482 results about "Test phase" patented technology

The invention discloses an electric power system abnormal remote signaling detection method based on a graph auto-encoder model, and the method comprises the steps: collecting measurement data of an electric power system, carrying out the preprocessing, obtaining a graph data set with an abnormal label, and dividing the graph data set into a training set and a test set; inputting the graph data in the training set into the graph auto-encoder model for training; after training is completed, abnormal score distribution is counted based on normal edge samples in a training set, a threshold value is set to serve as a follow-up judgment basis, and threshold value selection takes the accuracy rate and the recall rate on a test set as an adjustment and optimization target; in a test stage, image data in a test set are input to carry out edge feature reconstruction and anomaly scoring, anomaly judgment is carried out on edges in combination with a set threshold value, and a preliminary abnormal edge detection result is output; and the output abnormal edge detection result is input into the graph restoration module, the restored edge structure and edge features are output, the damaged remote signaling state in the power grid is restored, and the integrity of the graph structure and the operation credibility of the power system are improved.

The invention discloses a zero-sample industrial anomaly detection method based on knowledge distillation, and belongs to the technical field of image detection. The method comprises a training stage and a testing stage. In the training stage, normal industrial images and abnormal industrial images in any type of industrial products are selected; constructing a knowledge distillation network architecture which comprises a teacher model, a student model, an image encoder and a text encoder; training the teacher model by using the training set data, and transferring knowledge in the trained teacher model to the student model; and in the test stage, constructing an industrial anomaly detection model, and inputting the to-be-detected picture in the test set into the industrial anomaly detection model to obtain a detection result. According to the method, efficient zero-sample anomaly detection can be realized in industrial detection tasks with unknown categories and various anomaly forms, and a solution which is efficient, high in generalization and excellent in robustness is provided for industrial visual detection.

The invention discloses a method and system for testing a direct-current offset compensation circuit of an optical transceiving driving chip and a medium, and relates to the technical field of photoelectric integrated circuit testing, and the method comprises the following steps: carrying out the time alignment of a test waveform and an offset track of the optical transceiving driving chip, extracting the phase dislocation amount and the amplitude kick amount between beats, and carrying out the calculation of the phase offset amount and the amplitude kick amount; a continuous change result is mapped into a time sequence conflict observation band which is used for identifying a beat overlapping region; and on the basis of the phase dislocation trend of the time sequence conflict observation band, determining a beat overlapping point of the direct current offset compensation loop, and generating an overlapping beat index according to the duration of amplitude kick and the polarity direction for identifying an interference node. According to the method, millisecond-level beat observation and microsecond-level overlapping identification are realized in a test stage, interference nodes are accurately extracted, a coupling strength graph is constructed, and by combining beat rearrangement and an energy unloading strategy, nonlinear oscillation is inhibited, oscillation and overload risks are reduced, eye pattern quality and error code stability are improved, and chip test precision and robustness are enhanced.

The invention relates to a protocol fuzz testing method and system based on a long-life-cycle enumeration variable state. The method comprises the following steps: S1, a static enumeration declaration statement instrumentation analysis stage; s2, a short life cycle enumeration variable dynamic analysis stage; s3, a static assignment statement instrumentation analysis stage; and S4, a fuzzy test stage. The system comprises a static analysis module, a dynamic analysis module, a network IO module and a variation feedback module. According to the method, the source code of the protocol entity program to be tested is statically analyzed to capture distribution and use of enumeration type variables in the source code. State transition is represented by monitoring changes of enumeration variable value domains, and a corresponding state tree structure is constructed, so that stateful grey box fuzz testing is carried out on any protocol entity program to be tested under the condition that extra manual analysis is not needed.

The invention provides an aging test method and device of equipment, the equipment, a medium and a product, and relates to the technical field of laser test. The method comprises the following steps: acquiring a plurality of operation parameters of target equipment; determining the equipment performance stability of the target equipment based on the plurality of operation parameters; determining an aging test parameter combination for the equipment aging test stage of the target equipment according to the equipment performance stability; performing virtual verification of the aging test parameter combination on the target equipment to obtain an evaluation result; based on the evaluation result, correcting the aging test parameter combination to obtain a target aging test parameter combination; and according to the target aging test parameter combination, performing an equipment aging test on the target equipment. According to the invention, the accuracy of the equipment aging test is improved.

