50 results about "Genetic programming" patented technology

The invention discloses a path planning heuristic function generation platform and method based on collaborative optimization of a large-scale language model and evolutionary computation. According to the technology, the large-scale language model (LLM) and evolutionary computation (EC) work cooperatively. The platform generates or mutates a heuristic function expressed as an executable code through LLM based on a structured prompt containing an environment context and performance feedback; and an EC framework (such as genetic programming) is combined with performance evaluation feedback to perform selection and iterative optimization on a heuristic code population, and population diversity is maintained. The method aims at overcoming the limitation that a traditional heuristic design is difficult and poor in adaptability, a high-quality heuristic function adapting to a complex and dynamic environment is automatically generated, and therefore the efficiency of a path planning algorithm and path quality are remarkably improved.

The invention provides an intelligent inspection and diagnosis system, method and device for a photovoltaic power station unmanned aerial vehicle and a medium, and the system comprises a heterogeneous perception fusion module which is used for constructing digital mirror image mapping of a power station global physical field through multi-mode sensor space-time coding and electromagnetic fingerprint matching; the group intelligent decision module is used for realizing autonomous task negotiation and anti-fragile path evolution of a multi-unmanned aerial vehicle cluster based on a dynamic Bayesian game model; the embedded diagnostic kernel module is used for running a quantization feature extraction algorithm at an edge computing node to realize component-level defect subsurface-level diagnostic reasoning; the superbody self-evolution module is used for continuously reconstructing a diagnostic knowledge graph by means of a genetic programming framework to realize Darwin asymptotic optimization of a system cognitive architecture; the problems that in unmanned aerial vehicle inspection, fault type judgment and accurate geographic positioning cannot be conducted online, photovoltaic array arrangement changes and sudden shielding scenes cannot be self-adapted, and transmission bandwidth limitation and analysis lag are likely to happen in a 5G weak coverage area are solved.

The invention discloses an integrated circuit fault supervision method and system for dynamic time slot allocation, and the method comprises the steps: collecting and preprocessing multi-source time slot data, and generating a standardized data set; based on the standardized data set, genetic programming is used for generating a mathematical formula for describing the relation between time slot allocation and fault detection; clustering the standardized data set by using fuzzy C-means clustering, and identifying a data state category; dynamically adjusting a time slot allocation strategy in combination with a mathematical formula and a clustering result, and generating a repair result; if abnormity is detected, an adjustment formula is quickly generated based on a mathematical formula and a clustering category, and repair is executed; and feeding back the distribution and repair result, and adaptively updating the mathematical formula and the clustering result. According to the invention, efficient adaptive optimization of dynamic time slot allocation and intelligent fault supervision in an integrated circuit system is realized.

The invention relates to the technical field of graph neural networks, in particular to a graph neural network architecture optimization method based on grammar genetic programming, and the method comprises the steps: S1, constructing a grammar rule library of a graph neural network architecture GNN; s2, based on the grammar rule base, generating an initial GNN architecture population through genetic programming; s3, predicting the performance of the individual GNN architecture in the population by using a Gaussian process proxy model; s4, searching an optimal GNN architecture in the syntax tree space through a genetic algorithm; s5, for the individual GNN architecture in the population, calculating a training probability based on an expected improvement function of the individual GNN architecture, if the training probability is higher than a preset evaluation threshold, selecting the individual GNN architecture to carry out actual training evaluation, obtaining the authenticity performance of the individual GNN architecture, and updating the Gaussian process agent model by using the authenticity performance; and S6, judging whether a preset optimization termination condition is met or not, if so, outputting the optimized GNN architecture, and otherwise, returning to the step S3. According to the method, the automation degree, efficiency and model performance of GNN model architecture search can be improved.

