349 results about "Uncertainty factor" patented technology

The invention discloses a system combat ability dynamic game comprehensive evaluation method based on deep learning, and relates to the technical field of combat ability evaluation.According to the method, key features of time and space in a battlefield environment are dynamically extracted by combining a multi-sensor fusion technology with a time sequence convolutional network and a graph neural network, a situation model is updated in real time, and the dynamic game of the system combat ability is comprehensively evaluated. The optimization process of unmanned cluster marshalling and task allocation is accelerated by utilizing a near-end strategy optimization PPO and transfer learning technology, and adaptive adjustment of a marshalling scheme on complex task requirements is realized by defining a multi-task collaborative efficiency index; in the aspect of strategy optimization, a multi-agent game model driven by deep reinforcement learning is constructed, friend or foe resource allocation, dynamic environment change and uncertainty factors are integrated, an optimal strategy is effectively generated, and low-efficiency schemes are eliminated through combat scene simulation; and meanwhile, through a real-time monitoring and dynamic planning mechanism, emergencies such as target change and emergency task insertion are dealt with, and the task execution continuity and cooperative efficiency are improved.

The invention provides a harbor district energy double-layer coordination optimization method oriented to multiple interest subjects. The method comprises the steps of performing fusion processing and data cleaning on real-time operation data, historical operation data and environmental parameter data of a harbor district energy management system; performing multi-scale decomposition and feature importance evaluation by adopting a time sequence decomposition algorithm; probability modeling and multi-scale prediction are carried out on the basis of feature recognition uncertainty factors; constructing an upper-layer government regulation and control model and a lower-layer harbor district-ship east game model, and calculating a balance coefficient; and performing monthly strategy optimization, weekly scheduling optimization and hour-level real-time control based on the balance coefficient. By constructing a complete technical chain of data processing, feature extraction, prediction modeling, game optimization and real-time control, dynamic balance of benefits of the government, the harbor district and the ship eastern is realized, and the operation efficiency and the control precision of the harbor district energy system are remarkably improved.

The invention discloses a harbor district accident risk visualization analysis method based on a network topology structure, and the method comprises the steps: taking a key facility and an important region as network nodes in a harbor district, determining a connection relation to obtain a network topology structure, analyzing historical cases to obtain a determined risk factor set, obtaining an uncertain factor set through edge calculation, and carrying out the calculation of the uncertain factor set. The method comprises the following steps: constructing an accident tree to carry out quantitative evaluation on network nodes and connection risks, constructing a risk evolution model, extracting an accident cause chain and calculating a risk influence range, visualizing a network topology structure, carrying out color mapping on the accident cause chain and the risk influence range, and then adding the accident cause chain and the risk influence range to obtain a three-dimensional topology view. According to the method, the network topology structure visualization analysis of the accident risk of the harbor district can be realized, the risk is comprehensively evaluated, the subsequent management decision of the harbor district is optimized, and meanwhile, the method has relatively good interpretability.

The invention discloses a production safety accident emergency disposal scheme intelligent generation method and system, and the method comprises the steps: obtaining the spatial-temporal characteristics of historical accident cases, calculating the correlation degree, building an accident prediction network based on the correlation degree, simulating uncertain factors, calculating the similarity between a current accident and the historical cases, determining the prior probability, and carrying out the accident development reasoning. The method comprises the steps of tracing accident hazard degrees of different production links, obtaining an cause chain, generating an emergency resource allocation strategy set by utilizing Markov decision, constructing target function optimization, obtaining an emergency disposal scheme, monitoring production process, equipment state and personnel configuration changes in real time, and dynamically adjusting the emergency disposal scheme to adapt to the changes. According to the method, the historical data, the graph neural network and the Markov decision are combined, accident prediction and emergency resource intelligent allocation are realized, the method can adapt to the change of a production environment in real time, the disposal efficiency and safety are improved, and meanwhile, the method has relatively good interpretability.