The invention discloses a method, a system and equipment for predicting the stability of integrated circuit test equipment and a medium, and belongs to the technical field of integrated circuit test. The method comprises the following steps: firstly, carrying out preprocessing and feature selection on historical data in an FT test stage, and adopting a Gaussian mixture model (GMM) to cluster and identify different operation condition clusters of a test machine; then, establishing a health state GMM reference for each working condition cluster, calculating a KL divergence value of a normal sample and the reference, and setting a dynamic anomaly detection threshold by 99.73% quantile of the KL divergence value; and finally, in real-time monitoring, calculating a KL divergence value of real-time data and a corresponding working condition cluster benchmark, and comparing the KL divergence value with a dynamic threshold value to realize accurate anomaly marking. The method effectively solves the problem of abnormal detection of the test data of the integrated circuit under complex and changeable working conditions, and improves the monitoring accuracy and working condition adaptability.

The invention particularly relates to a hydrogeological analysis system and method based on big data, and relates to the technical field of hydrogeological analysis, and the method comprises the steps: placing a new model and an old model in an A / B test stage, and carrying out the parallel processing of real-time data; performing automatic judgment according to a preset performance index, and deciding whether to upgrade the candidate model to a new production model; and applying the model selected after decision making to hydrogeological analysis to solve the problem of long-term prediction precision under dynamic change of the hydrogeological system. According to the method, dynamic threshold monitoring, K-S outlier sample examination, sub-model optimization and A / B test smooth iteration processes are constructed, and a mechanism and machine learning coupling model and parallel calculation are combined, so that the model drift identification delay is reduced, the prediction precision is improved, scenes such as underground water over-mining prevention and control and pollution emergency are effectively supported, and the prediction accuracy is improved. And an accurate and efficient scientific decision basis is provided for water resource management.

The invention discloses a zero-sample industrial defect detection method and device based on visual enhancement and a medium, and the method comprises the steps: collecting an industrial product image and a text semantic tag corresponding to the industrial product image, and constructing a training set and a test set; building a zero-sample industrial defect detection model based on visual enhancement, and training by using the training set; and inputting the test set into the trained model for reasoning and evaluation. The model is composed of a text encoder and an image encoder, and deep interaction and optimization of text and image features are realized by introducing a bidirectional cross attention mechanism, a multi-task fusion module and an image feature refining module. In the training stage, the model learns uniform defect features from part of industrial product categories; in the test stage, defect identification and positioning are carried out on the types of industrial products which are not contacted. According to the method, the dependence on manual labeling is effectively reduced, the adaptability and detection precision of the model in a complex industrial scene are improved, and the method has good generalizability and industrial deployment value.

The invention belongs to the field of characterization learning, and particularly relates to a prostate cancer diagnosis method based on a multimodal large model prompt learning mechanism. Comprising the following steps: step 1, data preprocessing; 2, key frames and similarity are calculated, and irrelevant editing is compressed; step 3, text and image alignment training; step 4, a test stage; according to the method, a similarity-based screening mechanism is provided, ultrasonic videos under coarse-grained labels are preliminarily screened under segmentation of a large model, and focus areas are focused on in time sequence; meanwhile, a pre-processing mechanism based on a large model is provided, and the influence of a large amount of irrelevant information existing in prostate ultrasonic image scanning on the model is compressed at a data end, so that the diagnosis effect of the model is improved.

The invention relates to a multi-sampling-rate soft measurement method based on progressive transfer learning, and the method comprises the steps: carrying out the partitioning of training data from high to low according to the sampling frequency at a training stage, and training a variational progressive transfer network model; taking the model as a generator of a generative adversarial filling network, training the generative adversarial filling network by using original training data, and realizing automatic filling of unsampled data; based on the filled data, performing block processing on the original data again according to the original sampling frequency from high to low, and training a new variational progressive migration network model as a soft measurement model; in the test stage, the soft measurement model is used for predicting quality variables, and a prediction result is quantitatively evaluated. According to the method, the generation model is fully utilized to fill up the unsampled data in the soft measurement modeling stage, so that the soft measurement model extracts more valuable data information, and the prediction performance of the soft measurement model can be effectively improved.

