Real-time detection of grip length deviation during pull-type fastening: a Mahalanobis–Taguchi System (MTS)-based approach

In this study, a Mahalanobis–Taguchi system (MTS)-based diagnostic and root cause analysis scheme for monitoring grip length of pull-type fasteners in real-time is presented. The proposed approach is implemented on a fastening tool integrated with a strain gage, a linear variable differential transformer, a pressure sensor, and a mote for wireless communication. Experiments show that the process signature of strain-over-displacement ratio versus displacement has unique features that can be used to determine the grip length related deviations. The proposed approach takes as input various characteristics, such as peak strain, peak displacement, and depth and width of a bowl-shaped dip on the process signature in order to make real-time decisions. The experiments show that the proposed approach is effective in determining grip length deviations and in communicating the decision in real-time via a wireless network to a base station. Overall, the proposed architecture has merits to (1) detect quality problems in real-time during the fastening process and (2) reduce post-process inspection, thereby improving quality while reducing cost. In addition, the approach facilitates 100% data collection on each fastener as opposed to traditional statistical process control (SPC) techniques, which rely on sampling.     

PCA-based fault isolation and prognosis with application to pump

In this paper, the use of Linear and Kernel PCA for fault isolation and prognosis is explored since PCA is normally utilized for detection and isolation. Vector projection and statistical analysis were utilized to isolate and predict faults in the PCA domain. Linear PCA was applied to data collected from experiments on a one half horsepower centrifugal water pump both for normal and faulty operation consisting of the four fault scenarios: impeller failure, seal failure, inlet pressure sensor failure, and a filter clog. Upon close observation of the behavior of the principal component scores, it was determined that the linear PCA does not adequately isolate and predict the failures. Therefore, Kernel PCA, utilizing a Gaussian kernel, was applied to the same data sets. Analysis of the behavior shows that the principal component scores gained from the Kernel PCA performed better than linear PCA.     

Discrete-time neural net controller for a class of nonlineardynamical systems

A family of two-layer discrete-time neural net (NN) controllers is presented for the control of a class of mnth-order MIMO dynamical system. No initial learning phase is needed so that the control action is immediate; in other words, the neural network (NN) controller exhibits a learning-while-functioning-feature instead of a learning-then-control feature. A two-layer NN is used which is linear in the tunable weights. The structure of the neural net controller is derived using a filtered error approach. It is indicated that delta-rule-based tuning, when employed for closed-loop control, can yield unbounded NN weights if: 1) the net cannot exactly reconstruct a certain required function, or 2) there are bounded unknown disturbances acting on the dynamical system. Certainty equivalence is not used, overcoming a major problem in discrete-time adaptive control. In this paper, new online tuning algorithms for discrete-time systems are derived which are similar to ϵ-modification for the case of continuous-time systems that include a modification to the learning rate parameter and a correction term to the standard delta rule     

Motion control and obstacle avoidance of a mobile robot with an onboard manipulator

Navigation and control of autonomous mobile vehicles with onboard manipulator systems are currently being investigated for intelligent manufacturing applications. A systematic approach for modeling and base motion control of a mobile vehicle with an onboard robot arm is presented. Feedback linearization is used to take into account the complete dynamics with non-holonomic constraints, yet methods from potential field theory are incorporated to provide resolution among possibly conflicting performance goals (e.g. path following and obstacle avoidance). The feedback linearization provides an inner loop that accounts for possible motion of the onboard arm. The two cases of maintaining a desired course and speed, and following a desired Cartesian trajectory are considered. The outer control loop is designed using potential field theory, with the two objectives of homing and avoiding an obstacle. This simple result obtained using potential functions provides very naturally the necessary intelligence for online resolution of conflicting performance objectives. It gives capabilities to these autonomous vehicles for maintaining a desired course and speed or tracking a Cartesian trajectory, avoiding obstacles during the course of travel, and initiating new online path planning when the size of the object is large so that unnecessary wandering in the work space is avoided.     

Adaptive predictive congestion control of high-speed ATM networks

This paper proposes an auto regressive moving average (ARMAX)-based adaptive control methodology to prevent congestion in high-speed asynchronous transfer mode (ATM) networks. An adaptive controller is developed to control traffic where sources adjust their transmission rates in response to the feedback information from the network switches. Specifically, the buffer dynamics at a given switch is modeled as a nonlinear discrete-time system and an ARMAX controller is designed so as to predict the explicit values of the transmission rates of the sources so as to prevent congestion. Tuning methods are provided for the unknown coefficients of the ARMAX model to estimate the unpredictable and statistically fluctuating network traffic. Mathematical analysis is given to demonstrate the stability of the closed-loop system so that a desired quality of service (QoS) can be guaranteed. The QoS is defined in terms of cell loss ratio (CLR), transmission delay and buffer utilization. We derive design rules mathematically for selecting the parameters of the ARMAX algorithm such that the desired performance is guaranteed during congestion and potential tradeoffs are shown. Simulation results are provided to justify the theoretical conclusions for multiple source/single switch scenarios using both ON/OFF and MPEG data. The performance of the proposed congestion control scheme is also evaluated in the presence of feedback delays for robustness considerations.     

Force estimation and prediction from time-varying density images

We present methods for estimating forces which drive motion observed in density image sequences. Using these forces, we also present methods for predicting velocity and density evolution. To do this, we formulate and apply a Minimum Energy Flow (MEF) method which is capable of estimating both incompressible and compressible flows from time-varying density images. Both the MEF and force-estimation techniques are applied to experimentally obtained density images, spanning spatial scales from micrometers to several kilometers. Using density image sequences describing cell splitting, for example, we show that cell division is driven by gradients in apparent pressure within a cell. Using density image sequences of fish shoals, we also quantify 1) intershoal dynamics such as coalescence of fish groups over tens of kilometers, 2) fish mass flow between different parts of a large shoal, and 3) the stresses acting on large fish shoals.     

Generalized Hamilton–Jacobi–Bellman Formulation -Based Neural Network Control of Affine Nonlinear Discrete-Time Systems

In this paper, we consider the use of nonlinear networks towards obtaining nearly optimal solutions to the control of nonlinear discrete-time (DT) systems. The method is based on least squares successive approximation solution of the generalized Hamilton-Jacobi-Bellman (GHJB) equation which appears in optimization problems. Successive approximation using the GHJB has not been applied for nonlinear DT systems. The proposed recursive method solves the GHJB equation in DT on a well-defined region of attraction. The definition of GHJB, pre-Hamiltonian function, HJB equation, and method of updating the control function for the affine nonlinear DT systems under small perturbation assumption are proposed. A neural network (NN) is used to approximate the GHJB solution. It is shown that the result is a closed-loop control based on an NN that has been tuned a priori in offline mode. Numerical examples show that, for the linear DT system, the updated control laws will converge to the optimal control, and for nonlinear DT systems, the updated control laws will converge to the suboptimal control.     

Control of a class of nonlinear discrete-time systems usingmultilayer neural networks

A multilayer neural-network (NN) controller is designed to deliver a desired tracking performance for the control of a class of unknown nonlinear systems in discrete time where the system nonlinearities do not satisfy a matching condition. Using the Lyapunov approach, the uniform ultimate boundedness of the tracking error and the NN weight estimates are shown by using a novel weight updates. Further, a rigorous procedure is provided from this analysis to select the NN controller parameters. The resulting structure consists of several NN function approximation inner loops and an outer proportional derivative tracking loop. Simulation results are then carried out to justify the theoretical conclusions. The net result is the design and development of an NN controller for strict-feedback class of nonlinear discrete-time systems.