The invention belongs to the field of intelligent manufacturing, and particularly relates to an intelligent scheduling method for collaborative manufacturing of tunnel boring machines, in the method, multi-source heterogeneous data including design data, process data, production data, material data and the like are acquired, and a rich data basis is provided for intelligent scheduling. The data fusion method based on the ontology is adopted, and the problems of semantic heterogeneity and structural heterogeneity of multi-source heterogeneous data are effectively solved. By constructing the tunnel boring machine manufacturing field ontology model, semantic association and sharing of data from different sources are realized, and the availability and understandability of the data are improved. An algorithm combining mixed integer programming and deep reinforcement learning is provided for intelligent scheduling of tunnel boring machine collaborative manufacturing. A robust optimization method is introduced to enhance the robustness of the scheduling scheme, and the influence of uncertain factors such as raw material supply and equipment maintenance in the manufacturing process of the tunnel boring machine is considered.

The invention belongs to the technical field of multi-energy micro-grid cooperative regulation and control. The invention discloses a multi-energy micro-grid coordinated regulation and control system based on cross-layer knowledge injection and federated distillation. The system is characterized by comprising a cross-layer knowledge injection network; a federal knowledge distillation module; and the uncertainty map regulation and control module is used for constructing an MEMG uncertainty association map, learning the influence weight of each uncertainty factor on a regulation and control decision through a map attention mechanism, and realizing a dynamic risk avoidance strategy. The invention discloses a multi-energy micro-grid cooperative regulation and control method based on cross-layer knowledge injection and federated distillation. The method is characterized by comprising the following steps: step 1, MEMG topology knowledge coding; 2, cross-layer knowledge injection training is carried out; step 3, federal knowledge distillation optimization; and step 4, performing uncertainty map regulation and control. According to the system and the method, the precision, the robustness and the data privacy protection capability of MEMG regulation and control are improved, and the system and the method are suitable for efficient collaborative optimization of the park-level multi-energy microgrid.

The invention relates to the technical field of agricultural data dynamic perception, in particular to an agricultural data dynamic perception scheduling method based on the Internet of Things, and the method is realized based on an Internet of Things sensor, an edge computing platform and an edge server. Comprising the following steps: deploying Internet of Things sensors including a meteorological station, a soil humidity monitor and an unmanned aerial vehicle inspection system, and deploying a real-time data processing module on an edge server through an edge computing platform. According to the method, a dynamic cost-benefit analysis model is constructed, various factors and dynamic changes in agricultural production are comprehensively considered, a multi-objective optimization algorithm and a dynamic planning technology are applied, optimization of resource allocation and maximization of long-term benefits are achieved, in addition, uncertainty factors are processed by introducing a fuzzy mathematical method, and the method is suitable for large-scale popularization and application. The method improves the robustness and reliability of analysis, and solves the problems of lack of dynamics, incomplete consideration factors and limited optimization means in a traditional scheme.

The invention relates to the technical field of power grid side large-scale wind and light and energy storage configuration, in particular to a wind and light storage capacity distribution robust optimization configuration method, device and equipment and a medium. Establishing a power grid side wind and light energy storage optimization configuration model considering inertia constraint; uncertain factors in the optimal configuration model are considered, and a probability distribution fuzzy set based on a mixed norm is constructed; establishing a two-stage distribution robust optimization configuration model based on data driving; converting the two-stage distribution robust optimization configuration model into a mixed integer linear programming model by using a linearization technology; and solving the mixed integer linear programming model by using a column and number generation algorithm to obtain an optimal configuration and operation scheme of each device. According to the method, the economical efficiency and load fluctuation can be balanced, and the problems of frequency instability and the like of a large-scale wind and light energy grid-connected power grid are avoided by considering inertia constraint.

