322 results about "Testbed" patented technology

Disclosed are a high-performance loosely-coupled multi-modal data fusion system for a smart driving environmental perception system and a vehicle-mounted device, comprising: a fusion detection model based on a modality-independent feature interaction strategy, which is configured for converting a LiDAR point cloud, a camera image, and a millimeter-wave radar point cloud into a unified bird's-eye view representation, and performing multi-modal fusion; and a fusion tracking model based on a motion-appearance feature cascaded coupling data association strategy, which is configured for performing subsequent trajectory tracking and matching according to multi-modal fusion feature information. A VoD data set and a K-Radar data set are selected for training, verifying, and testing the comprehensive performance of the models, and a TensorRT accelerated inference model is applied, then quantized, and deployed to a vehicle-mounted computational testing platform. The present invention is compatible with mainstream sensor deployment solutions, and achieves the efficient complementary fusion of multi-source heterogeneous sensor information, significantly improving the reliability, accuracy, and adaptability of vehicle-mounted perception systems, thereby effectively responding to extreme operating conditions such as complex traffic scenarios and inclement weather.

An Edge-Client Collaborative Federated Graph Learning with Adaptive Neighbor Generation is provided. To promote the information flow in edge-client collaboration and extract more generalized potential relationships between clients. In SpreadFGL, an adaptive graph imputation generator incorporated with a versatile assessor is first designed to exploit the potential links between subgraphs, without sharing raw data. Next, a new negative sampling mechanism is developed to make SpreadFGL concentrate on more refined information in downstream tasks. To facilitate load balancing at the edge layer, SpreadFGL follows a distributed training manner that enables fast model convergence. Using real-world testbed and benchmark graph datasets, extensive experiments demonstrate the effectiveness of the proposed SpreadFGL.

A quantum-key distributed (QKD)-enabled communication architecture it devises for networked microgrids (NMGs). A real-time QKD-enabled NMGs testbed built in an RTDS environment, and a novel two-level key pool sharing (TLKPS) strategy it designs to improve the system resilience against cyberattacks. In the QKD-based microgrid testbed design there is used a real-time power system simulator, i.e., RTDS, including the QKD modeling, hardware connection, communication network design, and QKD integration. By integrating QKD features into a real-time microgrid simulator, this testbed offers a flexible and programmable testing environment for evaluating the performance of QKD-enabled microgrids under a variety of scenarios.

A new multi-edge smart community system consisting of communication, computing, and energy harvesting models, where the task execution delay and energy consumption are formalized as the optimization objectives under multiple constraints. For single-edge scenarios, we propose an improved twin-delayed DRL-based algorithm. For multi-edge scenarios, we develop a novel personalized FL-based training framework for DRL. Using the real-world settings and testbed, extensive experiments are conducted to validate the effectiveness of the proposed PFR-OA. The results show that the PFR-OA achieves better trade-offs between delay and energy consumption and exhibits higher task execution success rates than benchmark methods under different scenarios. Notably, the PFR-OA reaches a faster convergence speed compared to advanced DRL-based and FRL-based methods. Moreover, we further verify the practicality and superiority of the PFR-OA via real-world testbed experiments.

A QoS-aware service migration method in an IoV system based on CVX deep reinforcement learning is provided. Firstly, the optimization problem of service migration and resource allocation is decoupled into two sub-problems; then, a new actor-critic-based asynchronous-update deep reinforcement learning method is designed to explore the optimal service migration, where a delayed-update actor makes decisions of service migration and a one-step-update critic evaluates the decisions to guide the direction of the policy update; and on this basis, an optimal resource allocation method for an MEC server based on convex optimization is proposed to achieve the optimal resource allocation. According to the QoS-aware service migration method, extensive experiments are conducted based on a real-world testbed and a dataset of city vehicle trajectories, thereby verifying the feasibility and effectiveness of SeMiR. Compared with benchmark methods, the SeMiR has the best performance of service migration under various scenarios.