The invention provides a complex constraint-oriented time parallel unmanned aerial vehicle cluster dynamic planning method based on adaptive genetic programming, and belongs to the field of unmanned aerial vehicle path planning, and the method comprises the steps: initializing a genetic programming expression population; constructing a time parallel unmanned aerial vehicle cluster path planning model and performing adaptive value evaluation on the output of each individual in the population; the adaptive value loss of the failure scheme is set as dynamic penalty of self-adaptive change; and performing iterative optimization on the population based on survival of the fittest, and applying the optimal individual as a final path scheme to the unmanned aerial vehicle cluster to execute the inspection task. According to the invention, after the unmanned aerial vehicle takes off from the specified charging station, all inspection tasks can be completed in parallel under limited electric quantity, electric quantity supplementation is carried out through the charging station, and the unmanned aerial vehicle finally returns to the original station for maintenance and charging; according to the method, under the condition of complex problem constraint, approximate optimal path node selection can be effectively generated, a reasonable task allocation strategy and a routing inspection route are obtained, and the task completion efficiency is remarkably improved.

The invention discloses a modeling method and system for a hydrogen energy unmanned aerial vehicle cluster energy complementing scheme. The method comprises the steps that the flight process of an unmanned aerial vehicle is decomposed into a plurality of independent events; managing the independent events by adopting a three-alignment principle; calculating energy consumption in the flight process of the unmanned aerial vehicle based on a nonlinear energy consumption model; rasterization processing is carried out on the continuous flight space, obstacle avoidance planning is carried out on the flight path of the task unmanned aerial vehicle, and the flight path of the task unmanned aerial vehicle is formed; and circularly inserting random points in the flight path of the task unmanned aerial vehicle by using stack genetic programming to serve as energy complementing meeting points, and allocating the energy complementing meeting points to the corresponding energy complementing unmanned aerial vehicle path to form an energy complementing scheduling scheme. According to the method, complex constraints such as time, space and energy in a scene can be effectively modeled, a detailed model and a planning framework are provided for a collaborative energy complementing task of an unmanned aerial vehicle cluster, the difficulty of subsequent design of an optimization algorithm is reduced, the solving efficiency and feasibility are improved, and the accuracy of unmanned aerial vehicle planning is expected to be improved.

The invention discloses a dynamic scheduling strategy generation method and device based on a large language model, which utilizes the natural language processing capability of the large language model to generate and perfect a scheduling heuristic algorithm. Through an initialization method based on a big language model, a knowledge extraction method based on the big language model and a sorting selection method based on the big language model, complex scheduling requirements described by natural languages can be met, so that rapid adjustment can be performed without a large amount of manual intervention to adapt to constantly changing parameters; therefore, the flexibility of the scheduling algorithm is enhanced, the calculation burden of the genetic programming method is reduced to the greatest extent, and the dynamic scheduling effect is finally improved.

The invention discloses a hyper-heuristic order grouping and robot sorting path integrated planning method based on genetic programming. The method comprises the following steps: acquiring order demand information and warehouse layout information of an intelligent manufacturing workshop production system; determining an objective function of order grouping and sorting path planning; establishing a double-commodity network flow model integrating order grouping and path planning; setting constraint conditions for the double-commodity network flow model; a priority function rule is generated in a genetic programming hyper-heuristic mode, a dynamic programming strategy is combined, the double-commodity network flow model is solved, and the optimal result of order grouping and batching and robot sorting paths is obtained. According to the method, the sorting efficiency optimization problem of multi-variety and high-frequency orders in the intelligent manufacturing feeding warehouse is solved, and the solving efficiency and rule generalization ability can be remarkably improved, so that the sorting time is effectively shortened, the intelligent manufacturing short window requirement is met, and theoretical guidance and practical support are provided for improvement of the warehousing feeding efficiency.

The invention discloses a crop early recognition method and system based on genetic programming customization characteristics and a storage medium, and the method comprises the steps: obtaining an initial image of a target region and a ground sample collected on site, generating the initial characteristics of a target crop through the spectral band of the initial image, and generating an initial population according to the initial characteristics of the target crop; calculating a feature value of the initial feature, and performing binary classification on the feature value according to a preset feature threshold value; based on the classification label and the real label of the ground sample, obtaining an accuracy rate of binary classification, and obtaining a fitness value of the initial feature according to the accuracy rate; iterating the initial population through a selection method and a genetic operator to obtain customized features of the target crop; and performing crop classification on the target crops based on the customized features, and obtaining a classification drawing result of the early crops or seasonal crops according to a classification result. According to the method, the required sample size can be reduced, and meanwhile, accurate early-stage and season crop classification and mapping results can be obtained.

