37 results about "Constraint algorithm" patented technology

The invention provides a park integrated energy optimization scheduling method and system, and relates to the technical field of energy scheduling, and the method comprises the steps: obtaining the state information of a park integrated energy system; establishing an energy scheduling model according to the state information; determining a constraint condition and a target function of the energy scheduling model; solving the energy scheduling model through an epsilon-constraint algorithm under the constraint of a constraint condition by taking the minimization of the objective function as a target, and generating a scheduling solution set; processing the scheduling solution set in a fuzzy decision mode to generate an optimal scheduling solution; and taking the optimal scheduling solution as a scheduling scheme, and carrying out optimal scheduling on the park integrated energy system. The energy utilization efficiency can be improved, and the energy safety and flexibility of the park are enhanced.

This invention discloses a method, system, and device for measuring the orientation of nonwoven fibers, belonging to the field of nonwoven fabrics. The method binarizes a color image of the nonwoven fabric to extract the fiber skeleton. Based on this, a T-shaped corner detection algorithm is used to determine the intersection points of the fiber skeleton. A fiber length constraint algorithm is used to limit the length of the skeleton segments, and a fiber projection algorithm is used to calculate the projected length of the skeleton segments, thereby determining the orientation of each length-constrained skeleton segment. The T-shaped corner detection algorithm used in this invention can accurately handle fiber skeleton intersection points, the fiber length constraint algorithm can effectively avoid interference from long fibers on orientation measurement, and the fiber projection algorithm can accurately calculate the projected length of the fibers. These three algorithms together make the measurement of nonwoven fiber orientation more accurate and efficient, and are applicable to various types of nonwoven materials.

This application discloses a method, apparatus, and storage medium for printing imposition positioning, which improves imposition efficiency and accuracy while reducing the operational difficulty of imposition. The method includes: obtaining first imposition layout parameters for a selected printing press model from a limited dataset based on the selected model and task requirements; establishing a two-dimensional reference coordinate system based on the first imposition layout parameters, with the vertex of the printing plate of the selected model as the starting point; calculating the first reference position of a single row of code values ​​in the two-dimensional reference coordinate system according to a dynamic constraint algorithm; mapping the first reference position to a multi-row positioning network based on a topology expansion matrix; verifying whether the multi-row positioning network conforms to preset layout rules; if so, performing adaptive error compensation on the multi-row positioning network and outputting the final positioning result.

The application provides a park comprehensive energy optimization scheduling method and system, and relates to the technical field of energy scheduling. The method comprises the following steps: obtaining state information of a park comprehensive energy system; establishing an energy scheduling model according to the state information; determining constraint conditions and an objective function of the energy scheduling model; under the constraint of the constraint conditions, solving the energy scheduling model by an epsilon-constraint algorithm to generate a scheduling solution set, processing the scheduling solution set by a fuzzy decision method to generate an optimal scheduling solution, and taking the optimal scheduling solution as a scheduling scheme to optimize the park comprehensive energy system. The application can improve energy utilization efficiency and enhance park energy security and flexibility.

The application discloses a semi-supervised multi-view clustering method based on double-constraint concept decomposition, relates to the technical field of machine learning, combines point constraints with pair constraints, constructs a double-constraint algorithm based on prior label information of a complementary supervision mechanism, realizes maximum utilization and progressive propagation of limited supervision information, breaks through the limitation of data non-negativity of a traditional method by relying on a concept decomposition framework, processes complex data distribution by combining a kernel method, obtains a consensus matrix of multi-view data fusion as low-dimensional representation of a view, adopts a k-means algorithm for clustering, and outputs a final class division result. The application realizes effective processing of complex multi-view data, finally comprehensively improves the performance of a multi-view clustering task, and breaks through the bottleneck of the prior art in clustering precision, data adaptability and supervision information utilization efficiency.

The invention discloses a general-inductance integrated waveform power distribution method for the Internet of Vehicles, and belongs to the technical field of Internet of Vehicles and general-inductance integration. Comprising the steps of constructing a communication and sensing integrated system architecture based on the Internet of Vehicles, designing a power distribution scheme based on a communication data rate index and a sensing Cramer-Rao bound, designing a constraint algorithm of multi-objective optimization, solving a communication and sensing performance boundary to obtain an optimal distribution strategy and the like. Aiming at the advantage that a delay-Doppler domain modulation technology has high robustness in a high-speed vehicle network scene, the invention provides an Internet of Vehicles communication and inductance integrated waveform power distribution method under limited power budget, and meanwhile, the communication downlink sum rate and speed sensing Cramer-Rao bound performance is improved; and an efficient and reliable sensing means is provided for intelligent traffic cooperative control.