The invention provides an MES-based production line product quality test method and device, equipment and a storage medium. The method comprises the steps of obtaining product index information, data acquisition parameters and production order information; according to the production order information, equipment operation parameters are generated through the MES so as to control the production equipment unit to execute a production test; in the production test stage, the sensor unit is controlled to collect production test parameters of a product according to data collection parameters and send the production test parameters to the data transmission unit; and the MES compares the production test parameters with the product index information to obtain a production test result of the product. Real-time interaction between the MES software and hardware equipment is realized by simulating a real production environment and a real production process, various functions and performances of the MES software in the production process are comprehensively tested, and the reliability and stability of the software in practical application are ensured.

The invention discloses a digital-analog collaborative test method, which comprises the following steps of: in a parameter configuration stage, embedding a trigger mark into a preset vector row to generate a test vector, and writing the test vector into a digital board card; configuring a trigger event corresponding to the trigger signal and first delay time; in the test stage, the digital board card detects whether a to-be-executed vector line has a trigger mark or not; a trigger signal corresponding to the trigger mark is sent to the system board card; the system board card sends the trigger signal to a corresponding simulation board card, and the simulation board card determines first delay time and a trigger event according to the trigger signal; delaying the trigger event for a first delay time and then triggering; the digital board card delays a second delay time after sending the trigger signal and sends test data corresponding to the vector line to the to-be-tested device; in the triggering process of the triggering event, the end time of the second delay time is aligned with the end time of the first delay time. According to the invention, the efficiency of digital-analog collaborative testing can be improved.

Some examples of the present disclosure relate to risk analysis of test failures that occurred during a testing phase of a continuous integration pipeline. In one particular example, a system can detect a failure of a test during a testing phase of a continuous integration pipeline. The testing phase can involve executing a group of tests in a plurality of configurations prior to merging an update to source code into a code base of a software application. Based on detecting the failure of the test during the testing phase, the system can access historical data associated with prior executions of the test, determine a risk score associated with the failure of the test based on the historical data, and perform an action associated with the source code based on the risk score.

The invention discloses an automatic medium-pressure online detection and closed-loop control method for die steel, relates to the technical field of medium-pressure online detection, and is used for solving the problems that the probability of production deviation is increased and the precision of medium-pressure interval range adjustment is reduced due to abnormality discovery lag. Collecting a pressure fluctuation value and an off-center peak value to comprehensively judge whether the conditions are abnormal; when an abnormal instruction is generated, entering a pressure test stage, calculating a pressure scaling interval based on vibration deviation and fan frequency, adjusting a default pressure interval to obtain a new pressure control interval, and comparing the new pressure control interval with a pressure value; and when the temperature exceeds the range, the surface temperature uniformity of the steel billet is detected, a fault-tolerant proportional adjustment pressure scaling interval is calculated, a control interval is updated and subjected to secondary comparison, whether an abnormal instruction is eliminated or not is determined, production abnormity is found in time, the abnormity judgment accuracy is improved, the abnormity is found in time, and the dynamic adjustment precision of the pressure control interval is improved.

The invention provides a transmission system gear fault diagnosis method based on incremental learning, and the method comprises the steps: firstly collecting transmission system monitoring data through a sensor, constructing an incremental data set, and dividing the incremental data set into fault diagnosis tasks of different stages; constructing an initial model, and training the model based on the initial fault data; in the test stage, a generalized entropy index is defined to judge whether the fault is a new fault; when new fault type data appears, a small number of samples are randomly selected from the old type data and fused with the new type data to construct a training set, and in order to avoid forgetting of the model to the old type fault data, knowledge distillation is carried out on attention weight and old type prediction output during training; and when the generalized entropy index continues to judge that an unknown fault occurs, repeating the network training step to update the model, and finally realizing incremental learning of a fault mode. According to the method, continuous updating of the fault diagnosis model can be realized for streaming data, the state monitoring capability of the transmission system is improved, and a guarantee is provided for the service safety of a mechanical system.