The invention relates to the technical field of industrial scheduling, and discloses a flexible job shop self-organizing scheduling-oriented multi-target dual hyper-heuristic method, which comprises the following steps of: generating a process selection rule and an interval selection rule by utilizing a genetic programming rule, and generating a rule set; based on a deep reinforcement learning method, a dynamic decision strategy is constructed in combination with a rule set, and multi-step action sequence optimization is carried out when self-organizing scheduling is triggered; and generating an instance through random combination of parameter indexes of a predetermined dynamic event, and calculating a performance index according to the generated instance to realize feasibility verification. Through a dynamic collaborative optimization mechanism of self-organizing scheduling, an autonomous decision closed loop can be realized under multiple disturbances such as equipment failure, processing fluctuation, new order insertion and the like, and the self-healing capability, response speed and anti-interference toughness of a production system in a dynamic environment are remarkably improved; and an intelligent decision-making scheme with an autonomous evolution capability is provided for a complex scheduling problem in an intelligent manufacturing scene.

The invention belongs to the technical field of intelligent manufacturing, and discloses a digital twinning workshop real-time scheduling method for limited transportation resources and charging constraint scenes, which comprises the following steps: constructing a real-time scheduling framework based on digital twinning and deep reinforcement learning to realize real-time interaction of virtual and real data; proposing a two-stage real-time scheduling model based on deep reinforcement learning; taking the minimum completion time as a target, and establishing a Markov decision process of the DFJSP-LTR-C; five key elements including an interaction point, a real-time scheduling process, a real-time state feature, an action space based on improved genetic programming and a composite reward function are designed for the scheduling model; an IAD3QN training method based on a multi-head attention mechanism is provided to train a scheduling agent. According to the method, adaptive collaborative optimization of production and transportation resources is realized under the condition of considering limited transportation resources and charging constraints, the maximum completion time is effectively reduced, and the feasibility and robustness of a scheduling scheme in an actual workshop are improved.

Method and apparatus (10) for controlling a modification process of hygroscopic material (15) comprising method steps of: measuring at least one process variable from the modification process at least during the modification; measuring at least one process variable from the hygroscopic material at least during the modification; calculating at least one intermediate control parameter by a neural network busing at least the measured process variables as input parameters of the neural network; and controlling the modification process by using genetic algorithms and genetic programming based on the said at least one intermediate control parameter determined by the neural network.

The invention discloses an EFSM model error positioning method based on spectrum formula automatic combination optimization, and the method specifically comprises the following steps: obtaining a model spectrum of a to-be-tested EFSM model, generating risk assessment formulas through employing a genetic programming technology, and forming a candidate formula pool; a whale optimization algorithm is adopted to search an optimal formula subset in each formula cluster after candidate formula clustering; constructing and training an error positioning model; and inputting each risk assessment formula in the optimal formula subset into an error positioning model according to a normalized suspicion degree vector calculated by a model frequency spectrum of a to-be-tested EFSM model, generating a suspicion degree value for each transition in the to-be-tested EFSM model, and generating a transition check sorting table. According to the method, automatic generation, optimization and combination of the risk assessment formula are realized, the EFSM model transitions are ranked according to the suspicion value of each transition, and the performance and efficiency of error positioning are remarkably optimized.

The invention discloses a dual-tree genetic programming method for processing a long-tail image classification problem, and the method comprises the following steps: constructing a dual-tree genetic programming individual which comprises a data enhancement tree and a feature extraction tree; setting a staged sampler; performing a multi-generation evolution process, wherein each generation comprises population initialization, individual fitness evaluation, selection, crossover and mutation operation; after the evolution is finished, outputting a dual-tree individual with the highest fitness as a final classification model for classifying a new image; the method is simple and efficient in model deployment and has practical value.

A method for detecting changes in remote sensing images based on genetic programming is disclosed. This method is used to detect changes in two remote sensing images of the same area taken at different times. The method includes the following steps: Step A: Two remote sensing images of the same area taken at different times are acquired using a computer, and the two images are calibrated using the same coordinate system. Step B: From the two remote sensing images selected in Step A, at least 100 areal samples are selected as sample data. Step C: Based on the sample data obtained in Step B, a threshold function for comparing the two remote sensing images is calculated using genetic programming to detect changes between the two images. The genetic programming-based method for detecting changes in remote sensing images provided in this application can fully explore the implicit information between the features of images from different time periods, effectively improving the accuracy of change detection and significantly increasing detection efficiency.

