通渝隧道围岩变形的神经网络预测

隧道新奥法施工中，常以围岩变形量作为评判围岩稳定性和支护结构经济合理性的重要指标。公路隧道围岩变形量是随时间而变化的数据序列，因而可以建立一些实时跟踪预测模型和方法。根据通渝隧道围岩拱顶下沉位移变形的特性，采用神经网络技术来预测其变形量，结果表明该方法简易、有效。     

客车主要噪声源识别的试验研究

基于偏奇异值分析法识别噪声源的基本原理，采用了近场声压测量法，同步采集15个传感器的振动与声压信号，识别出客车车外噪声的主要噪声源，分析出各噪声源对车外噪声的贡献并做出降低车外噪声的预测分析。所采用的试验与分析方法具有计算量小、声源定位准确的特点，并且可以准确预测零部件的改进对车外噪声的影响。试验研究和实车应用表明，这种方法可以适用于复杂的工程实际。     

公路岩质边坡稳定性的工程地质分析

岩质边坡稳定性问题对公路工程建设的决策、造价和工期具有重要的影响和作用;同时,它还是公路边坡工程设计与施工的重要依据条件之一。针对漳龙高速公路XX段岩质边坡的稳定性问题,从边坡的地形地貌特征、岩石类型与特征、岩体结构类型与特性、结构面发育度与优势面状态等多方面因素,并采用赤平极射投影法;对该段岩质边坡的稳定性进行定性的工程地质分析。     

Tuning of transfer functions for analysis of wave–ship interactions

Transfer functions are often used together with a wave spectrum for analysis of wave–ship interactions, where one application addresses the prediction of wave-induced motions or other types of global responses. This paper presents a simple and practical method which can be used to tune the transfer function of such responses to facilitate improved prediction capability. The input to the method consists of a measured response, i.e. time series sequences from a given sensor, the 2D wave spectrum characterising the seaway in which the measurements are taken, and an initial estimate of the transfer function for the response in study. The paper presents results obtained using data from an in-service container ship. The 2D wave spectra are taken from the ERA5 database, while the transfer function is computed by a simple closed-form expression. The paper shows that the application of the tuned transfer function leads to predictions which are significantly improved compared to using the transfer function without tuning.     

基于ANN的船舶撞击高桩码头群桩损伤位置预测

本文采用有限元软件ABAQUS建立了船舶撞击高桩码头群桩的空间有限元模型。通过计算评估了撞击力、桩体刚度、撞击位置和撞击角度下对群桩结构损伤位置的影响。基于人工神经网络(ANN)方法,对不同参数组合下的群桩结构损伤位置进行了预测,并对ANN方法的可行性进行了评估。     

Forecasting current and next trip purpose with social media data and Google Places

Trip purpose is crucial to travel behavior modeling and travel demand estimation for transportation planning and investment decisions. However, the spatial-temporal complexity of human activities makes the prediction of trip purpose a challenging problem. This research, an extension of work by Ermagun et al. (2017) and Meng et al. (2017), addresses the problem of predicting both current and next trip purposes with both Google Places and social media data. First, this paper implements a new approach to match points of interest (POIs) from the Google Places API with historical Twitter data. Therefore, the popularity of each POI can be obtained. Additionally, a Bayesian neural network (BNN) is employed to model the trip dependence on each individual’s daily trip chain and infer the trip purpose. Compared with traditional models, it is found that Google Places and Twitter information can greatly improve the overall accuracy of prediction for certain activities, including “EatOut”, “Personal”, “Recreation” and “Shopping”, but not for “Education” and “Transportation”. In addition, trip duration is found to be an important factor in inferring activity/trip purposes. Further, to address the computational challenge in the BNN, an elastic net is implemented for feature selection before the classification task. Our research can lead to three types of possible applications: activity-based travel demand modeling, survey labeling assistance, and online recommendations.     

Driving cycle prediction model based on bus route features

Bus fuel economy is deeply influenced by the driving cycles, which vary for different route conditions. Buses optimized for a standard driving cycle are not necessarily suitable for actual driving conditions, and, therefore, it is critical to predict the driving cycles based on the route conditions. To conveniently predict representative driving cycles of special bus routes, this paper proposed a prediction model based on bus route features, which supports bus optimization. The relations between 27 inter-station characteristics and bus fuel economy were analyzed. According to the analysis, five inter-station route characteristics were abstracted to represent the bus route features, and four inter-station driving characteristics were abstracted to represent the driving cycle features between bus stations. Inter-station driving characteristic equations were established based on the multiple linear regression, reflecting the linear relationships between the five inter-station route characteristics and the four inter-station driving characteristics. Using kinematic segment classification, a basic driving cycle database was established, including 4704 different transmission matrices. Based on the inter-station driving characteristic equations and the basic driving cycle database, the driving cycle prediction model was developed, generating drive cycles by the iterative Markov chain for the assigned bus lines. The model was finally validated by more than 2 years of acquired data. The experimental results show that the predicted driving cycle is consistent with the historical average velocity profile, and the prediction similarity is 78.69%. The proposed model can be an effective way for the driving cycle prediction of bus routes.     

A hybrid deep learning based traffic flow prediction method and its understanding

Deep neural networks (DNNs) have recently demonstrated the capability to predict traffic flow with big data. While existing DNN models can provide better performance than shallow models, it is still an open issue of making full use of spatial-temporal characteristics of the traffic flow to improve their performance. In addition, our understanding of them on traffic data remains limited. This paper proposes a DNN based traffic flow prediction model (DNN-BTF) to improve the prediction accuracy. The DNN-BTF model makes full use of weekly/daily periodicity and spatial-temporal characteristics of traffic flow. Inspired by recent work in machine learning, an attention based model was introduced that automatically learns to determine the importance of past traffic flow. The convolutional neural network was also used to mine the spatial features and the recurrent neural network to mine the temporal features of traffic flow. We also showed through visualization how DNN-BTF model understands traffic flow data and presents a challenge to conventional thinking about neural networks in the transportation field that neural networks is purely a “black-box” model. Data from open-access database PeMS was used to validate the proposed DNN-BTF model on a long-term horizon prediction task. Experimental results demonstrated that our method outperforms the state-of-the-art approaches.     

Strain prediction for critical positions of FPSO under different loading of stored oil using GAIFOA-BP neural network

FPSO (floating, production, storage and offloading) units are widely used in the offshore oil and gas industry. Generally, FPSOs have excellent oil storage capacity owing to their huge oil cargo holds. The volume and distribution of stored oil in the cargo holds influence the strain level of hull girder, especially at critical positions of FPSO. However, strain prediction using structural analysis tools is computationally expensive and time consuming. In this study, a prediction tool based on back-propagation (BP) neural network called GAIFOA-BP is proposed to predict the strain values of concerned positions of an FPSO model under different oil storage conditions. The GAIFOA-BP combines BP model and GAIFOA which is a combination of genetic algorithm (GA) and an improved fruit fly optimization algorithm (IFOA). Results from three benchmark tests show that the GAIFOA-BP model has a remarkable performance. Subsequently, a total of 81 sets of training data and 25 sets of testing data are obtained from experiment using fiber Bragg grating (FBG) sensors installed on the surface of an FPSO model. The numerical results show that the GAIFOA-BP is capable of predicting the strain values with higher accuracy as compared with other BP models. Finally, the reserved GAIFOA-BP model is utilized to predict the strain values under the inputs of a 10-day time series of volume and distribution of stored oil. The predicted strain results are further used to calculate the fatigue consumption of measurement points.