NN-based Prediction Interval for Nonlinear Processes Controller

Neural networks (NNs) are extensively used in modelling, optimization, and control of nonlinear plants. NN-based inverse type point prediction models are commonly used for nonlinear process control. However, prediction errors (root mean square error (RMSE), mean absolute percentage error (MAPE) etc.) significantly increase in the presence of disturbances and uncertainties. In contrast to point forecast, prediction interval (PI)-based forecast bears extra information such as the prediction accuracy. The PI provides tighter upper and lower bounds with considering uncertainties due to the model mismatch and time dependent or time independent noises for a given confidence level. The use of PIs in the NN controller (NNC) as additional inputs can improve the controller performance. In the present work, the PIs are utilized in control applications, in particular PIs are integrated in the NN internal model-based control framework. A PI-based model that developed using lower upper bound estimation method (LUBE) is used as an online estimator of PIs for the proposed PI-based controller (PIC). PIs along with other inputs for a traditional NN are used to train the PIC to predict the control signal. The proposed controller is tested for two case studies. These include, a chemical reactor, which is a continuous stirred tank reactor (case 1) and a numerical nonlinear plant model (case 2). Simulation results reveal that the tracking performance of the proposed controller is superior to the traditional NNC in terms of setpoint tracking and disturbance rejections. More precisely, 36% and 15% improvements can be achieved using the proposed PIC over the NNC in terms of IAE for case 1 and case 2, respectively for setpoint tracking with step changes.

     

Target coverage in camera networks for manufacturing workplaces

In this paper, we investigate the camera network placement problem for target coverage in manufacturing workplaces. The problem is formulated to find the minimum number of cameras of different types and their best configurations to maximise the coverage of the monitored workplace such that the given set of target points of interest are each k-covered with a predefined minimum spatial resolution. Since the problem is NP-complete, and even NP-hard to approximate, a novel method based on Simulated Annealing is presented to solve the optimisation problem. A new neighbourhood generation function is proposed to handle the discrete nature of the problem. The visual coverage is modelled using realistic and coherent assumptions of camera intrinsic and extrinsic parameters making it suitable for many real world camera based applications. Task-specific quality of coverage measure is proposed to assist selecting the best among the set of camera network placements with equal coverage. A 3D CAD of the monitored space is used to examine physical occlusions of target points. The results show the accuracy, efficiency and scalability of the presented solution method; which can be applied effectively in the design of practical camera networks.     

A new second-order method for blind signal separation from dynamic mixtures

This paper presents a new approach to separate colored stationary signals mixed by convolutive channels. A cost function is proposed by employing linear constraint to the demixing vectors. The linear constraint is shown to be sufficient for avoiding trivial solution. The minimization of the cost function is performed using the Lagrangian method. Simulation results demonstrate the performance of the algorithm.     

DESIGN OF REDUCED‐ORDER FUNCTIONAL OBSERVERS FOR LINEAR SYSTEMS WITH UNKNOWN INPUTS

This brief paper presents new conditions for the existence and design of reduced‐order linear functional state observers for linear systems with unknown inputs. Systematic procedures for the synthesis of reduced‐order functional observers are given. Numerical examples are given to illustrate the attractiveness and simplicity of the new design procedures.     

Identification of concurrent control chart patterns with singular spectrum analysis and learning vector quantization

Identification of unnatural control chart patterns (CCPs) from manufacturing process measurements is a critical task in quality control as these patterns indicate that the manufacturing process is out-of-control. Recently, there have been numerous efforts in developing pattern recognition and classification methods based on artificial neural network to automatically recognize unnatural patterns. Most of them assume that a single type of unnatural pattern exists in process data. Due to this restrictive assumption, severe performance degradations are observed in these methods when unnatural concurrent CCPs present in process data. To address this problem, this paper proposes a novel approach based on singular spectrum analysis (SSA) and learning vector quantization network to identify concurrent CCPs. The main advantage of the proposed method is that it can be applied to the identification of concurrent CCPs in univariate manufacturing processes. Moreover, there are no permutation and scaling ambiguities in the CCPs recovered by the SSA. These desirable features make the proposed algorithm an attractive alternative for the identification of concurrent CCPs. Computer simulations and a real application for aluminium smelting processes confirm the superior performance of proposed algorithm for sets of typical concurrent CCPs.     