The invention relates to an online multi-dimensional comprehensive test evaluation method for an automatic driving test. The method comprises the following steps: constructing a test scene library; constructing a test scene complexity model; building an intelligent driving joint simulation test platform, and embedding the intelligent driving algorithm into the intelligent driving joint simulation test platform; constructing an automatic driving test multi-dimensional evaluation index system for performing multi-dimensional performance evaluation on the automatic driving vehicle; an intelligent driving joint simulation test platform is utilized to obtain vehicle test data, an evaluation index system and a test scene complexity model are combined to calculate objective evaluation index weights, then comprehensive performance quantitative scores are calculated, and finally an automatic evaluation report is output and obtained. Compared with the prior art, the subjectivity of manual evaluation can be reduced, and the evaluation efficiency of the automatic driving vehicle is improved; comprehensive and objective quantitative scoring can be carried out on the multi-dimensional performance of the automatic driving vehicle, and the influence of different test scenes on the scoring difference of the automatic driving vehicle is reduced.

The invention discloses a big data prediction model intelligent ammonia spraying control method and system suitable for kiln flue gas denitration. According to the ammonia spraying control method, historical and real-time data of multiple parameters such as the fuel gas flow of the glass kiln are collected firstly, the NOx amount is predicted through modeling of the LSTM-GRU hybrid neural network, the ammonia spraying amount is calculated through self-adaptive control, and the accuracy is ensured through two-stage correction. And the calculated ammonia spraying amount is transmitted to a production master control system to adjust an ammonia supply valve, and automatic alarm and manual control are switched in case of failure. The system comprises a data acquisition module, an intelligent prediction module, a self-adaptive control module and the like, and further comprises a dynamic catalytic reaction simulation test platform for optimization. According to the invention, intelligent automatic control of the big data model is realized, the ammonia spraying amount is accurately adjusted, the denitration efficiency and the ammonia utilization rate are improved, the operation cost is reduced, and the system reliability and stability are enhanced.

The invention belongs to the field of automatic driving test, and provides an end-to-end automatic driving system closed-loop confrontation test method based on a world model, and the method comprises the steps: building an end-to-end automatic driving system test platform based on the world model, providing end-to-end automatic driving system perception input information, and carrying out the modeling of a camera sensor, the accurate alignment among the multi-modal scene information is realized; constructing a traffic flow module, and providing map and scene global state information; a traffic vehicle multi-agent collaborative confrontation strategy balancing strategy convergence and strategy diversity is designed, a dense reward function is constructed and matched with an agent heterogeneous strategy adaptive adjustment method, a global exploration target is planned as a whole, and the test efficiency is improved; all the modules are integrated, an end-to-end automatic driving system to be tested is integrated, and efficient closed-loop testing is achieved. According to the method, efficient testing of the performance of the end-to-end automatic driving system can be achieved, the robustness and safety of the end-to-end automatic driving system can be evaluated, and functional defects of the system can be rapidly excavated.

The invention discloses an intelligent automobile interpretable abnormity diagnosis method and system, and relates to the technical field of intelligent traffic. The method comprises the steps of collecting multi-dimensional sensor data based on an intelligent automobile test platform, and constructing a directed causal graph and a causal adjacency matrix which are used for describing a causal relationship between the sensor data; designing a causal constrained graph attention mechanism based on the causal adjacency matrix, and constructing a causal constraint enhanced graph attention anomaly diagnosis model; and based on the directed causal graph and the graph attention anomaly diagnosis model, constructing a hierarchical anomaly diagnosis strategy integrating a feature reconstruction error, a variable causal relationship and a graph attention network weight, positioning an anomaly root cause and identifying a propagation path of the anomaly in the sensor network. According to the invention, the problems of false correlation and lack of exception explanation ability of graph attention network learning in the prior art can be overcome, and reliable exception detection and root cause diagnosis of intelligent automobile multi-sensor data are realized.

