For the most part, process control research has focussed on the synthesis and tuning of controllers, which has provided a plethora of techniques that can address virtually any application. With each new control technique, a steady stream of 'successful' application results are generated and reported. Recently, a considerable number of control researchers have turned their attention to assessing the performance of installed control systems and to the diagnosis of controller performance problems. Despite successes in the areas of controller synthesis, tuning and performance analysis, almost no research has addressed the fundamental issue of determining whether the economic performance gains that are expected accrue from a proposed process control project are sufficient to justify its execution. The work presented here proposes an optimization-based technique for calculating the expected economic performance of a given control system; a method, which is analogous to analysis of variance, for determining the expected economic benefit that will arise from a particular controller improvement effort; and a sensitivity analysis approach for determining the effect of specific assumptions on control system improvement decisions.

Purpose -The purpose of this paper is to present a neural network approach to control performance assessment. Design/methodology/approach -The performance index under study is based on the minimum variance control benchmark, a radial basis function network (RBFN) is used as the pre-whitening filter to estimate the white noise sequence, and a stable filtering and correlation analysis method is adopted to calculate the performance index by estimating innovations sequence using the RBFN pre-whitening filter. The new approach is compared with the auto-regressive moving average model and the Laguerre model methods, for both linear and nonlinear cases. Findings -Simulation results show that the RBFN approach works satisfactorily for both linear and nonlinear examples. In particular, the proposed scheme shows merits in assessing controller performance for nonlinear systems and surpasses the Laguerre model method in parameter selection. Originality/value -A RBFN approach is proposed for control performance assessment. This new approach, in comparison with some well-known methods, provides satisfactory performance and potentials for both linear and nonlinear cases.

3D pose estimation is an important part of 3D motion estimation, which is useful for visualized operation and control. The paper classified approaches of 3D pose estimation from a monocular image sequence into three types: feature-based approach, optical-flow-based approach and model-based approach. In feature-based approaches, 3D motion are estimated by observing a set of 2D features, such as points, lines, junctions and corners, over two or more images. On the contrary, opticalflow-based approaches estimate instantaneous 3D motion from image plane velocity. Both of them can complete the estimation without any a priori knowledge of the object, but the computation is complex and time-consuming. Mode-based approach avoids the burden of computation, but relies on the a priori knowledge of the object. Current research status of each approach is reviewed. Comparison of these three approaches and developing trends of 3D pose estimation are discussed in the conclusion.

Recognizing potentially hazardous objects is crucial in the field of transportation, especially in assisted and unmanned driving. However, most existing studies do not focus on defensive driving as they only identify accidents ahead of the vehicle in which they are not involved. In this paper, a driving assistance system is proposed to predict the risk score of potential targets ahead of the vehicle and provide an early warning, which relies on a deep architecture called Fusion-Residual Predictive Network (FRPN) that fused multi-scale residual features and improved adversarial learning. This architecture provides an environment for the generator to perform joint learning from ground-truth images and discriminators with gradient penalty constraints. The deeper convolutional neural network can greatly improve the quality of the image by fusing residual features. Several deep convolutional neural network models were used to evaluate the method on various datasets; among them, the prediction model based on the VGG network, with peak signal-to-noise ratio of 32.67 and structural similarity index of 0.921, respectively, yielded the best results. Subsequently, we utilize the tracking model to design a risk score evaluation method based on the location of the target and it have an improvement in ability to give early warning with 1.95s earlier in the best case. These results prove that our method can effectively reduce the risk of traffic accidents.INDEX TERMS Generative adversarial network, video predicition, recurrent neural network, convolution nerual network, object tracking, traffic warning, unsupervised learning, risk score assessment. I.