Goal-driven automation of a deep space communications station: a case study in knowledge engineering for plan generation and execution

Abstract: This paper describes the application of Artificial Intelligence techniques for plan generation, plan execution, and plan monitoring to automate a Deep Space Communication Station. This automation allows a communication station to respond to a set of tracking goals by appropriately reconfiguring the communications hardware and software to provide the requested communications services. In particular this paper describes: (1) the overall automation architecture, (2) the plan generation and execution monitoring AI technologies used and implemented software components, and (3) the knowledge engineering process and effort required for automation. This automation was demonstrated in February 1995, at the DSS13 Antenna Station in Goldstone, CA on a series of Voyager tracks and the technologies demonstrated are being transferred to the operational Deep Space Network stations.     

An output-based adaptive iterative learning controller for high relative degree uncertain linear systems

In this paper, we derive an output tracking error model based on signals filtered from plant input and output, and then present a new output-based adaptive iterative learning controller for repeatable linear systems with unknown parameters, high relative degree, initial resetting error, input disturbance and output noise. The proposed controller solves the important robustness issues without assuming the bounds of uncertainties to be sufficiently small and can be applied to high relative degree plants without using output differentiation. Control parameters are updated between successive iterations so as to compensate for unknown system parameters and uncertainties. It is shown that the internal signals inside closed-loop learning system remain bounded and the output tracking error will asymptotically converge to a profile tunable by some design parameters. Furthermore, the learning speed is easily improved if the learning gain is increased.     

Clean up of Petroleum-Hydrocarbon Contaminated Soils Using Enhanced Bioremediation System: Laboratory Feasibility Study

The objective of this study was to assess the potential of applying enhanced bioremediation on the treatment of petroleum-hydrocarbon contaminated soils. Microcosm experiments were conducted to determine the optimal biodegradation conditions. The control factors included oxygen content, nutrient addition, addition of commercially available mixed microbial inocula, addition of wood chip and rice husk mixtures (volume ratio = 1:1) as bulking agents, and addition of organic amendments (chicken manures). Results indicate that the supplement of microbial inocula or chicken manures could significantly increase the microbial populations in soils, and thus enhance the efficiency of total petroleum hydrocarbon (TPH) removal (initial TPH = 5,500?mg/kg). The highest first-order TPH decay rate and removal ratio were approximately 0.015?day?1 and 85%, respectively, observed in microcosms containing microbial inocula (mass ratio of soil to inocula = 50:1), nutrient, and bulking agent (volume ratio of soil to bulking agent = 10 to 1) during 155 days of incubation. Results indicate that the first-order TPH decay rates of 0.015 and 0.0142?day?1 can be obtained with the addition of microbial inocula and chicken manures, respectively, compared with the decay rate of 0.0069?day?1 under intrinsic conditions. Thus, chicken manures have the potential to be used as substitutes of commercial microbial inocula. The decay rate and removal ratio can be further enhanced to 0.0196?day?1 and 87%, respectively, with frequent soil shaking and air replacement. Results will be useful in designing an ex situ soil bioremediation systems (e.g., biopile and land farming) for practical application.     

Iterative learning of model reference adaptive controller for uncertain nonlinear systems with only output measurement

In this paper, a model reference adaptive control strategy is used to design an iterative learning controller for a class of repeatable nonlinear systems with uncertain parameters, high relative degree, initial output resetting error, input disturbance and output noise. The class of nonlinear systems should satisfy some differential geometric conditions such that the plant can be transformed via a state transformation into an output feedback canonical form. A suitable error model is derived based on signals filtered from plant input and output. The learning controller compensates for the unknown parameters, uncertainties and nonlinearity via projection type adaptation laws which update control parameters along the iteration domain. It is shown that the internal signals remain bounded for all iterations. The output tracking error will converge to a profile which can be tuned by design parameters and the learning speed is improved if the learning gain is large.     

Correlation between structural and optical properties of 30 nm and 60 nm lead sulfide nanowires

PbS nanowires with 30 nm and 60 nm diameter fabricated under the same condition of electrochemical deposition with sulfuric and oxalic anodic alumina membranes (AAM), respectively, have been successfully prepared in order to study their optical properties in relation to their size. Scanning electron microscopy indicates that the 60 nm PbS nanowire arrays have the same shape with the 30 nm. X-ray diffraction result shows that 60 nm PbS nanowires are crystalline and have a highly (200) preferential orientation like 30 nm ones. UV spectrum considers the nanowire size decrease as the absorption peak shifts to the blue. The quantum confinement effects compared between 30 nm and 60 nm PbS nanowire arrays were observed by the measurements of ultraviolet-visible absorption spectroscopy (UV-vis).     

