1152 results about "Monte carlo em" patented technology

A method, system and computer program product for choosing actions in a state of a planning problem. The system simulates one or more sequences of actions, state transitions and rewards starting from the current state of the planning problem. During the simulation of performing a given action in a given state, a data record is maintained of observed contextual state information, and observed cumulative reward resulting from the action. The system performs a regression fit on the data records, enabling estimation of expected reward as a function of contextual state. The estimations of expected rewards are used to guide the choice of actions during the simulations. Upon completion of all simulations, the top-level action which obtained highest mean reward during the simulations is recommended to be executed in the current state of the planning problem.

The invention provides a water quality model based regional environment risk assessment method. The water quality model based regional environment risk assessment method includes five steps of establishing a regional environment risk source information database, and utilizing a Monte Carlo algorithm to simulate discharge of risk source pollutants; selecting a water quality model, and constructing a water quality model which meets characteristics of an assessment region source intensity water quality response relationship; calculating vulnerability indexes of risk receptors by using a fuzzy integral method with the risk assessment goal of influence on water ecology, human health and social economy; utilizing the water quality model to predict the distribution of regional pollutant concentration under all possible source intensity situations, and analyzing dangerousness of risk sources; characterizing regional environment risks with a risk curve under the synthesis of dangerousness of the risk sources and vulnerability indexes of the receptors. According to the risk curve, regional environment risk assessment can be performed, high-risk regions, and key risk sources and vulnerary receptors are identified, so that a reference is provided for planning a targeted region risk prevention and control scheme.

The invention discloses an optimization design method for a step stress accelerated degradation test based on a Bayesian theory, and is applied to the technical field of the accelerated degradation test. The optimization design method comprises the steps as follows: firstly, determining product performance degradation and acceleration models, and based on the historical data, giving prior distribution of model parameters; secondly, determining an optimization design space, and forming a test scheme set; thirdly, creating an expected utility function or an expected loss function, determining optimization goals, and based on a Markov Chain Monte Carlo method, determining optimization goal values of designs in the test scheme set; and lastly, finding the optimal test scheme by using a curve fitting method. According to the optimization design method, the shortcoming of high possibility of larger deviation due to the implementation of the traditional (local) test optimization design method when the values of the model parameters are supposed to be known is avoided, and the optimization scheme obtained in the implementation of the test optimization design when the prior distribution of the model parameters is given is more reasonable and more actual.

The invention provides a method for analyzing the machining precision reliability sensitivity of a numerically-controlled machine tool, belongs to the field of machine tool precision design, and particularly relates to a space error modeling method of a three-axis machine tool and a method for analyzing the machining precision reliability and the machining precision reliability sensitivity of the machine tool. A multi-body system motion feature analysis method is used for setting up a space error model of the machine tool, and combined with a Monte-carlo digital analogy method for analyzing the machining precision reliability of the machine tool, and the degree of influence on the machining precision reliability from the wave action of all items of geometric errors of the machine tool, so that the critical geometric errors influencing the machining precision reliability are identified. Guiding advice can be given for designing, assembling and machining of the machine tool, and the machining precision reliability of the machine tool is improved fundamentally.

The invention discloses a wind farm risk evaluation method based on a Monte Carlo method. The wind farm risk evaluation method includes the steps: (1) building a wind speed sequence prediction model on the basis of a time sequence method by means of original data standardization, model recognition and parameter determination; and (2) evaluating the reliability of a large power grid system concerning a wind farm on the basis of the sequential Monte Carlo method by means of random sampling and reliability evaluation. Randomness of the wind speed is adequately considered on the basis of a large quality of wind power databases, and the method is high in speed by the aid of the Monte Carlo high-speed algorithm.

A method of performing a Monte Carlo analysis uses a graphical processor unit of a computer system, individual data sets to be analyzed are allocated to respective pixel locations in a graphical processor unit memory for Monte Carlo simulation and the outcome of the Monte Carlo simulation is calculated for each data set using stream processing in the graphical processor unit.