The invention belongs to the technical field of shoreline identification, and provides a shoreline identification and optimization method based on a point cloud neural network in an intelligent ship. Point cloud data are collected through the laser radar and are not affected by illumination conditions. The problem that a visual algorithm is limited by weather and illumination is solved, and the method adapts to dynamic environments such as foggy days and tidal changes. The point cloud density is reduced through voxel grid filtering, the data processing amount is reduced, the Edge-Aware Point Net network is improved, characterization learning of dense features does not need to be carried out, the lightweight design of the network structure is achieved, the end-to-end processing delay time is shortened, the ship berthing real-time requirement is met, and the real-time bottleneck is overcome. Differentiation features of a natural shoreline and an artificial shoreline are adaptively processed through a double-path U-net full-convolution integral segment network, and the problem that a traditional method is poor in adaptability to different types of shorelines is solved; the normal vector consistency constraint is introduced into the dynamic constraint K-means algorithm, and the fitting precision of clustering to the complex shoreline form is improved.

The invention relates to the technical field of intelligent layout of building and mechatronics, and particularly provides an intelligent layout generation method and system for a public washroom based on a generative algorithm, and the method comprises the steps: obtaining multi-modal data of a public washroom space of which the layout is to be generated; analyzing the multi-modal data and constructing a multi-relation graph of the public washroom space; based on the constraint of the multi-relation graph, generating a Top-K set of nearly feasible layout first draft by adopting a submerged space diffusion model; taking the nearly feasible layout first draft as an initial state, constructing a Markov decision process of reinforcement learning, and performing strategy fine adjustment through a constraint PPO algorithm to obtain an optimized compliance layout scheme; and performing clause-level recheck and topology consistency check on the optimized compliance layout scheme. According to the method, a Top-K set of nearly feasible layout first draft is generated under a rule mask through a condition generation model, then a lightweight evaluator is used for driving an RL strategy to carry out multi-target iteration, and a clause-geometry-physics consistent automatic checking and repairing mechanism is formed.

The invention discloses a method, a device and a system for planning a transportation route of a large cargo. The method comprises the following steps: inputting and loading parameters of a transportation vehicle, cargoes and a transportation scene; performing path planning based on a multi-constraint algorithm to generate a feasible path; performing three-dimensional dynamic simulation on the feasible path; verifying whether the three-dimensional dynamic simulation is passed or not; if not, adjusting the parameters or manually modifying the path and then returning to the previous step; and if yes, outputting a path and a simulation report. According to the invention, comprehensive parameters of transport vehicles, goods and transport scenes are stored and updated in real time through the data support layer, so that planning deviation caused by data missing or lagging is avoided; by means of constraint matching analysis and multi-constraint path planning of the processing layer, feasible paths meeting the requirements of the height, the gradient, the turning radius, the bearing capacity and the like can be screened out, the scheme does not need to be repeatedly adjusted to adapt to actual transportation conditions, and time and labor cost are saved.

The invention provides a multi-mode cooperative control method and system for an oral surgery robot, and belongs to the technical field of medical robots. The method comprises the steps that operation planning and space registration are completed, and a drill bit and an optical tracking ball are rigidly fixed to the tail end of a mechanical arm; a manual mode is started for coarse positioning, the mechanical arm is dragged, the optical navigator tracks the pose in real time and visualizes deviation, and the mechanical arm provides force assistance; after the drill bit reaches the preset range of the target area, the drill bit is switched to an automatic mode, and fine adjustment is completed through hand-eye calibration, probe calibration and closed-loop control; then switching to a cooperation mode, locking a preset direction dimension by the mechanical arm, controlling the implantation depth, and ensuring that a motion path is stable by the central processing unit through a dynamic constraint algorithm; and after the drill bit reaches the planned depth, the mechanical arm locks the depth direction, and the cooperation mode ends. According to the invention, the problems of insufficient precision and poor flexibility of the traditional technology are solved, and the positioning precision, the operation safety and the clinical execution efficiency of the oral surgery are improved.