The invention provides a latticed column perpendicularity control method based on multi-source fusion and predictive compensation, and belongs to the technical field of perpendicularity control, a novel anti-interference sensor is combined with multi-point distributed installation and advanced data transmission and processing technologies, perpendicularity data of a latticed column can be accurately obtained in real time, and the perpendicularity control accuracy of the latticed column is improved. A reliable three-dimensional deviation cloud picture is generated; according to the intelligent hydraulic jack set control system based on real-time data feedback, the adjustment time is greatly shortened, the problem that the insertion deviation exceeds the limit due to adjustment lag is solved, the perpendicularity control precision of the latticed column is improved, and it is ensured that the insertion deviation of the latticed column is controlled within a small range; through comprehensive optimization of the construction process, including drilling pretreatment, equipment debugging and calibration, lowering process monitoring, concrete pouring process monitoring and the like, the stability and reliability of the whole latticed column perpendicularity control process are further improved, uncertain factors in the construction process are reduced, and the engineering quality and the construction efficiency are improved.

The invention belongs to the technical field of automatic driving, and particularly relates to an automatic driving decision-making method and system with dynamic risk perception and attention focusing and a vehicle, and the method comprises the steps: predicting the track of a surrounding vehicle in real time through a multi-feature Gaussian weighted particle filtering algorithm, and improving the prediction precision through combining a vehicle kinematic model and resampling optimization; constructing a comprehensive evaluation model fusing transverse and longitudinal risks, and dynamically quantifying the collision risk of the vehicle and surrounding vehicles; and inputting the risk value as a key state feature into a double-depth Q network based on attention mechanism enhancement, focusing key information through a feature attention distribution mechanism, and generating an optimal driving decision in combination with a multi-target reward function. Compared with the prior art, the method solves the problems of insufficient quantification of uncertainty factors, incomplete risk assessment and low decision-making efficiency of automatic driving in a complex dynamic environment, and significantly improves the risk perception capability and decision-making safety of the automatic driving vehicle.

The invention belongs to the technical field of virtual power plant instruction decomposition, and particularly relates to a virtual power plant dispatching instruction rapid decomposition method based on multiple agents. According to the method, the change and demand fluctuation of the power system can be more flexibly coped with, the compensation value is calculated based on the historical data and the current state of the intelligent agent, reasonable distribution and optimal use of system resources, loads and power are ensured, the overall operation efficiency of the virtual power plant is improved, and through the setting of the instruction decomposition level, the operation efficiency is improved. Task allocation of the intelligent agents can be dynamically adjusted according to actual conditions, overload of a single intelligent agent is avoided, execution efficiency of scheduling instructions is improved, high-energy-consumption tasks can be preferentially arranged when power is low by combining current power data, or generating capacity and operation cost are reduced when the power is high, economic benefits are improved, and the method is suitable for large-scale popularization and application. Compensation value calculation and decision making are carried out by utilizing historical data of the intelligent agent, so that the scientificity and accuracy of dispatching instruction decomposition are improved, and the influence of uncertain factors in the dispatching process is reduced.

The invention relates to a flexibility demand modeling method based on a probability box, and belongs to the field of flexibility demands of power systems. According to the method, a probability box theory P-Box is introduced to describe random uncertainty and cognitive uncertainty of wind power output, photovoltaic output and load demand prediction errors; introducing a conditional value-at-risk theory CVaR to a confidence interval boundary of the probability box, and intercepting an uncertainty factor boundary; and establishing a source-load double-side flexibility quantification model based on a prediction error of intercepting an uncertain factor boundary.

The invention relates to the technical field of feed production, and discloses a feed production control method and system based on deep learning. Aiming at the problems of low production efficiency and unstable product quality caused by uncertain factors such as raw material quality fluctuation, equipment state change and the like which are difficult to deal with by a traditional feed production method, an improved CrossFormer deep learning model is adopted, and feed production process data are acquired and preprocessed in real time; and inputting the preprocessed data into a model to carry out validity evaluation on the current production strategy, and giving an adjustment instruction. And automatically adjusting a feed production strategy according to an output result of the model and an adjustment instruction, and recording all implemented adjustment measures, production data comparison before and after adjustment and equipment monitoring information to form a production optimization log. According to the method, the intelligent level of feed production is remarkably improved, the production cost is reduced, and the product quality and the market competitiveness are improved.