The invention discloses an active power distribution network reliability analysis method based on pseudo sequential Monte Carlo simulation and belongs to the technical field of power system control. The method utilizes a pseudo sequential Monte Carlo simulation method to perform reliability analysis on an active power distribution network, the operation time is shortened, and the analysis accuracy is also improved. In addition, characteristics of the active power distribution network are further fully considered in the method, states of a communication system and power electronic devices in power distribution automation are involved in system state sampling, intelligent operation is performed on the system in a normal state, processing is performed through a traditional passive power distribution network during breakdown, the method is consistent with the actual situation of the active power distribution network, and obtained reliability data have confidence level.

The invention relates to robustness analysis method for a spacecraft orbit control strategy, and belongs to the technical field of the spacecraft orbit dynamics and control. The robustness analysis method comprises the following steps: modeling orbital motion of the spacecraft through a Gauss orbit element perturbation equation; analyzing the non-spherical perturbation of a low-orbit satellite and the atmospheric drag perturbation; designing an orbit maintaining strategy to execute the maintaining control to the spacecraft orbit elements; using a differential correcting algorithm to improve the precision of the orbit maintaining; building a position error, velocity error and engine thrust error model in the running process of the spacecraft; designing a calculation model of spacecraft control error mean, variance and error distribution proportion; and using a Monte Carlo simulation method to execute the simulation analysis to the spacecraft orbit control strategy with the error, and building a robustness evaluation system of the orbit control strategy. In the control strategy design, the actual situation of the satellite orbit control is considered adequately, and the feasibility of the method in the actual project is guaranteed under the precondition of simpliness and convenience and according with the actual situation.

The present application discloses a monitoring indicator optimization method of a business operation analysis early warning system. An early warning analysis method comprises three stages which are a threshold design phase, a static early warning stage and a dynamic early warning stage. The threshold design is based on large sample historical data, a Monte Carlo simulation method is used, and a threshold can be set according to the development change trend of an operational performance indicator. According to static early warning, a multi-layer radar chart analysis method is statically used, and the identification of a key indicator which generates unusual action is facilitated. According to dynamic early warning analysis, a prediction of combining logic regression and a neural network is used, and the indicator change trend can be predicted. Thus, according to the method, the corresponding reaction of the change trend of the operational performance indicator can be effectively carried out, and the change trend of the operational performance indicator can be quantitatively analyzed. In addition, through the method, the problems of insufficient unusual action identification and prediction functions of the key indicator and weak support ability of large sample data in the previous comprehensive early warning can be solved.

The invention provides a novel signal detection scheme aiming at a 60GHz millimeter wave non-linear communication system, wherein the scheme is based on the Bayesian statistical inference mechanism, and capable of effectively solving the problems of system nonlinear distortion and frequency selective multipath fading, and achieving united blind estimate of channel gains and source signals. The method of the detection of the signal of the 60GHz millimeter wave communication system designs an important function applied to the nonlinear system and therefore overcomes the limits of the nonlinear characteristics to the traditional bayes method, further approaches an actual probability distribution function (PDF) through a series of dispersed particles with weights based on the thoughts of the Monte Carlo sequential importance sampling (MC-SIS), and finally utilizes the particle filtering technology to achieve real-time estimating and multi-channel iteration replacement of code element signals (shown in a attached diagram). The method and the device of the detection of the signal of the 60GHz millimeter wave communication system can be applied to the detection of signals of the nonlinear system, improve transmission performance of the system, need no training sequence, and at the same time can achieve the real-time estimating and detection of the signals.

Businesses typically have large amounts of data about customer transactions and other customer information which is not fully utilized. The present invention provides a means of using this information to make predictions about future customer behavior, for example by estimating the probability that a customer will leave a bank. Using these predictions the business is able to take action in order to improve its performance. Using customer data a Bayesian statistical model is generated and this model used to generate statistical estimators of customer behavior. The statistical model is formed using hidden Markov model techniques by clustering customer data and attributes (e.g. Age, sex, salary) into a finite number of states. The number of states is unobserved and considered random. Bayesian prior probability distributions are specified and combined with the data to produce Bayesian posterior probability distributions. Using these Bayesian posterior probability distributions the statistical estimators are obtained. For example, Monte Carlo sampling techniques are used or alternatively the posterior distributions are calculated numerically or analytically.

