Deborah F. Cook

Combining a neural network with a genetic algorithm for process parameter optimization

Abstract A neural-network model has been developed to predict the value of a critical strength parameter (internal bond) in a particleboard manufacturing process, based on process operating parameters and conditions. A genetic algorithm was then applied to the trained neural network model to determine the process parameter values that would result in desired levels of the strength parameter for given operating conditions. The integrated NN–GA system was successful in determining the process parameter values needed under different conditions, and at various stages in the process, to provide the desired level of internal bond. The NN–GA tool allows a manufacturer to quickly determine the values of critical process parameters needed to achieve acceptable levels of board strength, based on current operating conditions and the stage of manufacturing.

Using radial basis function neural networks to recognize shifts in correlated manufacturing process parameters

Traditional statistical process control (SPC) techniues of control charting are not applicable in many process industries because data from these facilities are autocorrelated. Therefore the reduction in process variability obtained through the use of SPC techniques has not been realized in process industries. Techniques are needed to serve the same function as SPC control charts, that is to identify process shifts, in correlated parameters. Radial basis function neural networks were developed to identify shifts in process parameter values from papermaking and viscosity data sets available in the literature. Time series residual control charts were also developed for the data sets. Networks were successful at separating data that were shifted 1.5 and 2 standard deviations from nonshifted data for both the papermaking and viscosity parameter values. The network developed on the basis of the papermaking data set was also able to separate shifts of 1 standard deviation from nonshifted data. The SPC control charts were not able to identify the same process shifts. The radial basis function neural networks can be used to identify shifts in process parameters, thus allowing improved process control in manufacturing processes that generate correlated process data.

Predicting the internal bond strength of particleboard, utilizing a radial basis function neural network

Abstract Development of a model to identify process relationships and predict parameter values in a continuous manufacturing operation is often a difficult undertaking. Process parameters are typically dynamic, and are functions of complex relationships and interactions between process parameters. A radial basis function (RBF) neural network was used to develop a process model for predicting the strength of particleboard. The RBF algorithm was modified using a conscience function to ensure that the distribution of the data was described in each dimension. The trained network was successful at predicting the internal bond strength parameter with an average prediction error of 12.5%. This predictive capability is superior to other neural-network and statistical models developed to predict internal bond. Predictions of this accuracy would allow the trained network model to be used to improve process control in a particleboard manufacturing plant.

Utilization of neural networks for the recognition of variance shifts in correlated manufacturing process parameters

Traditional statistical process control (SPC) charting techniques were developed for use in discrete industries where independence exists between process parameters over time. Process parameters from many manufacturing industries are not independent, however, but they are serially correlated. Consequently, the power of traditional SPC charts was greatly weakened. The paper discusses the development of neural network models to identify successfully shifts in the variance of correlated process parameters. These neural network models can be used to monitor manufacturing process parameters and signal when process adjustments are needed.

Combining a neural network with a rule-based expert system approach for short-term power load forecasting in Taiwan

Abstract A back-propagation neural network with the output provided by a rule-based expert system is designed for short-term power load forecasting. To demonstrate that the inclusion of the prediction from a rule-based expert system of a power system would improve the predictive capability of the network, load forecasting is performed on the Taiwan power system. The hourly load for one typical day was evaluated and, in that case, the inclusion of the rule-based expert system prediction significantly improved the neural networks prediction of power load. Moreover, the proposed combined approach converges much faster than the conventional neural network and the rule-based expert system method. Extensive studies were performed on the robustness of the built network model by using different specified censoring time. The prediction intervals of future power load series are also provided, to evaluate the prediction efficiency of the neural network model.

An augmented neural network classification approach to detecting mean shifts in correlated manufacturing process parameters

Statistical process control (SPC) techniques have traditionally been used to identify when the mean of a manufacturing process has shifted out of control. In situations where there is correlation among the observed outputs of the process, however, the underlying assumptions of SPC are violated and alternative approaches such as neural networks become necessary in order to characterize the process behaviour. This paper discusses the development of a neural network technique that provides a significantly improved capability for recognizing these process shifts as compared to the current techniques in the literature. The procedure in question is an augmented neural-network based approach, which incorporates a data preprocessing classification algorithm that provides information to facilitate early detection of out of control operating conditions. This approach is shown to improve significantly upon the performance of previous neural network techniques for identifying process shifts in the presence of correlation.