The invention relates to a cross-domain few-sample fault diagnosis method based on a geometric perception coordinated penalty prototype network, and belongs to the technical field of fault diagnosis, and the method comprises the following steps: S1, dividing samples through employing vibration monitoring signals in a data set; s2, obtaining respective support sets and query sets through source domain samples and target domain samples, and generating meta-tasks used in training and testing stages; s3, extracting input sample features by using a feature extractor; s4, mining an internal geometric structure of the data by using an adaptive manifold mapping module (AMMM), and converting sample features to manifolds; s5, calculating to obtain a coordination penalty prototype HPP; s6, classification is carried out through a dynamic high-sensitivity distance DHSD, loss is calculated, model parameters are updated through back propagation, and training of the GAHPPN is completed; and S7, quickly adapting to the meta-task of the target domain through the trained GAHPPN model, and diagnosing the health state of the target domain sample.

The invention discloses a radar HRRP target open set identification method based on hierarchical prototype loss function constraint, and aims at improving the generalization performance of a model for known categories when a test set comprises targets which do not appear in a training stage in an open environment in RATR practical application, and improving the recognition efficiency of the model. And information about the relationship between the unknown category and the known category is provided while the unknown category is identified. Specifically, firstly, a category hierarchical structure is constructed based on prior knowledge to guide training and testing stages. Then, a hierarchical prototype loss (HPL) is proposed to constrain the consistency of the feature space distribution and the category hierarchical structure. And finally, performing prediction according to a hierarchical structure by using the trained prototype network so as to provide information of a relationship between an unknown category and a known category. Wide experiments on actually measured HRRP data verify the effectiveness of the provided method on open set identification.

The invention discloses a wiring detection method, device and equipment of an inverter parallel system and a medium, the inverter parallel system comprises a host and at least one slave, the wiring detection method comprises the following steps: when the voltage of the host reaches a target phase, obtaining a test phase of the voltage of the slave, and then according to the target phase and the test phase, determining the voltage of the slave according to the target phase and the test phase; a master-slave voltage phase difference is obtained; according to the voltage phase difference of the master and slave machines, the wiring result between the master machine and the slave machine is determined, whether the plurality of inverters in the inverter parallel system have the condition of dislocation wiring or not is judged, interphase short circuit caused by inconsistent phases of the inverters is avoided, and therefore it is ensured that the whole inverter parallel system can operate stably.

The invention provides a reinforcement learning-based distributed Android application automatic test method, which is executed by a plurality of agents in parallel: a) an independent test stage: each agent interacts with a tested application within a preset round duration, and executes the following operations: generating a state representation according to a current interface structure; selecting and executing actions based on a reinforcement learning strategy, and recording state transition and reward values; maintaining a global state set to track states found by all agents; b) an experience aggregation stage: at the end of a preset round duration, aggregating learning experiences of all agents to generate a global strategy, the learning experiences at least comprising a Q table and an action execution frequency; c) a strategy synchronization stage: distributing a global strategy to all agents as an initial strategy of a next time period; and repeating the steps a)-c) until the test is ended. Through distributed architecture design, a state similarity driven reward function and a regular experience aggregation mechanism, efficient exploration and test case generation are realized.

The invention is suitable for the technical field of driver software testing, and provides a driver software automatic testing method and platform based on an AI agent. According to the method, full-automatic operation of test management, equipment management and a test process of the driver software is realized, a complex environment of a bottom driver software test is flexibly coped with through an artificial intelligence technology, manpower required by the test is reduced, and the test quality and the test efficiency are improved. Meanwhile, by defining the test stage, the uncertainty degree of the artificial intelligence technology in the aspect of content generation is reduced, and the test stability is improved.

The invention provides a sequence perception attack-resisting method and system for a scene text recognition model, and belongs to the field of computer vision and countermeasure machine learning, and the method comprises the steps: S1, obtaining a data set and the information of the scene text recognition model; s2, converting the scene text recognition model into a test stage, and screening out input pictures which can be recognized by the model; and S3, constructing and executing an attack algorithm, generating an adversarial sample, and constructing a loss function to reduce the difference between the adversarial sample and the input picture. According to the method, the sequence prediction characteristic of the scene text recognition model is utilized, the attack success rate is remarkably increased, the disturbance amplitude is reduced, an efficient attack tool is provided for robustness evaluation of the scene text recognition model, and the method can also be used for existing frontier privacy protection and copyright protection schemes.