The invention provides a static safety probability assessment method of a new energy grid power system. A new energy force output model adopting wind speed, sunlight intensity and other meteorologicalelement time period features comprehensively reflects weather random fluctuation features and time change rules, the nondeterminacy of system operation is reflected through a probabilistic load flowmethod based on Monte Carlo simulation, and the new energy force output model and the probabilistic load flow method are combined to set up the static safety probability assessment method of the new energy grid power system. A system load flow out-of-limit probability index is put forward to analyze the weak link and high-risk time frame of the system. A system N-1 risk assessment index is put forward to assess the system N-1 risk level and the risk change condition caused by new energy access scene changes. Compared with traditional and deterministic system static safety analysis, the nondeterminacy of the new energy grid power system is considered, the probability of static safety is assessed through the probability assessment method and an index assessment system, more comprehensive information is provided for system operation, and reference is provided for medium-term and long-term planning, scheduling and the like of the power system.

The invention provides a compilation method for a reliability test load spectrum of an electric drive assembly mechanical system, and the method comprises the following steps: step 1, collecting userload data, carrying out preprocessing, and dividing road condition segments; step 2, determining five typical working conditions; step 3, selecting a reliability test cycle segment of each typical working condition; step 4, adopting Monte Carlo simulation to extrapolate damage targets of all parts in the full life cycle; step 5, calculating the number of cycles of each reliability test cycle segment covering multiple damage targets by using a multi-objective optimization method; step 6, splicing the reliability test cycle segments to obtain a reliability test cycle condition; and step 7, compiling to obtain a reliability test load spectrum according to the cycle index of the reliability test cycle segment and the reliability test cycle working condition. The load spectrum compiled by the method is associated with user load data and covers high damage strength, and reference and basis are provided for reliability design and verification of the electric drive assembly.

The invention relates to a method for tracking multi-target vehicles by adopting the MCMC (Markov Chain Monte Carlo) algorithm, comprising the following steps: modeling the multi-target vehicle tracking process by adopting the MCMC algorithm, establishing various preselection states, traversing the preselection states by using the Metropolis-Hastings sampling based simulated annealing algorithm, and selecting the preselection state with the maximum connection probability as the optimal solution. In the method, a limit is set to the transfer equivalence for the first time, and the parameters in the data association are estimated by the experimental data regression fitting, thus the optimal vehicle motion trajectory with maximum posteriori probability significance is obtained, and the vehicles are tracked. The invention solves the problems of frequent shielding splitting of the multi-target vehicles and has the advantages of high multi-target vehicle tracking precision and good real-time performance.

The invention discloses a self-improved recovery strategy method for complex network local destruction based on improved reinforcement learning, so as to solve the problem of recovery strategy generation when a complex network is subjected to cluster maintenance. The method comprises the following steps: 1, according to local destruction information, a complex network cluster maintenance state matrix is built; 2, based on an initial cluster maintenance state, a complex network adjacency matrix is generated; 3, based on a neural network model, a cluster prior maintenance state transition probability and a maintenance strategy value are predicted; 4, based on a Monte Carlo tree search algorithm, cluster maintenance strategy solution space is traversed, and the global best maintenance actionat present time is selected; 5, based on changes of the cluster maintenance state, the complex network adjacency matrix is updated; 6, based on the cluster maintenance state and the adjacency matrix,the recovery degree of the complex network is calculated and checked; 7, based on reinforcement learning experiment parameters, neural network parameters are trained; and 8, based on a series of bestmaintenance actions during a recovery strategy self improvement process, a complete maintenance recovery scheme is generated.

Stochastic ray-tracing methods such as Monte-Carlo ray-tracing may be adapted to provide more efficient and more realistic ultrasound imaging systems and methods. Many random ray paths that are perturbed according to a probability distribution may be generated until they converge to the correct solution. New surface thickness and roughness models enable to reproduce complex ultrasound interactions such as multiple reflections and refractions. The contribution of each ray path may be further weighted to better simulate a beamformed ultrasound signal. Tracing many individual rays per transducer element is easily parallelizable on modern GPU computing architectures.