Well-conditioned configurations of fault-tolerant manipulators

Fault-tolerant motion of redundant manipulators can be obtained by joint velocity reconfiguration. For fault-tolerant manipulators, it is beneficial to determine the configurations that can tolerate the locked-joint failures with a minimum relative joint velocity jump, because the manipulator can rapidly reconfigure itself to tolerate the fault. This paper uses the properties of the condition numbers to introduce those optimal configurations for serial manipulators. The relationship between the manipulator’s locked-joint failures and the condition number of the Jacobian matrix is indicated by using a matrix perturbation methodology. Then, it is observed that the condition number provides an upper bound of the required relative joint velocity change for recovering the faults which leads to define the optimal fault-tolerant configuration from the minimization of the condition number. The optimization problem to obtain the minimum condition number is converted to three standard Eigen value optimization problems. A solution is for selected optimization problem is presented. Finally, in order to obtain the optimal fault-tolerant configuration, the proposed method is applied to a 4-DoF planar manipulator.     

Effects of Silver and Antimony Content in Lead-Free High-Temperature Solders of Bi-Ag and Bi-Sb on Copper Substrate

Replacing high-temperature leaded solders with lead-free alternatives is an important issue in the electronics industry. This study investigates the viability of lead-free Bi-Ag and Bi-Sb solder alloys, ranging in composition from 1.5 to 5 wt.% Ag and Sb. The effects of melting point, wetting angle, microstructure, and morphology were analysed by differential scanning calorimetry, optical microscopy, and scanning electron microscope–energy dispersive x-ray analysis. The results showed that all tested alloys had suitable melting temperatures, ranging from 271 to 276°C. The wetting angle increased by raising the Sb content, but, in contrast, by increasing the wt.% of Ag, the wetting angle decreased. A Cu-rich phase was present in all Bi-Ag alloys, The Cu-rich phase was also present in decreasing amounts with increasing Sb, but, with 5Sb, there was no Cu-rich phase, and a Cu3Sb intermetallic compound was present in the interface and as precipitates in the solder. Grooving along Cu grain boundaries was observed at the interface for the rest of the alloys.     

A new manufacturable filter design approach for spectral reflectance estimation

Selection of the best possible filter set among a set of available filters is the obvious method of increasing dimension of camera signals for spectral reflectance reconstruction. There are also methods that are focusing on the filter design regardless of noticing to the constructability of the designed filters. This study shows that direct optimization of physical variables of filter manufacturing technique is more reliable than indirect approach of designing and then physical manufacturing of the designed filters. Direct optimization of the transmission‐controlling primaries in filter manufacturing process would guarantee having the designed filters in reality. Combination of some solvent dyes was used as the spectral transmission matching system for filter manufacturing. As a conventional technique, filters were designed and best possible dye concentrations that match the desired filters were calculated. As an alternative approach, filters were also designed using direct optimization of dyes concentrations. The results showed that direct optimization of dye concentrations exhibits better performance in comparison with the conventional technique. © 2016 Wiley Periodicals, Inc. Col Res Appl, 42, 316–326, 2017     

Performance analysis of three advanced controllers for polymerization batch reactor: An experimental investigation

The performances of three advanced non-linear controllers are analyzed for the optimal set point tracking of styrene free radical polymerization (FRP) in batch reactors. The three controllers are the artificial neural network-based MPC (NN-MPC), the artificial fuzzy logic controller (FLC) as well as the generic model controller (GMC). A recently developed hybrid model (Hosen et al., 2011a. Asia-Pac. J. Chem. Eng. 6(2), 274) is utilized in the control study to design and tune the proposed controllers. The optimal minimum temperature profiles are determined using the Hamiltonian maximum principle. Different types of disturbances are introduced and applied to examine the stability of controller performance. The experimental studies revealed that the performance of the NN-MPC is superior to that of FLC and GMC.     

Dielectrophoretically assembled particles: feasibility for optofluidic systems

This work presents the dielectrophoretic manipulation of sub-micron particles suspended in water and the investigation of their optical responses using a microfluidic system. The particles are made of silica and have different diameters of 600, 450, and 250 nm. Experiments show a very interesting feature of the curved microelectrodes, in which the particles are pushed toward or away from the microchannel centerline depending on their levitation heights, which is further analyzed by numerical simulations. In doing so, applying an AC signal of 12 V_p–p and 5 MHz across the microelectrodes along with a flow rate of 1 μl/min within the microchannel leads to the formation of a tunable band of particles along the centerline. Experiments show that the 250 nm particles guide the longitudinal light along the microchannel due to their small scattering. This arrangement is employed to study the feasibility of developing an optofluidic system, which can be potentially used for the formation of particles-core/liquid-cladding optical waveguides.