AIAA
Publication September 1998
Paul Van Buskirk
Quality Monitoring and Control
Total
Systems Evaluation
& Sensor Health
Abstract
Many methods of statistical observation in the performance of a process are commonly used in industry. The range is from standard run charts and controls to monitoring certain indices such as total quality, energy and / or profit. Historically, these methods have proven beneficial but lack cohesiveness in determination of the root cause of improper system performance. On this basis, a performance index system has been developed that provides a relative index ranking and addresses the root cause of operational instability. This paper provides the fundamental analysis and utilization of the performance metering system to monitor systems.
Background
Advances in AI modeling techniques, such as artificial neural networks (ANN), e-Model, genetic algorithms, VB-Model, etc., provide a robust tool for monitoring, control and optimization of a system. Monitoring is used for data verification, fault detection, forecasting and/or prediction. Total system or subsystem performance can be ranked when combined with statistical methods. When variables are adjustable, the system can be regulated to provide the “Very-Best” results through direct or fuzzy-logic control and optimization methods. This is not for the future; this is the capability that personal computers and artificial intelligence provide today.
Technologies
Applications of AI modeling tools provide a vast range of utilization technologies that are used for sensor, subsystem and total system monitoring and control. These techniques have been successfully implemented into the chemical industry and will be improved with developments in computerized software and hardware systems.
The following provides a brief discussion of current technologies as implemented to improve total system performance in the process industries:
· Utilization of ANN models for sensor validation and fault detection is in common use. A reliable fault detection technique that uses several AI modeling tools is described in reference (2). This application is most effective when all sensors are monitored as part of a preventative maintenance program. The keys to successful process control and optimization implementation are reliable and accurate sensors.
· Prediction is primarily used for forecasting. Applications include market analysis, sales projections, product properties, process variable inferred values, etc. Reference (3) is a good starting point for the utilization of ANN models in the process industries. The major use of ANN models in the process industries is in the prediction mode, either real-time or for off-line analysis and troubleshooting.
· Sensitivity analysis is used to determine the important variables in a process. This provides a fundamental understanding of the process in terms of key variable rankings to control a process result. Numerical derivatives (D Output/ D Input) of the ANN model provides the sensitivity results. Most ANN software providers furnish this feature. Sensitivity analysis is classically the first step towards implementing supervisory controls into a process or system. Numerical derivatives of a process provide what is termed the gain array, which is the starting point for multivariable control and optimization.
· Equipment performance monitoring can be applied through the use of several approaches. A direct approach is to develop an AI model to determine the performance index of the equipment. The calculated index from the AI model is then monitored to determine the performance decay rate. From the decay rate preventive maintenance requirements are determined using “rule-based” AI technologies. This type of approach can be used for the majority or process equipment designs and subsystems.
· Total process indexing provides a single auditing measurement to monitor the performance of a process or system. This method combines the sensitivity of a process with statistical process control (SPC). The auditing measure, “Process Index”, is calculated by the following equation (4):
Where xi = data point evaluated at ith sampling of input variable x.
Fi
= model
prediction at ith
sampling point.
=
Target input variable setting.
s
= Standard deviation.
=
2.71828182846.
The exponential term is the normalized Gaussian distribution function. The Process Index weights the sensitivities of a process with this distribution function. Input variables with high sensitivities will have a larger impact on the Process Index than those with low sensitivities (for the same departure from the target values).
The
Process Index provides focus for the variables that most affect stability or
quality in operations. The index
value is scaled from 100% (ideal) to 0% (unacceptable).
The index should be configured as a run chart to monitor total process
performance.
· Control monitoring provides an application technology that gives the best pairings of controls in a process. With a process that can be regulated, certain variables can be independently manipulated, termed control inputs. These control inputs are adjusted to control certain system requirements and/or specifications, termed control outputs. Control monitoring provides the best pairing of manipulated-to-controlled variables.
