228 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 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 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 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 provides an aircraft flight control system comprehensive automatic test platform and method based on a network architecture. The platform comprises automatic test software, test control software, test control simulation equipment and a flight control subsystem airborne finished product to be tested. The test control simulation device comprises a comprehensive test control simulation device and a plurality of flight control subsystem test control simulation devices. Each flight control subsystem test control simulation device is connected with the corresponding flight control subsystem airborne finished product and is used for sending configuration information to the flight control subsystem airborne finished product and receiving acquisition information provided by the flight control subsystem airborne finished product; the test control software comprises ground maintenance data acquisition software, comprehensive test control software and flight control subsystem test control software; the test control software is connected with the test control simulation equipment, sends a control instruction to the test control simulation equipment, and receives response information of the control instruction sent by the test control simulation equipment; the ground maintenance data acquisition software is connected with the comprehensive test control simulation equipment and the plurality of flight control subsystem test control simulation equipment and is used for receiving acquired information; and the automatic test software is connected with the test control software, sends a control instruction to the comprehensive test control software and the flight control subsystem test control software, obtains a response, and obtains acquisition information sent by the ground maintenance data acquisition software. The comprehensive test technology of multi-bus acquisition and lumped control is combined, the establishment of the comprehensive test platform of the aircraft flight control system is optimized and completed, and the automatic comprehensive control and detection of the aircraft flight control system are realized.

The invention discloses a hardware-in-the-loop-based seat adjustment testing device and an automatic parameter calibration method. The device comprises an upper computer, a CAN board card, an HIL test platform, a seat VIU controller and a to-be-tested seat. According to the method, the whole travel of a seat is divided into non-uniform density position intervals, PID parameters of all the intervals are dynamically optimized based on a step response curve, and a calibration parameter MAP is generated after preset performance constraints are met. The core innovation lies in that the HIL platform simulates the motor load and mechanical resistance characteristics with high precision; an XCP protocol is adopted to realize uninterrupted online parameter refreshing; and a partition calibration strategy is combined with a dead point buffering mechanism to improve the control precision and safety. The seat calibration efficiency and precision are remarkably improved, and the method is suitable for development of an automobile seat control system.

The invention discloses a performance test platform and test method for a thermal defect detection device of a contact network. The platform comprises a thermal defect detection module, a contact network simulation device, a Sudoku temperature measurement test module and an intelligent control platform, the thermal defect detection module, the contact network simulation device and the Sudoku test module are respectively connected with the intelligent control platform. The trolley is controlled by the intelligent platform to move to simulate operation of the detection vehicle, the sliding table is driven to accurately position the black body to a sudoku designated position, the temperature of the heating piece is adjusted to simulate the heating defect of the contact network component, and automatic testing of five functions is achieved. According to the invention, the problems of low manual test efficiency and insufficient sampling coverage rate are solved, and the test efficiency is improved.

The invention is suitable for the technical field of noise testing, and particularly relates to a noise testing method and system for an electric drive assembly of a new energy automobile, and the method comprises the steps: constructing an electric drive noise testing platform, delimiting a testing region, drawing a traffic network distribution diagram in the testing region, marking all road sections, and collecting a live-action image of each road section. Generating environment data, wherein the environment data at least comprises road condition information, types and traffic flow; and through the test platform, obtaining the data reading authority of the test vehicle, selecting the deployment position of the pickup device at the electric drive assembly, collecting audio data, positioning the real-time position of the test vehicle, and passing through a preset timestamp. By generating the test report, the road section corresponding to the noise can be intuitively displayed, and the noise data and the road attribute are subjected to correlation analysis, so that the concentrated area of the abnormal noise is quickly identified, and the accuracy and readability of the noise test result are improved.

The invention discloses an aircraft actuator simulation loading test platform and method, and relates to the field of control systems. The platform comprises an actuator test board arranged at the top of the fixed platform, a loading spring group and a fixed rear support; in the actuator test bench, the top of a first base is sequentially provided with a fixed support, a movable support, a rigidity simulator and an actuator rear moving seat in the axial direction, the top of a second base is slidably connected with an actuator front moving seat, a grating ruler and an inertia simulator are fixed to the side face of the second base, and a tested actuator is arranged between the actuator front moving seat and the actuator rear moving seat. According to the invention, the real working state of the actuator can be simulated in the loading test, more accurate working data can be obtained, and the test result is more real and reliable. The platform adopts a mode of combining a rigid tool and a flexible tool, is compact in structure, firm and durable, can quickly reconstruct and adjust the positioner so as to adapt to different actuator appearances, and greatly shortens the time of an actuator loading test process.

The application provides a piezoelectric energy feedback suspension equivalent stiffness and damping measurement method and device, and relates to the technical field of suspension stiffness and damping measurement. The method comprises the following steps: building a test platform; simulating the motion process of the excitation gear and the piezoelectric cantilever beam when the piezoelectric energy feedback suspension vibrates, obtaining the vibration displacement of the free end of the piezoelectric cantilever beam, and measuring the voltage signal generated by the piezoelectric cantilever beam during the vibration process; obtaining the speed change curve of the free end of the piezoelectric cantilever beam based on the change of the vibration displacement with time; drawing the voltage change curve of the piezoelectric cantilever beam during the vibration process according to the voltage signal; obtaining the continuous stiffness of the piezoelectric cantilever beam, so as to obtain the equivalent stiffness and equivalent damping of the piezoelectric energy feedback suspension. The application can measure the equivalent stiffness and damping of the piezoelectric energy feedback suspension, and provides a theoretical basis for the dynamic characteristic analysis and real vehicle application of the piezoelectric energy feedback suspension.

The invention relates to the technical field of drilling machine and tool testing, in particular to an indoor real simulation test platform for a drilling tool core barrel for an extra-deep well, which comprises a base station, a cabin body, a cabin cover, a hydraulic motor, an electric heater, a core barrel mounting assembly and a third transmission shaft, and the specific structure of the core barrel mounting assembly is as follows: a core barrel to be tested is mounted between a third sleeve and a core shaft; two ends of the to-be-tested core barrel are pressed by end covers, the end covers are fixedly connected to two ends of the third sleeve, and the end cover on the left side is fixedly connected with the right end of the third transmission shaft through a coupler; and the right end of the mandrel is fixedly connected with the fixed tailstock. The third transmission shaft drives the to-be-tested core barrel to rotate, the core barrel rotates and rubs on the surface of the mandrel, and the wear resistance of the inner wall of the core barrel can be tested. The performance test and the service life test of the core barrel of the drilling machine can be completed in a real environment.