The invention belongs to the technical field of fuel cells, and particularly relates to a high-dimensional multi-target multi-working-condition optimization method and system for a fuel cell centrifugal air compressor, and the method comprises the steps: constructing a fuel cell air compressor performance analysis and optimization system, a comprehensive performance test platform is built, a multi-physics field coupling CFD simulation model is built, and the simulation and optimization efficiency is improved in combination with a machine learning algorithm; the pressure ratio and isentropic efficiency are defined as optimization targets based on fuel cell system requirements, and the performance of the air compressor is evaluated through experiment and simulation data; a multi-objective multi-population optimization method, an archive sharing technology, a genetic algorithm and the like are fused to establish an MMPS algorithm, and high-dimensional multi-objective optimization is carried out on related structure parameters of an impeller, a volute and a diffuser. The technical problems that the multi-target collaborative optimization requirement of an existing fuel cell centrifugal air compressor is difficult to meet, the high-dimensional variable optimization difficulty is large, and complex flow characteristic control is difficult are solved.

A method is provided that is performed by a first node of a fat tree network for management of a plurality of traffic flows having differentiated service requirements. The method includes receiving, from a simulation model or a testbed environment, joint observations for the traffic flows. The traffic flows correspond to routing paths comprising different combinations of at least one leaf node, at least one spine node, and at least one super spine node of the fat tree network per routing path. The method further includes identifying, with a first reinforcement learning model, a first action to take to reduce or prevent congestion at the first node. The first action includes a reconfiguration of the first node for an identified routing path. The method further includes outputting, to a controller node, the reconfiguration of the first node.

The invention relates to a simulation test platform for a 1553B bus of a spacecraft, which is suitable for stand-alone test and system test of a 1553B bus interface of a satellite model, and comprises an application layer, a communication layer and a data interface connected with the application layer and the communication layer, the application layer comprises a main control module, a database module and a user interaction module; the communication layer comprises a non-periodic data communication module and a periodic data communication module. The method can be suitable for ground tests of multiple satellite models at the same time, the research and development cost is saved, great convenience is brought to the satellite ground tests, and therefore the development progress of the satellite models is effectively guaranteed.

The embodiment of the invention provides a method and device for evaluating the health state of a front-end isolated switching power supply of an aging table, and relates to the technical field of aging tests.The method comprises the steps that in the aging test process, the front-end isolated switching power supply of the aging testbed can generate monitoring signals such as voltage and current; a directly measured monitoring signal is large in data size and contains a large amount of redundant information, firstly, feature extraction is conducted on directly measured data, and a feature sequence with high information density is obtained; further spatial mapping is carried out on the feature sequence by using a neighbor component analysis algorithm, and automatic segmentation of the health state and the degradation state of the new test sample is realized; and performing quantitative calculation of the health state on the mapped feature sequence by using a multi-distance measurement fusion algorithm with automatic weight optimization, and completing health assessment of the front-end isolated switching power supply of the aging test stand.

The invention relates to the technical field of edge computing, electric automobile testing and the like, and provides an electric automobile instrument testing method based on end-cloud collaboration, which comprises the following steps of: constructing a lightweight virtualized resource isolation environment at an edge computing node, loading signal generation, communication agency and state monitoring micro-service; a test platform with elastic capacity expansion and contraction and fault self-recovery capability is formed; historical test data are collected at a cloud end, and an equipment health degree prediction model is trained and deployed to an edge node to support a local intelligent test; constructing a dynamic test service chain, generating and pre-distorting and compensating an enhanced test signal, and then acting the enhanced test signal on the instrument; through multi-modal signal acquisition and unified preprocessing, in combination with wavelet packet decomposition and a deep neural network, high-dimensional feature extraction is realized, a test report containing a health trend is finally output, and a test process is actively intervened based on a trend prediction result. According to the method, the authenticity of test signals, the health assessment precision and the safety and efficiency of the test process are effectively improved.