This invention relates to the fields of artificial intelligence and computer vision, and provides a few-shot fine-grained image classification method based on multi-scale feature extraction, attention, and relation enhancement using genetic programming. The method includes: extracting multi-scale deep features using a pre-trained deep feature extraction network (preferably ResNet-18); designing a strongly typed genetic programming tree structure comprising an input layer, a multi-scale feature extraction layer, a channel selection layer, an attention layer, a feature concatenation layer, and an output layer; enhancing discriminative regions and suppressing background noise through a spatial attention mechanism; developing a prototype-query relation enhancement module to amplify the regions of common interest between the support set and the query set to enhance feature representation; and using the sum of classification accuracy and cluster separation score as a fitness function to guide the evolutionary search. This invention combines deep neural network representation with genetic programming evolutionary search, achieving excellent classification performance on fine-grained few-shot image classification tasks while maintaining interpretability.

The invention discloses a method for generating circuit topology based on a transfer function, relates to the technical field of circuit design, and solves the technical problem that it is difficult to combine an artificial intelligence method in circuit design to improve the efficiency and reliability of analog circuit design. The method comprises the following steps: based on a graph theory, establishing a connected graph G under a given RLC circuit structure and element parameters; deriving the relationship between the transfer function and the impedance or admittance of the network nodes of the connected graph G based on the RLC circuit; searching and calculating a tree and a secondary tree required by the transfer function, and calculating to obtain a final expression of the transfer function; analyzing the order and the structure of the transfer function, and combining specification constraints and design specifications of circuit design to obtain a circuit design rule; and searching topology and parameters of the RLC circuit through genetic programming to obtain an optimal topological structure and an optimal element admittance value. According to the method, automatic search of genetic programming is guided by analyzing the hard constraint rule set, and the efficiency and reliability of circuit comprehensive design are remarkably improved.

The invention discloses an eVTOL collaborative design optimization method based on improved genetic programming, and the method comprises the steps: firstly constructing pneumatic, propulsion and dynamics high-fidelity models of an eVTOL takeoff stage, building an original collaborative optimization problem, and solving the problem through a direct transcription method; secondly, multi-target genetic programming fusing a root mean square error, an akaike information criterion, a predicted residual sum of squares and a Bayesian information criterion is creatively adopted, and an agent model for calculating thrust is constructed to replace a high-fidelity thrust model to solve and obtain optimal design parameters. The error between the optimal solution obtained by the method and the optimal solution obtained by using the high-fidelity model is very small, the calculation cost is remarkably reduced, and multidisciplinary efficient collaborative optimization is realized.

The invention discloses a pre-training model guided genetic programming-based battery life prediction method. The method comprises the steps of defining a battery life prediction target and battery cycle characteristics; the method comprises the following steps: generating a data point pair set by using a mathematical expression containing battery cycle characteristics, constructing a training data set, and pre-training a Transform model; collecting battery data, and constructing a battery data set; inputting the battery data set into a Transform model, generating a guide sub-population by using the Transform model, and combining the guide sub-population with the generated random sub-population to construct a hybrid initial population of genetic programming; iterative evolution is carried out on the mixed initial population, mutation operation is carried out, and the mutation operation is executed based on semantic back propagation and semantic guidance of a Transform model; and judging whether the evolution reaches a termination condition, if the evolution is terminated, outputting a mathematical expression, and inputting the battery cycle characteristics of the to-be-tested battery into the mathematical expression to obtain a battery life prediction result.

The invention relates to a complex product assembly sequence planning problem solving method considering human factors, and the method comprises the steps: comprehensively introducing human factors such as cognition, physiology, psychology, skills and organization in a complex product assembly sequence planning process, and carrying out the optimization solving of an assembly sequence based on genetic programming. By effectively deciding the human factor data acquisition mode, obtaining the state data of the workers and combining with the constraint of human factors to adjust the assembly sequence, the optimal assembly sequence planning considering the states of the workers is finally realized, so that the efficiency and reliability of the assembly process are improved. Therefore, the problems that in the prior art, manual planning depends on experiences of engineers, human factors are difficult to comprehensively consider, and modern complex product manufacturing requirements cannot be met are solved.

