On the use of multiagent systems for the monitoring of industrial systems
 1.2k Downloads
 1 Citations
Abstract
The objective of the current paper is to present an intelligent system for complex process monitoring, based on artificial intelligence technologies. This system aims to realize with success all the complex process monitoring tasks that are: detection, diagnosis, identification and reconfiguration. For this purpose, the development of a multiagent system that combines multiple intelligences such as: multivariate control charts, neural networks, Bayesian networks and expert systems has became a necessity. The proposed system is evaluated in the monitoring of the complex process Tennessee Eastman process.
Keywords
Multivariate process Hotelling \(T^{2}\) control chart Multiagent system Bayesian network Neural networkIntroduction
The process monitoring is a critical task in all industrial plant. It can be realized by the use of three principal approaches (Venkatasubramanian et al. 2003): (1) the analytical methods based on mathematics models. These methods compare the realsystem outputs to the mathematical model outputs, (2) the methods based on knowledge (Stamatis 2003; Dhillon 2005) that use the human knowledge [risk analysis, failures modes effects and critically analysis (FMECA), decision trees], and (3) the databased methods that focus on statistic development of the process. The last kind of the method uses, generally, the control charts [(Page 1954), cumulative SUM (CUSUM) (Roberts 1959)] or exponentially weighted moving average (EWMA) (Alt et al. 1985) for the fault detection in the industrial process.
Currently, the manufacturing processes become more and more complex and multivariate. In these systems, the operator recuperates a vast data amount to be analysed. The high volume of data and the big number of process variables make the operator task fastidious. To avoid such problems, the databased methods are more suitable for the process monitoring. The multivariate control charts [Hotelling \({T}^{2}\) control chart, multivariate CUSUM (MCUSUM), multivariate EWMA (MEWMA)] have been used for the control of multivariate process and have proved their adequacy to reduce the complexity of such process monitoring. Moreover, the monitoring of a multivariate process is a complex task, and it can be devised into four subtasks which are: the detection of abnormal situation, the diagnosis of the faults, the identification of variables that involved in the faults and finally the reconfiguration of the process (Venkatasubramanian et al. 2003).
Many researches have used the control charts for process monitoring (YuChang et al. 2015; Xia 2015; Ehsan and Sadigh 2014; Vijayababu and Rukmini 2014; Assareh et al. 2013). To identify the variables that make an outofcontrol in \({T}^{2}\), a decomposition of the statistic \({T}^{2}\) into independent terms has been suggested by Jing et al. (2008). The “MYT approach” has been applied by Mani and Cooper (1999) for the variables identification. The “MYT approach” has a big disadvantage which is the number of \({T}^{2}\) decompositions. For a process with p variables, the number of decompositions is p!. To reduce this number and to identify the relationship among the variables, the Bayesian networks have been applied for variables identification by Friedman (2000), Li et al. (2006), Li and Shi (2007), Sylvain (2007).
In this paper, we regroup all the tasks of the multivariate process monitoring in one approach. Our contribution is to determine the best combination of multivariate control charts, neural networks, Bayesian networks, expert systems. The result of this research is a multiagent system that applied to a multivariate process monitoring. This multiagent system uses: multivariate control chart for abnormal detection, neural network for faults diagnosis, Bayesian network for variables identification and expert system for reconfiguration task.
The rest of this paper is organized as follows: the process monitoring approach is presented in “The proposed multiagent system” section with the monitoring algorithm. In “Application of the proposed model on the Tennessee Eastman process” section, a case study of simulated Tennessee Eastman process (TEP) (Downs and Vogel 1993) is employed to illustrate the validity of the proposed approach, including the detection by multivariate control charts executor agent (MCCEA), diagnosis by diagnosis artificial neural network agent (DANNA), identification by Identification Bayesian network agent (IBNA) and the reconfiguration by reconfiguration agent (RA). Finally, conclusions and future works are suggested.
The proposed multiagent system
The interface agent
The interface agent (IA) is a reactive agent which represents the interface for the human user access; hence, it receives the request from the users (monitoring the process state). Besides this, the IA transforms the agent’s responses to the users. The IA receives a request from the user about the process state, and it sends a message to the MCCEA. If the process is under control, the IA will display to the operator the decision of the MCCEA. In the other case, when the process is out of control, the IA waits the response from the RA and displays it to the user.
The multivariate control chart executor agent
This agent is responsible on the execution of the multivariate control charts [\({T}^{2}\) control chart (Hotelling 1947), multivariate CUSUM (MCUSUM) (Pignatiello and Runger 1990), multivariate EWMA (MEWMA) (Lowry et al. 1992)]. The control charts (\({T}^{2}\)) control chart, MEWMA and MCUSUM can successfully detect the process instability, but it cannot give any information about the fault that appeared in the process and the variables that are responsible about the process instability. The use of one chart for process monitoring is not sufficient to detect all out of control situation. So, to monitor successively the process, we suggest to use a software agent that can execute simultaneously a set of multivariate control charts and detect easily the process instability. These different control charts are utilized in the design and implementation of the MCCEA.
The diagnosis artificial neural network agent
We use the neural networks in the diagnosis task because it demonstrated its efficiency in the resolution of classification problem. In addition, the neural networks—after the learning step—has a short response time and a good classification rate. We create a classical multilayer perceptron (MLP), with three layers: (1) the input layer: the number of neurons in this layer is the number of the process parameters, (2) the output layer: in this layer, the number of the neurons represents the number of classes (faults of the process), (3) the hidden layer: it is generally known that the number of neurons in this layer is problematic research. We carried out a set of tests, and we find that the optimal number is equal to: (number of neurons in the input layer + the number of neurons in the output layer)/2. This neural network is used in the implementation of the DANNA. So, in our system the DANNA is responsible for the diagnosis task. When the process is out of control, DANNA receives report from the MCCEA. Its principle objective is to find the fault that appeared in the process. After, it sends a report to the IBNA.
The identification Bayesian network agent
The IBNA receives report from DANNA about the fault that appeared in the process. It builds a Bayesian net using the causal decomposition algorithm of \({T}^{2}\) proposed by Sylvain (2007). It finds the variables involved in the fault. This agent simplifies the variable identification in the process. After, it sends report to the RA.
The reconfiguration agent
For the objective, to regroup all the process monitoring tasks (detection, diagnosis, identification and reconfiguration) in one system, we add the RA which helps the operator to reconfigure the process after its failure. It receives report from the IBNA about the variables that involved in the fault. It must propose a reconfiguration plan to the operator, to maintain the process. Also, it sends its reconfiguration plan to the IA. This agent has been developed using an expert system technology.
The proposed monitoring algorithm
Start
Get data from data base
Create the MCCEA
MCCEA runs the controls charts
If(MCCEAdecision=stableprocess)Then
MCCEA sends report to the IA
Else
Create the DANNA
Create the IBNA
Create RA
DANNA creates the ANN using MLP
IBNA creates the Bayesian net
For (i=1 to number of observations) Do
DANNA gives its diagnosis of the observation i
DANNA sends the diagnosis to the IBNA
End For
IBNA receives the diagnosis from DANNA
IBNA uses BN to find the variables that are out of control
IBNA sends the report to the RA
RA receives report about the variables involved in the fault
RA finds the reconfiguration plan
RA sends report to the IA
IA receives report from RA
End If
End
Application of the proposed model on the Tennessee Eastman process
Introduction to the Tennessee Eastman process
The Tennessee Eastman process (TEP) is proposed by Downs and Vogel (1993) to provide a simulated model and to evaluate the monitoring methods of industrial complex process. The process consists of five principal units: a condenser, a separator, a reactor, a compressor and a stripper. Four gaseous reactants (A, C, D and E) and inert B are fed to the reactor. It produces two components (G and H) and the undesired byproduct F. The reaction equations are listed in equation number (1–4). All the reactions are irreversible, exothermic and approximately first order with respect to the reactant concentrations. The reaction rates are expressed as Arrhenius function of temperature. The reaction producing G has higher activation energy than that producing H, thus resulting in more sensitivity to temperature (Fig. 2).
Measurement variables in the Tennessee Eastman process
Variable  Description  Units 

