镀锡板生产线深基坑施工实践

采用钻孔灌注桩作为深地坑的围护结构，在坑内设排水沟、集水井排水。成功地在珠江三角洲地区狭窄场地进行地坑开挖，既保证了工程质量又有其特色。     

Deep Web 研究现状与展望

随着Deep Web数量和规模的快速增长,通过对其发起查询请求以得到存储在后台数据库中的相关信息,日渐成为用户获取信息的主要方式。为了方便用户有效地利用Deep Web中的信息,越来越多的研究者致力于这一领域的研究,重点之一是Deep Web后台数据库的数据集成。由于Deep Web后台数据库存储的主要是文本信息,使得从文本处理角度出发,针对Deep Web中存储的内容进行查询与检索的研究具有十分广阔的应用前景。本文对Deep Web的研究现状进行了较为详细的分析,同时对研究的发展方向进行了展望。     

带平衡约束矩形布局优化问题的深度强化学习算法

带平衡约束的矩形布局问题源于卫星舱设备布局设计,属于组合优化问题。深度强化学习利用奖赏机制,通过数据训练实现高性能决策优化。针对布局优化问题,提出一种基于深度强化学习的新算法DAR及其扩展算法IDAR。DAR用指针网络输出定位顺序,再利用定位机制给出布局结果,算法的时间复杂度是O（n³）;IDAR算法在DAR的基础上引入迭代机制,算法时间复杂度是O（n⁴）,但能给出更好的结果。测试表明DAR算法具有较好的学习能力,用小型布局问题进行求解训练所获得的模型,能有效应用在大型问题上。在两个大规模典型算例的对照实验中,提出算法分别超出和接近目前最优解,具有时间和质量上的优势。     

基于横纵向联合控制的多目标优化车辆跟驰研究

为解决车辆在拥堵环境中因车速波动较大所带来的跟驰平稳性较差、跟踪无效或不安全等问题,提出了基于车辆模型和深度强化学习的多目标优化跟驰方案。首先基于车辆横纵向动力学建立车辆跟驰模型,然后根据车间距误差、速度误差、横向偏差及相对偏航角等,利用深度确定性策略梯度算法得到跟驰车的加速度和转向角,以更平稳安全地控制跟驰车辆。经NGSIM公开驾驶数据集进行测试与验证,该方案可有效地提升跟驰车辆的稳定、舒适与安全性,对保证交通安全和提升道路通行能力具有重要意义。     

基于深度神经网络的高位滑坡范围预测

以贵州尖山营滑坡为工程背景,通过对深度学习的总结与分析,建立多层感知器模型以对该滑坡危险区范围进行非线性预测研究。通过对深度神经网络算法的优化,构建64-128-32-1四层多层感知器模型,并以滑坡最大高差、滑坡体积、滑源区坡度、坡脚坡度、地层倾角作为输入量,以滑坡最大水平运动距离作为输出量对该模型进行训练,实现影响因素与运动距离的非线性映射。根据对贵州省尖山营滑坡调查和研究,尖山营滑坡区域面积约648 700 m2,体积约1 200万 m3,属于特大型滑坡。依据最优模型对该滑坡进行滑距预测,滑坡平面直线距离1 769 m区域内为危险区域。     

Automatic Channel Detection Using DNN on 2D Seismic Data

Geologists interpret seismic data to understand subsurface properties and subsequently to locate underground hydrocarbon resources. Channels are among the most important geological features interpreters analyze to locate petroleum reservoirs. However, manual channel picking is both time consuming and tedious. Moreover, similar to any other process dependent on human intervention, manual channel picking is error prone and inconsistent. To address these issues, automatic channel detection is both necessary and important for efficient and accurate seismic interpretation. Modern systems make use of real-time image processing techniques for different tasks. Automatic channel detection is a combination of different mathematical methods in digital image processing that can identify streaks within the images called channels that are important to the oil companies. In this paper, we propose an innovative automatic channel detection algorithm based on machine learning techniques. The new algorithm can identify channels in seismic data/images fully automatically and tremendously increases the efficiency and accuracy of the interpretation process. The algorithm uses deep neural network to train the classifier with both the channel and non-channel patches. We provide a field data example to demonstrate the performance of the new algorithm. The training phase gave a maximum accuracy of 84.6% for the classifier and it performed even better in the testing phase, giving a maximum accuracy of 90%.     