The invention discloses a historical data driving method and system for power load prediction, and relates to the technical field of load prediction. Compared with a previous load prediction model, the problem that a common single power load prediction model is difficult to adapt to power load prediction requirements of different time lengths in different power utilization areas is solved; through a historical data driving method, short-term and long-term power load prediction of a region or a grid can be effectively carried out, and a short-term load prediction model further optimizes an LSTM network which carries out parameter optimization based on an improved particle swarm algorithm through an A3C algorithm, so that the overall prediction performance can be improved. And important support is provided for operation and planning of a power system. The short-term load prediction model is further adjusted to be a long-term load prediction model based on an improved Monte Carlo simulation method, various possible scenes and uncertainty factors can be considered, the prediction performance of long-term load prediction is improved, and important data support is provided for efficient operation and optimization of a power system.

The invention discloses a network construction type novel energy storage multi-objective optimization coordinated scheduling method, which comprises the following steps: S1, energy storage classification and data acquisition: (1) according to application scene function requirements, dividing energy storage types according to rated continuous discharge duration; (2) data acquisition; s2, calling an energy storage scene and combining with weight parameter setting to construct a multi-objective optimization model: (1) establishing the multi-objective optimization model with the purposes of minimizing the system operation cost, maximizing the energy storage utilization rate and improving the power grid stability; (2) setting constraint conditions; s3, a dynamic optimization algorithm: (1) adopting an improved multi-target particle swarm algorithm or a genetic algorithm, introducing an adaptive weight mechanism, and combining real-time data to dynamically adjust the weight of a target function; (2) aiming at uncertainty factors, embedding a scene analysis method or a robust optimization strategy, and judging whether the comprehensive efficiency is optimal or not; and S4, scheduling execution and monitoring.

The invention discloses an urban multi-water-source joint scheduling method based on a discrete scene set and a robustness decision, and the method comprises the steps: researching the characteristics of multiple uncertainty factors of urban multi-source water supply, and generating a multiple uncertainty scheduling scene set through a Latin hypercube sampling method; constructing a water supply city regulation and storage reservoir and external water source joint scheduling model and a water receiving unit internal optimization scheduling model; and constructing a robustness decision-making-based urban annual multi-water-source combined scheduling model. A multi-uncertainty scene set and a robustness measurement method based on an expected benefit index are utilized, the minimization of the annual water level fluctuation risk and the urban water shortage risk of a regulation and storage reservoir is taken as a scheduling target, an urban multi-water-source combined scheduling model based on a robustness decision is constructed, the rationality and the applicability of the robustness scheduling model are verified, and the urban multi-water-source combined scheduling model is established. And analyzing a robust decision scheduling result under an uncertain condition.

The invention discloses a cross-basin water transfer project adaptability regulation and control method under uncertainty, and belongs to the technical field of reservoir regulation and control. Comprising the following steps: step 1, generating multiple uncertain scenes as an input side of an interbasin water transfer project simulation scheduling model; step 2, constructing an interbasin water transfer project simulation scheduling model, and analyzing project operation conditions in an uncertain scene; 3, constructing an adaptive scheduling framework based on a hedging principle, and performing multi-objective optimization by using an NSGA-II algorithm; according to the method, an AOMU model for coordinating water transfer, power generation and energy consumption targets under adverse conditions is established, the model can be used in a cross-basin water transfer project under uncertainty, the toughness of the project to cope with the uncertainty and adverse water transfer conditions can be effectively improved, and economic benefits are improved while water transfer is guaranteed; the problem that supply and demand imbalance is easily caused by improper scheduling of traditional uncertainty factors is solved.

