334 results about "Test phase" patented technology

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 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 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 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 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 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 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.

Examples provide a system and method for dynamically improving and validating automation plans using generative artificial intelligence (AI). An automation manager analyzes automation plans during the design phase and the testing phase. The automation plan makes suggestions for improving the automation plan in real time using natural language prompts. The automation plan validates the automation plan against guardrails defining restrictions on the actions performed by the system during automation plan execution. The system generates explainability data describing the next planned actions and reasons why each planned action is selected for execution during the automation to increase user confidence in the automation. The system requests user approval prior to performing each action for more accurate and efficient workflow automation while reducing system resource usage consumed during execution of inefficient or ineffective automation plans.

The invention provides a satellite-borne router network access test system and a test method thereof. The satellite-borne router network access test system comprises a constellation network node simulation platform, a performance test evaluation platform, an interface protocol conversion device, a constellation service traffic simulator and a network router digital model. Through joint simulation of the virtual nodes and the physical nodes, a simulation test platform can be provided for design and optimization of the satellite-borne router through scene simulation of a complex satellite network environment in a design stage, and the development efficiency is improved; on the other hand, in the product development and system test stage, the full-constellation operation scene can be simulated, the function and the performance of the satellite-borne router can be assessed and verified in the full-constellation scene in the ground environment, the method is particularly suitable for the low-orbit large-scale batch emission large-scale networking scene, the test coverage and the test effectiveness of the product are greatly improved, and the test cost is reduced. Development risks of insufficient verification, delayed verification time and the like before launching are effectively released, and meanwhile, the test verification cost is reduced.

The invention belongs to the technical field of federated learning, and particularly relates to a personalized federated learning method for asynchronous optimization and prototype perception reasoning of a classifier. According to the method, an asynchronously updated double-classifier mechanism is designed in a training stage, a prototype perception technology is utilized in a testing stage, and the output weights of the two classifiers are adaptively calculated, so that the model can adaptively judge the confidence coefficient of personalized knowledge and generalization knowledge, and the reliability of the model is improved. Therefore, dynamic complementation and balance of the two are realized. In order to ensure that the features generated by the client feature extractors have global consistent semantic expressions, a bilateral prototype clustering strategy is introduced to generate a unified category prototype, and the client feature extractors are adaptively guided to update towards a consistent direction, so that the problem of performance degradation caused by domain migration is effectively relieved. According to the method, on the premise of protecting the data privacy, the multi-client collaborative challenge in the label offset and domain offset environment is effectively handled.

The utility model relates to a detection device, and provides a cable immersion pressure resistance detection device, which comprises a shell, a control platform, a cover plate, a water tank, a water injection pipe and the like, a control platform is arranged on the front side of the shell and composed of a control module, an instrument, a screen and the like, a cover plate is rotatably arranged on the upper portion of the shell, a water tank is arranged on the lower portion in the shell, a water injection pipe is arranged on the lower portion of the water tank, and the other end of the water injection pipe penetrates out of the shell. According to the utility model, a program is preset in the control module, when cables of different models are tested, test conditions are automatically matched according to set data, the data can be recorded and fed back in real time in a test stage, meanwhile, a closed test instrument is arranged, the test cables are separated from an operator in the test process, and the test efficiency is improved. And potential safety hazards during working are reduced.

The invention discloses a large-model-based auxiliary vehicle-mounted test case compiling method and device, and relates to the field of vehicle-mounted testing, and the method comprises a preparation stage and a testing stage; the preparation stage comprises a data acquisition and preprocessing step and an installation and deployment step; in the test stage, the method comprises the steps of generating a test case, adjusting and confirming the test case, executing and feeding back, generating a report and adjusting and optimizing the report. Wherein in the installation and deployment step, the preparation for generating the test case is in a standby state; and test case generation: calling the model to generate a preliminary test case. Through the above scheme, based on cloud deployment or / and local deployment, the client side or / and the server side are arranged, and an automatic processing mode of the vehicle-mounted test is formed. A large model is used as an important data processing means, data is efficiently processed, and a reliable test case is formed.

The invention provides a failure oscillation interval determination method, a temperature control method and related equipment, and the method comprises the steps: setting the width of a failure oscillation interval as the ith width at an ith test stage, obtaining the current chip temperature of a processor according to a preset period interval, and executing an error integral temperature control strategy to obtain a current frequency point corresponding to the current chip temperature, taking the current frequency point as an operation frequency point of the processor in the current period; monitoring whether the current chip temperature exceeds the target temperature or not in the ith test stage; if not, determining the target width of the failure oscillation interval according to the ith width, and further determining the lower limit of the failure oscillation interval. By formulating the failure oscillation interval when the error integral temperature control strategy is executed, when the chip temperature is in the failure oscillation interval, the updating of the integral error is stopped, so that the adjustment amplitude of the temperature is changed, the chip temperature is prevented from oscillating up and down near the target temperature, or the oscillation amplitude is reduced.