The application discloses a kind of complex equipment system visual simulation method and system based on digital twinning, comprising: S1, obtains multi-source observation data and control data;S2, constructs digital twinning mechanism model, establishes state mapping relationship;S3, constraint perception hash addressing mechanism is introduced by Instant-NGP algorithm, and multi-resolution hash coding is executed;S4, state deviation is calculated;S5, input improved 4DGS model, introduce mechanism residual error gate projection mechanism, and execute gate projection;S6, based on SDS constraint algorithm, introduce feasible region constraint calculation of distillation gradient, and execute gradient update;S7, execute consistency determination, and output visual simulation result.The application realizes the high consistency, high stability and high real-time visual simulation output of complex equipment system under complex working condition, strong interference and multiple constraint conditions.

The invention relates to an intelligent link sensing platform design and implementation method based on fragment retransmission, and belongs to the technical field of data transmission and communication. According to the method, the link state is acquired and perceived through the steps of fragment identifier implantation, fragment state feedback, multi-dimensional index calculation, index real-time reporting and the like; a link state is input, a double-constraint algorithm is used for calculating the size of an optimal fragment, and after whether a fragment redundancy strategy is adopted or not is decided, a transmission strategy is formed and issued; a transmission strategy is received and analyzed, a retransmission strategy is executed through data fragmentation processing and packet loss fragmentation detection, a redundancy supplementary retransmission mechanism is adopted, retransmission failure is avoided, and retransmission parameters are fed back; and carrying out iterative optimization on the strategy parameters by using a Q-Learning reinforcement learning algorithm, and carrying out strategy issuing through a gray level issuing strategy. According to the invention, the transmission efficiency can be improved, and stable and efficient data transmission service can be provided in a complex and changeable network environment.

The application discloses a kind of robust prestack seismic inversion methods and devices based on coherence constraint algorithm, belong to unconventional oil and gas exploration and development field, comprising: through the extraction of seismic coherence attribute of centrifugal window of space transformation;Based on the approximate formula of azimuthal anisotropy reflection coefficient, the forward operator of fracture reservoir is deduced and constructed, and the positive problem of prestack seismic inversion prediction is clear;Based on the prestack seismic inversion prediction positive problem, under the Bayesian framework, the coherence attribute is added to the objective function of inverse problem as the prior information of seismic inversion prediction, and stable prestack and poststack joint seismic inversion prediction is carried out.The application not only considers the influence of large-scale fracture in post-stack, but also considers the azimuthal anisotropy characteristics caused by small-scale fracture, which can greatly improve the stability of anisotropy parameter inversion of fracture reservoir, and has better predictability for small-scale fracture associated with large-scale fracture.

This invention discloses an integrated design method for multiple support systems on a research vessel, relating to the field of shipbuilding technology. This method comprises two main parts: a spatial constraint algorithm applicable to the integration of support systems on a research vessel and a hydraulic power source integration design method. This method, for the first time applied to a scientific research vessel, utilizes a multi-parameter spatial constraint algorithm, effectively improving the efficiency and effectiveness of the integrated design and ensuring the rational layout and coordinated operation of multiple research support systems within a limited space. Furthermore, the integrated design of the hydraulic power source, tailored to the specific research support systems of a scientific research vessel, allows for flexible pressure supply to each subsystem under different operating conditions, effectively addressing the support needs of various operating conditions in complex multi-support systems, reducing system complexity, and optimizing the overall resource allocation of the research vessel.

This invention discloses a fault-constrained Dal-UNet stratigraphic surface reconstruction method, applicable to the fields of information processing and oil and gas exploration. Existing deep learning reconstruction algorithms, based on supervised learning, require extensive data and manually labeled training data for pre-training, resulting in high economic and time costs. Data quality directly impacts algorithm performance, and in geological studies with relatively scarce data, supervised deep learning algorithms are prone to overfitting, making them even more difficult to apply directly to stratigraphic surface reconstruction tasks involving complex geological structures with faults. This invention utilizes the Dal-UNet network to capture hidden features from limited and sparse stratigraphic surface data and combines it with a fault-constrained algorithm to reconstruct complex stratigraphic surfaces containing faults, effectively restoring the true topography.