The application discloses a data efficient image classification method based on multi-tree genetic programming, comprising the following steps: obtaining an image to be classified; pre-processing the image to be classified; a genetic programming individual respectively processes red, green and blue channels of the image, and performs multi-scale operation, region extraction, feature extraction and feature connection on the channels; the individual obtained through evolution is used for feature conversion on the image to be classified to obtain new features and normalization; and the new features are input into a classifier to output a classification result of the image to be classified. The color feature extraction method based on the multi-tree genetic programming can learn color features with discrimination and rich information, thereby improving classification accuracy; and the multi-scale feature extraction can enhance the ability of capturing more comprehensive and rich image features for classification.

The application belongs to the field of artificial intelligence and finance, and relates to a risk identification factor mining method, which comprises the following steps: obtaining different data types of data, setting different types of operators according to an insurance risk identification target, constructing a genetic programming model according to the different types of operators, initializing a formula population, iteratively calculating a risk explanation degree, continuously optimizing a formula tree through a genetic algorithm, obtaining a final formula tree population, selecting a formula tree with the highest risk explanation degree from the final formula tree population as a risk identification factor, and testing and optimizing the risk identification factor to obtain an optimal risk identification model. The application also provides a risk identification factor mining device, a computer device and a storage medium. In addition, the application also relates to blockchain technology, and text data and numerical data can be stored in the blockchain. The application can better realize automatic identification of insurance risks and improve the accuracy of risk identification.

The application discloses a photovoltaic power station power prediction method based on prior knowledge guided genetic programming, first, obtaining training data preprocessed by symbol normalization, learning photovoltaic power generation symbol rules through self-supervised pre-training of a Transformer model, and outputting a prior symbol vector of a target function; a double fitness collaborative optimization mechanism containing numerical fitting accuracy and physical mechanism similarity is designed, and the prior vector is used to strengthen and select individuals with high physical matching degree; a Pareto multi-objective optimization is used to balance the double-dimensional conflict, the prior knowledge is transferred to the whole evolution process of genetic programming, and finally the optimal explainable prediction model is extracted from the Pareto frontier solution set. The application solves the problems of traditional genetic programming evolution blindness, easy falling into local optimum and poor physical consistency of generated model, realizes explicit physical explainability of the model while ensuring prediction accuracy, and can be widely applied to power generation scheduling and operation optimization of photovoltaic power stations.

The present invention discloses a method, system and storage medium for early crop recognition based on customized features of genetic programming. The method includes: obtaining an initial image of a target area and ground samples collected in the field, generating initial features of a target crop by using spectral bands of the initial image, and generating an initial population according to the initial features of the target crop; calculating eigenvalue of the initial features, and performing binary classification on the eigenvalue according to a preset feature threshold; obtaining the accuracy of the binary classification based on the classification label and the true label of the ground samples, and obtaining the fitness value of the initial features according to the accuracy; iterating the initial population through a selection method and genetic operators to obtain customized features of the target crop; classifying the target crop based on the customized features, and obtaining a classification mapping result of early crops or in-season crops according to the classification result. The present invention can obtain accurate classification and mapping results of early and in-season crops while reducing the required sample size.

A method is provided that includes accessing a multivariate time series of flight data for an aircraft, and iteratively performing runs of genetic programming on groups of the sensors. A population of computer programs is randomly generated from a selected group of the plurality of sensors, and primitive functions selected from a library of primitive functions. The population is iteratively transformed into new generations of the population, and includes sub-rankings of the group of sensors based on a quantitative fitness determined according to selected fitness criterion. A ranking of the group of sensors from the sub-rankings of the group of sensors is produced. An aggregate ranking of the plurality of sensors is produced from the ranking of the group of sensors over a plurality of iterations. And the subset of sensors is selected from the aggregate ranking of the plurality of sensors, and according to selected optimization criterion.

