Many industrial processes have multiple operation modes due to different manufacturing strategies or varying feedstock. Fault detection for a multimode process is a complex problem, as monitoring for both stable and transitional modes should be taken into consideration. In this paper, a novel method based on the similarity of data characteristics is proposed to realize mode identification for modeling data. Different models are developed to capture the major tendencies of process variables. Especially, the transitional regions between neighboring stable modes, which have their particular dynamic characteristics, are modeled, respectively. Online monitoring procedures are formulated on the basis of mode identification. It is more efficient than a model matching strategy using traversing method. At last, the efficacy of the proposed method is illustrated by applying it to a continuous annealing line process and the Tennessee Eastman process. Both results of real application and simulation clearly demonstrate the effectiveness and feasibility of the proposed method.

A multimedia game was designed to serve as a dual-purpose intervention that aligned with National Science Content Standards, while also conveying knowledge about the consequences of alcohol consumption for a secondary school audience. A tertiary goal was to positively impact adolescents' attitudes toward science through career role-play experiences within the game. In a pretest/delayed posttest design, middle and high school students, both male and female, demonstrated significant gains on measures of content knowledge and attitudes toward science. The best predictors of these outcomes were the players' ratings of the game's usability and satisfaction with the game. The outcomes suggest that game interventions can successfully teach standards-based science content, target age-appropriate health messages, and impact students' attitudes toward science.

Multiphase characteristics and uneven-length batch duration have been two critical issues to be addressed for batch process monitoring. To handle these issues, a variable moving window-k nearest neighbor (VMW-kNN) based local modeling, irregular phase division, and monitoring strategy is proposed for uneven batch processes in the present paper. First, a pseudo time-slice is constructed for each sample by searching samples that are closely similar to the concerned sample in which the variable moving window (VMW) strategy is adopted to vary the searching range and the k nearest neighbor (kNN) rule is used to find the similar samples. Second, a novel automatic sequential phase division procedure is proposed by similarity evaluation for local models derived from pseudo time-slices to get different irregular phases and ensure their time sequence. Third, the affiliation of each new sample is real-time judged to determine the proper phase model and fault status can be distinguished from phase shift event. The proposed strategy can be readily extended to the case with limited batches. To illustrate the feasibility and effectiveness, the proposed algorithm is applied to a typical multiphase batch process, i.e., injection molding process, with an uneveness problem.

The version presented here may differ from the published version or, version of record, if you wish to cite this item you are advised to consult the publisher's version. Please see the 'permanent WRAP URL' above for details on accessing the published version and note that access may require a subscription.

Anomaly detection in crowd scene is very important because of more concern with people safety in public place. This paper presents an approach to automatically detect abnormal behavior in crowd scene. For this purpose, instead of tracking every person, KLT corners are extracted as feature points to represent moving objects and tracked by optical flow technique to generate motion vectors, which are used to describe motion. We divide whole frame into small blocks, and motion pattern in each block is encoded by the distribution of motion vectors in it. Similar motion patterns are clustered into pattern model in an unsupervised way, and we classify motion pattern into normal or abnormal group according to the deviation between motion pattern and trained model. The results on abnormal events detection in real video demonstrate the effectiveness of the approach.