The technology is based on an AI model to generate the gain array (from process sensitivities). Minimum interaction of manipulated-to-controlled variables is the goal (5). The maximum performance occurs when interactions are eliminated. The performance indicator is named the “Stability Index”. A value of one is ideal. Negative values indicate an uncontrollable control scheme. High positive values indicate a system that is marginal.
· Multivariable non-linear process control and optimization methods directly follow from the methods presented. Once a neural net model is developed, the equations can be imported into several optimizers.
However, for “real-time” control and optimization applications, a time dependent-dynamic model is needed. Reference 5 gives an overview for several “adaptive” or other state-of-the-science methods. Additionally, multi-variable linear and non-linear process control and optimization methods are currently available from several software developers.
Application of a Total System Monitoring Technology
The total performance monitoring system is a recently developed technology for total system and subsystem evaluations. It's underlying technology merges statistical process control and modeling methods. From the model, the sensitivities of a process are analyzed and weighted by the total integral evaluation of the Gaussian distribution curve. This weighting, in effect, provides the amount of departure times the sensitivity in the process for each of the system variables. With this procedure, the important variables in a process are given higher weight than variables of lower importance for reaching a process goal. However, items of low importance, or sensitivity, will show an impact on the system performance when the amount of departure from the "normal" is high. An example of the process index, termed Plant Index Meter, is given below:
Process Index for Polymer Manufacture
The following graphical Plant Index example shows the results of an analysis for
polymer manufacture. The top graph
provides a model's prediction versus the measured product melt index (MI).
The MI is a polymer property used for sales specification.
The highlighted list gives the model-input variables.
Prod_MI is the modeled, or output, variable. The four top factors that contribute to a Plant Index reading
of 64.65% are listed on an instantaneous and average basis.
The Plant Index individual values are also listed.
In this example Recycle_Flow contributes 16.01% from the product being
produced off targeted values, i.e. a Plant Index of 100% is ideal.
Complete derivation of the process index metering system is beyond the scope of this paper. Please see reference (4). However, this derivation shows the power of this technique by blending process derivatives, Gaussian distributions and the total integral in one compact form for the evaluation of the performance of a processing system. This technique can be applied to any system in any industry. Important in this analysis is that a common indexing system across all process variables are evaluated. Additionally, the root cause of operational instability is pinpointed. No other technique or technology is available that provides this combination of information for the successful operation of systems. This method also pinpoints suspect measurements or sensors.
Conclusions
Presented is a method for total system auditing and monitoring. This method can also be used in process or system regulation and control. The technology provided is a recent development and has been shown to provide the root cause of instability in actual manufacturing processes. No know technology exists that provides this information on the stability and operational opportunities within a process. This technology additionally provides the root cause or causes in instability or loss in opportunity in an operational process and can be used to monitor sensor or measurement health and stability on a system wide basis.
Paul Van Buskirk is a Principal with Quality Monitoring & Control. He may be reached at 281.359.4471 or via email at QMC_Plus@MSN.com.
References:
1. Bhagat, P., “An Introduction to Neural Nets.”, Chem. Eng. Progress, p 55 (Aug 1990)
2. Smith, S., “SDI’s e: Real Time Prediction in the Chemical Industry”, PC AI, p 18 (Jan/Feb 1998)
3. Chitra, S., “Use Neural Networks for Problem Solving”, Chem. Eng. Progress, p 45 (April 1993)
4. Van Buskirk, J., “Modeling of a High-Density Polyethylene (HDPE) Process”, Texas A&M University, Masters Thesis (Dec 1996)
5. Ogunnaike, B. and W. H. Ray, Process Dynamics, Modeling, and Control , Oxford University Press, 1994
6. Serth, R.W., Heenan, W.A., "Gross Error Detection and Data Reconciliation in Steam-Metering Systems", AIChE Journal, p 733 (May 1986)
7. Heenan, W.A., Serth, R.W., "Detecting Errors in Process Data", Chemical Engineering, p 99 (Nov 86)
8. Van Buskirk, P. D., "Neural Networks for Monitoring, Control and Optimization", PC AI, p 28 (May/June 1998)