A Collaborative Caching Framework for Multi-edge Systems with Robust Federated Deep Learning is provided. First, we design a new partitioning mechanism for multi-dimensional cache space, enabling precise content recommendations in user classification intervals. Next, we develop a VQ-VAE-based accurate prediction for content popularity by overcoming posterior collapse. Finally, we create a new training mode and proactive cache replacement strategy based on robust federated deep learning. Specifically, residual-based detection for adversarial model updates and similarity-based federated aggregation are integrated to avoid the model destruction caused by adversarial updates, which enables the proactive cache replacement adapting to optimized cache resources and thus enhances cache performance. Using real-world testbed and MovieLens datasets, extensive experiments verify that RoCoCache achieves higher cache hit rates and efficiency than benchmark methods while ensuring better robustness. Moreover, we demonstrate the effectiveness of the components designed in RoCoCache via ablation experiments.

The invention discloses a volute spiral spring quality testing device for an aero-engine, and relates to the technical field of sample testing, the volute spiral spring quality testing device for the aero-engine comprises a testing machine body, and a testing platform of the testing machine body is provided with a testing mechanism used for installing and testing various samples. When a fatigue test is carried out on a volute spiral spring sample, the positions of the inner end mounting assembly and the outer end mounting assembly can be adjusted through the driving part according to the shape and size of the sample, so that the device is suitable for test mounting of the sample, does not need to be replaced and is convenient to use, the mounting time of the sample fatigue test is saved, and the sample test efficiency is improved; the sample testing device can be suitable for testing all samples within the adjusting range of the inner end installation assembly and the outer end installation assembly, the detection range of sample testing is widened, the functionality of the sample testing device is improved, and the technical problem that the functionality of a volute spiral spring sample testing device for an aero-engine is low is solved.

The invention provides a flight space cognition test platform and method based on multi-modal data fusion, and relates to the technical field of data processing, an evaluation task program module is obtained, real-time synchronous data sampling is performed through an eye movement tracking module and an fNIRS monitoring module, flight space environment multi-modal data is transmitted to a data fusion and analysis module, and the flight space cognition test platform and method based on multi-modal data fusion are obtained. And according to the data fusion and analysis module, designing a data synchronization and fusion algorithm model, determining a multi-modal data machine learning model, carrying out synchronous fusion on the flight space multi-modal feature data, evaluating the flight multi-modal feature fusion data, and obtaining a flight space cognition test result. The technical problems of inaccurate flight space cognitive test result and insufficient coverage in the prior art are solved. The technical effect of improving the accuracy and reliability of the flight space cognitive test result is achieved.

The invention discloses a data processing method and device, relates to the field of data processing, and is used for solving the problem of low efficiency of manually writing a test case. The method comprises the steps that recording operation on a first interface of target equipment is started, interface element information of the first interface is obtained, the interface element information comprises position information of all elements presented in the first interface, in response to operation of a user on the first interface, a target element corresponding to the operation is determined, and the target element is recorded. And generating first information according to the position information of the target element, the operation type of the operation and the operation parameters, and sending the first information to a test platform. Through the scheme, the interface elements and the operation information (test cases) can be automatically recorded.

The invention belongs to the technical field of unmanned aerial vehicle testing, and discloses an air-ground unmanned aerial vehicle wind resistance performance testing platform based on a physical information neural network. The air-ground unmanned aerial vehicle wind resistance performance test platform is composed of a wind field simulation system, a physical information neural network control system and an unmanned platform indoor positioning system. The wind field generated by the wind field simulation system is accurately controlled based on the physical information neural network control system, the complex wind field required by the air-ground unmanned aerial vehicle in the wind resistance test process of the air and ground subsystems is simulated, and the uniformity of each index of the wind field is ensured.

Disclosed are systems and methods that provide a novel functional, computerized testing framework for an integrated, unified standard testbed for network (e.g., WiFi) devices. In some aspects, the disclosed framework involves components referred to as OpenSync Reference Testbed (OSRT) and Unified Standard Testbed (USTB). OSRT provides a reference testbed for end-to-end (E2E) system testing for firmware release verification (FRV) and for functional unit testing (FUT). USTB corresponds to standard devices, software images, wiring schemes, and the process for setting up and running a functional testbed for networked devices. In some embodiments, OSRT can include a fully assembled USTB with a predetermined number (e.g., three (3)) of reference extenders, which can allow for the testing configuration and functionality discussed herein. The disclosed framework can provide novel functionality for testing, verifying and configuring network equipment and connections for a particular and / or set of software stacks.