The invention discloses a method and system for evaluating the operation reliability of a micro-grid. The method comprises the steps of determining total sampling times of monte-carlo simulation; carrying out iterative computation of sampling times and obtaining the total electricity capable of supplying a load with the electricity and the load demand in a sampling period corresponding to current sampling of the micro-grid; obtaining a load power shortage time expected value under the condition of considering an energy storage device in the sampling period; if the sampling times is not greater than the total sampling times, further carrying out iterative computation of the sampling times; and or else, existing sampling iteration, computing the power shortage probability and the load power shortage time expected value of the micro-grid in a reliability analysis period of the micro-grid and evaluating the operation reliability of the micro-grid. According to the method and the system, an intermittent uncontrolled distributed power supply is simulated by adopting a multi-state model, a normal distribution-based multi-stage load level model is adopted by the load, and the method and the system are suitable for operation reliability analysis of various micro-grids and have good application prospects.

The invention relates to a grid-connected microgrid reliability evaluation method considering peak load shifting. The method includes the following steps that: the fuzzy membership degree of a peak period and a valley period is set according to the load curve of a power system; the fuzzy similarity matrix R and equivalence matrix R<^> of various time points of the load curve are determined, dynamic clustering is carried out through a lambda-cut relation, so that the division of the peak period and the valley period can be realized; adjustment is made according to the order of the power market and the actual electricity consumption demands of people, so that a corrected typical load peak period, normal period and valley period can be obtained; a load demand response model is established according to three constraint elements, namely, the total electricity consumption of loads, electricity price and customer' satisfaction, and an objective function described in the descriptions of the invention is provided, and a solution can be obtained through using a particle swarm algorithm, and a corrected load curve is determined; and the reliability of a corrected load curve-based grid-connected microgrid is determined through using a Monte Carlo simulation method. The method of the invention has the advantages of great universality and simple algorithm interface.

The invention relates to a Monte-Carlo simulation accelerating method and system based on cloud computing. The method comprises the steps that Hadoop and Monte-Carlo software are installed on a local computer, and the Hadoop is configured to run in a pseudo-distributed mode; a MapReduce procedure is written in the local computer, and a stimulation input text is manufactured; a machine image provided with the Hadoop and the Monte-Carlo software is manufactured at a cloud terminal, the manufactured machine image is utilized for instantiating a certain number of virtual servers, and Hadoop on all the virtual servers is configured to run in a fully-distributed mode to form a Hadoop cluster; the local MapReduce procedure and the stimulation input text are uploaded to the virtual servers, the MapReduce runs on the cloud terminal Hadoop cluster, and Monte-Carlo simulation distributed computation is carried out. The number and configuration of the virtual servers can be flexibly selected, and the method and system can be used at any place where a network has access.

The invention discloses a stock ground material volume measurement method and system, and the method comprises the steps: S1, obtaining the point cloud data of a stock ground material pile through a laser scanner; S2, extracting color features of the point cloud data, and performing coarse segmentation on a stock ground background region and a stock pile target region according to the color features to obtain point cloud data of the stock pile target region; S3, performing fitting registration on the point cloud data of the material pile target area by adopting a coarse registration method anda fine registration method; and S4, according to the point cloud data obtained through fitting registration, calculating the volume of the material pile by using a mode of combining a Monte Carlo method and an integral method, and completing volume measurement. According to the invention, the volume of the material pile can be rapidly and accurately obtained, automatic measurement of the materialvolume of the material pile is realized, the labor cost is reduced, and the accuracy is high.

