedback path and judging whether the input power exceeds the limit; if so, carrying out an air interface radiation test and evaluating a received signal-to-noise ratio; and if the signal-to-noise ratio is insufficient, iteratively increasing the power until the power reaches the standard, locking the optimal test power, and then starting a formal test. According to the application, full-automatic safe adaptation and accurate optimization of the test power can be realized, and the safety, reliability and measurement accuracy of the test process are remarkably improved.

The invention discloses a bevel gear power closed transmission system variable speed loading optimization method, and belongs to the field of gear transmission system loading test method optimization. The problem that according to an existing variable speed loading method, constant load loading or simple program control step loading exists, and consequently loading time is long is solved. According to the method, the dynamic characteristics of the bevel gear closed power system are analyzed, and a novel dynamic characteristic value is calculated by collecting a vibration signal and a vibration acceleration signal of the system. The optimal test loading sequence is determined by ingeniously applying a quantum particle swarm optimization method, and the method is mainly applied to the bevel gear power closed loading test.

This application discloses a linear actuator test bench, relating to the field of linear actuator testing technology. It includes a test bench body, a loading device fixed to its upper end, a test rod mounted on one side of the loading device, a weight rack fixed to the side of the loading device away from the test rod, an indicating device fixed to the upper end of the test bench body, an actuator body mounted on the upper end of the test bench body, a power supply chassis mounted on the side of the test bench body, a control platform fixed to the upper end of the power supply chassis, and an installation structure for quick assembly and disassembly of the actuator body on the upper end of the test bench. This installation structure enables rapid assembly and disassembly of the actuator body, greatly shortening clamping time, and significantly improving overall testing efficiency, especially in batch testing scenarios. Simultaneously, the automatic centering calibration function ensures that the actuator is in the optimal testing position during each test, effectively improving the accuracy and repeatability of the test results.

The utility model relates to a multidimensional force sensor testing device, which comprises a bottom plate, a multidimensional force sensor body, a mounting mechanism, a connector and a tester, and is characterized in that the multidimensional force sensor body to be tested is placed in a mounting groove of a mounting disc, a push plate is pushed to move through two air cylinders, and the push plate drives a moving plate to move, so that the mounting disc moves; an air cylinder pushes a push plate, a driving piece controls a mounting disc to rotate, the sensor is adjusted to the optimal testing angle, an electric push rod drives a contact plate to press downwards, the contact plate is tightly attached to the contact face of the top of the sensor, the actual stress condition is simulated, and after the sensor is stressed, an electric signal is output and transmitted to a detector through a connector. The detector processes signals in real time and displays test data on the digital display screen, and if the detector does not display data, the detected multi-dimensional force sensor body fails, so that whether the multi-dimensional force sensor body operates normally or not is judged.

The invention discloses an automatic driving function test system, method and device based on vehicle-road cloud integration, and the system comprises a test management module which is used for configuring initial test parameters, a test scene and an automatic driving model, completing the initialization of each stage of test passing standard and maximum test times, and issuing a test starting instruction; the reinforcement learning module is used for adjusting the initial test parameters based on a reinforcement learning algorithm to obtain optimal test parameters, replacing the initial test parameters in the test starting instruction with the optimal test parameters, and issuing the updated test starting instruction to the simulation test module; the simulation test module is used for calling the scene library to execute a simulation test, and synchronizing the optimal test parameters to the cloud when the test frequency is smaller than the maximum test frequency and the test result meets the standard; and the HIL test module is used for carrying out HIL test by utilizing the optimal test parameters and the automatic driving model, and generating an OTA deployment package for real vehicle test when the test times are smaller than the maximum test times and the test result meets the standard.

The invention discloses a testability diagnosis strategy generation method and system based on a correlation model, and relates to the technical field of testability engineering.The method comprises the steps that a multi-signal correlation model containing functions, faults and test signals is constructed, a correlation matrix is generated, test points are optimized through an information gain greedy algorithm, a test point optimization set is obtained, and the test point optimization set is obtained; and automatically generating a diagnosis strategy, then performing testability parameter simulation prediction, comparing a predicted value with a distribution index to generate a verification result, and when the verification result is not passed, triggering a closed-loop iterative optimization mechanism to perform optimization adjustment until the predicted value meets the distribution index, and generating a diagnosis optimization strategy. According to the method, the technical problems that index distribution and engineering practice are disjointed and diagnosis scheme design and verification links are separated in complex equipment testability design are solved, and the technical effects that complex equipment testability index distribution fits the practice, a diagnosis scheme and verification form collaboration and can be dynamically optimized, and later reworking is avoided are achieved.

The present application relates to the technical field of silicone key conductivity test, and discloses a silicone key conductivity reinforcement learning test system and method, wherein the silicone key conductivity reinforcement learning test method comprises the following steps: constructing a silicone key conductivity test environment; establishing a test knowledge base, extracting general feature representation of key conductivity performance through feature mapping and domain adaptation algorithm; constructing a test parameter optimization model, modeling the test process as a Markov decision process, and learning the optimal test strategy based on a reward function; adjusting the test parameters in real time during the test process, performing reliability analysis after obtaining the test results, and feeding back the new test experience to the knowledge base to realize the accumulation and reuse of test knowledge; the present application realizes the self-adaptive optimization of test parameters and the cross-key knowledge transfer by fusing reinforcement learning, transfer learning and meta-learning technology.

The invention discloses an antenna bandwidth extension optimization method and device which can be used in the field of railway communication, and the method comprises the steps: obtaining geometric parameters of a to-be-optimized antenna, extracting data features of the geometric parameters, and obtaining a feature data set; after the feature data set is subjected to normalization processing, a learning label is added to each group of data features in the feature data set; determining the plurality of groups of data features added with the learning labels as a plurality of groups of sample sets, and for a ridge regression model, a polynomial regression model and a random forest model, training each model by using each group of sample sets; and constructing a feature set according to the resonance bandwidth response value predicted by each model and the multiple groups of sample sets, performing intensive training on each model by using the feature set, determining a model with an optimal test result, and optimizing antenna bandwidth extension by using the model with the optimal test result. The antenna design optimization cost can be reduced, and the antenna performance can be improved.