Search

Fracture energy is always used to represent the fracture performance of concrete structures/beams, which is crucial for the application of concrete. However, due to the nature of concrete material and the complexity of the fracture process, it is difficult to accurately determine the fracture energy of concrete and predict the fracture behavior of different concrete structures. In this study, artificial intelligence approaches were tried to seek a feasible way to solve these prediction issues. Firstly, the ridge regression (RR), the classification and regression tree (CART), and the gradient boosting regression tree (GBRT) were selected to construct the predictive models. Then, the hyperparameters were tuned with the particle swarm optimization (PSO) algorithm; the performances of these three optimum models were compared with the test dataset. The mean squared errors (MSEs) of the optimum RR, CART, and GBRT models were 0.0447, 0.0164, and 0.0111, respectively, which indicated that their performances were excellent. Compared with the RR and CART models, the hybrid model constructed with GBRT and PSO appeared to be the most accurate and generalizable, both of which are significant for prediction work. The relative importance of the variables that influence the fracture energy of concrete was obtained, and compressive strength was found to be the most significant variable.

Yaw control system (YCS) is the critical part to actively control nacelle direction parallel to the inflow direction. Aiming at the aged units, the YCS would result in the loss of power production due to a shifting error. In this paper, a yaw zero-point misalignment calibration method is proposed to improve wind direction signal accuracy. A 2MW horizontal-axis wind turbine (HAWT) in Huashan wind farm Hubei Province, is selected as the studied object. From the purpose of quantitative analysis, the zero-point shifting error of wind direction sensor, i.e. wind vane, is firstly constructed to illustrate relevance between sensor data and control signal. The improved SCADA data-driven algorithm is then established to assess the value of misalignment, with the comparison of conventional method. Besides, field test and numerical analysis of misalignment calibration with nacelle-mounted lidar are carried out in the case studies, the calibration of both data-driven algorithm and LiDAR test show great consistency, while offset between LiDAR and wind vane measurement is unexpected. Result and following illustration of the proposed test is presented in conclusion, that data-driven algorithm could be used to assess yaw misalignment and refer to the calibration.

The fracture properties (e.g. tensile strength, fracture toughness) are regarded as the material constants, which could be used to predict the fracture behavior of concrete. However, the scattered distribution and size effect of test results make the prediction in conventional methods difficult. In this study, the artificial intelligence (AI) approaches and the Boundary Effect Model (BEM) closed-form solution were tried to analyze such complex relations between the fracture test results and specimen geometries in the 3 PB tests. Firstly, a cluster of data were collected and divided into the training set and testing set. Then, based on the training data, the ensemble algorithm (Random Forests) and the Particle Swarm Optimization (PSO) were combined to establish the hybrid AI predictive model, and the fracture properties and predictive domain were determined with the BEM closed-form solution and normal distribution analysis. After that, the testing data were used to evaluate the behavior of these two predictive methods. The performance of the AI predictive model was quantified with R2 = 0.947, and the unknown data in testing set all fell into the predicted domain which was determined by using the BEM predictive model. The merits of the two predictive methods in predicting the fracture performance of concrete specimens were compared and expected to integrate together in the future work.

The traditional methods used for distribution network planning are challenged because of the access of the stochastic distributed generation. A new distribution network planning model is proposed by converting the distribution network planning with distributed generation into solving the Steiner tree problem. Moreover, in order to solve the problem that the time of calculation multiplied along with the increase in the amount of Steiner nodes, an improved particle swarm optimization algorithm is proposed to solve the Steiner tree Non-deterministic Polynomial problem. In this algorithm the problem of premature convergence is solved by applying a small disturbance to the global optimum and the searching results are more reliable and accurate by improve the search ability for global optimum. Typical results of the proposed algorithm and the traditional algorithm are further illustrated and compared through an actual 54 nodes system to prove the validity of the methods in this paper.

This paper proposes the MLR (multiple linear regression) algorithm for parameter estimation of power system post-fault configuration based on the PMU real-time measurement and generator dynamic equations. Using real-time data collected by wide-area measurement system, the algorithm can take complicated cascading fault events into consideration without any information about the specific parameter and fault type or structure of the power system. This attractive feature avoids the difficult problem to determine the parameter and the topology state of a transient event in actual projects, making it possible for the complex perturbed trajectories prediction. The proposed algorithm has been tested on various sample power systems with promising and accurate simulation results.

When predicting the noise level of substation, the model of transformers and reactors as noise sources is very important. A new acoustic mode of the transformers and reactors is built in ultra-high voltage substation. Each of the transformers and reactors is equivalent to several point sources based on equivalent source method. And in the process of the equivalent, the measurement and calculation are made easier by using sound power level to represent the equivalent sources intensity. A model of 9 equivalent point sources is chosen to verify the accuracy of the model. This acoustic model of the transformers and reactors is combined with outdoor point sound sources attenuation theory to predict the substation noise value. Simulation of a 1000kV substation has been down which shows that the model is feasible to calculate the noise level anywhere inside the substation.

The logistics industry is the foundation and guarantee of the rapid development of manufacturing industry, and the manufacturing industry makes a huge demand for the development of logistics industry, therefore, it shows coordinated development trend between manufacturing industry and logistics. Using Logistic model, this paper gives quantitative research in the impact of Chinese manufacturing industry in driving the development of logistics industry and the impact of Chinese logistics in promoting the development of manufactory industry, which is an empirical of coordinated development between Chinese manufacturing industry and logistics. The paper also raises some suggestions to accelerate the development between Chinese manufacturing industry and logistics.

This paper addresses coordination problem of a supply chain comprising one supplier and one retailer under production cost and market demand disruptions. Assume the market demand is sensitive to retail price in an exponential form, the optimal strategies are obtained for different disruption scale under centralized-decision system, and it is shown that the original production plan of the supply chain has certain robustness under the disrupted production cost and the disrupted market scale. For the decentralized-decision system, it is proved that the supply chain can be fully coordinated by the quantity discount contracts appropriately.