32 results about "Uncertainty factor" patented technology

The present application belongs to the field of remanufacturing scheduling, and discloses a remanufacturing job shop robust scheduling method and device considering carbon emission constraints, which comprises obtaining machine information and workpiece information of a remanufacturing job shop, taking minimization of expected total cost and cost deviation as an optimization target, introducing carbon emission constraints, and constructing a robust optimization model containing a discrete scene set; a particle swarm optimization algorithm is used to solve the robust optimization model to obtain an optimal remanufacturing scheduling scheme, and the solution of the particle swarm optimization algorithm is represented by a process-based encoding sequence, wherein each element in the process-based encoding sequence is a positive integer, the numerical value represents a workpiece number, and the number of occurrences of the same numerical value represents a process number. The present application considers the mutual influence between uncertainty factors in actual production and dynamic carbon cost, solves the remanufacturing job shop robust scheduling problem under carbon emission constraints, and improves the accuracy and robustness of remanufacturing job shop scheduling.

The application relates to a cloud platform-based water resource management method, device, equipment and medium. The method integrates multi-source water data through a cloud platform, constructs a hierarchical Bayesian model after data cleaning, uniformly quantizes model parameters, input and posterior distribution of structural errors, drives ensemble Kalman filtering dynamic assimilation of real-time observation data based on the same, generates a prediction distribution fusing multi-source uncertainty, further analyzes the contribution source of prediction variance in real time through a Sobol' index, identifies dominant uncertainty factors, constructs a coupled error model according to the same, feeds the coupled error model back to the assimilation cycle as a state variable for online correction, and finally forms an improved prediction model capable of dynamically tracking and quantifying the uncertainty coupling propagation mechanism, thereby significantly improving the accuracy and reliability of hydrological prediction, and providing risk quantification basis and optimization scheme for flood control scheduling, water resource allocation and urban drainage management decision-making.

The present application relates to a geological modeling method for a geological feature uncertain reservoir. The method comprises the following steps: identifying uncertainty factors of the geological feature uncertain reservoir; parameterizing the uncertainty factors; determining possible distribution modes of the uncertainty parameters; respectively performing random sampling on each uncertainty parameter under each distribution mode to obtain a plurality of certain parameter combinations; each certain parameter combination corresponds to a certain geological model; predicting the geological feature uncertain reservoir through the certain geological model to obtain a plurality of prediction results; and statistically analyzing the prediction results to evaluate the prediction probability and prediction risk of each certain geological model. The present application provides a plurality of certain reservoir geological models varying with key geological features such as stratigraphic plane, fault plane and fracture plane, can be fitted through production history, can invert all the modeled uncertainty parameters, can reduce model uncertainty, and is more suitable for practical use.

The application relates to the field of ethylene industry diagnosis, in particular to an ethylene cracking COT prediction method and system based on Bayesian sparse self-encoding, which comprises the following steps: performing Bayesian random self-encoding processing on a process time sequence parameter sequence of an ethylene cracking furnace to obtain a plurality of random process parameter sparse feature sequences; extracting a time sequence dependency relationship of the random process parameter sparse feature sequences to obtain process parameter time sequence features; performing nonlinear mapping processing on the process parameter time sequence features to obtain random furnace tube outlet temperature prediction values; and calculating furnace tube outlet temperature prediction values according to the random furnace tube outlet temperature prediction values of the random process parameter sparse feature sequences. Compared with the prior art, the application can reflect random uncertain factors of the ethylene industry by performing Bayesian random self-encoding processing to obtain random process parameter sparse feature sequences, and can predict furnace tube outlet temperature prediction values through all the random process parameter sparse feature sequences, thereby effectively improving the prediction accuracy.

This invention discloses a distributed resource planning method for a data center integrated energy system under a diversified market environment, belonging to the field of power system planning. The method constructs a two-layer optimization framework. The upper layer uses a multi-objective robust Bayesian optimization algorithm under input noise to optimize distributed resource capacity. The lower layer establishes a simulation model of the data center integrated energy system operation based on the diversified market benefits of energy storage. It incorporates Gaussian distributed noise to model uncertainty factors, trains a robust Gaussian process surrogate model, and selects sampling points for iterative optimization through a robust expectation hypervolume improvement function. Finally, it outputs a robust optimal configuration scheme through Pareto sorting. This invention solves the problems of poor robustness, imbalance in multi-objective optimization, single energy storage value assessment, and algorithm inefficiency in existing methods, achieving stable configuration schemes, balanced objectives, and accurate benefits, thereby improving system economy and renewable energy absorption rate.