对空域图像LSB隐写术的提取攻击

隐写分析的研究一直集中于检测隐藏信息的存在性,而关于如何提取隐藏信息(即对隐写术的提取攻击)的研究还非常少.对于使用密钥的隐写术,提取攻击等价于恢复隐写密钥.文中结合隐写分析中的检测技术和密码分析中的相关攻击技术,对空域图像LSB隐写术提出了一种隐写密钥恢复方法.理论分析说明:此攻击方法的计算复杂度主要由所需的样本量决定,并且当嵌入率r接近0或1时攻击将失败.作者通过混合高斯模型给出了一个估计最小样本量的方法.针对隐写软件"Hide and Seek 4.1"的实验表明:此攻击方法可以成功恢复隐写密钥,从而提取隐藏的消息.如果消息长度L未知,当嵌入率5.3%＜r＜94.7%时攻击可以成功;如果L已知,当1.1%＜r＜98.4%时攻击可以成功,并且当11%＜r＜50%时,使用估计的最小样本量可以将攻击速度提高10%～45%.     

对DCT域连续LSB隐写术的提取攻击

基于JPEG图像的空域特征,针对DCT域连续LSB隐写术提出一种唯载密提取攻击方法。根据JPEG图像编码块在空域的块不连续性,将嵌入消息起止点估计问题转化为序列突变点的估计问题,建立逼近理想序列模型估计序列突变点。新模型不仅适用于对连续JSteg算法的提取攻击,对一类可抵抗χ²检验攻击的连续JSteg改进算法同样有效。实验结果表明,对消息嵌入起止点的平均估计误差约为260个系数。     

Retrieving Aerial Scene Images with Learned Deep Image-Sketch Features

This paper investigates the problem of retrieving aerial scene images by using semantic sketches, since the state-of-the-art retrieval systems turn out to be invalid when there is no exemplar query aerial image available. However, due to the complex surface structures and huge variations of resolutions of aerial images, it is very challenging to retrieve aerial images with sketches and few studies have been devoted to this task. In this article, for the first time to our knowledge, we propose a framework to bridge the gap between sketches and aerial images. First, an aerial sketch-image database is collected, and the images and sketches it contains are augmented to various levels of details. We then train a multi-scale deep model by the new dataset. The fully-connected layers of the network in each scale are finally connected and used as cross-domain features, and the Euclidean distance is used to measure the cross-domain similarity between aerial images and sketches. Experiments on several commonly used aerial image datasets demonstrate the superiority of the proposed method compared with the traditional approaches.     

An effective and interpretable method for document classification

As the number of documents has been rapidly increasing in recent time, automatic text categorization is becoming a more important and fundamental task in information retrieval and text mining. Accuracy and interpretability are two important aspects of a text classifier. While the accuracy of a classifier measures the ability to correctly classify unseen data, interpretability is the ability of the classifier to be understood by humans and provide reasons why each data instance is assigned to a label. This paper proposes an interpretable classification method by exploiting the Dirichlet process mixture model of von Mises–Fisher distributions for directional data. By using the labeled information of the training data explicitly and determining automatically the number of topics for each class, the learned topics are coherent, relevant and discriminative. They help interpret as well as distinguish classes. Our experimental results showed the advantages of our approach in terms of separability, interpretability and effectiveness in classification task of datasets with high dimension and complex distribution. Our method is highly competitive with state-of-the-art approaches.     

An intelligent system for wafer bin map defect diagnosis: An empirical study for semiconductor manufacturing

Wafer bin maps (WBMs) that show specific spatial patterns can provide clue to identify process failures in the semiconductor manufacturing. In practice, most companies rely on experienced engineers to visually find the specific WBM patterns. However, as wafer size is enlarged and integrated circuit (IC) feature size is continuously shrinking, WBM patterns become complicated due to the differences of die size, wafer rotation, the density of failed dies and thus human judgments become inconsistent and unreliable. To fill the gaps, this study aims to develop a knowledge-based intelligent system for WBMs defect diagnosis for yield enhancement in wafer fabrication. The proposed system consisted of three parts: graphical user interface, the WBM clustering solution, and the knowledge database. In particular, the developed WBM clustering approach integrates spatial statistics test, cellular neural network (CNN), adaptive resonance theory (ART) neural network, and moment invariant (MI) to cluster different patterns effectively. In addition, an interactive converse interface is developed to present the possible root causes in the order of similarity matching and record the diagnosis know-how from the domain experts into the knowledge database. To validate the proposed WBM clustering solution, twelve different WBM patterns collected in real settings are used to demonstrate the performance of the proposed method in terms of purity, diversity, specificity, and efficiency. The results have shown the validity and practical viability of the proposed system. Indeed, the developed solution has been implemented in a leading semiconductor manufacturing company in Taiwan. The proposed WBM intelligent system can recognize specific failure patterns efficiently and also record the assignable root causes verified by the domain experts to enhance troubleshooting effectively.