11results about How to "Verify performance" patented technology

The utility model discloses a simulation multi-string battery pack monomer output circuit, which relates to the technical field of energy storage system detection and comprises a voltage reduction module and a plurality of simulation monomer cell voltage circuits connected in series. The voltage reduction module is used for reducing voltage of an external test power supply to supply power to the simulation single cell voltage circuit; the single cell voltage simulation circuit comprises an isolation power supply module and a reference power supply module; the isolation power supply module supplies power to the reference power supply module. The reference power supply module is used for simulating voltage output of the single cell; the reference power supply modules are connected in series, and the analog cells are connected in series. The circuit is applied to a BMS circuit test, simulates a battery pack to output a group of high-precision battery cell voltages, and compares the voltages acquired by the BMS with an output standard voltage to confirm whether a sampling error meets a standard or not, so that the performance of an AFE chip of the BMS and a related acquisition circuit can be effectively verified before leaving a factory, and the quality of a shipment product is ensured.

The application discloses an interpretable analysis and decision sharing verification method and system for a colorectal cancer prognosis model, and relates to the field of medical artificial intelligence interpretability. The method comprises the following steps: performing gradient weighted class activation mapping analysis on the prognosis model to generate an image heat map; calculating the contribution degree of multi-modal features by using a SHAP interpreter; constructing an integrated visualization interface to present the patient data, model prediction and the above-mentioned explanation results to doctors; the doctors perform independent risk assessment based on the interface information; and finally, the decisions of the doctors and the model are compared to evaluate the auxiliary performance of the model. Through multi-level explanation and innovative doctor-model decision sharing verification mechanism, the transparency and clinical credibility of the complex AI prognosis model are significantly improved, the value of time series data in dynamic risk assessment can be verified, and the clinical landing application of the AI model is effectively promoted.

The application discloses a kind of infectious disease epidemic period short-term power load prediction method and device, by constructing including different geographical area power load data, time information, weather data and mobile data knowledge base, with the knowledge base trained migration deep learning model, the input of the migration deep learning model is the time information, weather data and mobile data of different geographical area, the output of the migration deep learning model is the short-term power load prediction result of different geographical area, in training with depth reinforcement learning to determine the optimal hyperparameter of the migration deep learning model shared weight layer, with the migration deep learning model of optimal hyperparameter trained to carry out power load prediction.The application can improve prediction accuracy, and overcome the problem of limited mobile data related to infectious disease epidemic.

This invention discloses a weightlessness simulation exercise aid device, relating to the field of fitness equipment technology. Specifically, it includes: a support part; a frame for fixing the fitness equipment, and a third movable frame that can move freely in the XY plane is provided inside the frame. The support part is slidably mounted on the third movable frame along the Z direction, and a floating lifting cylinder is provided inside the third movable frame to inhibit the sliding of the support part. This weightlessness simulation exercise aid device separates the weightlessness aid from the fitness equipment, allowing the fitness equipment to be used independently in space. The weightlessness aid part can be used to verify the performance of other space fitness equipment. Moreover, by using a floating support part, it can meet the needs of users to exercise in positions other than lying down, thereby solving the problem of limited usage scenarios.

The application relates to a power charging pile data security protection risk assessment method, which comprises the following steps: determining the working state of a charging pile as a charging test mode, testing and charging the charging pile, and obtaining test power data; dividing a preset historical time period into a first historical time period and a second historical time period, and respectively obtaining charging power data in the first historical time period and the second historical time period; obtaining historical power data according to the charging power data in the first historical time period and the second historical time period; obtaining a historical difference factor according to the difference between the test power data and the historical power data, obtaining a rated difference factor according to the ratio of the test power data to preset rated power data of the charging pile, and obtaining a risk assessment value according to the historical difference factor and the rated difference factor; and determining the danger level of the charging pile according to the risk assessment value and a preset risk interval. Therefore, the safety and reliability of the charging pile are more comprehensively improved according to differentiated historical data and rated data.