The application discloses a kind of three-rotor layout micro unmanned aerial vehicle high dynamic attack guidance and control method, comprising the following steps: establishing the linear time-invariant system dynamics model of micro unmanned aerial vehicle, setting initial path;Linear time-invariant system dynamics model is updated based on the initial path, and path is obtained;Micro unmanned aerial vehicle parameter uncertainty function and the sliding mode variable structure controller based on learning law are constructed;Nonlinear robust adaptive control is realized based on path, unmanned aerial vehicle parameter uncertainty function and the sliding mode variable structure controller based on learning law.The application can complete high dynamic path planning under the condition of obstacle, target motion parameter and micro unmanned aerial vehicle itself maneuverability constraint, ensure guidance accuracy, ensure that unmanned aerial vehicle realizes stable flight under the interference of external environment and internal system uncertainty factor.

A method of optimal scheduling of multi-energy complementary system considering bilateral uncertainties of supply and demand is proposed to deal with the uncertainty challenge of energy supply and load demand in multi-energy complementary system. Firstly, the supply characteristics of various energies and the dynamic variation law of load demand in multi-energy complementary system are analyzed in depth, and the random fluctuation of energy supply on the source side and the uncertainty of load on the demand side are quantified. On this basis, an optimal scheduling model is constructed with the minimum system operation cost and the maximum energy utilization efficiency as the objectives. To effectively handle the uncertainty factors, robust optimization or stochastic optimization methods are introduced to transform the bilateral uncertainties of supply and demand into processable constraint conditions or objective function items. Through the coordinated control of different energy conversion devices and energy storage devices, the reasonable allocation and optimal scheduling of energy in multi-energy complementary system are realized, and the actual example is simulated for verification.

The application discloses a judgment method of front and side face features based on hotspot area feature fusion, and relates to the field of data recognition. The method comprises the following steps: determining a data set, dividing an original training set and an original test set; performing feature extraction on hotspot gray images in the data set to obtain a hotspot gray image feature image training set and a hotspot gray image feature image test set; taking the hotspot gray image feature image training set as the input of a classification model, taking front face labels, left side face labels and right side face labels in the original training set as classification labels, performing model training on a classification model constructed by using a traditional machine learning method to obtain a final classification model; and inputting any one of the hotspot gray image feature images in the hotspot gray image feature image test set into the final classification model to complete front and side face judgment. The application solves the problems of slow judgment speed and poor robustness under uncertain factors such as illumination and shielding of a front and side face judgment method based on a traditional machine learning classification model.

This invention provides a dynamic risk assessment method and system for risk control in the electricity spot market, relating to the field of hydropower station management technology. It constructs a unified database by collecting and integrating heterogeneous data from multiple sources, including meteorology, power grid, and the market. A multi-timescale dynamic risk assessment model is used to predict key uncertainty factors, and a multi-objective optimization scheduling model is constructed using mixed-integer linear programming to achieve cascade linkage and risk-return balance. Simultaneously, it generates position optimization and robust pricing strategies, and introduces a CVaR (Continuous Value Assurance) pricing model to dynamically adjust risk hedging strategies. The system comprises a data layer, a model layer, an application layer, and a presentation layer, enabling data management, model calculation, interactive decision-making, and visualization, effectively improving the risk resilience and economic benefits of large hydropower stations in the spot market.

The application provides a mobile robot self-learning robust control method based on a hybrid Kalman filter and belongs to the technical field of robots.The technical scheme comprises the following steps: step 1, a dynamic model of an uncertainty factor;step 2, real-time estimation of state parameters and model parameters of the mobile robot to optimize the original dynamic model;step 3, introduction of an adaptive forgetting factor recursive least square method to dynamically adjust filter parameters;step 4, design of a non-singular fast terminal sliding mode controller based on a saturation function as a system main controller;step 5, establishment of an error correction RBF neural network and introduction of an adaptive error learning strategy;step 6, completion of stability analysis and proof of the control system by means of Lyapunov stability theory and simulation experiment of the optimized model.The application effectively suppresses the chattering of the sliding mode control and significantly improves the control precision and robust performance of the four-wheel robot.

