Selection of optimal material and operating conditions in composite manufacturing. Part I: computational tool

The Genetically Optimized Neural Network System (GONNS) is proposed as a human-like decision-making tool for the selection of optimum composite material and operating conditions. Multiple neural networks represent the characteristics of the system after a training process and genetic algorithms find the optimum operating conditions. The error of the GONNS was found to be less than 1% when the neural networks-represented analytical functions and genetic algorithms were used to select the optimal conditions. The GONNS is very promising for many complex optimization problems when analytical equations are not available to represent the characteristics of the system.     

Selection of optimal cutting conditions by using GONNS

Machining conditions are optimized to minimize the production cost in conventional manufacturing. In specialized manufacturing applications, such as micro machining and mold making, achievement of specific goals may be the primary objective. The Genetically Optimized Neural Network System (GONNS) is proposed for the selection of optimal cutting conditions from the experimental data when analytical or empirical mathematical models are not available. GONNS uses Backpropagation (BP) type neural networks (NN) to represent the input and output relations of the considered system. Genetic Algorithm (GA) obtains the optimal operational condition by using the NNs. In this study, multiple NNs represented the relationship between the cutting conditions and machining-related variables. Performance of the GONNS was tested in two case studies. Optimal operating conditions were found in the first case study to keep the cutting forces in the desired range, while a merit criterion (metal removal rate) was maximized in micro-end-milling. Optimal operating conditions were calculated in the second case study to obtain the best possible compromise between the roughness of machined mold surfaces and the duration of finishing cut. To train the NNs, 81 mold parts were machined at different cutting conditions and inspected.     

Simulation of turning operations

One of the most important factors affecting the quality and productivity of turning operations is the dynamics of the system. In this study a computer program is developed to simulate turning operations. The program represents turning operations with a tool geometry simulation module, and the discrete transfer functions of machining process and machine tool structure. The discrete transfer functions of the turning operation are determined by dynamic experiments. The developed program is run at different depth of cuts to study the development and finite amplitude vibrations of chatter. The characteristics of the simulated data agree with the results of previous experimental studies. The simulation program is very convenient to study the chatter susceptibility of machine tool, workpiece and tool geometries.     

The chaotic characteristics of three dimensional cutting

Chatter is an important problem in turning operations. However, there are very few studies on severe chatter because of the difficulties related to data collection and the complexities associated with non-linear cutting dynamics. In this study, cylindrical turning of long slender bars was simulated at three different cutting speeds by using experimentally identified cutting and structural dynamics transfer functions. The simulations were prepared at various depths of cuts, and variations of the cutting forces and displacements were investigated. Visual inspection and the Lyapunov spectrum of the cutting force signals suggested the chaotic nature of the cutting force signals. Although the frequency of the displacement signal remained constant, the amplitude of the signal appeared to have a chaotic nature. The same characteristics were also observed on the experimental data. During the design of a chatter detection or suppression system, the chaotic nature of the force and displacement signals must be considered. The unpredictable nature of the signals may cause prediction errors.     

Basic computational tools and mechanical hardware for torque-based diagnostic of machining operations

In the industry, only rotary dynamometers can be used for monitoring when multiple spindles are used in machining operations. The current commercial rotary dynamometers are bulky and expensive for most machining centers. The basic hardware and computational tools proposed are for a smaller, more cost effective Torque-based Machining Monitor (TbMM). The objective of the TbMM concept is to estimate the remaining tool life, detect chatter from the torque signal inside the proposed device, and communicate with the central computer only when problems arise. The remaining tool life estimation and chatter detection algorithms of the TbMM were developed by analyzing the experimental data collected by a commercial rotary dynamometer. The mechanical hardware of the TbMM was designed to generate voltage proportional to the cutting torque using a piezoelectric composite element. The remaining tool life was estimated from the standard deviation (or variance) of the torque signal. Teager-Kaiser algorithm (TKA) based procedure detected the chatter based on the frequency estimations only from four samples at a time. The accuracy and characteristics of the signal of the mechanical component of the TbMM were found satisfactory in the estimation of machining problems such as wear and chatter. The TbMM is a good choice particularly when multiple spindles work simultaneously on the same workpiece.     

Output feedback adaptive stabilization and command following for minimum phase dynamical systems with unmatched uncertainties and disturbances

In this article, we develop an output feedback adaptive control framework for continuous-time minimum phase multivariable dynamical systems for output stabilisation and command following. The approach is based on a nonminimal state-space realisation that generates an expanded set of states using the filtered inputs and filtered outputs and their derivatives of the original system. Specifically, a direct adaptive controller for the nonminimal state-space model is constructed using the expanded states of the nonminimal realisation and is shown to be effective for multi-input, multi-output linear dynamical systems with unmatched disturbances, unmatched uncertainties and unstable dynamics. The proposed adaptive control architecture requires only knowledge of the open-loop system's relative degree as well as a bound on the system's order. Several illustrative numerical examples are provided to demonstrate the efficacy of the proposed approach.     