XMEAS(1)  A feed (stream 1)  kscmh 
XMEAS(2)  E feed (stream 3)  kg/h 
XMEAS(4)  Total feed (stream 4)  kg/h 
XMEAS(5)  Recycle flow (stream 8)  kscmh 
XMEAS(6)  Recycle flow (stream 6)  kscmh 
XMEAS(7)  Reactor pressure  kPa gauge 
XMEAS(8)  Reactor level  \(\%\) 
XMEAS(9)  Reactor temperature  C\(^{\circ }\) 
XMEAS(10)  Purge rate (stream 9)  kscmh 
XMEAS(11)  Product sep temp  C\(^{\circ }\) 
XMEAS(12)  Product sep level  \(\%\) 
XMEAS(13)  Prod sep pressure  kPa gauge 
XMEAS(14)  Prod sep underflow (stream 10)  \({\mathrm{m}}^{3}{/}\)h 
XMEAS(15)  Stripper level  \(\%\) 
XMEAS(16)  Stripper pressure  kPa gauge 
XMEAS(17)  Stripper underflow (stream 11)  \({\mathrm{m}}^{3}{/}\)h 
XMEAS(18)  Stripper temperature  C\(^{\circ }\) 
XMEAS(19)  Stripper steam flow  kg/h 
XMEAS(20)  Compressor work  kW 
XMEAS(21)  Reactor cooling water outlet temp  C\(^{\circ }\) 
XMEAS(22)  Separator cooling water outlet temp  C\(^{\circ }\) 
Variable  Description  Stream 