The application discloses a kind of self-adapting global fractional order terminal sliding mode serpentine robot control methods.In order to solve the problem of high complexity in modeling process, it is difficult to solve, an error dynamics model is constructed, and the design difficulty of control system is further simplified. In response to the uncertain terms and unknown disturbances that may exist in the model, a radial basis function neural network observer is introduced, which effectively approximates the estimation of these uncertain factors. In order to ensure that the joint serpentine robot system can converge quickly, an adaptive constant rate control strategy is designed, and combined with the global fractional order terminal sliding surface, not only the high-precision control of the system is realized, but also the robustness of the system is significantly enhanced.

This application relates to the field of data processing technology and discloses a method and system for digital management of the entire engineering construction process. The method includes: collecting and standardizing multi-source data throughout the entire engineering construction cycle; constructing a stacked integrated prediction system using the standardized data to obtain predicted values ​​for three-dimensional indicators; allocating resources based on the predicted values ​​and an ergonomic risk index to obtain a configuration plan; quantifying the uncertainty factors of the configuration plan; calculating the optimal solution set through a multi-objective symbiotic algorithm to form a management strategy. This application achieves high-precision prediction of three-dimensional indicators for engineering projects through a stacked integrated algorithm, combining ergonomic risk assessment with resource allocation optimization, and solving the technical shortcomings of traditional methods that neglect human factors engineering.

This invention discloses a method and system for power planning and allocation in receiving provinces that considers uncertainties. The method includes: formulating a basic power supply plan; constructing a probabilistic scenario set of annual hydropower utilization hours based on historical water inflow data; setting green and low-carbon targets and calculating the inter-provincial renewable electricity volume required to meet the renewable energy consumption responsibility weight under different scenarios; establishing an inter-provincial transaction cost model to calculate the cost per kilowatt-hour and total transaction cost for each scenario; constructing a system annual operating cost model to obtain the total system cost under each scenario and then averaging it to obtain the expected total cost; and iteratively optimizing the installed capacity of new energy sources with a fixed increment until convergence, outputting the economically optimal solution. This invention achieves a coordinated balance between the economy, greenness, and security of power allocation by probabilistically handling hydropower uncertainties and introducing inter-provincial green electricity trading as an optimization variable.

This invention relates to a multi-dimensional evaluation method and system for the carrying capacity of distribution networks based on probabilistic assessment. The method includes: collecting distribution network operation data and constructing a distributed generation processing probability model and a load demand uncertainty model; performing sampling and power flow calculations based on the distributed generation processing probability model and the load demand uncertainty model; calculating and normalizing multi-dimensional indicators based on the calculation results at each sampling time; the multi-dimensional indicators include resilience indicators, including transient voltage stability index, islanding reconstruction power, and energy storage throughput margin; calculating the subjective and objective weights of the multi-dimensional indicators and fusing them to obtain a comprehensive weight; calculating the score for each sampling and the expected score based on the comprehensive weight and the normalization result; calculating the risk probability based on the expected scores of all samplings; and classifying the carrying capacity level based on the expected score and the risk probability. Compared with the prior art, this invention improves the reliability of carrying capacity evaluation for distribution networks with uncertainties.

The application discloses a PE pipe microwave detection uncertainty evaluation method and device and equipment thereof, and relates to the technical field of nondestructive testing.The method comprises the following steps: obtaining detection data of uncertainty factors in a PE pipe microwave detection process, wherein the uncertainty factors are labeled with data property identifiers; converting the detection data into membership vectors based on the data property identifiers and corresponding preset conversion rules, wherein the preset conversion rules comprise membership function conversion based on a combination of trapezoidal distribution and triangular distribution, and weight vector direct quantization conversion based on expert scoring and engineering experience adjustment; and performing fuzzy comprehensive evaluation on the uncertainty factors based on the membership vectors and preset weights to obtain a comprehensive evaluation result.Under the premise of not relying on repeated measurements or physical tracing required for uncertainty evaluation, the method realizes structured, operable and engineering interpretable comprehensive evaluation of the uncertainty factors in the PE pipe microwave detection process.