The invention relates to a disturbance-containing mechanical arm trajectory tracking control double-Q reinforcement learning method, and belongs to the technical field of mechanical arm intelligent control. According to the method, a double-Q reinforcement learning method is adopted to solve the problem of trajectory tracking control of the interfered mechanical arm. An interference observer is designed to estimate and counteract the influence of external interference and model inaccuracy, and the control precision and interference suppression capability of the mechanical arm system are improved; a tracking controller based on a double-Q reinforcement learning method is designed, and the control cost is kept while the dynamic and steady-state performance of the system is improved by utilizing the excellent performance of a double-Q learning algorithm; in addition, the problem that the Q value is too high in a traditional Q learning method is solved through the double-Q reinforcement learning method. According to the method, the advantages of the double-Q reinforcement learning method are effectively utilized, under the condition that the system contains disturbance and uncertain factors, the fast tracking performance of the mechanical arm system on the expected trajectory is achieved, and the good steady-state performance is achieved.

The invention provides a radiation shielding multi-objective optimization design method based on a Bayesian neural network, and the method is characterized in that the method comprises the following steps: S1, obtaining sample data; s2, network construction and evaluation; s3, robust design optimization is carried out; according to the method, cognitive uncertainty in the modeling process of an agent model is quantified by using a loss function based on variational inference and KL divergence derivation, a nuclear radiation shielding calculation agent model considering uncertainty factors is obtained, and radiation shielding calculation is performed on an objective function in multi-objective optimization design through the constructed agent model. And a Pareto optimal solution set with certain robustness is obtained in combination with robust optimization design. According to the method, prior distribution is added to the weights of a neural network model, then the change conditions of the weights when data are given are obtained to measure the cognitive uncertainty in radiation shielding simulation, and the robustness of an optimization result is improved.

The invention provides an unmanned aerial vehicle adaptive path planning method and system fused with environment uncertainty, and the method comprises the steps: obtaining surrounding environment data based on an environment perception module, generating a local grid map and a dynamic obstacle list, inputting the local grid map and the dynamic obstacle list into an environment uncertainty evaluation module, obtaining an uncertainty factor, and carrying out the calculation of the uncertainty factor; and performing path planning through a global path planner and a local path planner based on the uncertainty factor, and adjusting the weight of a global path and the weight of a local path according to the environment uncertainty factor through a dynamic weight fusion device to obtain a final track. According to the method, the flexibility and the real-time performance of unmanned aerial vehicle path planning are effectively improved, the obstacle avoidance capability and the flight stability of the unmanned aerial vehicle in a complex environment are enhanced, and the flight efficiency is improved.

The invention discloses a source-load-storage coordinated active power distribution network cooperative operation optimization method, and belongs to the technical field of active power distribution network optimization. Comprising the following steps: partitioning the power distribution network by using an electrical coupling degree and a power matching degree to obtain an optimal power distribution network partitioning result; taking the minimum comprehensive operation cost of the active power distribution network as a target function, introducing a demand response constraint, and constructing an active power distribution network partition collaborative optimization model; and constructing a regional agent for each regional partition based on the optimal power distribution network partition result, modeling an objective function into a distributed partial observable Markov decision process, and performing iterative optimization on the active power distribution network partition collaborative optimization model through the regional agent to obtain the real-time electricity price in each region. Distributed management of flexible resources of each region can be realized, and the problem that the operation regulation and control difficulty is increased due to multivariate uncertainty factors and ever-increasing structure complexity in the existing ADN is solved.