XMEAS(23)  Component A  6 
XMEAS(24)  Component B  6 
XMEAS(25)  Component C  6 
XMEAS(26)  Component D  6 
XMEAS(27)  Component E  6 
XMEAS(28)  Component F  6 
XMEAS(29)  Component A  9 
XMEAS(30)  Component B  9 
XMEAS(31)  Component C  9 
XMEAS(32)  Component D  9 
XMEAS(33)  Component E  9 
XMEAS(34)  Component F  9 
XMEAS(35)  Component G  9 
XMEAS(36)  Component H  9 
XMEAS(37)  Component D  11 
XMEAS(38)  Component E  11 
XMEAS(39)  Component F  11 
XMEAS(40)  Component G  11 
XMEAS(41)  Component H  11 
Manipulated variables in the Tennessee Eastman process
Variable  Description 

XMV(1)  D feed flow (stream 2) 
XMV(2)  E feed flow (stream 3) 
XMV(3)  A feed flow (stream 1) 
XMV(4)  Total feed flow (stream 4) 
XMV(5)  Compressor recycle valve 
XMV(6)  Purge valve (stream 9) 
XMV(7)  Separator pot liquid flow (stream 10) 
XMV(8)  Stripper liquid product flow (stream 11) 
XMV(9)  Stripper steam valve 
XMV(10)  Reactor cooling water flow 
XMV(11)  Condenser cooling water flow 
XMV(12)  Agitator speed 
The known faults of the Tennessee Eastman process
Variable  Description  Type 