The present application relates to the technical field of low-temperature metal fatigue life analysis, and particularly relates to a low-temperature metal fatigue life evaluation method considering uncertainty factors. The method comprises the following steps: collecting low-temperature metal material fatigue life test data; determining a low-temperature metal material fatigue life prediction model parameter distribution range; obtaining a jth membership value of an ith fuzzy number; judging whether all fuzzy numbers are valued; determining all fuzzy number values under the jth membership; calculating a low-temperature fatigue life interval of the metal material under the jth membership; judging whether all memberships are calculated; and obtaining a low-temperature metal fatigue life analysis result considering uncertainty factors. The improved low-temperature metal material fatigue life prediction model proposed in the method fully considers material performance degradation under low-temperature conditions, improves fatigue life prediction accuracy, and fully considers parameter uncertainty in the low-temperature fatigue life prediction model, so that the prediction result is more referable.

The application provides an intelligent water quality prediction and regulation method in a power plant descaling process, and relates to the technical field of water quality prediction, and specifically comprises the following steps: collecting data recorded during chemical cleaning and descaling of a boiler of a power plant and performing data preprocessing to construct a power plant descaling water quality data set; introducing a local fluctuation suppression weight, a water temperature deviation adjustment weight, a reagent mutation suppression factor and a time decay weight to generate an enhanced delay vector; constructing a global state vector through a covariant weight and a direction perception expression; combining the global state vector, a reagent change amount and a temperature deviation to form a prediction input, adopting a heteroscedastic robust task loss based on a Huber loss and an uncertainty factor for optimization, and finally realizing multi-step prediction of a pH value, a Langelier saturation index, a calcium ion concentration, a silicate radical concentration, a conductivity and a turbidity in the next 15 minutes.

The application discloses a cascaded large model robot motion planning method based on timing logic constraints, which comprises the following steps: a task planner receives user instructions and corresponding STL expressions, environment information, decomposes the user instructions and corresponding STL expressions, and obtains sub-tasks and corresponding STL expressions; whether the decomposed sub-tasks meet the logic constraints, time constraints and space constraints is detected by an STL checker; if yes, correct controllers are generated according to the sub-tasks; the generated correct controllers are integrated with a robot model, a Monte Carlo method is used to generate multiple groups of random parameters based on uncertainty factors, real environment disturbances are simulated, an Euler method is used to discretize and iteratively solve trajectories of the robot continuous kinematics equation, the trajectories are checked by the STL checker to make the trajectories meet the requirements of the user instructions, and finally correct trajectories are obtained. The application realizes user instructions containing space, time and kinematics constraints.

The application discloses a kind of scheduling optimization method and system considering source load bilateral uncertainty, the method includes: first, the planned data of power grid is brought into the security constrained unit commitment model constructed in advance to obtain the scheduling plan of conventional unit optimization calculation;Then the branch or section flow distribution when intermittent power is connected to power grid in the scheduling plan period of the conventional unit is calculated;Finally, the branch or section flow distribution when intermittent power is connected to power grid is based on the conventional unit scheduling plan optimization;The security constrained unit commitment model is constructed based on the uncertainty of demand response load under price incentive;The conventional unit includes coal-fired unit and gas turbine unit;The intermittent power includes wind turbine and photovoltaic unit.The present application overcomes the shortcomings that large-scale wind power integration does not specifically consider the mathematical characteristics and distribution law of wind power uncertainty, while considering the uncertainty factors of demand response.

The present disclosure relates to the technical field of oil exploration and development, and particularly relates to a method and device for predicting recoverable reserves of an oil and gas reservoir based on uncertain factors. The corresponding method comprises the following steps: determining a prediction frequency of the recoverable reserves of the oil and gas reservoir according to the production stability of a production well of the oil and gas reservoir; predicting the production loss of the production well according to historical production influence data and future production influence data of the production well; determining corresponding production capacity parameters according to the current actual production and the production loss of the production well according to the current prediction frequency and the well type; and predicting the recoverable reserves of the oil and gas reservoir according to the production capacity parameters of all production wells of the oil and gas reservoir and a future drilling sequence. The present disclosure improves the prediction accuracy of the production decline law of various production wells by introducing the production loss, and at the same time, by analyzing the uncertainty that may occur in the future of each part of the key parameters, different schemes for predicting the recoverable reserves are obtained, which can be effectively applied to various oil and gas reservoirs.