The invention discloses an inducer efficient anti-cavitation numerical optimization method based on blade reverse parameterization, and relates to the technical field of optimization design of inducers for pumps, the inducer is designed and machined through five-axis linkage numerical control, and meanwhile, an inducer visual cavitation test testbed is built; hydraulic performance and cavitation erosion tests are carried out through a test bed, and curves of lift, efficiency, net positive suction head and cavitation erosion area changing along with time are obtained; finding an inducer turbulence model, an inducer cavitation model and a cavitation erosion calculation model with the minimum calculation error; carrying out reverse parametric modeling on the inducer blade; building an inducer parameterized intelligent computing platform based on modeling; screening main geometric parameters of the inducer; optimizing the inducer based on the turbulence model, the cavitation model, the cavitation erosion model and the intelligent computing platform; and performing hydraulic performance test and cavitation erosion test verification on the optimized inducer. The anti-cavitation performance of the inducer can be effectively improved.

The invention discloses an ATS controller integration test platform, and relates to the technical field of thermal management of automobiles and electronic equipment, and the ATS controller integration test platform comprises a test platform case which comprises an upper computer, a test platform MCU and a communication system. The ATS controller integrated test platform provided by the embodiment of the invention can simulate a complex working condition, realizes comprehensive test of the ATS controller, greatly improves the test range, can evaluate the performance of the ATS controller more comprehensively compared with the test of a single function in the prior art, and improves the test efficiency by simulating a real working environment. The communication between the whole vehicle and the ATS controller is accurately simulated by utilizing RS485 communication and a CAN bus protocol, meanwhile, the working condition can be truly restored through the temperature sensor, the pressure sensor and the flow sensor, the performance of the ATS controller can be accurately evaluated, the reliability of a test result is ensured, and through the arranged upper computer, the reliability of the ATS controller is ensured. The possibility of errors caused by human intervention is reduced, and the testing efficiency is improved.

A space vehicle includes a massless payload. The massless payload comprises dynamically modifiable software configured to indicate one or more actions to be taken by the space vehicle. The space vehicle also includes a primary controller that includes software that is not modified based on modifications to the massless payload, a test controller operatively communicating with the massless payload. The system also includes one or more operational systems including at least one of actuators or sensors of the space vehicle that are controlled based on commands from the test controller during a test condition generated to implement the one or more actions indicated by the massless payload and by the primary controller during normal operation.

A network function configuration and test generation framework are configured to generate a test script indicative of a configuration and test cases for verifying a virtual function implemented in a virtualized computing environment. A test input is received that encodes information for verifying a network function. The information includes identification of a test tool, a target testbed for testing the network function, and network information including parameters for network conditions to be operational during testing of the network function. A data parser translates and formats the test input. The formatted test input in input to a topology discoverer configured to identify a network topology of the testbed and which network functions deployed on the testbed are emulated and which network functions deployed on the testbed are real. A configuration generator generates a configuration file usable to configure applicable network functions and their functionalities.

A network function configuration and test generation framework are configured to generate a test script indicative of a configuration and test cases for verifying a virtual function implemented in a virtualized computing environment. A test input is received that encodes information for verifying a network function. The information includes identification of a test tool, a target testbed for testing the network function, and network information including parameters for network conditions to be operational during testing of the network function. A data parser translates and formats the test input. The formatted test input in input to a topology discoverer configured to identify a network topology of the testbed and which network functions deployed on the testbed are emulated and which network functions deployed on the testbed are real. A configuration generator generates a configuration file usable to configure applicable network functions and their functionalities.

