Multitask learning for health condition identification and remaining useful life prediction: deep convolutional neural network approach

Predicting remaining useful life (RUL) is crucial for system maintenance. Condition monitoring makes not only degradation data available for RUL estimation but also categorized health status data for health state identification. However, RUL prediction has been treated as an independent process in most cases even though potential relevance exists with health status detection process. In this paper, we propose a convolution neural network based multi-task learning method to reflect the relatedness of RUL estimation with health status detection process. The proposed method applied to the C-MAPSS dataset for aero-engine unit prognostics supported superior performances to existing baseline models.

     

A run-to-run controller for a chemical mechanical planarization process using least squares generative adversarial networks

Achieving high processing quality for chemical mechanical planarization (CMP) in semiconductor manufacturing is difficult due to the distinct process variations associated with this method, such as drift and shift. Run-to-run control aims to maintain the targeted process quality by reducing the effect of process variations. The goal of controller learning is to infer an underlying output–input reverse mapping based on input–output samples considering the process variations. Existing controllers learn reverse mapping by minimizing the total mapping error for sample data. However, this approach often fails to generate inputs for unseen target outputs because conditional input distributions on target outputs are not captured in the learning. In this study, we propose a controller based on a least squares generative adversarial network (LSGAN) that can capture the input distributions. GANs are deep-learning architectures composed of two neural nets: a generator and a discriminator. In the proposed model, the generator attempts to produce fake input distributions that are similar to the real input distributions considering the process variation features extracted using convolutional layers, while the discriminator attempts to detect the fake distributions. Competition in this game drives both networks to improve their performance until the generated input distributions are indistinguishable from the real distributions. An experiment using the data obtained from a work-site CMP tool verified that the proposed model outperformed the comparison models in terms of control accuracy and computation time.

     

Customer entrepreneurship on digital platforms: Challenges and solutions for platform business models

Drawing on the mixed methods of qualitative research and agent‐based simulation, this study examines: (a) how end‐users use digital platforms to become customer–entrepreneurs undertaking commercial activities on platforms; and (b) how platform providers can convert this customer entrepreneurship into a revenue stream. Considering that end‐users have traditionally been defined as passive and uncharged actors in platform business models, an in‐depth understanding of their commercial activities and the viable revenue model to monetize this emerging customer practice is warranted. Our qualitative study reveals that customer–entrepreneurs make substantial use of platform offerings to advertise their products; communicate with end‐consumers; and accept payments. These commercial activities are largely exercised for free on platforms, even though they could otherwise serve as a source of revenue. On this point, our simulation results identify two pricing models achieving the generation of nearly identical revenues over time. First, platform providers may charge both advertising and transaction fees, which maximize the survival of professional customer–entrepreneurs. Second, platform businesses may levy advertising fees only, which maximizes the survival of informal customer–entrepreneurs operating on a micro‐scale and part‐time basis. This study offers theoretical, methodological, and managerial implications for platform studies.     

A new spatial IP assignment method for IP-based wireless sensor networks

Wireless sensor networks (WSNs), one of the commercial wireless mesh networks (WMNs), are envisioned to provide an effective solution for sensor-based AmI (Ambient Intelligence) systems and applications. To enable the communications between AmI sensor networks and the most popular TCP/IP networks seamlessly, the best solution model is to run TCP/IP directly on WSNs (Mulligan et al. 2009; Hui and Culler 2008; Han and Mam 2007; Kim et al. 2007; Xiaohua et al. 2004; Dunkels et al. 2004; Dunkels et al. 2004; Dunkels 2001; Dunkels et al. 2004). In this case, an IP assignment method is required to assign each sensor node a unique IP address. SIPA (Dunkels et al. 2004) is the best known IP assignment method that uses spatial relations and locations of sensor nodes to assign their IP addresses. It has been applied in Contiki (Dunkels et al. 2004), a famous WSN operating system, to support the 6LowPAN protocol. In Chang et al. (2009), we proposed the SLIPA (Scan-Line IP Assignment) algorithm to improve the assignment success rate (ASR) obtained by SIPA. SLIPA can achieve a good ASR when sensor nodes are uniformly distributed. However, if sensor nodes are deployed by other distributions, the improvements would be limited. This paper proposes a new spatial IP assignment method, called SLIPA-Q (SLIPA with equal-quantity partition), to improve SLIPA. Experiments show that, by testing the proposed method 1,000 times with 1,000 randomly deployed sensor nodes, the average ASR obtained by SLIPA-Q is over two times of that obtained by SLIPA. Under the same 88% ASR, the average numbers of sensor nodes those can be successfully assigned by SLIPA-Q, SLIPA, and SIPA are 950, 850, and 135, respectively. Comparing to previous spatial IP assignment methods, SLIPA-Q can achieve dramatic improvements in ASR for assigning IP addresses to a large set of sensor nodes.     