This invention relates to the field of radio astronomy, providing a method and apparatus for identifying electromagnetic interference from radio telescopes. The method includes: separating the original monitored spectrum signal into a background signal A and a residual signal B; fitting A to obtain a first residual signal, performing a confidence level test to obtain an abnormal signal set C1; fitting B to obtain a second residual signal, performing a confidence level test to obtain an abnormal signal set C2; and merging C1 and C2 to obtain an interference signal set C. The apparatus includes a signal separation module, a data fitting module, a residual analysis module, and a merging module. This invention fits the background and residual signals separately and obtains the residuals, achieving "stable processing" and avoiding subjective judgment bias. Compared with the traditional method using threshold decision, the algorithm of this invention has more objective criteria, less human intervention and uncertainty factors, and achieves "automation" in actual measurements. The algorithm is simple to implement, has low computational load, and fast program execution speed.

The application discloses a power distribution network reliability fast evaluation method and system based on uncertainty factors, and the method comprises the following steps: S1, obtaining basic operation data and multiple types of uncertainty factor original data of a power distribution network, preprocessing the basic operation data and the uncertainty factor original data to obtain a standardized data set; S2, constructing a multi-scale uncertainty spectrum decomposition-cause decoupling fast equivalent evaluation mechanism, mapping the multiple types of uncertainty factors to a unified reliability influence spectrum domain and converting them into equivalent reliability degree disturbance parameters, and the application relates to the technical field of power systems. The power distribution network reliability fast evaluation method and system based on uncertainty factors can dynamically identify the influence intensity of each uncertainty factor in the power distribution network by establishing an uncertainty coupling intensity adaptive reduction mechanism, and can eliminate factors with weak influence, thereby optimizing the evaluation process, and further improving the calculation efficiency and evaluation accuracy.

The application discloses a kind of based on climate, economic and energy system coupling's power system long-term supply and demand time sequence scene generation method and system, belong to the load prediction and new energy output prediction technical field of power system.The method of the present application is by to the wind power output time sequence sequence, photovoltaic hourly output sequence and hourly load prediction sequence, energy closure is carried out under the same scenario, time sequence unification and constraint checking processing, generates power system long-term supply and demand time sequence scene.The present application can be fully considered when constructing load and new energy prediction scene climate and economic factors, thereby improve the accuracy and reliability of prediction result, especially under the influence of extreme weather and uncertainty factor, can effectively deal with the challenge brought by load fluctuation and new energy output fluctuation, provide more scientific basis for the planning, operation scheduling and risk assessment of power system.

This invention relates to the fields of intelligent transportation systems and urban planning technology, specifically a novel simulation and prediction method for engineering traffic impact assessment. First, it constructs a multi-source dynamic data framework integrating mobile phone signaling, roadside sensing, weather, and event data. Second, it innovatively employs a three-layer hybrid model of "GWRFR+LSTM+Kalman filtering" to sequentially capture the spatial heterogeneity and nonlinear relationship between traffic and the environment, learn the spatiotemporal dependence characteristics of traffic flow, and perform real-time corrections for sudden disturbances. Then, it divides the dynamic parameter set for the entire lifecycle of the project, introduces uncertainty factors, and outputs probabilistic evaluation results through Monte Carlo simulation. Finally, it quantifies the interactive impact of modes such as private cars, public transportation, and cycling through a multi-modal traffic coordination module. This invention significantly improves prediction accuracy and dynamic adaptability, providing more scientific and reliable support for the comparison of engineering schemes and traffic management decisions.

The application provides a path planning and tracking control method and system of an unmanned ship under a timing logic task, comprising the following steps: S1, establishing an STL formalized model of the timing logic task of the unmanned ship; S2, based on a kinematic model and a dynamic model of the unmanned ship, establishing an unmanned ship control strategy under a double-layer framework of multi-time scale planning and tracking control; S3, based on the STL formalized model of the timing logic task, realizing speed planning; and S4, based on the unmanned ship control strategy and the speed planning in S3, realizing speed tracking by robust model predictive control. The application considers the characteristics of the underactuated system of the unmanned ship and the complex environment on the sea, establishes a double-layer multi-time scale planning-tracking control framework, considers the interference and uncertainty factors in the marine environment, plans the speed of the unmanned ship, considers the interference factors, realizes fast and stable tracking of the planned speed under the robust model predictive control, and realizes the optimal control of the complex timing logic task of the unmanned ship.