The invention provides a bearing fault diagnosis method and system based on a twin neural network under a small sample, and relates to the technical field of mechanical fault diagnosis and artificial intelligence. The method comprises the following steps: collecting X-axis, Y-axis and Z-axis vibration signals of a bearing, slicing, and generating a time-frequency grey-scale map through short-time Fourier transform to enhance feature expression; the method comprises the following steps: constructing same-class and different-class sample pair training sets, training by adopting a weight-shared twin neural network model which comprises two same sub-networks, and optimizing model parameters by calculating the Euclidean distance of sample pair features and combining a cross entropy loss function; in the test stage, unknown samples are matched based on One-shot and N-shot strategies, and the fault category is judged with the maximum similarity probability. According to the method, the accuracy of 95% or above is achieved under 70 training samples, the noise immunity and generalization ability under the small sample condition are remarkably improved, and the method is suitable for low-cost intelligent diagnosis of industrial equipment.

The invention discloses a zero-sample industrial defect detection method and device based on text guidance and a medium, and the method comprises the steps: obtaining an image and a text semantic tag of an industrial product, and constructing a training set and a test set; constructing a zero-sample industrial defect detection model based on text guidance, and training the model by adopting the training set; inputting the test set into the trained model for testing; wherein in the training stage, the model learns and extends to unified text prompts of other industrial products by utilizing defect information in part of types of industrial products; in the testing stage, the model can be used for testing the types of industrial products which are not trained, detecting whether the industrial products have defects or not and positioning the defects. According to the method, priori knowledge contained in the pre-trained multi-modal large model CLIP is fully utilized, so that the model can adaptively learn general text prompts for different objects, zero sample defect detection of various industrial products is realized, and the method can be widely applied to the technical field of computer vision.

The invention relates to the technical field of gas hydrate phase equilibrium tests, in particular to a gas hydrate phase equilibrium condition testing device and method under the normal pressure condition, and the testing device adopts a core framework integrating hydrate synthesis and phase equilibrium testing under the normal pressure into the same reaction kettle unit. And aiming at the functional difference of phase balance test under synthesis and normal pressure, independent high and low temperature control subsystems and pressure control modules are respectively arranged, so that the efficiency of a high-pressure synthesis stage is guaranteed, and the precision requirement of a low-pressure test stage is met. According to the testing method, a constant-volume gradual heating decomposition method is adopted, high-precision micro-pressure change monitoring is combined, and the phase equilibrium point of the hydrate under the low-pressure condition can be accurately captured. The problem that hydrate phase equilibrium experiment data in the area near the normal pressure is deficient is solved, and key data support can be provided for model verification and safety design.

The invention provides a training method and system for a vision-text pre-training model during open category testing based on double low-rank adaptation, and the method comprises the steps: embedding a double low-rank adaptation matrix in an upper sampling layer of a feedforward network in the vision-text pre-training model, namely, a base-class low-rank adaptation matrix and a new-class low-rank adaptation matrix, the low-rank adaptation technology utilizes a low-rank matrix decomposition method; training the model on base class data by using a base class low-rank adaptation matrix, and performing fine tuning through a cross entropy loss function; in the open class test stage, the trained base class low-rank adaptation model is used for predicting test data, and low-quality prediction data and potential new class data are screened out; gradually adapting to the data of the new category by adjusting the low-rank adaptation matrix of the new category; and completing a classification decision according to a joint prediction result of the base class and new class low-rank adaptation models. According to the method, the adaptability and accuracy of the model in an open category environment are improved, and classification tasks of known categories and classification tasks of unseen categories can be processed at the same time.