The invention relates to the field of traditional Chinese medicine diagnosis, and discloses a traditional Chinese medicine diagnosis and treatment knowledge graph construction method and system based on knowledge reasoning, and the method comprises the steps: constructing a traditional Chinese medicine diagnosis and treatment knowledge graph, and carrying out the node attribute distribution and node relation determination; on the basis of a mode of combining anomaly detection of statistical analysis and machine learning, abnormal nodes in the traditional Chinese medicine diagnosis and treatment knowledge graph are judged, and root cause node alternative items are identified; the centrality of each node in the traditional Chinese medicine diagnosis and treatment knowledge graph is analyzed and calculated through a graph theory, and root cause node alternative items are preliminarily sorted according to the centrality; optimizing the sorting rule of the root cause node alternative items by using genetic programming and a causal discovery algorithm to obtain sorted root cause node alternative items, and determining root cause nodes; and constructing a diagnosis and treatment path knowledge graph according to the root cause nodes, the related diagnosis and treatment information nodes and the causal relationship among the nodes. According to the invention, the accuracy and efficiency of the traditional Chinese medicine diagnosis and treatment path are improved, and the root cause node identification sorting is optimized.

The invention discloses a battery capacity degradation curve prediction model based on a genetic programming optimization encoder. The method comprises the following steps: firstly, acquiring time sequence data of battery charging and discharging multiple signals, and constructing a variational auto-encoder for each signal; replacing an encoder of the auto-encoder with a genetic programming GP structure, and capturing a complex nonlinear relationship between signals; and a multi-tree GP structure is adopted and pruning optimization is carried out, so that the model precision and efficiency are improved. And combining the output of the optimized GP encoder into a strong encoder, and carrying out joint modeling on multiple signals. And an artificial neural network (ANN) is used as a decoder to decode the low-dimensional features generated by the GP encoder to predict the battery capacity. And training an ANN decoder in combination with the real capacity data to generate a battery capacity decline curve. The method can accurately capture the state change rule of the battery, and has wide application prospects in the fields of battery management, life prediction, health monitoring and the like.

The present invention relates to the technical field of production scheduling, and specifically to a flexible job shop scheduling method for reconfigurable manufacturing unit capabilities, comprising: obtaining configuration parameters; constructing a scheduling model using the configuration parameters; establishing two heuristic genetic programming individuals, including the selection and reconstruction of reconfigurable manufacturing units and the sorting of current operations in the reconfigurable manufacturing units; initializing the population and calculating the fitness of each genetic programming individual in the current population, and then determining whether the evolution completion condition has been met. If so, the optimal genetic programming individual in the current population is selected for flexible job shop scheduling; otherwise, the population is evolved and the step of calculating the fitness of each genetic programming individual in the current population is returned. The priority of each choice at the decision point is generated heuristically, and the optimal individual is obtained for flexible job shop scheduling with the optimization objectives of minimizing delay, minimizing maximum duration, and minimizing total running time, thereby ensuring the performance of the flexible job shop.

This invention discloses a method and system for constructing a rainfall-runoff model. The method involves collecting and preprocessing relevant daily sequence data within a watershed; constructing a hydrological model component library; pre-assembling the hydrological model structure; defining a parameter space; performing a collaborative search using genetic programming; simulating daily runoff using the optimal model structure and parameters obtained through the search and calibration; evaluating the model's generalization performance; and outputting the optimal model structure type, optimized parameter vector, calibration set, validation set performance indicators, and runoff simulation sequence. This invention can automatically generate rainfall-runoff models with adaptive model structures and interpretable hydrophysical mechanisms, effectively improving the automatic discovery capability of model structures and the interpretability of hydrophysical mechanisms, while reducing manual workload while avoiding overfitting.

The invention discloses a multi-robot collaborative scheduling forest fire extinguishing method based on genetic programming, and the method comprises the steps: obtaining task data through analog simulation, and dividing a training set and a test set; calculating phenotypic features of the individuals, and constructing an agent auxiliary model; in the evolution process, a large number of filial generations are generated through crossover and variation, then the filial generations are divided into two sub-populations, firstly, niche division is conducted on the first sub-population through phenotypic characteristics, an individual with the minimum scale is selected from each niche, then the fitness of individuals in the second sub-population is estimated through an agent model, and the individuals with the top ranking are selected; and after iterative evolution is completed, selecting an individual with the optimal fitness to test to obtain an optimal scheduling rule. Under the condition of complex constraints, multiple robots can be reasonably dispatched, the fire extinguishing and rescue time is shortened, the system performance is improved to the maximum extent, and good stability and interpretability are achieved.