An investigation of the effect of online consumer trust on expectation, satisfaction, and post-expectation

This study proposes a framework regarding the relationship between consumer trust, satisfaction, expectation, and post-expectation in the context of electronic commerce. In particular, the framework draws together from three theories: social exchange theory, expectation-confirmation theory, and post-acceptance model of IS continuance. Following the longitudinal pre-purchase and post-purchase stages, this study provides a theoretical framework combining trust, expectation, satisfaction, and post-expectation (i.e., perceived usefulness) and tests the proposed model empirically using Internet consumer behavior data collected via two rounds of Web surveys. The empirical findings suggest that both consumer’s trust and expectation have positive influences on consumer’s satisfaction; a significant and positive relationship is detected between consumer’s trust and expectation; customer’s satisfaction and perceived usefulness as post-expectation belief are important predictors of repurchase intention. In consequence, the study provides a framework explaining the subsequent relationships of trust, expectation, confirmation, satisfaction, post-expectation, and repurchase intention (i.e., consumer trust → expectation → confirmation → satisfaction → post-expectation → repurchase intention) across pre-purchase and post-purchase stages. Theoretical and practical implications are discussed.     

基于Cookie的安全防护技术研究

Cookie的使用方便了人们的网上生活,但同时对用户的许多隐私信息构成了威胁。文章首先介绍了Cookie技术的发展背景、相关概念、应用领域及基本特征,说明了Cookie的工作原理和Cookie结构;其次讲述了常见的Cookie技术的漏洞,Cookie欺骗和Cookie注入的原理和方法;最后介绍了针对Cookie技术的安全防护措施,并详细描述了一种基于Cookie特性分析的系统设计思想及其在VC环境下的实现过程。系统主要包含两个核心模块：Cookie特性分析模块和Cookie安全防护模块。实现了Cookie查看、修改Cookie属性、删除Cookie、禁用Cookie、监视Cookie等功能。系统为普通用户和专业用户提供了不同的防御功能,让用户一定程度上可以更清晰地认识Cookie、提高自身安全意识和防范本地Cookie失窃。     

面向服务的装甲装备PHM体系结构研究

为适应装甲装备维修保障方式改革的需要,提出一种面向服务的装甲装备故障预测与健康管理(PHM)体系结构;分析了几种典型PHM体系结构,得出PHM体系结构应具备的共性特征;结合面向服务架构的原理和装甲装备综合电子信息系统的特点,研究和设计了面向服务的装甲装备PHM体系结构,详细阐述了其组成、功能及特点;该结构具有分布式、层次化、开放性等特点,满足装甲装备PHM系统分布式应用环境要求。     

装甲装备故障预测与健康管理系统技术研究

预测和健康状态管理(PHM)技术是一种先进测试、维修技术;从视情维修保障的背景出发,介绍了装甲装备PHM系统的内涵,进行了装甲装备故障模式影响和危害分析,明确了PHM系统具备的功能,初步构建了基于开放体系的装甲装备PHM系统的技术框架,并对其中的关健技术进行了深入研究,对炮控系统进行故障预测分析,结果和实际应用一致。     

Volterra filter modeling of nonlinear discrete-time system using improved particle swarm optimization

This paper focuses on the identification problem of nonlinear discrete-time systems using Volterra filter series model. Generally, to update the kernels of Volterra model, the most commonly used method is the gradient adaptive algorithm. However, this method probably traps at the local minimum for searching parameter solutions. In this study, a new intelligence swarm computation of the global search is considered. We utilize an improved particle swarm optimization (IPSO) algorithm to design the Volterra kernel parameters. It is somewhat different from the original algorithm due to modifying its velocity updating formula and this can promote the algorithm?s searching ability for solving the optimization problem. Using the IPSO algorithm to minimize the mean square error (MSE) between the actual output and model output, the identification problem for nonlinear discrete-time systems can be fulfilled. Finally, two different kinds of examples are provided to demonstrate the efficiency of the proposed method. Moreover, some examinations including the Volterra model memory size and algorithm initial condition are further considered.     

Simple culling methods for continuous collision detection of deforming triangles

We present a simple and efficient approach for continuous collision detection of deforming triangles based on conservative advancement. The efficiency of our approach is due to a sequence of simple collision-free conditions for deforming triangles. In our experiment, we show that our CCD algorithm achieves 2-30 times performance improvement over existing algorithms for triangle primitives.