IDV(1)  A/C feed ratio, B composition constant (stream 4)  Step 
IDV(2)  B composition, A/C ratio constant (Stream 4)  Step 
IDV(3)  D feed temperature (stream 2)  Step 
IDV(4)  Reactor cooling water inlet temperature  Step 
IDV(5)  Condenser cooling water inlet temperature  Step 
IDV(6)  A feed loss (stream 1) Step  Step 
IDV(7)  C header pressure lossreduced availability (stream 4)  Step 
IDV(8)  A, B, C feed composition (stream 4)  Random variation 
IDV(9)  D feed temperature (stream 2)  Random variation 
IDV(10)  C feed temperature (stream 4)  Random variation 
IDV(11)  Reactor cooling water inlet temperature  Random variation 
IDV(12)  Condenser cooling water inlet temperature  Random variation 
IDV(13)  Reaction kinetics  Slow drift 
IDV(14)  Reactor cooling water valve  Sticking 
IDV(15)  Condenser cooling water valve  Sticking 
Simulation and results analyses
The proposed approach has been implemented using the Java environment Netbeans IDE. Also, we use the agent design platform Java Agent Development framework JADE. To simplify the development of the neural network and Bayesian network with Netbeans, java offers many libraries. Moreover, we use Jess Tab which is a rule engine for the Java platform to produce our rules in the knowledge base. In this work, we use FIPA Agent Communication specifications that deal with Agent Communication Language (ACL) messages , message exchange interaction protocols and content language representations.

The Detection
All the persons that are worked on TEP take rate to obtain wrong alarm equal to \(0.01\%\). In this work, we use the \({T}^{2}\) control chart for instability detection. A performance of detection system is evaluated by calculating its reliability (Kononenko 1991). The detection reliability is defined as: (the number of obtained alerts in the test period/the total number of sample in the period test).
The MCCEA runs the \({T}^{2}\) control chart; if it detects an abnormal process state, it sends message to the DANNA. The detection reliability obtained in this work is the same that been obtained by Sylvain (2007). Figure 3 shows the detection reliability of MCCEA, and some faults are easily detectable [IDV (1), IDV (2), IDV (4), IDV (5), IDV (6), IDV (7), IDV (8), IDV (10), IDV (12), IDV (14)]. But other faults are difficult to detect [(IDV (3), IDV (9) and IDV (15)]. The last faults [(IDV (3), IDV (9), IDV (15)] are very identical. So the use of one chart (in this work, we use the \({T}^{2}\) control chart) is not sufficient. The run of many control charts simultaneously will augment the reliability of detection.

The Diagnosis
This task is realized by the DANNA. When it receives message from the MCCEA that the process is not stable, it creates the neural network using MLP, for the purpose to find the fault that appeared in the process. In the next paragraph, we will show the diagnosis obtained by the DANNA and we will evaluate the acquired results to the result of other classifiers proposed in the literature.
Diagnosis of the known faults in the Tennessee Eastman problem
We have done the diagnosis of all the faults, i.e. IDV (1) to IDV (15) in TEP, as shown in Fig. 4. The used neural network is a MLP of three layers:

The input layer contains 53 neurons that represent the process parameters,

The hidden layer contains 34 neurons (number of neurons in input layer + number neurons in output layer/2),

The output layer contains 15 neurons that represent the process faults.
Table 4 represents a comparison between the diagnosis realized by DANNA, and some other approaches proposed to the TEP faults diagnosis. Sylvain (2007) used Bayesian network for classification; however, the PC1DARMF (Li and Xiao 2011) is a supervised pattern classification method which uses onedimensional adaptive rankorder morphological filter.
Diagnosis of IDV (4), IDV(9), IDV(11) in TEP
The most difficult faults to be classified in the TEP are: IDV (4), IDV (9) and IDV (15). The created neural network composed by 53 neurons (TEP parameters) in the input layer, 28 neurons in the hidden layer and 3 neurons in the output layer. Table 5 presents the rate of correct classification of the faults IDV (4), IDV (9) and IDV (15) of the TEP. It is a comparison between the DANNA diagnosis and the approach which proposed by ElFerchichi (2013).

