Search

Explosive increase of industrial data collected from sensors has brought increasing attractions to the data-driven predictive maintenance for industrial machines in cyber-physical systems (CPSs). Since machinery faults are always caused by performance deterioration of components, learning the deteriorating mode from observed sensor data facilitates the prognostics of impeding faults and predicting the remaining useful life (RUL). In modern CPSs, several key performance indicators (KPIs) are monitored to detect the corresponding fine-grained deteriorating modes of industrial machines. However, the overall deterioration estimation and RUL prediction based on these KPIs with various patterns have been a great challenge, especially without labels of deteriorating index or uninterpretable of root causes. In this paper, we proposed K-PdM , a cluster-based hidden Markov model for the machinery deterioration estimation and RUL prediction based on multiple KPIs. The method uncovers the fine-grained deteriorating modes of machines through each unlabeled KPI data and learns a mapping between each deteriorating KPI index and RULs. Accordingly, an overall deterioration estimation and RUL prediction of machine are able to be achieved based on the combination of each KPI’s deterioration estimation. Moreover, a set of interpretable semantic rules are setup to analyze the root cause of performance deterioration among KPIs. An experimental application is proposed to demonstrate its applicability based on the PHM08 data sets. The obtained results show their effectiveness to predict the RULs of machines.

To effectively predict traffic fatalities and promote the friendly development of transportation, a prediction model of traffic fatalities is established based on support vector machine (SVM). As the prediction accuracy of SVM largely depends on the selection of parameters, Particle Swarm Optimization (PSO) is introduced to find the optimal parameters. In this paper, small sample and nonlinear data are used to predict fatalities of traffic accident. Traffic accident statistics data of China from 1981 to 2012 are chosen as experimental data. The input variables for predicting accident are highway mileage, vehicle number and population size while the output variables are traffic fatality. To verify the validity of the proposed prediction method, the back-propagation neural network (BPNN) prediction model and SVM prediction model are also used to predict the traffic fatalities. The results show that compared with BPNN prediction model and SVM model, the prediction model of traffic fatalities based on PSO-SVM has higher prediction precision and smaller errors. The model can be more effective to forecast the traffic fatalities. And the method using particle swarm optimization algorithm for parameter optimization of SVM is feasible and effective. In addition, this method avoids overcomes the problem of “over learning” in neural network training progress

In order to learn the performance degradation mode of machines for diagnostics and prognostics in Cyber-Physical System (CPS), it is necessary to analyze observed sensor data to find the internal run-to-failure states of a system. In this paper, the research goal focuses on learning the internal state and transition of the degraded states from original data, which has some advantages to reveal the working dynamics of the system. Due to the existence of unlabeled data, the paper proposes an unsupervised framework based on clustering and Hidden Markov Model, named Cluster-based Hidden Markov Model (cHMM). The cHMM aims at converting raw sensory stream into a sequence of symbols as the initial observation and hidden state sequences, and then an extended Viterbi algorithm based on Hidden Markov Model (HMM) is used to discover the final stable hidden states and transitional rules in a dynamic programming way. Based on the learned model and expert's knowledge, performance degradation failure and the root-cause could be predicted and reasoned. Finally, experiments and proof-of-concept demonstration are given to validate the feasibility and effectiveness of the framework based on C-MAPSS turbofan engine dataset.

Web of Things (WoT) facilitates the discovery and interoperability of Internet of Things (IoT) devices in a cyber-physical system (CPS). Moreover, a uniform knowledge representation of physical resources is quite necessary for further composition, collaboration, and decision-making process in CPS. Though several efforts have integrated semantics with WoT, such as knowledge engineering methods based on semantic sensor networks (SSN), it still could not represent the complex relationships between devices when dynamic composition and collaboration occur, and it totally depends on manual construction of a knowledge base with low scalability. In this paper, to addresses these limitations, we propose the semantic Web of Things (SWoT) framework for CPS (SWoT4CPS). SWoT4CPS provides a hybrid solution with both ontological engineering methods by extending SSN and machine learning methods based on an entity linking (EL) model. To testify to the feasibility and performance, we demonstrate the framework by implementing a temperature anomaly diagnosis and automatic control use case in a building automation system. Evaluation results on the EL method show that linking domain knowledge to DBpedia has a relative high accuracy and the time complexity is at a tolerant level. Advantages and disadvantages of SWoT4CPS with future work are also discussed.

Integrating semantic technology to the Web of Things (WoT) facilitates the creation of a networked knowledge infrastructure with more interoperable data from both physical and cyber world. However, most of current solutions relies on manual methods based on domain-specific ontology, which is only suitable for domain expert and developers but not compatible with large-scale knowledge construction. This paper proposes a semi-automatic annotation framework for the metadata representation of WoT resource. This framework is based on a probabilistic graphical model to collectively infer entities, classes and relations from schematic WoT resources mapping to domain independent knowledge base. A proof-of-concept implementation and performance evaluation are illustrated to show a feasibility of our method.

Web of Things (WoT) unifies the syntactic representations of physical objects via web pattern, which facilitates the integrations and mashups of heterogeneous data and web services. However, the lack of unified representation markup tools and methods at semantic layer hinders the interoperability, integration and scalable search of things. This paper proposes a Semantic Web of Things Framework to improve the interoperability among domain-specific Web of Things applications by providing a unified WoT Knowledge Base construction framework. For this purpose, a Microdata vocabulary extended from Semantic Sensor Network ontology is proposed to facilitate manual annotation on HTML-based WoT representations. Moreover, to improve the scalability of extraction of semantics of structured Web of Things resources, a semi-automatic semantic annotation method based on entity linking model is also proposed. To testify the technical feasibility of the framework, a reference implementation and quantitative evaluation on annotation results are illustrated.

This paper investigates a well-known complex combinatorial problem known as the vehicle routing problem with time windows (VRPTW). Unlike the standard vehicle routing problem, each customer in the VRPTW is served within a given time constraint. This paper solves the VRPTW using an improved artificial bee colony (IABC) algorithm. The performance of this algorithm is improved by a local optimization based on a crossover operation and a scanning strategy. Finally, the effectiveness of the IABC is evaluated on some well-known benchmarks. The results demonstrate the power of IABC algorithm in solving the VRPTW.