Stock Price Forecasting: An Echo State Network Approach

Forecasting stock prices using deep learning models suffers from problems such as low accuracy, slow convergence, and complex network structures. This study developed an echo state network (ESN) model to mitigate such problems. We compared our ESN with a long short-term memory (LSTM) network by forecasting the stock data of Kweichow Moutai, a leading enterprise in China’s liquor industry. By analyzing data for 120, 240, and 300 days, we generated forecast data for the next 40, 80, and 100 days, respectively, using both ESN and LSTM. In terms of accuracy, ESN had the unique advantage of capturing nonlinear data. Mean absolute error (MAE) was used to present the accuracy results. The MAEs of the data forecast by ESN were 0.024, 0.024, and 0.025, which were, respectively, 0.065, 0.007, and 0.009 less than those of LSTM. In terms of convergence, ESN has a reservoir state-space structure, which makes it perform faster than other models. Root-mean-square error (RMSE) was used to present the convergence time. In our experiment, the RMSEs of ESN were 0.22, 0.27, and 0.26, which were, respectively, 0.08, 0.01, and 0.12 less than those of LSTM. In terms of network structure, ESN consists only of input, reservoir, and output spaces, making it a much simpler model than the others. The proposed ESN was found to be an effective model that, compared to others, converges faster, forecasts more accurately, and builds time-series analyses more easily.     

Semisupervised Encrypted Traffic Identification Based on Auxiliary Classification Generative Adversarial Network

The rapidly increasing popularity of mobile devices has changed the methods with which people access various network services and increased network traffic markedly. Over the past few decades, network traffic identification has been a research hotspot in the field of network management and security monitoring. However, as more network services use encryption technology, network traffic identification faces many challenges. Although classic machine learning methods can solve many problems that cannot be solved by port- and payload-based methods, manually extract features that are frequently updated is time-consuming and labor-intensive. Deep learning has good automatic feature learning capabilities and is an ideal method for network traffic identification, particularly encrypted traffic identification; Existing recognition methods based on deep learning primarily use supervised learning methods and rely on many labeled samples. However, in real scenarios, labeled samples are often difficult to obtain. This paper adjusts the structure of the auxiliary classification generation adversarial network (ACGAN) so that it can use unlabeled samples for training, and use the wasserstein distance instead of the original cross entropy as the loss function to achieve semisupervised learning. Experimental results show that the identification accuracy of ISCX and USTC data sets using the proposed method yields markedly better performance when the number of labeled samples is small compared to that of convolutional neural network (CNN) based classifier.     

Mechanical procedure for proof construction via closed terms in typed λ calculus

In this paper is presented an algorithm for constructing natural deduction proofs in the propositional intuitionistic and classical logics according to the analogy relating intuitionistic propositional formulas and natural deduction proofs, respectively, to types and terms of simple type theory. Proofs are constructed as closed terms in the simple typed calculus. The soundness and completeness of this method are proved.     

Aluminum. II. Derivation of C v0from C p and comparison to C v0 calculated from anharmonic models

The specific heat at constant pressure, C _p, of aluminum measured by Ditmars, Plint, and Shukla has been reduced to the volume V ₀ appropriate for 0 K employing the Murnaghan equation. The C _v0 thus obtained is compared with the theoretical C _v0 calculated in the harmonic and the lowest-order anharmonic approximation from three different pseudopotentials (Harrison, Ashcroft, and Dagens-Rasolt-Taylor) as well as a phenomenological Morse potential. The higher-order ( ⁴) anharmonic contributions are calculated from the same nearest-neighbor Morse potential as in the lowest-order anharmonic theory. The role of the vacancy and the higher-order anharmonic contributions to C _v0 has been examined and we conclude that the ⁴ contributions to C _v0 are much smaller than the vacancy contribution. After removal of the vacancy contribution, the reduced C _v0 is found to be in excellent agreement with the Ashcroft and Harrison pseudopotentials as well as the Morse potential including the ² and ⁴ contributions to C _v0.