سیستم هوشمند برای نظارت بر فرایند چند متغیره آماری و تشخیص
|کد مقاله||سال انتشار||مقاله انگلیسی||ترجمه فارسی||تعداد کلمات|
|5480||2002||16 صفحه PDF||سفارش دهید||6748 کلمه|
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : ISA Transactions, Volume 41, Issue 2, April 2002, Pages 255–270
A knowledge-based system (KBS) was designed for automated system identification, process monitoring, and diagnosis of sensor faults. The real-time KBS consists of a supervisory system using G2 KBS development software linked with external statistical modules for system identification and sensor fault diagnosis. The various statistical techniques were prototyped in MATLAB, converted to ANSI C code, and linked with the G2 Standard Interface. The KBS automatically performs all operations of data collection, identification, monitoring, and sensor fault diagnosis with little or no input from the user. Navigation throughout the KBS is via menu buttons on each user-accessible screen. Selected process variables are displayed on charts showing the history of the variables over a period of time. Multivariate statistical tests and contribution plots are also shown graphically. The KBS was evaluated using simulation studies with a polymerization reactor through a nonlinear dynamic model. Both normal operation conditions as well as conditions of process disturbances were observed to evaluate the KBS performance. Specific user-defined disturbances were added to the simulation, and the KBS correctly diagnosed both process and sensor faults when present.
Statistical methods for detecting changes in in- dustrial processes are included in a field generally known as statistical process control ~ SPC ! or sta- tistical quality control. The most widely used and popular SPC techniques include univariate meth- ods that involve observing a single variable at a given time, obtaining the mean and variance of the variable, and checking its value against upper and lower control limits. While a univariate approach may indeed work for monitoring a small number of process variables that are not correlated, current capabilities in data acquisition hardware allow a large ~ several thousand ! number of variables to be easily measured. Application of univariate statisti- cal process monitoring ~ SPM ! methods to larger multivariable systems becomes difficult, if not im- possible, and is often erroneous. This simplified approach to process monitoring requires an opera- tor to continuously monitor perhaps dozens of dif- ferent univariate charts, which substantially re- duces the ability of plant personnel to make accurate assessments about the state of the pro- cess. Multivariable statistical process monitoring ~ MSPM ! techniques offer the proper theoretical framework for monitoring multivariable pro- cesses. MSPM techniques reduce the amount of raw data presented to an operator and provide a concise set of statistics that describes the process behavior. Many of the current MSPM techniques are only valid for data that are independent and identically distributed ~ iid ! . The independence as- sumption means that the data must not be corre- lated with each other, either in current measure- ments or lagged values, and that each have similar statistical distributions. This assumption, however, only applies to very idealized data and is not com- monly observed in real processes. Correlations in the data include autocorrelation, which indicates a correlation of a single variable with its past obser- vations, and cross-correlation, which indicates a relationship between two or more variables at ei- ther the current observations or past observation. Most process data are correlated, such as tray tem- perature readings in a distillation column or tem- perature and concentration in a chemical reactor; consequently, it is necessary to utilize MSPM methods capable of monitoring such processes. @ 1 # Data-driven MSPM methods that are capable of handling correlated data include methods based on principal component analysis, projection to latent structures ~ PLS ! , and canonical variate and sub- space state space modeling. Data-driven tech- niques are dependent on data collected from a real process in order to formulate a model that de- scribes the variability of that process. System identification methods suitable for linear processes with correlated data such as principal components regression, PLS, canonical variate state space modeling, and subspace state space modeling are described in @ 1–4 # . System identification method- ologies that can handle nonlinear systems have also been proposed @ 5–7 # . The model developed is used to predict the future values of monitored pro- cess variables. The difference between the model predictions and the process measurement is re- ferred to as the model residual. The residuals be- tween the predicted and actual values may be as- sessed for statistical significance; a significant increase in residuals suggests the presence of ab- normal conditions in the process. In addition to measuring the magnitude of the residuals, one may also examine trends in the residuals. Sensor errors in the form of a bias change, drift, or excessive noise may be diagnosed by examining the residu- als over time. Periodically performing sensor au- dits @ 2,8,9 # by examining the residuals for statisti- cally significant changes can greatly enhance the credibility of the data as well as significantly re- duce the number of false alarms The aforementioned monitoring techniques may be integrated with an automated system to provide real-time process monitoring and diagnosis. Knowledge-based systems ~ KBSs ! or expert sys- tems are computer systems designed in an attempt to emulate the decision-making capabilities and knowledge of a human expert in a specific field. A KBS consists of a knowledge base, decision rules, and an inferencing engine. The knowledge base is comprised of a set of knowledge, data, and facts pertaining to a specific problem and process. De- cision rules are rules, developed by human experts based on intimate knowledge about the process, to reach a conclusion given the facts, such as process data. The inference engine processes the rules based on