A predictive neural network modelling system for manufacturing process parameters

A methodology to predict the occurrence of out-of-control process conditions in a composite board manufacturing facility was developed using neural network theory. Multi-variable regression and time series analysis techniques were applied to analyse the data set for comparison and informational purposes. Regression models were developed to mode] specific process parameters and could account for only 25% of the variation in those parameters. When analysed as a time series, the data stream was non-stationary in the variance and transformations failed to achieve stationarity. Back-propagation neural networks were successfully trained to represent the process parameters. Inputs to the network consisted of data representing the current process condition along with historical data on relevant parameters, including temperature, moisture content, and bulk density. The training data set was graphically analysed to demonstrate the type of response surface successfully modelled. The trained neural networks were able...

Multivariate measurement system analysis in multisite testing: An online technique using principal component analysis

Multisite testing improves manufacturing throughput and reduces costs by applying simultaneous testing to products with multiple measurement instruments in parallel. It is important to perform measurement system analysis (MSA) on a multisite testing system to assess its testing capability. Traditional MSA methods are designed to be either univariate or multivariate in a single-site system. They are not capable of analyzing a complex multisite testing system where there are multivariate measurements and multiple instruments in parallel. We propose an online multivariate MSA approach to detecting faulty test instruments in a multisite testing system. In order to pinpoint a faulty test instrument in a multisite testing system we compare the performance of each test instrument to the overall performance of all the parallel instruments in the system. A modified principal component analysis (PCA) method is proposed to transform multivariate measurement data with dependent variables into those with independent principal components. Assuming that all the instruments have the same measurement accuracy and precision we consider a faulty instrument as one whose principal component values are beyond the three sigma control limits of the principal component values of all instruments. We conduct an experiment to provide empirical evidence that the proposed approach is capable of identifying the faulty instruments in a multisite testing system. This approach can be implemented as an online monitoring technique so that production is not interrupted until a faulty instrument is identified.

Impact of HIPAA provisions on the stock market value of healthcare institutions, and information security and other information technology firms

Title 1 of the Health Insurance Portability and Accountability Act (HIPAA) was enacted to improve the portability of healthcare insurance coverage and Title II was intended to alleviate fraud and abuse. The development of a health information system was suggested in Title II of HIPAA as a means of promoting standardization to improve the efficiency of the healthcare system and ensure that electronic healthcare information is transferred securely and kept private. Since the legislation places the onus of providing the described improvements on healthcare institutions and part of these requirements relate to information technology (IT) and information security (IS), the process of complying with the legislation will necessitate acquiring products and services from IT/IS firms. From the viewpoint of stock market analysts, this increase in demand for IT/IS products and services has the potential to boost the profitability of public IT/IS firms, in turn positively enhancing their stock market valuation. Following the same logic, the legislations compliance burdens shared by healthcare firms are expected to require hefty costs, thus potentially reducing the profitability of healthcare firms and reflecting negatively on their stock price. The intent of this paper is to evaluate the stock market reaction to the introduction of HIPAA legislation by evaluating the abnormal movement in the price of the stock of public healthcare institutions, IT, and IS firms. We conduct event-study analyses around the announcement dates of the various provisions of HIPAA. An event study is a standard statistical methodology used to determine whether the occurrence of a specific event or events results in a statistically significant reaction in financial markets. The advantage of the event study methodology for policy analysis is that it provides an anchor for determining value, which eliminates reliance on ad hoc judgments about the impact of specific events or policies on stock prices. While event studies have been conducted that examine the market effect of security and privacy breaches on firms, none has attempted to determine the impact, in terms of resulting market reaction, of the HIPAA legislation itself. The results of the study confirm the logic above, while also providing insight into specific stages of the legislative path of HIPAA.

Evaluation of neural network variable influence measures for process control

Decision-making frequently involves identifying how to change input parameters in a given process in order to effect a directed change in the process output. Artificial neural networks have been used extensively to model business and manufacturing processes and there are several existing neural network-based influence measures that allow a decision-maker to assess the relative impact of each variable on process performance. The purpose of this paper is to review those neural network-based measures of variable influence, and to identify the combination of those measures that results in a comprehensive approach to characterizing variable influence within a trained neural network model. We then demonstrate how this comprehensive approach can be used as a tool to guide decision makers in dynamic process control.