Disclosed in the present invention are a shared energy storage configuration optimization method and system for a wind farm cluster. The method comprises: constructing a shared energy storage double-layer programming model; on the basis of the output of a wind farm cluster, an electricity price in an electric energy market and a compensation price in a frequency-modulation auxiliary service market, obtaining multiple uncertainty sets, using an improved K-means clustering method to perform joint clustering on the multiple uncertainty sets so as to obtain a typical scenario, and on the basis of the annual occurrence frequency of the typical scenario, calculating a typical scenario probability; and using a distributionally robust optimization method to model the multiple uncertainty sets on a short-time scale so as to obtain an extreme uncertainty scenario, using the typical scenario probability and the extreme uncertainty scenario to update the shared energy storage double-layer programming model so as to obtain an updated shared energy storage double-layer programming model, and using a particle swarm algorithm to perform solving so as to obtain a configuration result. By means of the method, shared energy storage configuration optimization is performed by means of taking various uncertainty factors into consideration, thereby improving the accuracy of shared energy storage configuration optimization.

The invention discloses a Tube MPC-based hybrid electric vehicle layered energy management method. The method comprises the following steps of performing longitudinal dynamic modeling on a hybrid electric vehicle, determining a vehicle demand power formula, constructing an evaluation function of equivalent fuel consumption, and constructing an output power model of a vehicle engine and a battery; carrying out uncertainty analysis on the energy management system, determining uncertain parameters in the vehicle model, quantifying the uncertainty of the uncertain parameters based on probability distribution, and constructing an uncertainty set of the uncertain parameters; on the basis of a dynamic programming algorithm, under the global working condition, the minimum amount of equivalent fuel consumption serves as a target function, an optimal control sequence of the engine is output, and an SOC reference trajectory is generated; and performing tracking solution on the control variables and the state variables in the uncertainty set by applying a Tube model predictive control (Tube MPC) method to obtain an optimal control sequence under uncertain factors, and outputting a first control variable.

The invention relates to a power plant unit maintenance optimization method considering multiple uncertain factors of a power market, and belongs to the technical field of power system operation management. The method comprises the following steps: firstly, obtaining spot market electricity price and new energy output data in each time period of a historical year in a power plant; a random scene set considering spot market electricity price and new energy output is established based on historical data, time-varying features are described through data segmentation, state space division and a non-uniform Markov model, and the random scene set is generated by using a Monte Carlo method; and finally, taking maximization of the total expected income of the power plant as an objective function, constructing an optimization model in combination with preset constraint conditions of the unit, inputting the random scene set into the optimization model for solving, and outputting an optimized unit operation and maintenance strategy which comprises maintenance plans of wind power, photovoltaic and thermal power units and corresponding output plans. Multiple uncertain factors in the power market can be effectively handled, and the operation and maintenance benefits of a power plant are improved.

The invention provides an underground chamber stability assessment method based on deep learning and fusion uncertainty, and relates to the technical field of underground chamber stability assessment, and the method specifically comprises the steps: constructing an instability assessment model, and employing crustal stress parameters and rock mechanics parameters collected historically as a training set, the stability coefficient of the underground chamber is used as a label, and the stability of the underground chamber can be analyzed more accurately through training of a deep learning model; besides, a function relationship of the influence of the rock parameters on the stability of the underground chamber is constructed, and multiple groups of current second influence coefficients are obtained by inputting multiple groups of current rock parameters into the function, so that the comprehensiveness and the accuracy of evaluation are improved; and finally, through data processing and correction, uncertainty factors are comprehensively considered, and the stability and reliability of an evaluation result are improved. The method can overcome the technical defects that constants are difficult to determine, parameter processing is incomplete, and evaluation results are unstable in a traditional method.

The invention discloses a mechanical arm path planning method, which belongs to the technical field of mechanical arm path planning, is used for planning a mechanical arm path, and comprises the following steps: acquiring parameter information and preset parameter information of a to-be-detected area, and positions of a starting point and a target point of a cooperative manipulator at the tail end of a mechanical arm; defining a state sampling space; performing oriented random sampling in the state sampling space according to the target deviation factor to obtain a random point; gravitational search is added in calculation of new nodes of the RRT algorithm; performing optimization processing on the found path by using a greedy algorithm, and performing smoothing processing on the found path by using a B spline curve; and initial moving target point location information of the mechanical arm tail end cooperative manipulator is obtained and analyzed, and the next moving target point location of the mechanical arm tail end cooperative manipulator is obtained. Compared with the prior art, the method has the advantages that a feasible path can be quickly found in a high-dimensional space, discretization is not needed, and a dynamic environment and uncertain factors can be processed.