The invention relates to the technical field of document processing, and discloses a document content restoration method and system based on artificial intelligence, and the method comprises the steps: collecting document image information as an input source through a camera, and then carrying out the page scanning of the preprocessed document image information through a multi-modal layout analysis model, positioning various layout elements, obtaining physical layout parameters, deducing a geometric constraint relation through a geometric constraint algorithm, and generating a structured layout model; carrying out multi-language character recognition, picture graph classification and metadata extraction, formula format conversion and table structure detection and reconstruction, and outputting corresponding structured data; distinguishing different semantic blocks and constructing a tree hierarchical structure by combining a context semantic encoder with a conditional random field and text features, and extracting and restoring text fonts and paragraph format styles; and reading the basic metadata of the document, and restoring and complementing the associated information of the document elements based on the large model to complete the information improvement work. And efficient and accurate restoration of the document content is realized.

The invention relates to the technical field of three-dimensional data processing, in particular to an assembly segmentation and three-dimensional reconstruction method and electronic equipment, and the method comprises the following steps: S1, a preprocessing module; s2, a registration module; s3, segmenting the module; s4, a post-processing module; s5, reconstructing a module; according to the method, firstly, high-quality point clouds are acquired and preprocessed through a dynamic structured light camera; stable and accurate alignment of the scanning data and the model is realized by adopting a fine registration strategy of coarse registration and a normal vector constraint ICP algorithm; part-level segmentation is carried out based on a part generation extension envelope box, and a high-precision part point cloud consistent with an original model in shape is obtained by propelling front surface reconstruction; according to the method, a complete technical link from scanning to a part-level digital model is constructed, reflective interference and registration errors are effectively overcome, a reliable high-precision data basis is provided for geometric modeling and simulation of complex products, and the method has remarkable technical value and application prospects.

This invention discloses an online monitoring and optimization control method and system for acid mist in HRS processes. The method establishes an online monitoring and optimization control system for acid mist based on the conditions of a sulfuric acid workshop and collects sulfuric acid data. Based on preliminary investigation and analysis of the acid mist tower, it identifies the points influencing acid mist concentration and constructs an acid mist concentration matrix. Based on the acid mist concentration matrix, it defines an acid mist control optimization problem and constructs a neural network model. A loss function combined with a constraint algorithm is then used to optimize the neural network model and determine the optimal control scheme. This invention uses machine learning as the main technology for optimization control and combines it with data preprocessing to achieve precise control of sulfuric acid mist concentration. Facing the challenge of high nonlinearity from small sample data in the field, it innovatively adopts a three-layer neural network architecture of ReLU activation + Adam optimizer to achieve efficient feature extraction and overfitting risk control.

The invention provides a hydropower medium-and-long-term electric quantity decomposition curve intelligent generation method considering multi-time scale coordination, and relates to the technical field of electric power markets. The method comprises the steps that three types of contract electric quantity curves of insurance price, bidding and marketization are generated, the insurance price curve adopts K-means and DTW clustering and dynamic weight matching, the bidding curve gives consideration to performance and arbitrage through a double-channel decomposition mechanism, and the marketization curve optimizes an uncertain decision based on a double-constraint Q-learning algorithm; through LSTM price prediction and DBSCAN clustering, peak and valley periods are divided, a curve form is optimized through a double-target model and Pareto screening, and constraint violation is corrected according to priorities; and establishing a year-month-ten-day level-day level four-layer linkage mechanism, and resolving inter-period decision conflicts according to rules. Physical constraints and market factors are coupled, the curve adaptability and decision-making efficiency are improved, the default risk of hydropower enterprises is effectively reduced, and the economical efficiency and compliance of electric quantity decomposition are considered.

The application belongs to the field of artificial intelligence and natural language processing, and relates to an efficient event extraction method based on controllable pattern generation, which comprises the following steps: obtaining a text sequence to be tested, performing entity extraction on the text sequence to be tested to obtain an event entity set, a trigger word set and a position vector sequence; constructing multiple events according to the event entity set and the trigger word set; the event contains the relationship between the entity and the trigger word; inputting the event and the position vector sequence into a trained event pattern generation model to obtain an event pattern; merging and filtering the event pattern to obtain an event structure; the application learns the definition process of the event pattern based on the candidate mentioned entity by using the generation model, and then automatically generates the event pattern, thereby avoiding modeling of all pre-defined event types and improving the generation efficiency; and the application designs a decoding constraint algorithm to finely control the pattern generation process, prevents obtaining non-standard results and ensures that the number of generated roles corresponds to the number of entities.