The invention relates to the field of memory management, and provides a DDR memory frequency switching test method and device. The method comprises the following steps: acquiring a plurality of preset frequency gears of the DDR memory; constructing a multi-stage test flow of at least two different switching modes; for each test stage, generating target data before executing the frequency switching action, acquiring actual data from the DDR memory in the process of executing the frequency switching action, performing consistency comparison on the target data and the actual data, and detecting whether the frequency switching process causes data hopping or not; performing reliability judgment on a corresponding switching mode of the DDR memory based on a comparison result of each test stage, establishing a fault association relationship among the plurality of test stages, and when any test stage detects data hopping, determining a potential frequency switching fault currently existing in the DDR memory; and carrying out collaborative verification on the actual data in different switching modes in the multi-stage test process to form a frequency switching test report. The frequency switching test reliability and test efficiency can be improved.

Techniques and apparatuses are described that implement a signal fingerprint. In an example aspect, a fingerprint module can monitor signals distributed between a host board and peripherals during an operation performed by the host board. The fingerprint module can generate a signal fingerprint that represents characteristics of the signals that correspond to the operation. With the signal fingerprint, the fingerprint module can improve user experience by protecting the electronic device from anomalous behavior. The fingerprint module can also use the signal fingerprint to improve the user experience and improve system performance through appropriate electronic device component selection. The disclosed techniques and systems can therefore provide electronic device operation reliability, protect sensitive data, and improve electronic device performance while reducing costs and time associated with the design and testing phases of such devices.

The invention relates to a wire harness quality prediction and evaluation method fusing historical data, and the method comprises the steps: collecting the real-time data of wire harness design, production and test stages, and equipment operation, image collection and defect classification parameters, obtaining the historical data of the same type of wire harnesses according to batch specifications, and building a mapping index to form a basic data pool; extracting and fusing features to construct a multi-dimensional matrix; establishing a failure rule set and a weight model in combination with historical cases; inputting a trained machine learning model to generate a quality prediction result; and supplementing new data to update related rules and models after abnormal traceability to form a closed loop. According to the invention, by fusing real-time and historical data and combining feature extraction, model training and closed-loop updating, accurate prediction and efficient fault tracing of the wire harness quality are realized, the evaluation system is continuously optimized, and the reliability and production applicability of wire harness quality evaluation are remarkably improved.

The invention discloses a battery health state prediction method based on variational feature extraction and composite kernel function optimization Gaussian process regression. The method comprises the following steps: firstly, collecting battery cycle data, extracting features by utilizing VAE, screening out an optimal feature set by adopting PCC, and jointly dividing the optimal feature set and SOH data into a training set and a test set; in the training process, the optimal modal number K of the VMD is determined through the envelope entropy, a composite kernel function CKFGPR model fusing a linear kernel, a radial basis kernel and a periodic kernel is constructed, and hyper-parameters are optimized through maximum likelihood estimation. In the test stage, the features are decomposed into K intrinsic mode components by using VMD, the K intrinsic mode components are respectively input into the CKFGPR model for prediction and reconstruction, and finally the CKFGPR model is input again to realize SOH prediction. According to the method, the feature robustness is enhanced through cooperative application of the VAE and the VMD, the fitting capability of the GPR to the battery degradation behavior is improved in combination with the composite kernel function, and the SOH prediction precision is effectively improved.

The invention discloses a multi-modal intelligent garbage detection method based on dynamic adaptive meta-learning, and the method comprises the steps: constructing a framework based on a Faster R-CNN two-stage detector fusing uncertainty estimation and multi-modal features, fusing a dynamic adaptive meta-learning mechanism, and supporting and querying a set to achieve robust adaptation through environment interaction; an enhanced garbage proposal module is designed, multi-modal feature fusion is adopted, and deep interaction with query features is supported; and constructing an advanced garbage classification module, and introducing a dynamic soft attention mechanism to realize space-semantic alignment. In the training stage, mixed meta-learning is adopted, an extended FSOD data set is combined with self-supervised pre-training, N-way K-shot subtask training is performed, meta-knowledge is acquired, and dynamic fine tuning is performed by using a labeled junk image in combination with real-time environment data. In the optimization stage, real-time detection of various types of garbage is realized in the test stage through a multi-task joint loss function supervision framework.

The invention relates to the technical field of intelligent terminals and network testing, in particular to an automatic testing system and method based on an AI large model.According to the system, parameters are configured and manually rechecked according to the testing type and the network environment, knowledge base data are retrieved through the RAG technology, an optimal testing case combination is dynamically generated in combination with the testing stage, the equipment model and the like, and the testing efficiency is improved. Testing of reliability, stability, performance and the like is automatically executed, key indexes are collected and re-checked by professionals after AI intelligent merging analysis, finally, a standardized report is output and fed back to a data optimization system and a knowledge base, a computing power-model-agent collaborative system is constructed, and automation of a whole test link is achieved; according to the method, the test period is shortened by more than 50%, the test precision and coverage are remarkably improved, the method is adaptive to multiple types of terminals and multiple scenes, test resources are optimized, it is ensured that results are objective and repeatable, and the method has sustainable evolution ability.