the data and conclusions reached by other rules ~ inferences ! to reach a conclusion such as fault diagnosis. Knowledge-based systems increased in popular- ity during the early 1980s when many people viewed knowledge-based systems as ‘‘magic bul- let’’ solutions to every problem. Unfortunately, the high expectations of knowledge-based systems ul- timately led to widespread distrust of the technol- ogy after such systems failed to perform as ex- pected. Knowledge-based systems are gradually becoming more popular for performing such tasks as monitoring and diagnosis—tasks that KBSs are able to perform very well. Additionally, current computer hardware and software—technology that was unavailable when the KBS first gained popularity—are ideal for real-time KBS develop- ment and run-time platforms. KBSs are useful for solving problems that can only be done by human experts or are repetitive in nature and perform effectively due to their inher- ently well-defined knowledge space. The advan- tage over human experts is access to very large databases and fast execution time. While a human expert may need to search volumes of printed text for a piece of information, a KBS can quickly search electronic databases in short time. Knowledge-based systems excel at qualitative pro- cessing, which is beneficial in diagnosis of process faults and monitoring applications. Human experts routinely perform qualitative analysis using pro- cess specific information and heuristics. There- fore, one can design a KBS to perform a specific task by transferring the knowledge from a human to a computer code. Of course, the ability of the KBS to reason is directly related to the quality of knowledge supplied by the knowledge engineer. If the KBS is supplied with incorrect or irrelevant knowledge, the performance of the KBS will be poor. Furthermore, if the KBS is designed for a specific application, it typically cannot be applied to a different application without significant modi- fications to the knowledge base. Several knowledge-based systems for process monitoring and fault diagnosis in areas of chemi- cal engineering have been reported @ 8–16 # . Addi- tionally, several knowledge-based systems for sys- tem identification are available @ 17–24 # . They are based on linear single-input–single-output or multiple-input–single-output models and typically require significant user input and operate offline. The KBS developed by Norvilas et al. @ 25 # is the predecessor of the work presented in this paper; however, the original KBS did not incorporate sensor validation or subspace identification tech- niques. While these systems represent the state of technology for KBS-based monitoring and diagno- sis, systems that integrate methods of system iden- tification, process monitoring and control, and sensor fault diagnosis have not been reported. A robust system for monitoring and diagnosis of a multivariable process must utilize the powerful MSPM techniques that have been developed for analysis of these processes as well as features of KBS for qualitative reasoning. Such a hybrid sys- tem will use the best of both techniques. While commercial monitoring software is gradually in- corporating more advanced statistical monitoring techniques, a large portion of the available com- mercial software for MSPM and KBS is used off- line, that is, data are processed and analyzed after an event has occurred or the process operation has ceased. A real-time monitoring and diagnosis sys- tem is necessary to detect and diagnose faults as they occur, in order to take immediate corrective measures. The KBS emulates the behavior of a human engineer responsible for interpreting vari- ous statistical tests performed on the process data in real time and decides what data are to be used when building models for prediction purposes, se- lects the type of system identification model build- ing techniques to use, schedules monitoring and diagnosis events, coordinates alarm handling, and suggests corrective actions in the event of a pro- cess fault. A process monitoring and fault diagnosis system that combines the strengths of system identification, MPSM, and real-time KBS is reported in this paper. The KBS automatically performs all opera- tions of data collection, identification, and moni- toring and sensor fault diagnosis with little or no input from the user. Navigation throughout the KBS is achieved through menu buttons on each user-accessible screen. Selected process variables are displayed on charts showing the history of the variables over a period of time. Multivariate statistical tests and contribution plots are also shown graphically. The KBS was evaluated using simulation studies with a polymer- ization reactor through a nonlinear dynamic model.
نتیجه گیری انگلیسی
A process monitoring and fault diagnosis system integrating multivariate statistical techniques with knowledge-based techniques was developed. Use of MSPM charts such as T 2 and SPE results in improved monitoring of the multivariable process when compared to the use of univariate SPM tech- niques. Contribution plots are able to select the variables causing the disturbances in the T 2 chart, and through the use of process knowledge stored in production rules, the root cause of the distur- bances can be diagnosed on-line. The system gives the user access to model-based monitoring tools and knowledge-based diagnosis techniques inte- grated in a real-time system with an easy user in- terface. Sensor auditing was developed for multi- variable continuous processes based on functional redundancy generated by a state space process model. The method can detect and discriminate between bias change, drift, and noise. The method can be implemented to run repeatedly at frequent intervals based on data sets collected for a suffi- ciently long period and warn plant personnel about incipient sensor faults. The integration of statisti- cal tools with knowledge-based techniques reduces the amount of data that must be continu- ously analyzed by process operators. Consequently, process faults may be detected more rapidly and consistently by the integrated KBS than by using statistical or knowledge-based techniques exclusively.