40results about How to "Shorten the optimization cycle" patented technology

The invention discloses a hybrid electric vehicle matching parameter and control strategy synergistic combination optimization method which comprises the steps of building a hybrid electric vehicle system model and a vehicle driving resistance model; building a hybrid electric vehicle control strategy; setting a gearbox transmission ratio as a matching parameter to be optimized, and adopting the engine torque top and bottom limitation, the battery SOC during engine intervention and the engine starting rotary speed as control strategy parameters to be optimized; integrating the vehicle model, acontrol strategy model and a combination optimization algorithm, running the built hybrid electric vehicle model and the built control strategy, and simulating-calculating the acceleration time, theclimbing degree, the oil consumption and the power consumption of the vehicle; and building the combination optimization algorithm, adopting 100-kilometer comprehensive energy consumption as a targetfunction value, setting a constraint condition, and operating the combination optimization algorithm to obtain the matching parameter to be optimized and a control strategy parameter optimal value. According to the hybrid electric vehicle matching parameter and control strategy synergistic combination optimization method provided by the invention, the matching parameter and the control strategy can be synergistically and automatically optimized at the same time, so that the vehicle and control strategy optimization cycle is greatly shortened, and the working efficiency is improved.

Obtaining statistical effectiveness data of each recommendation algorithm; obtaining the traffic distribution probability of each recommendation algorithm according to the weight of the effectiveness data of each recommendation algorithm in the recommendation algorithm; distributing traffic requests for each recommendation algorithm according to the traffic distribution probability.

The invention discloses a method for optimizing the fuel injection strategy of an in-cylinder direct injection engine, which comprises the following steps: step 1, simplify the engine operating condition map to minimap; step 2, test the spray characteristics of the fuel injector; step 3 , according to the test conditions and test data of the spray characteristics, the spray model of the simulation tool is revised; in step 4, the DOE design of the fuel injection strategy parameters is carried out, and the simulation tool is used to simulate the oil and gas mixing process in the cylinder, and the oil and gas distribution is adjusted according to the engine operating conditions. According to the requirements, the theoretical optimal fuel injection strategy is obtained. Step 5, bench verification and calibration are performed to complete the minimap fuel injection strategy optimization; Carry out bench verification and calibration, and complete the fuel injection strategy optimization of the engine operating condition map. It can avoid destroying the engine prototype, reduce the development cost and shorten the development cycle.

The aerodynamic optimization method of a variant aircraft for improving the expected improvement degree of the position vector disclosed by the invention belongs to the technical field of overall optimization of the aircraft. Select the initial reference airfoil and related shape coefficients to determine the design conditions; establish an optimization model considering structural consistency constraints to solve the shape coefficient of the deformed airfoil, and establish a high-precision aerodynamic analysis model to solve the lift coefficient and drag coefficient of the airfoil; establish The Kriging surrogate model of the high-precision aerodynamic analysis model, optimize the Kriging surrogate model to obtain a pseudo-non-dominated solution, and determine whether the prediction variance of the Kriging surrogate model is greater than the threshold; if the prediction variance is not less than the threshold, use the position vector expectation improvement criterion to obtain new samples The point is used to update the Kriging surrogate model, otherwise the new sample points are filtered from the pseudo-non-dominated solution to update the Kriging surrogate model. By filtering new sample points, the accuracy of the Kriging surrogate model at the Pareto frontier is improved, the optimality and distribution of the optimized non-dominated solution are improved, and the optimization efficiency is improved and the cost is saved.

The invention discloses a reactive power optimization control method for a large double-fed wind farm, which includes: grouping the wind turbines; establishing an objective function with the maximum total active power output by the wind farm; The upper and lower limits of the reactive power output of a double-fed fan unit; the upper and lower limits of the reactive power output of the double-fed fan unit, the voltage deviation of each node of the wind farm, and the reactive power dispatching command of the power grid to the wind farm are used as constraints to establish a constraint function; The reactive power optimization control strategy solves the optimization model composed of the optimization objective function and the constraint conditions to form a reactive power control method for wind farms that meets requirements.

The invention discloses a method for the multi-working condition optimization design of the spokes of an axial flow pump, comprising the steps of: determining the initial conditions for the multi-working conditions optimal design of the spokes, including design parameters and typical operating conditions; reasonably arranging tests based on the orthogonal test design program, and numerically calculate the test program for each typical working condition to obtain the head value of each sample point; use the multivariate quadratic regression model to establish the functional relationship between the spoke parameters and the head; use the comprehensive objective method to transform the multi-objective optimization problem into The combination of linear weighting method and particle swarm optimization algorithm is used to obtain the optimal parameter combination of spokes under multi-working conditions, and its improvement effect is verified and analyzed. The invention can effectively suppress the formation of "saddle area" under the stall condition while ensuring that the external characteristics of the axial flow pump are not affected under the rated working condition, and is beneficial to improving the overall hydraulic performance of the axial flow pump.

The invention provides a tracing method for a GPU computing performance problem. The method comprises the following steps: (1) describing behavior characteristics of a CUDA program kernel function level by using a CUDA task parallel model CTPM, thereby identifying a performance low-efficiency behavior of the CUDA program kernel function level, and expanding kernel function level performance optimization work; and (2) for the internal data parallel part of the CUDA program kernel function, using a hierarchical iteration attribute reduction algorithm LIAR to identify the key metric, performing deep performance mining on the CUDA program, and optimizing the internal performance problem of the CUDA kernel function. According to the method, by analyzing the CUDA development operation environment and the programming model based on the GPU hardware characteristics, an effective performance problem tracing method is found, the accuracy of performance bottleneck positioning is improved, and thepurpose of shortening the optimization period is achieved.

The invention discloses an energy management method based on working condition identification, which includes, using the K-means clustering algorithm to classify the working conditions of four typical working conditions, and calculating the cluster centers of the four typical working conditions; The minimum control strategy for effective fuel consumption; combining the multi-island genetic algorithm and the sequence quadratic programming algorithm, and using the Task component in the Isight software to construct a combined optimization model; using the combined optimization model to analyze the variables and four typical equivalent fuel consumption minimum control strategies The cluster centers of the working conditions are integrated and optimized to obtain the final cluster centers and the corresponding optimal equivalent fuel coefficients under four typical working conditions; extract a section of random driving condition characteristic parameters, and classify the working conditions. The typical working condition type and the optimal equivalent fuel coefficient are used for optimal distribution of power; the invention can realize the identification of working condition characteristic parameters, and at the same time solve the shortcomings of a single local or global optimization algorithm.