The invention relates to a test time training method based on invariant graph learning, and the method comprises the following steps: 1, a joint training stage, a joint training encoder fg, a main task classification head pi m and self-supervision task classification heads pi s1 and pi s2 are trained through a graph classification task and an auxiliary self-supervision task by using marked training set data, and the joint training stage is divided into two parts including invariant graph recognition and multi-level graph comparison learning; step 2, in a test time training stage, realizing self-adaption of the model on test data by minimizing the difference of feature distribution of a training domain and a test domain; and step 3, a test stage: in a model test stage, carrying out specific processes and strategies of model evaluation and fine adjustment by using a test sample. According to the scheme, through a test time training method, the model is finely adjusted by using label-free test data distribution, and the generalization performance of the model in a distribution offset scene is improved.

The invention discloses a multi-mode missing learning method based on dual-prompt cross-state alignment distillation and calibration adaptation, and belongs to the technical field of multi-mode learning. According to the method, various modal missing conditions can be effectively processed without depending on a complex modal reconstruction model, so that the calculation overhead and the storage cost are effectively reduced; the inter-modal shared structure is captured by fully utilizing scarce complete data, the inter-modal shared structure and task specific decision boundary knowledge are transmitted to an inference network through cross-state alignment distillation (feature level + prediction level), and the value of the scarce complete data is fully mined; according to the method, the model parameter efficiency is guaranteed, the performance of an incomplete multi-modal learning task is improved, and the method has good generalization ability for the unseen mode missing modes by combining a mask condition mixing module; meanwhile, the robustness of the model to the distribution offset is further improved through single-step calibration prompt adaptation in the test stage.

This invention discloses a control method, system, and medium for a DC offset compensation circuit of an optical transceiver driver chip, relating to the field of optoelectronic integrated circuit testing technology. The method includes the following steps: time-aligning the test waveform and bias trajectory of the optical transceiver driver chip; extracting the phase misalignment and amplitude jump between beats; and mapping the continuous changes to a timing conflict observation band for identifying beat overlap regions. Based on the phase misalignment trend of the timing conflict observation band, the beat overlap points of the DC offset compensation loop are determined, and an overlap beat index is generated based on the duration and polarity of the amplitude jump to identify interfering nodes. This invention achieves millisecond-level beat observation and microsecond-level overlap identification during the testing phase, accurately extracting interfering nodes and constructing a coupling strength map. Combined with beat rearrangement and energy unloading strategies, it suppresses nonlinear oscillations, reduces oscillation and overload risks, improves eye diagram quality and bit error rate stability, and enhances the accuracy and robustness of chip testing.

The invention aims to provide a dual-camera focusing and focus checking system based on a UVC mode, and the system achieves the automatic switching of an equivalent test distance between a main camera and an auxiliary camera through a cooperative control mechanism of an electric sliding rail type Chart platform and a teleconverter module. MTF threshold tables corresponding to different test stages are called according to different test stages of focusing, focus checking, final inspection and the like of the camera, so that the MTF values of the different test stages are compared; through adaptive focusing and focus checking of the double cameras based on the UVC mode, the cameras delivered to a user can work in an optimal use state.

The invention provides an interface checking method, belongs to the field of automobile electronic software development, and unifies interface naming specifications. Creating a software component model according to the interface naming specification; performing interface verification according to the software component model to ensure the interface consistency between the software components and avoid subsequent problems caused by interface mismatching; potential problems such as data type mismatching and parameter transmission errors are found in advance, restoration can be carried out in an earlier stage, and the later modification cost is reduced. The integration risk is minimized, normal and stable interaction between software components is ensured, and the workload and time cost in the integration test stage are reduced.

The application discloses a three-dimensional point cloud zero sample classification method and device based on a mutex cooperation network, which comprises the following steps: data set preprocessing, dividing the data set into visible category and invisible category samples, and obtaining semantic feature vectors of each category; constructing a mutex cooperation neural network, including a point cloud encoder, a mutex learning module, a double-branch learning module and a classification module; in the training stage, a mutex loss, a classification loss and a regularization loss function are used to update the gradient propagation, and the network is trained in an end-to-end manner; in the test stage, the double-branch features are fused, and are matched with the category semantic feature vectors to obtain a classification result. The application learns 3D features divergently through mutex learning, so that more discriminative parts of an object can be found clearly, and in order to enhance the learning features of these different parts of the object, further design is made through the utilization of a graph to propagate cooperation information between activation regions, so that the performance and accuracy of three-dimensional point cloud zero sample classification are improved.