The invention discloses an elastic evaluation method for a comprehensive energy distribution network in the field of power systems and energy management, and the method comprises the following steps: S10, constructing a dynamic coupling model and a comprehensive evaluation index system of the comprehensive energy distribution network, the dynamic coupling model of the comprehensive energy distribution network comprises energy flow equations and equipment operation constraints of a power network, a natural gas network and a thermal network, and the comprehensive evaluation index system comprises an energy coupling index, a recovery capability index and an uncertainty index. According to the invention, through multi-energy coupling and uncertainty comprehensive evaluation, the coupling relationship of multiple energies and various uncertainty factors are comprehensively incorporated into an elastic evaluation system of the comprehensive energy distribution network, a set of complete comprehensive evaluation index system is established, and the limitation that a traditional evaluation method only pays attention to single energy or ignores uncertainty is broken through; and the actual elasticity condition of the system can be reflected more truly.

The invention relates to the technical field of power system real-time scheduling, and discloses a power system real-time scheduling method, system and device and a medium, and the method comprises the steps: predicting the wind and light load uncertainty of a power system under different time scales; constructing a flexible resource model adapted to different response times; constructing a net load set based on uncertainty; determining a power system flexibility constraint; and establishing and solving a scheduling model containing the constraints so as to realize real-time scheduling. According to the method and the device, the accuracy and the reliability of real-time scheduling are improved by considering uncertain factors and flexible resource response in the power system. According to the method, a flexible resource model and a net load uncertainty set adaptive to different time scales are constructed so as to adapt to dynamic change of a system and support stable operation. The method can also reduce the operation cost and improve the resource utilization efficiency, and has an important influence on the sustainable development of a power system.

The invention is suitable for the technical field of workshop scheduling, and particularly relates to a dynamic flexible operation semiconductor workshop scheduling method of a knowledge-driven evolutionary algorithm, and the method comprises the steps: obtaining workshop working condition data which at least comprises workpiece data and machine data; constructing a workshop scheduling mathematical model based on the workshop working condition data; and solving the workshop scheduling data model based on a genetic algorithm, Q-learning and a variable neighborhood search algorithm based on knowledge driving to generate a workshop scheduling scheme. According to the method, workpiece transportation time, machine adjustment time and machine fault uncertainty factors are introduced on the basis of traditional flexible job shop scheduling, energy-saving scheduling is also considered, and the energy-saving purpose is achieved while the production requirement is met by reducing energy consumption. While the efficiency is improved, the energy consumption can be reduced, and the market competitiveness and sustainable development capability of enterprises are enhanced.

The invention discloses a civil engineering construction task automatic scheduling method and system. The method comprises the steps that a heterogeneous graph model representing construction task elements and the incidence relation of the construction task elements is constructed; processing the heterogeneous graph model by using a graph neural network to mine a dependency relationship between processes and extract risk association features related to uncertainty to form a construction state graph; constructing a Bayesian network based on the construction state atlas; probabilistic reasoning is carried out through a Bayesian network, the influence of uncertain factors is quantified, and key information representing risk conduction is fed back to the graph neural network so as to dynamically correct recognition of the graph neural network on a process dependency relationship; the dependency constraint output by the graph neural network and the risk quantification result output by the Bayesian network are fused, and a construction task scheduling scheme is generated; and synchronously updating the heterogeneous graph model, the graph neural network and the Bayesian network according to field construction feedback data to realize closed-loop iterative optimization of a scheduling scheme.