The application provides a kind of support extended vehicle-mounted multi-channel camera simulation method and system.Method includes: obtaining specified picture or video data, generating the original picture data of each frame, and according to the format of PPI, it is packed into PPI data format, and the ECC and CRC data required for each line are calculated;According to the resolution size of each camera, the required simulation simulation platform memory space is generated;The generated PPI, ECC and CRC data are injected into the memory space;According to the output state of the platform, update the data in the memory space to the next frame data during frame blanking;Using the PPI format module of the platform, according to the configuration of each channel, the data is divided into different Lane according to PPI format, and is output to CSI2 HOST according to PPI format.The application can simulate different types of cameras and their parameters.

The application discloses a kind of seamless positioning methods of quadrotor unmanned aerial vehicle based on multi-source fusion, belong to unmanned aerial vehicle positioning technical field.The application according to the position accuracy factor of GNSS divides positioning area into indoor area and outdoor area, uses VIO positioning mode in indoor;In outdoor, it uses the GNSS / VIO loose coupling positioning mode based on federal Kalman filter, first, in the sliding window, the idea of time series difference is used to calibrate the external parameter of GNSS subsystem and VIO subsystem online, realize real-time spatial alignment, then use federal Kalman filter to fuse positioning information.Simultaneously, the smooth switching scheme of positioning system is designed, so that when the positioning area changes, the system can accurately identify and smoothly transition.The application is proposed, enhances the high-precision positioning ability of quadrotor unmanned aerial vehicle in complex environment, provides strong three-dimensional perception solution for the vertical application of unmanned aerial vehicle in low-altitude economy.

The application discloses a kind of reliability test method and test system of display panel, comprising: at least two display panels to be tested are placed on bearing substrate;Obtain the test area of display panel to be tested;According to test area, set first preset test parameter, and according to first preset test parameter, obtain first threshold voltage test value;Set first preset threshold voltage range;According to first threshold voltage test value and first preset threshold voltage range, obtain the performance test result of display panel to be tested;According to test area, set second preset test parameter, and according to second preset test parameter, obtain threshold voltage difference value;Set second preset threshold voltage range;According to threshold voltage difference value and second preset threshold voltage range, obtain the life test result of display panel to be tested;According to performance test result and life test result, judge the reliability of display panel to be tested, guarantee the reliability of device in display panel, guarantee the use effect of display panel.

The application relates to the field of spacecraft propulsion technology, in particular to a continuous adjustable electric propulsion testing method and device, the method comprising setting a test instruction change period synchronized with a satellite orbit period; constructing an atmospheric resistance interference model changing with an orbit phase and converting the atmospheric resistance interference model into a dynamic thrust demand benchmark; generating at least one dynamic thrust instruction in a sine wave, a triangular wave, a step signal or a composite waveform; using a three-dimensional interpolation matrix to solve power and gas supply parameters in real time and driving a thruster to perform wide-range dynamic adjustment; and evaluating dynamic tracking performance based on a root mean square error and a frequency response characteristic index. The application realizes high-fidelity ground reproduction of a complex interference environment of a satellite in orbit, overcomes the limitations of existing static tests and single working conditions, and provides a scientific and effective testing scheme for dynamic performance verification of a continuous adjustable electric propulsion system.

This invention discloses a load cell, method, and electronic device for testing vehicle controllers. The load cell includes: a communication device for acquiring test requirement information and hardware parameter information of the vehicle controller to be load tested; a test environment simulation device connected to the communication device for constructing a simulated environment for load testing of the vehicle controller based on the test requirement information and hardware parameter information; an information acquisition device connected to the vehicle controller for acquiring operational status information generated by the vehicle controller during operation in the simulated environment; and a controller connected to the information acquisition device for performing load testing on the vehicle controller based on the operational status information. This invention solves the technical problem of low efficiency in load testing of vehicle controllers in related technologies.

The embodiment of the application provides a test method and system of a compulsory parent node based on a Mesh network, the method comprises the following steps: defining a topology structure of the Mesh network based on a test requirement, the topology structure containing an association list of a child node and a target parent node; extracting configuration information of each child node, generating a configuration instruction based on the configuration information, and enabling the child node side to establish a connection relationship with the target parent node based on the configuration instruction; checking based on a connection result periodically fed back by the child node, generating a health state level corresponding to each link, and generating a corresponding response strategy according to different health state levels; executing a corresponding test case based on the test requirement, and recording test data; after receiving a test requirement update instruction, determining a change mode based on the update instruction, modifying a parent node configuration of the child node based on the change mode, recording a change time stamp, and determining a dynamic response capability of the child node.