The application provides a GNSS dual-antenna directional state constraint method and system, which comprises calculating a baseline length between master and slave antennas estimated by Kalman filtering, updating a state variance covariance matrix by baseline state information estimated by Kalman filtering; when the Kalman filtering converges, judging whether the baseline state information estimated by Kalman filtering is available; when the baseline state information is available, calculating a state constraint gain of the dual antennas; correcting the baseline state information estimated by Kalman filtering and the state variance covariance matrix according to the state constraint gain. Based on the GNSS dual-antenna directional state constraint method, a GNSS dual-antenna directional state constraint system is also provided. The application is a post-test information based on Kalman filtering estimation independent baseline length constraint algorithm, which can improve the dual-antenna directional precision in a multipath environment and improve the stability of the heading of a mobile carrier in a complex environment with serious shielding.

The application relates to the technical field of marine environment monitoring, and particularly discloses a full-process intelligent management system for a sea red tide checking task, which comprises a visual control platform, and the visual control platform is communicatively connected with the following modules: a fragment task integration module used for fusing a fuzzy C-means clustering algorithm and a spatial topological constraint algorithm, automatically merging fragment tasks at a boundary and attributing a responsible party, the fragment task integration module comprising a fuzzy boundary membership weight unit and a jurisdiction buffer zone forced attribution unit; the application automatically merges fragment tasks at the boundary and attributes the responsible party according to the overlapping degree and historical rules by performing fuzzy C-means clustering membership weight on edge pixels of a remote sensing water color abnormal area and jurisdiction attribution based on a dynamic buffer zone, solves the problem of an unclaimed area, ensures that the checking task is quickly implemented, eliminates ambiguity of the attribution of the boundary task, and improves the emergency response time.

The application provides a global network topology metaphor map construction and visualization method and device based on a network space situation, and is applied to the field of data processing. The application completes accurate matching of network space objects and geographic elements through multi-rule mapping, and then generates a metaphor map by adaptively and continuously deforming the geographic space according to asset weights; node standard layout is realized in the deformation space through a constraint algorithm, a continuous network potential field is constructed by combining topological characteristics to complete potential energy assignment; the range of the potential field is constrained by contour extraction and boundary clipping, and a differentiated visualization effect is generated for network connection by adopting semantic hierarchical path generation; finally, multi-element integration is realized to achieve multi-layer rendering and interactive control, high-definition images and structured data are output, and a complete, standard and engineerable network space topology map construction process is formed.

An augmented reality calibration method and apparatus based on adaptive corner homography estimation, the method includes: (1) using a line segment morphology constraint algorithm to identify the 2D key corner coordinates of the tracking marker; (2) acquiring CT images and performing segmentation and three-dimensional reconstruction of craniofacial organs; (3) using a three-dimensional scanner to acquire three-dimensional models of the bidirectional tracking marker and organs; (4) extracting the 3D corners of the tracking marker in the above-mentioned scanning model based on the template of the tracking marker; (5) spatially registering the CT model and the scanning model, and aligning the 3D feature points and 2D feature points of the tracking marker based on the particle swarm optimization algorithm; (6) during the tracking process, extracting the 2D corner coordinates of the tracking marker in each frame, and using PNP homography to estimate the motion posture of the camera.

The invention belongs to the technical field of linkage decision-making of underground cavern site selection and axis selection, and provides an underground cavern axis generation and site selection scheme linkage decision-making method based on an arrangement rule base and a geometric constraint algorithm, and the method comprises the following steps: firstly, determining a candidate axis direction; secondly, based on the candidate axis direction, setting a main plant positioning and axis application rule, a correlation cavern relative position rule, a cavern spacing and geometric constraint rule and a geologic feature avoidance rule, and establishing a plant site-axis binding scheme; then, establishing a dynamic quantitative evaluation index related to the axis, and carrying out batch scoring on the factory site-axis binding scheme; and finally, obtaining an optimal factory site position and an optimal axis direction based on a scoring result.