The invention discloses an urban traffic simulation model evaluation method and system based on data driving. The method comprises the following steps: detecting and tracking an intelligent body target in a video stream in real time through a camera, and outputting a target category, a position and a tracking identifier; wherein the intelligent body targets are vehicles and pedestrians; performing multi-modal data association and time-space consistency modeling on the motion trail of the intelligent body target; through a data-driven optimization algorithm, a road scene simulation technology is fused, and complex traffic test conditions are dynamically restored; carrying out authenticity measurement on a simulation result by utilizing a dictionary evaluation system, and quantifying speed distribution, density distribution and track error indexes; the simulation data are fed back to the test platform, the model parameters are optimized, and a virtual test report is generated. According to the invention, road testing is partially replaced and complemented with the road testing, so that the testing period can be greatly shortened, the testing cost can be reduced, and the life safety of testing personnel can be protected.

The invention discloses a cloud control intelligent driving vehicle in-the-loop test platform and method, and relates to intelligent driving, and the method comprises the steps: building a test scene through a scene simulation module; the dynamics simulation module builds a dynamics model; the traffic flow simulation module builds a virtual traffic environment; the sensor and signal simulation system simulates a sensor function and V2X and GNSS signals; the cloud control basic platform calculates a control instruction; the intelligent network connection controller carries out logic calculation and controls the chassis part to execute a command; the road simulation system assists the tested vehicle in completing action execution; the measurement and control system collects output data of the tested vehicle and evaluates the intelligent networking function and performance. By integrating the road simulation system, the virtual simulation system, the sensor and signal simulation system, the cloud control basic platform, the measurement and control system and the like, the intelligent network connection vehicle can complete various function and performance tests of the whole vehicle in a laboratory, the development period of the whole vehicle is shortened, the test coverage is increased, and the test cost and the safety risk are reduced.

The invention belongs to the field of tire-road three-dimensional stress testing, and discloses a tire-road contact three-dimensional stress testing system and method, which are characterized in that a plurality of functional modules such as a test piece manufacturing module, a contact testing module, a three-dimensional finite element modeling module, a three-dimensional point cloud generation module, a precision correction module and a three-dimensional stress calculation module are integrated; the accurate measurement of the three-dimensional stress in the contact process of the tire and the road surface is realized; the accuracy and the reliability of a test result are obviously improved; the test piece manufacturing unit ensures authenticity and repeatability of a pavement test piece, the contact test platform simulates a real contact environment, the three-dimensional finite element model generation platform provides an accurate model basis for mechanical analysis, and the three-dimensional point cloud generation platform realizes accurate acquisition of deformation data. The precision correction unit improves the simulation precision by iteratively optimizing the friction coefficient, and finally the three-dimensional stress calculation unit outputs a three-dimensional stress distribution result, so that a scientific basis is provided for tire design, pavement maintenance and vehicle safety performance evaluation.

The invention relates to the technical field of reliability tests of automobile bodies and chassis parts, in particular to a system and method for testing the mud splashing degree of automobile parts. The device comprises a mud splashing simulation assembly used for carrying out mud splashing test on to-be-tested parts of a to-be-tested vehicle; the rotary test platform is used for accommodating the to-be-tested part and driving the to-be-tested part to rotate so as to concentrate muddy water in the to-be-tested part; and the image detection assembly is used for carrying out image shooting on the to-be-tested part of the rotary test platform before and after the mud splashing test so as to respectively obtain first image data and second image data, and comparing the first image data with the second image data so as to judge the mud splashing degree of the to-be-tested part. According to the application, the rotary test platform and the image detection equipment are arranged, and the to-be-detected parts before and after the splash test are rotated to the same position posture through the rotary test platform, so that the image detection equipment can conveniently collect images of the to-be-detected parts.

System and methods for a digital twin simulator according to various aspects of the present invention operate in conjunction with a source of actual National Airspace System data, a testbed, a set of interfaces containing instructions on how to process archived data, a set of external components for processing the archived data according to the interfaces, and a simulator. The testbed receives archived National Airspace System data during a test and feeds the data to the external components. Processed results are forwarded to the simulator to run a simulation. The digital twin simulator may then compare differences between the simulated results and the archived National Airspace System data.