The invention discloses an unmanned aerial vehicle obstacle avoidance and path planning method, which combines Monte Carlo tree search and contrast reinforcement learning algorithms, overcomes the problem of insufficient signals of a GPS (Global Positioning System) in a specific environment, and realizes the obstacle avoidance and path selection functions of an unmanned aerial vehicle in a complex environment. The method includes the following steps: (1) constructing an environment simulator; (2) the unmanned aerial vehicle obtains observation information in the simulator, and the observation information is processed by using a deep neural network; (3) performing coarse-grained path planning by utilizing Monte Carlo tree search, and generating stage target points in the advancing path of the unmanned aerial vehicle for training of a subsequent reinforcement learning algorithm; (4) learning a fine control strategy and fine-grained path planning of the unmanned aerial vehicle by using reinforcement learning; (5) accelerating unmanned aerial vehicle training based on comparative learning. According to the method provided by the invention, the unmanned aerial vehicle has an autonomous decision-making capability in a complex environment with high difficulty coefficient and large uncertain factors, and can cope with emergencies to a certain extent to complete specific tasks.

The present invention discloses a power system reliability assessment method considering optimized scheduling of cascade hydropower stations, by which the reliability of the power system is improved, comprising following steps: establishing power system optimization models; inputting the sequential wind speed, runoff and load data within 24h; in accordance with reliability parameters of units and by the sequential Monte Carlo method, sampling the state durations of three kinds of units and segmenting the state durations on a 24-hour cycle; calculating the sequential output of wind farms within 24h according to wind speed data and the state of wind power units; calculating the hourly loss-of-load, according to the state of wind power units and thermal power units as well as the optimization models; optimizing for 365 days according to the method described in the step 4, and calculating reliability indices; and determining convergence or not, and if not, continuously repeating the steps S3 to S7 until convergence.

The invention relates to a turning repair decision optimization method for rail transit vehicle wheel sets. The turning repair decision optimization method includes: subjecting eight wheel of one carriage to wheel set abrasion data preprocessing; establishing wheel set abrasion data driving models such as a wheel diameter abrasion model, a rim thickness abrasion model and a wheel set turning repair proportion coefficient distribution model; performing Monte Carlo simulation on rail transit vehicle wheel set abrasion and turning repair to acquire expected wheel set service life under the combination of different rim thickness preventing turning repair value and turning repair recovery value. By means of a genetic algorithm in the simulation, the expected rim thickness value and wheel diameter value after one specific turning repair are optimized with the optimization objectives that the wheel diameter loss is as low as possible and is possibly close to the rim thickness recovery value after turning repair; optimal turning repair decisions, namely the optimized rim thickness preventing turning repair value and turning repair recovery value, can be finally analyzed according to the expected simulated service life of the wheel sets.

The invention discloses a mechanical arm robust optimization design method based on interval and bounded probability hybrid uncertainty. The method comprises the following steps: considering two kindsof uncertainty of interval and bounded probability distribution influencing the mechanical arm performance, describing the bounded probability distribution as a random variable obeying generalized beta distribution, and establishing a mechanical arm robust optimization design model; direct solution is carried out based on a genetic algorithm; the robustness of a population individual constraint performance function is analyzed by utilizing the uncertainty boundness, and the feasibility of individuals is judged; for a feasible individual, calculating a mean value and a standard deviation of anobjective function of the feasible individual by adopting a Monte Carlo method based on multi-layer encryption Latin hypercube sampling; and then sorting the individuals of the current population according to the total feasible robustness index and the negative ideal solution approaching distance of the constraint performance function to obtain robust and optimal mechanical arm parameters. The mechanical arm robustness optimization model established by the method truly reflects uncertainty distribution, the optimization process is intelligent and efficient, and the method has good engineeringapplicability.

The invention provides a Monte Carlo simulation method for underwater uplink laser communication. The Monte Carlo simulation method for underwater uplink laser communication comprises the steps that the initial coordinates of photons are determined, that is, the initial quantity of the photons is obtained, a Gaussian light source of laser is sampled, and an initial light source is generated; a next coordinate position is calculated according to the previous photon coordinate position,that is, a random free step length of photons is generated, an initial scattering angle is generated by a scattering phase function, a random azimuth angle is determined, and an initial transmission direction cosine of the photons is determined; and whether the photons are scattered in the next step is judgedaccording to different heights of the photons. According to the Monte Carlo simulation method for underwater uplink laser communication, scattering and weight attenuation of photons in the transmission process are simulated, the scattering positions and weights of the photons are further calculated and judged, the underwater communication condition is accurately simulated, and important guiding significance is provided for improving the quality and stability of underwater communication.

