9 results about "Collision analysis" patented technology

This invention provides a reverse vehicle search method, apparatus, device, and storage medium, comprising: acquiring a target person identifier and target vehicle information of a target vehicle; acquiring target image data collected by multiple cameras in a designated area; the multiple cameras are distributed along a driving lane in the designated area, and parking spaces are set around the driving lane; based on the target vehicle information and the target person identifier, performing target tracking and trajectory fitting processing on the target image data of each camera to determine a first driving trajectory corresponding to the target vehicle and a second movement trajectory corresponding to the user; performing trajectory collision analysis on the first driving trajectory and the second movement trajectory to determine the target location where the target vehicle is parked, and determining a reverse vehicle search path based on the user's current location and the target location. Using this invention can reduce the hardware cost of reverse vehicle search.

The application discloses a vehicle collision detection method based on elastic waves and a multimodal large model, which comprises the following steps: collecting elastic wave signals by a vehicle end MCU, performing threshold judgment through an instant response layer, triggering a safety system immediately if it is a high-intensity collision, inputting the signals into an EWCN model of an edge intelligent layer by the vehicle end MCU if it is not a high-intensity collision, performing fine-grained classification on the non-high-intensity collision signals, directly adopting the classification result if the EWCN model outputs a high confidence or low confidence result, uploading multimodal data packets to a cloud deep analysis layer if the EWCN model outputs a to-be-confirmed scene, receiving data by a cloud server, performing fusion analysis on the multimodal input data by calling a VLM model, outputting an event type judgment result and corresponding explanation and returning to the vehicle end. The application solves the problem that a traditional scheme cannot simultaneously satisfy instant response and accurate classification, and meets the dual demands of rapid triggering of a safety airbag and fine collision analysis.

The application discloses a B column of a vehicle and a design method thereof, wherein a roof protection section and a side impact protection section of the B column are symmetrically arranged on the upper side and the lower side of a plate main body. The side impact protection section comprises a performance surplus optimization region, a collapse energy absorption region, a chest protection region and an abdomen protection region arranged in sequence from bottom to top, the thickness of each region is determined by the result of collision analysis, the thickness of each region of the roof protection section is symmetrically arranged with the thickness of the side impact protection section with the center line of the plate main body as a symmetric center, and the plate main body is formed by continuous section change rolling through a flexible roll process. The application can improve the material utilization rate of the flexible roll process, reduce the setting of additional reinforcing structures and local thickening structures, and thus reduce the material cost and the processing cost.

This invention provides a vehicle scheduling method and system for a two-way, two-lane unsignalized intersection, comprising: Step S1: Preprocessing vehicles based on given real-world traffic conditions at a two-way, two-lane intersection to determine the likelihood of collisions and analyze conflict relationships between vehicles; Step S2: Constructing a vehicle scheduling model based on deep search of conflict relationships; Step S3: Utilizing nonlinear programming to make vehicle action decisions, determining the optimal passage time and vehicle acceleration; and based on the vehicle scheduling model, performing lower-level planning to design a vehicle scheduling strategy for the unsignalized intersection; Step S4: Building a simulation scenario of the intersection based on a given real-world intersection scenario and initializing vehicle information for each vehicle; Step S5: Inputting the vehicle information into the vehicle scheduling model to make behavioral decisions and obtain the action output of each vehicle at the next moment. This invention can improve vehicle traffic efficiency and reduce the probability of accidents.

Methods and systems for detecting vehicle crash events using real-time sensor data are disclosed. In some embodiments, an application executing on a computing device disposed in a vehicle receives a stream of time-series data from one or more motion sensors during a drive. For each contiguous interval of a first predefined length, the application generates a crash prediction indicative of whether a crash occurred during that interval. Generating the crash prediction includes executing a crash detection neural network on sensor data collected over a time period that comprises the interval and has a second, greater predefined length. For each crash prediction, the application determines whether the prediction meets one or more predefined threshold criteria. In response to meeting the criteria, the application generates a crash analysis using the corresponding sensor data.

The application provides a digital garment factory three-dimensional model building method and device, which comprises the following steps: based on the quantity of workstations required, a sewing workstation model is instantiated on a three-dimensional scene floor grid to obtain a sewing unit; based on the maximum rotating diameter and the maximum physical swing radius of the finished garment after hanging, a sweep radius is determined; based on the peripheral boundary of the sewing unit, a safety isolation ring line is generated outward with the sweep radius as the offset distance; a three-dimensional shelf model library is called in the area outside the safety isolation ring line, and a hanging shelf array is generated based on the finished garment storage capacity requirement; an AGV transportation model is instantiated based on the track data of the safety isolation ring line, collision analysis is performed based on the AGV transportation model and the safety isolation ring line, and an AGV navigation path is obtained; and based on the spatial position relationship of the AGV navigation path, the sewing unit and the multi-layer hanging shelf array, rendering is performed to generate a digital garment factory three-dimensional panoramic model. The application eliminates the safety hazards of mixed human-machine operation.

The application relates to the technical field of ship structure collision response analysis, in particular to a structure collision analysis method and system based on domain decomposition PINN, the method comprises the following steps: carrying out calculation domain division based on the contact relationship between an impact object and a structure, generating training point coordinates of each subdomain and corresponding boundaries, uniformly scaling the training point coordinates and multidimensional parameters, taking the training point coordinates after scaling as input to construct a collision analysis model, constructing a loss function to calculate the total loss of a submodel, configuring an independent optimizer for each allocated neural network, and outputting complete structure collision displacement field and stress field prediction results, the application can accurately capture stress concentration phenomena in the structure collision process, avoids the stress concentration capture failure problem caused by the discontinuous boundary conditions of the traditional PINN and the oscillation problem of the finite element method in the high gradient area, and improves the prediction accuracy and stability of the structure collision displacement field and the stress field.

The application relates to the technical field of building construction, in particular to a round pipe column foot pre-burying positioning method and device. The method comprises the following steps: obtaining a steel structure construction drawing; constructing a round pipe column and pre-burying foot bolt construction model according to the steel structure construction drawing; establishing the positioning connection of the pre-burying foot bolt and vertical main reinforcement according to the construction model; carrying out construction model collision analysis and three-dimensional simulation experiment based on the positioning connection of the pre-burying foot bolt and the concrete main reinforcement; and carrying out steel structure device processing and installation based on the construction model. The engineering quality is improved by optimizing the construction node, the problem that the pre-burying steel plate cannot be reused is solved, the vertical column reinforcement and the foot bolt pre-burying steel plate grinding tool can be freely stretched and contracted to control the position of the reinforcement, the effect of reusing different column diameters is achieved, the construction efficiency is improved, the progress is accelerated, and good economic and social benefits are achieved.

The application is suitable for the technical field of traffic safety, and provides a traffic safety guarantee method, device, terminal equipment and storage medium, wherein the traffic safety guarantee method comprises the following steps: obtaining self-motion state information and perceived-motion state information of a target person, the self-motion state information being obtained based on a self-measuring device of the target person, and the perceived-motion state information being obtained based on an external perception device; fusing the self-motion state information and the perceived-motion state information to obtain fused-motion state information of the target person; obtaining predicted-motion state information of the target person based on the fused-motion state information; performing collision analysis between a traffic tool and the target person according to the predicted-motion state information, and making a corresponding action based on an analysis result. The application can improve the guarantee of safety of the target person.