Improving transient performance of adaptive control architectures using frequency-limited system error dynamics

Although adaptive control theory offers mathematical tools to achieve system performance without excessive reliance on dynamical system models, its applications to safety-critical systems can be limited due to poor transient performance and robustness. In this paper, we develop an adaptive control architecture to achieve stabilisation and command following of uncertain dynamical systems with improved transient performance. Our framework consists of a new reference system and an adaptive controller. The proposed reference system captures a desired closed-loop dynamical system behaviour modified by a mismatch term representing the high-frequency content between the uncertain dynamical system and this reference system, i.e., the system error. In particular, this mismatch term allows the frequency content of the system error dynamics to be limited, which is used to drive the adaptive controller. It is shown that this key feature of our framework yields fast adaptation without incurring high-frequency oscillations in the transient performance. We further show the effects of design parameters on the system performance, analyse closeness of the uncertain dynamical system to the unmodified (ideal) reference system, discuss robustness of the proposed approach with respect to time-varying uncertainties and disturbances, and make connections to gradient minimisation and classical control theory. A numerical example is provided to demonstrate the efficacy of the proposed architecture.     

Development of a decision support system for machining center selection

The machining centers are key resources for manufacturing companies in their dealing with their fierce competitive market environments. However, although selecting the most appropriate machining center is a very important decision for manufacturing companies, the availability of wide-range of types and models makes the selection process a complex and difficult task. In this study, a decision support system (DSS), namely MACSEL, is developed to help the decision makers in their machining center selection decisions. Several issues and applicability of the MACSEL is illustrated with case problems in the paper.Within the developed DSS, to select the feasible set of machining centers fifteen questions are placed in the elimination (pre-selection) module. The developed DSS uses fuzzy analytical hierarchy process (FAHP) or fuzzy technique for order preference by similarity to ideal solution (FTOPSIS), which are extended versions of multi-criteria decision making approaches, to rank the feasible machining centers. In the DSS, FAHP is used if a detailed pair-wise weighting of the hierarchically structured criteria is wanted. On the other hand, when a simpler separate weighting of each criterion is be considered as enough, FTOPSIS is used.     

Fault diagnosis on bottle filling plant using genetic-based neural network

Timely detection of the pneumatic system problems is important in industry. Many techniques have been employed to solve this problem. In this paper, Genetic Algorithm (GA) based optimal configuration of neural networks is proposed for fault diagnostic of bottle filling systems. Back-propagation is used for neural networks algorithm. The back-propagation algorithm had six inputs and one output. A fitness function was designed to the minimize execution time of ANN model by keeping the number of hidden layer(s) and nodes as low as possible while the mean square error of estimated output error is minimized. The designed GA–ANN combination and the graphical user interface (GUI) eliminate the trial and error process for selection of the fastest and most accurate configuration. The performance of the proposed system was evaluated by using experimental data collected at a pneumatic work cell which attach caps to the bottles. The sensory data was collected at normal operating conditions and a series of faults were imposed to the system such as missing bottle, attaching nonworking bottle caps at two different cylinders, two air pressure problems (insufficient and low air), and not filling water. The study demonstrated the convenience, accuracy and speed of the proposed GA–NN environment. It may also be used for training for selection of ANN configurations at various applications.     

Kinetics of colour,chlorophyll, and ascorbic acid content in spinach baked in different types of oven

Spinach was baked in steam-assisted hybrid ovens, natural and forced convection ovens, and saturated steam ovens at different temperatures and baking times. The moisture content, water activity, peroxidise activity, colour, ascorbic acid, and chlorophyll content were determined for each baking time and kinetic analysis of thermal degradation of the colour, chlorophyll, and ascorbic acid were evaluated. Degradation of green colour, total chlorophyll, and ascorbic acid in spinach leaves during the baking process was considered as first order reaction kinetics and temperature dependency of degradation was described by the Arrhenius equation. Baking in steam-assisted hybrid ovens resulted in the highest rate of reaction for both colour change and chlorophyll degradation, followed by forced convection and then natural convection ovens. The existence of steam in the baking chamber resulted in an acceleration of the baking process and better ascorbic acid retention in spinach was determined by baking in steam-assisted hybrid ovens. Degradation kinetics could allow definition of optimum baking temperatures and times in different types of ovens and shorter baking times should be preferred in steam-assisted hybrid ovens if fresh appearance (high greenness) is desired.