The invention discloses a satellite anomaly detection method based on a Bayesian neural network, and the method comprises the steps: different from an anomaly detection method employing a conventionalneural network, introducing the Bayesian idea into the neural network, and enabling the weight of the network not to be a single value, but to accord with certain probability distribution. The Bayesian thought gives uncertainty to the neural network, and gives better mathematical explanation to the neural network which is a black box model. The method comprises the following steps of firstly, creating a traditional long-short-term neural network according to satellite data; secondly, introducing a Bayesian thought, establishing a Bayesian long-short-term neural network, performing approximateinference by using a dropout method, and learning a network weight by minimizing KL divergence between approximate distribution and posteriori distribution of the network weight; and then, outputtinga network result in a Monte Carlo sampling approximate weight distribution mode; calculating the uncertainty of an anomaly detection classification result by adopting two measurement modes of prediction entropy and mutual information; finally, further judging manually the classified samples with high uncertainty or through an auto-encoder, so that the accuracy of anomaly detection can be better improved.

The invention discloses a multi-objective optimization method considering joint planning of a distributed power supply and a charging station. The method aims at solving the planning problem of a distributed power supply and an electric vehicle charging station in a power distribution network. The timing sequence of the distributed power supply and the charging load is considered; establishing a time sequence output model of the distributed power supply; describing behavior transition probability distribution of residents in the planning area within one day in the form of a travel chain; fitting the characteristic quantity on the electric vehicle group time travel chain by using a Gaussian mixture model and a maximum expectation algorithm; fitting the space travel chain by using a probability transfer matrix; a Monte Carlo method is used to simulate the charging load of an electric vehicle group in a region. And finally, constructing a multi-objective optimization model with the minimum active power loss of the power distribution network, the maximum grid-connected total capacity of the distributed power supply and the minimum extra mileage for charging the electric vehicle group,determining constraint conditions, determining a coding mode for the optimization model, and solving by using a non-dominated sorting genetic algorithm with an elitist reservation strategy.

The invention discloses a pneumoelectric interconnection system optimization operation method considering wind power uncertainty. The method comprises the steps: building a pneumoelectric interconnection system random optimization operation model through employing the minimization of the total operation cost of a pneumoelectric interconnection system as a target and combining with a set related operation constraint; aiming at the nonlinear power flow equation constraint of a natural gas network, adopting a linearization method for processing; describing the uncertainty of wind power output byusing a scene analysis method, generating a large number of wind power output scenes through a Monte Carlo simulation method, then applying a scene reduction method based on synchronous back substitution elimination to reduce the scenes to obtain a small number of representative scenes, and then converting the random optimization problem of the pneumoelectric interconnection system considering thewind power uncertainty into a mixed integer linear programming problem of a plurality of deterministic scenes to be solved. Under the condition that the wind power output is uncertain, the economicalefficiency and safety of the operation of the pneumoelectric interconnection system and the absorption capacity of the wind power are effectively improved through optimal scheduling.

The invention discloses a multi-return-period tsunami disaster evaluation method based on Monte Carlo stochastic simulation. The method comprises: S1, applying multiple source parameter estimation methods to establish a seismic activity parameter logic tree of potential tsunami source areas; S2, applying linear tsunami numerical simulation to establish a tsunami unit source Green's-function library; S3, applying a Monte Carlo stochastic simulation to generate a stochastic seismic event set according to the above logic tree; S4, applying stochastic slippage simulation to generate a tsunami waveamplitude set according to the tsunami unit source Green's-function library and a stochastic seismic event set; and S5, carrying out counting and uncertainty analysis on multi-return-period tsunami disaster distribution results according to the tsunami wave amplitude set. According to the above method, problems that in the prior art, risk evaluation results are higher, and corresponding occurrence probability thereof cannot be given can be solved, multiple types of uncertainty are fused into a final evaluation result, credibility of the result is increased, running efficiency is improved at the same time, and targeted disaster prevention and mitigation deployment and urban construction planning of decision makers are facilitated.