The Identification
The IBNA is the responsible on the realization of the identification task using Bayesian net. It receives a report about the fault that appeared in the process from DANNA. To develop the Bayesian network, Sylvain (2007) used the causal decomposition of \({T}^{2}\). Figure 4 presents the Bayesian network that is created in the normal functionality of process. We take rate of false alarm \(= 0.005\). The IBNA takes the observation that represents the fault, and then, it finds the variables that are involved in the fault. The variables involved in the fault have probability value under 0.995. We take the case of the observation 240 of IDV (5) that is classified as an IDV (4). The IBNA detects two variables that have a probability value under 0.995. The two variables are (XMV11) and (XMEAS21). The IBNA sends the variable identification to the RA.

The Reconfiguration
The RA receives report from IBNA which contains the identification of the variables that cause the process instability. In our example, the identified variables are (XMV11) and (XMEAS21). The RA finds that: the variable (XMV11) represents the liquid cooling flow to the condenser, whereas the variable (XMEAS21) represents the cooling liquid temperature at the reactor outlet. In conclusion, these two variables involved in the fault IDV (5), so the fault that appeared in the process is the IDV (5) and not the IDV (4). It proposes the reconfiguration plan to the operator. The development of this agent requires knowledge of an expert human, which we will use to find the ideal reconfiguration plan.
Classification rate of the known 15 faults in TEP
Faults  DANNA (%)  Sylvain (2007) (%)  PC1DARMF Li and Xiao (2011) (%) 

IDV(1)  97.01  97.5  30 
IDV(2)  95.34  98.125  95 
IDV(3)  82.10  22  0.00 
IDV(4)  97.34  82.375  25 
IDV(5)  96.67  98  100 
IDV(6)  100  100  65 
IDV(7)  97.67  100  0.00 
IDV(8)  100  97  5 
IDV(9)  79.06  22.625  0.00 
IDV(10)  71.42  86.875  15 
IDV(11)  69.1  75.5  0.00 
IDV(12)  96.67  98.25  5 
IDV(13)  100  76.125  5 
IDV(14)  93.02  98.75  5 
IDV(15)  92.69  23.5  0.00 
Classification rate of IDV (4), IDV (9) and IDV (15) in TEP
Faults  DANNA (%)  ElFerchichi (2013) (%) 