The invention discloses a 5G control plane vulnerability mining method based on dual guidance of a state machine and security attributes, and aims to solve the problems that protocol analysis is easy to make mistakes and vulnerability mining cost is high due to frequent update of a 5G protocol version and realize efficient and automatic security analysis of a control plane protocol. According to the main technical scheme, the method comprises the following steps: firstly, automatically analyzing a protocol document based on a natural language processing technology, and generating an accurate protocol state machine (PSM) to replace complex and error-prone manual modeling; secondly, the generated state machine is used as legal process guidance, and a violation test template is generated in combination with 5G security attributes; and finally, dynamically generating a high-quality test case through grammar perceptual variation and a cost constraint algorithm, and executing an efficient fuzzy test on the 5G control plane protocol. Experimental results prove that the deep protocol logic vulnerabilities caused by unexpected state transition can be automatically mined, the vulnerability mining efficiency and coverage rate are remarkably improved, and meanwhile distribution of test resources is optimized.

The invention provides an emergency rescue path planning method and system based on old people falling detection, and relates to the technical field of path planning, and the method comprises the steps: collecting real-time video stream data in different regions of a pension community; inputting the real-time video stream data into a tumble detection model, and outputting an old man tumble detection result; when the old people fall down, determining accurate three-dimensional coordinates of the falling old people in a pre-constructed binocular SLAM map through a virtual binocular-scale consistency constraint algorithm; according to the accurate three-dimensional coordinates, semantic information in the binocular SLAM map and contextual information of rescuers, a Pareto optimal rescue path set is planned through a multi-objective optimization search algorithm; and introducing a dynamic weight vector, performing dynamic weighting operation on each Pareto optimal rescue path in the Pareto optimal rescue path set, and selecting the Pareto optimal rescue path with a minimum dynamic weighting result as a final rescue path.

The application provides a sub-health monitoring and early warning system based on a smart bracelet, and relates to the technical field of intelligent health monitoring and processing. Firstly, the photoelectric pulse wave, inertia and temperature multi-modal data collected by the smart bracelet are preprocessed, the heart rate variability features containing mixed information of metabolic noise and nervous pressure are extracted from the pulse wave, and the mixed factors representing the current body activity and heat metabolism state are constructed by using the inertia and temperature data. Then, based on the orthogonal projection constraint algorithm, the metabolic mixed factors are actively separated from the mixed heart rate variability features in the high-dimensional hidden space to obtain the pure autonomous nervous features after eliminating the environmental and metabolic interference. Finally, the pure features are quantified by the deviation from the individual historical rhythm benchmark, the risk index truly reflecting the psychological or nervous sub-health state is dynamically evaluated, and the graded early warning is triggered.

The application discloses a natural resource investigation and monitoring task management method and device based on a crowdsourcing mode, equipment and medium, relates to the technical field of data management, and comprises the following steps: constructing a structured data set by standardizing and packaging a natural resource investigation polygon task; calculating a matching degree and generating an allocation scheme by using a multi-constraint algorithm in combination with the state of crowdsourcing personnel; issuing an instruction to guide a terminal to collect encrypted data packets on site; obtaining a review result through automatic preliminary screening and multi-source cross verification; and dynamically updating a personnel credit file and adjusting a matching weight to realize hierarchical self-adaptive task allocation. The method can expand investigation manpower, intelligently schedule resources, control evidence quality in the whole process, form a credit self-optimization closed loop, and improve investigation efficiency and data standardization.

The application provides a high-quality and high-efficiency hologram generation method based on a complex amplitude constraint algorithm. The method comprises three steps: first, based on the intensity map and the depth map of the three-dimensional scene, the three-dimensional scene is processed in layers to obtain a set of layered images. Second, the inverse wavefront propagation calculation is performed on the layered images to generate the initial complex amplitude field on the hologram plane; then the wavefront propagation calculation is performed on the initial complex amplitude field on the hologram plane to generate the target complex amplitude field on the target plane. Third, the hologram is initialized by using the initial complex amplitude field on the hologram plane, and the wavefront propagation calculation is performed on the hologram to generate the reconstructed complex amplitude field of the hologram on the target plane; then the reconstructed complex amplitude field is constrained by using the target complex amplitude field on the target plane, and the reconstructed complex amplitude field is iteratively optimized to finally generate a high-quality hologram.