The invention discloses a secret key integrity verification method and system, a medium and a program product, and belongs to the technical field of secret key verification. The method is used for an SoC security system and comprises the following steps: an initialization stage: electrifying a load board of test equipment, and then releasing external global reset of a chip; in the verification stage, a secret key SM3 verification value programming test sequence is operated, and secret key integrity verification is carried out by using an SM3 algorithm; in the testing stage, a secret key SM3 verification value test is carried out, whether the secret key SM3 verification value test is passed or not is judged, if the secret key SM3 verification value test is passed, it is judged that the chip is a good product, other chip tests continue to be carried out, and if the secret key SM3 verification value test is not passed, it is judged that the chip is a defective product. According to the invention, the secret key stored in the OTP / eFuse component is verified through the SM3 security algorithm, and the verification value is stored in the OTP / eFuse component, so that the algorithm verification of the integrity of the secret key is realized, and the security and the reliability are greatly improved.

The invention belongs to the technical field of mechanical fault diagnosis, and discloses a rolling bearing small sample fault diagnosis method and system based on an online soft label Gaussian prototype network. The method comprises the following steps: collecting bearing vibration signals under different working conditions to construct a data set, dividing the data set into a meta-training set and a meta-test set, and splitting the data set into a support set and a query set; constructing a Gaussian prototype network model containing an embedding module, a prototype calculation module and a classification module; in the meta-training stage, soft labels are dynamically generated by adopting an online soft label strategy, and multi-task training is carried out in combination with hard label loss to obtain optimal parameters; in the meta-test stage, a Gaussian prototype is constructed based on a support set, classification is achieved by calculating the Euclidean distance between a sample and the prototype, and prototype parameters are finely adjusted to adapt to cross-working-condition diagnosis when feature distribution drifts. According to the method, label noise interference is effectively relieved, the diagnosis precision can still be ensured under a small number of labeled samples, and the model generalization ability and the diagnosis stability are remarkably improved.

The invention discloses a man-machine interaction language model output post-processing system supporting field-level score comparison and a rule engine and an optimization method. And the post-processing system cooperatively works through an information recording module, a score comparison module, a modification module, a manual check confirmation module and a data output module. According to the post-processing optimization method, a framework and a prototype software product are built according to the post-processing logic of the test stage and the post-processing logic of the working stage. According to the post-processing optimization method, firstly, a generation result and a structured demand are collected and marked, then the text quality is evaluated through BLEU and ROUGE, optimization and modification are carried out according to a scoring result, finally, the text is output according to a standard format and is in butt joint with an industrial system, and it is ensured that the text is accurate and available. According to the method, traceable, intervening and integratable high-quality post-processing of the output result of the language model is realized, and the requirements of complex task scenes in industrial application on the content, structure and quality control of the intelligently generated text are met.

The present invention provides a Turing-like double-blind machine-versus-human driving test system and method for an autonomous vehicle. The system comprises a road network, one or more target vehicles, a test vehicle, one or more communication networks, a target vehicle driving facility and a Turing-like test vehicle testing facility. The method comprises a startup stage, a capturing stage, a testing stage, an inspection stage and an assessment stage. The present invention creates a brand-new test method, and the method is simple and easy to implement, and perfectly solves the problems that existing test-field testing cannot compare human driving to assess the safety of autonomous driving, and public road testing is impractical and cannot provide sufficient evidence to prove the safety of autonomous vehicles.

The invention discloses a small sample HSI classification method based on prototype mask comparison and cross-stage feature refinement, and the method comprises the steps: carrying out the meta-task training in a source domain and a target domain in a crossing manner, carrying out the spectral dimension unification of samples of a support set and a query set in each meta-task, carrying out the multi-dimensional feature fusion resistant to the dependence of adjacent pixels, and carrying out the classification of the multi-dimensional features. Obtaining support features and query features; constructing positive and negative sample pairs representing a prototype under each meta-task, and performing prototype mask comparison through graph convolution; according to the method, feature redundancy elimination refining is carried out based on emphasis mapping of a cross-domain shared multi-layer perceptron, cross-stage feature refining is carried out on support features and query features through the multi-layer perceptron and directional calibration coordination, refined support features and refined query features are obtained, and different losses are optimized in two training stages; in the test stage, small samples of a target domain are used, and a K-nearest neighbor classifier is trained for classification prediction through features extracted after dimensionality unified mapping, a feature extraction module and a multi-layer perceptron in sequence.