8results about How to "Overcome consistency" patented technology

The invention discloses a design method capable of giving consideration to both toughening and crack path controllability for a brittle material, and belongs to the technical field of fracture mechanics and artificial intelligence crossing, and the method comprises the steps: employing an input coding method based on space-response double-domain fusion to carry out feature extraction; introducing a channel attention mechanism to perform weighted fusion on the extracted double-domain features, and generating prediction results for different key tasks; evaluating the reliability of a prediction result by adopting a phase field verification and closed-loop adaptive optimization mode, and carrying out iterative training and optimization on the neural network; and taking the optimized neural network as a fitness evaluation function of double-target genetic optimization, and performing multi-target optimization on defect generation parameters. According to the invention, through fusion of the spatial domain and the response domain, geometric morphology and dynamic response characteristics are cooperatively extracted, and the prediction precision of complex fracture behaviors is improved; through non-dominated sorting multi-objective optimization under physical constraints, a high-toughness and path-controllable optimal solution is output, and brittle materials are pushed to cross an active controllable fracture design.

The invention provides a foundation pit inclinometer depth positioning method based on magnetic field feature matching, and relates to the technical field of foundation pit horizontal displacement monitoring, and the method comprises the steps: controlling an inclinometer to move in an inclinometer pipe, and synchronously collecting IMU data, three-axis magnetic field data and odometer data which are marked at unified time; fusing the IMU data and the odometer data by adopting a filtering algorithm to obtain a motion state estimation sequence of the inclinometer; performing spatial resampling on the three-axis magnetic field data based on the odometer data, converting the three-axis magnetic field data into a magnetic field feature sequence distributed along the mileage direction, and matching the magnetic field feature sequence with a pre-constructed background magnetic field feature database to obtain a matched mileage value; and associating the motion state estimation sequence of the inclinometer with the matched mileage value, recalibrating the accurate depth coordinate of each deformation point of the inclinometer by taking the matched mileage value as a unified depth reference, and calculating the deformation quantity of the same depth position in different periods.

The application provides a point cloud segmentation method, device, storage medium and electronic equipment, and belongs to the technical field of data processing. The point cloud segmentation method comprises the following steps: obtaining a point cloud to be segmented; based on the point cloud to be segmented, a multi-channel depth image is constructed, the points in the point cloud to be segmented and the pixels of the multi-channel depth image are one-to-one corresponding, and the multi-channel depth image has geometric neighborhood features and three-dimensional structure features of the point cloud to be segmented; a preset panoramic segmentation model is used to perform panoramic segmentation on the multi-channel depth image to obtain a segmented image, wherein the segmented image comprises instance IDs and semantics of each pixel; and the segmented image is mapped to the point cloud to be segmented to obtain a point cloud segmentation result, wherein the point cloud segmentation result comprises instance IDs and semantics of three-dimensional points. The application has higher segmentation accuracy, more stable real-time performance and more suitable characteristics for embedded platform deployment.

The embodiment of the invention relates to a full-spine X-ray film configurable quality control system and method. The system comprises a configuration and knowledge base which is set to set operation environment parameters through a preset configuration file and to evaluate anatomical standards, a label mapping dictionary and examination rules required by a full-spine X-ray film; the data adaptation and standardization module is set to read full-spine X-ray labeling data according to the operating environment parameters, carry out standardized label mapping according to the label mapping dictionary, and normalize pixel coordinates of an input full-spine X-ray film to a preset standard coordinate space; the anatomical feature extraction module is configured to receive the data of the whole-spine X-ray film after the standardization label and the coordinate normalization, and output a structural feature measurement value required by consistency check; the consistency checking engine is set to carry out quality checking according to the structural feature measurement value and the checking rule; and the report output module is set to generate a quality report containing the quality level according to the inspection result.