IDV(4)  97.34  67.37 
IDV(9)  100  66.25 
IDV(15)  100  33.75 
Conclusion
An approach with several intelligences has been proposed in this paper for multivariate process monitoring. In this approach, we use the perfect tool for the realization of each task in a complex process monitoring. We use the multivariate control charts in the detection task. We utilize the artificial neural network classifier with MLP algorithm in the diagnosis task. For the identification task, we exploit the Bayesian network that has been proposed by Sylvain (2007). Moreover, to help the operators that are not specializing in realm, to realize the correction actions of the process, we suggest developing an expert system for reconfiguration task. To facilitate the use of the proposed approach with high efficiency, we integrate the different proposed subsystem (detection, diagnosis, identification and reconfiguration) in one system that is multiagent system. The proposed model has been evaluated on a multivariate process (Tennessee Eastman process).
From the simulation results, we find that the proposed classifier gives a good result compared with some works applied on Tennessee Eastman process. In addition, the proposed approach gives good results for each task in the process monitoring. In the case study, we have seen that some faults are difficult for detecting; our future works will concentrate on the development of the detection task. The developed reconfiguration agent realizes the reconfiguration tasks for known faults, and we will focus also on adding the reconfiguration plan in case when a new fault appear in the process.
Notes
Acknowledgments
The authors would like to express their sincere appreciation for all support provided.
Supplementary material
References
 Alt FB, Kotz NL, Johnson C (1985) R, Read multivariate quality control. Encycl Stat Sci 6:111–122Google Scholar
 Assareh H, Noorossana R, Mengersen KL (2013) Bayesian change point estimation in poissonbased control charts. J Ind Eng Int 9:32CrossRefGoogle Scholar
 Dhillon B (2005) Reliability, quality, and safety for engineers. CRC Press, Boca RatonMATHGoogle Scholar
 Downs JJ, Vogel EF (1993) A plantwide industrial process control problem. Comput Chem Eng 17(3):245–255CrossRefGoogle Scholar
 Ehsan B, Sadigh R (2014) Economic design of Hotellings \(\text{ T }^{2}\) control chart on the presence of fixed sampling rate and exponentially assignable causes. J Ind Eng Int 10:229–238CrossRefGoogle Scholar
 ElFerchichi S (2013) Ph.d. Thesis: selection and extraction of attributes for classification problem, National School of engineering of TunisGoogle Scholar
 Friedman N (2000) Using Bayesian networks to analyze expression data. J Comput Biol 7(3–4):601–620CrossRefGoogle Scholar
 Hotelling H (1947) Multivariate quality control. In: Eisenhart C, Hastay MW, Wallis WA (eds) Techniques of statistical analysis. McGrawHill, New York, pp 111–184Google Scholar
 Jing L, Jionghua J, Jianjun S (2008) Causationbased \(\text{ T }^{2}\) decomposition for multivariate process monitoring and diagnosis. J Qual Technol 40(1):1–13Google Scholar
 Kononenko I (1991) Seminaive bayesian classier, proceeding of the European working session on learning on machine learning, pp 206–219Google Scholar
 Li H, Xiao D (2011) Fault diagnosis of Tennessee Eastman process using signal geometry matching technique. J Adv Signal Proc (83). doi: 10.1186/16876180201183 Google Scholar
 Li J, Shi J, Satz D (2006) Modelling and analysis of disease and risk factors through learning Bayesian network from observational data, Technical reportGoogle Scholar
 Li J, Shi J (2007) Knowledge discovery from observational data for process control using causal Bayesian networks. IIE Trans 39(6):681–690CrossRefGoogle Scholar
 Lowry CA, Woodall WH, Champ CW, Rigdon SE (1992) A multivariate exponentially weighted moving average control chart. Technometrics 34(1):46–53CrossRefMATHGoogle Scholar
 Mani S, Cooper GF (1999) A study in causal discovery from populationbased infant birth and death records. In: Proceeding of the AMIA annual fall symposium. Philadelphia, pp 315–319Google Scholar
 Page ES (1954) Continuous inspection schemes. Biometrika 41:100115CrossRefGoogle Scholar
 Pignatiello J, Runger G (1990) Comparisons of multivariate cusum charts. J Qual Technol 22(3):173186Google Scholar
 Roberts SW (1959) Control chart tests based on geometric moving averages. Technometrics 1(3):239250CrossRefGoogle Scholar
 Stamatis DH (2003) Failure mode and effect analysis: FMEA from theory to execution. ASQ Quality Press, MilwaukeeGoogle Scholar
 Sylvain V (2007) Diagnostic et surveillance des processus complexe par rseaux baysiens.(Diagnosis and monitoring of complex process using bayesian networks), doctoral thesis, University of Angers, FrenchGoogle Scholar
 Venkatasubramanian V, Rengaswamy R, Yin K, Kavuri S (2003) A review of process fault detection and diagnosis, part I: quantitative modelbased methods. Comput Chem Eng 27(3):293–311CrossRefGoogle Scholar
 Vijayababu V, Rukmini VK (2014) Economic design of xbar control charts considering process shift distributions. J Ind Eng Int 10:163171Google Scholar
 Xia P (2015) Horizontal cumulative variance chart: A quality control scheme monitoring shifts in process variation. Int J Ind Syst EngGoogle Scholar
 YuChang L, ChaoYu C, ChungHo C (2015) Robustness of the EWMA median control chart to nonnormality. Int J Ind Syst EngGoogle Scholar
Copyright information
Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.