This invention discloses a method for preparing an ultrathin ordered macrocyclic molecular membrane. The method involves synthesizing macrocyclic molecules with high polymerization activity and amphiphilic guest molecules. The inclusion complexes formed by the macrocyclic molecules and guest molecules are orderedly assembled using Langmuir-Blodgett (LB) technology. Photopolymerization is then employed to achieve ordered cross-linking of the macrocyclic molecules, resulting in an ultrathin ordered macrocyclic molecular membrane. The macrocyclic molecular membrane prepared by this invention is monomolecular in thickness and possesses good mechanical strength. With the assisted orientation of the amphiphilic guest molecules, the macrocyclic molecules achieve ordered assembly at the water-air interface. The membrane preparation process proposed in this invention is simple, cost-effective, versatile, and easily scalable, making it significant for the field of high-performance separation membranes.

The invention relates to an urban low-altitude airspace navigation network performance test and evaluation method and device. The method comprises the following steps: acquiring key operation parameters of navigation service in a test area corresponding to an urban low-altitude airspace navigation network; according to the key operation parameters, evaluation indexes of the navigation service in the test area are determined, and the evaluation indexes comprise coverage rate, continuity, alarm time delay and positioning precision; and obtaining an evaluation result of the navigation service in the test area according to the evaluation index. Through the method provided by the invention, the problems of low efficiency and poor consistency caused by single test item and dependence on artificial experience in the prior art are solved, multi-dimensional quantitative evaluation of the overall performance of the navigation network is realized, powerful technical support is provided for planning, construction, acceptance, operation and maintenance of the low-altitude navigation network, and the method is suitable for popularization and application. And the low-altitude aircraft can operate in a safe and reliable navigation environment.

The invention relates to the technical field of point cloud extraction, in particular to a point cloud topographic feature intelligent extraction method based on regional quasi-geoid constraint. The method comprises the following steps: acquiring airborne laser radar point cloud and global navigation satellite observation data, constructing a regional quasi-geoid refinement model, and realizing point cloud elevation datum unification; constructing a ground point cloud triangulation network model based on the constrained point cloud elevation, calculating a terrain inclination angle and a linear expression error of a triangular surface, and adaptively determining a feature extraction parameter; and traversing the point cloud data in the triangular surface projection range, extracting the significant topographic feature points meeting the relative height condition, optimizing the triangulation network structure through iterative subdivision until a termination condition is met, and outputting a topographic feature extraction result. According to the method, through the synergistic effect of the regional quasi-geoid constraint and the adaptive feature discrimination mechanism, the unification of the elevation reference of the complex terrain point cloud, the effective suppression of the pseudo features and the synchronous improvement of the terrain feature extraction precision and stability are realized.

The invention belongs to the technical field of greenhouse crop water and fertilizer management and green efficient sustainable production, and particularly relates to a greenhouse tomato yield and quality grading evaluation water and fertilizer management method, which is characterized by sequentially comprising the steps of data collection, weight determination, sorting, grading and optimal mode determination, weight determination adopts an integrated entropy weight method, sorting adopts a TOPSIS model, and the optimal mode determination adopts a TOPSIS model. And an AISM model is adopted in a grading manner, and finally an EWM-TOPSIS-AISM comprehensive evaluation model is constructed. The method has the advantages that an EWM-TOPSIS-AISM comprehensive evaluation model is constructed on the basis of field experiments, water and nitrogen management of greenhouse drip irrigation tomatoes in the northeast region is optimized on the basis of multiple targets, an optimal water and nitrogen supply mode is established, and a theoretical basis and technical support are provided for formulating a precise drip irrigation and fertilization strategy for greenhouse tomatoes in the northeast region; (2) the EWM-TOPSIS-AISM comprehensive evaluation model has the advantage that the problems of subjectivity and inconsistent results of a single model are effectively solved through a combined evaluation method, and (3) the evaluation result is stable and reliable through bidirectional verification of UP type and DOWN type topological hierarchy directed graphs.