You are on page 1of 6

Copyright © IFAC On-line Fault Detection and Supervision

in the Chemical Process Industries, Delaware, USA, 1992

A REAL-TIME, FUZZY, DEEP-KNOWLEDGE BASED


FAULT-DIAGNOSIS SYSTEM FOR A CSTR
V_J. Terpstra, H.B. Verbruggen, M.W. Hoogland and R.A.E. Ficke

Delft University of Technology , Department of Electrical Engineering, Control Laboratory, p.a. Box 5031,
2600 GA De/ft, The Netherlands

Abstract. An on -line. real -time. fuzzy. deep-knowledge based fault detection and diagnosis system (FDD system) for a
CSTR (Continuous Stirred Tank Reactor) has been developed and implemented in the expert system shell 02. The FDD system
is tested on a dynamic simulation of the CSTR. The FDD system is fully separated from the model of the process it diagnoses.
lt operates independently of the model of the specific CSTR application and can be used for other processes. The model is
structured according to a hierarchical object oriented description. The FDD system is based on a diagnosis method called the
'governing equations'-method, in combination with fuzzy logic, to obtain a stable diagnosis. The FDD system is a real-time
system whose features include progressive reasoning with an 'any-time' mechanism and a minimization of the worst-case fault
detection-time.

Keywords. Artificial intelligence, Chemical industry, Expert systems, Failure detection, Fault diagnosis, Fuzzy systems,
Hierarchically intelligent control. Integrated plant control, Supervisory control.

1 Introduction

This paper reports some of the work within the scope of the
SCWERE project (Supervisory Control With Embedded
Real-time Expert systems). This is a joint project between
the faculties of Informatics and Electrical, Mechanical and
Chemical Engineering of the Delft University of Technology
and is linked to some industrial organizations.
The aim of this project is to support plantwide control
systems on a supervisory level by means of artificial intelli-
gence techniques. This support is envisaged in the areas of Fig, 1 The CSTR process.
fault detection and diagnosis, planning in response to faults,
However, another limitation of many FDD systems, namely
scheduling, optimization, on-line model updating. preven-
the assumption that the sensors are functioning correctly, is
tion of alarm inflation, etc . Emphasis is given to the on-line
not necessary in the FDD system presented in this paper. In
and real-time aspects of these tasks [Terpstra, 1991).
paragraph 12 an extension is presented to include not fore-
In the chemical process industry it is necessary, for econom- seen, unknown faults. In paragraph 13 some ideas are pre-
ical and safety reasons, to detect and diagnose a fault as soon sented about the extension of the FDD to a process which
as possible and plan actions to continue or resume the proc- operates in a dynamic state.
ess operations. This task is usually performed by human
operators. The complexity of a chemical process makes it
very difficult for humans to accomplish this task fast enough 2 The FDD method
and in a correct way. A possible solution is to accomplish
these actions automatically by means of a FDD system. Error detection and fault diagnosis 1 is an area which is
The FDD system uses a model of the CSTR process widely studied. The FDD research field can be divided into
(see Fig. I) and operates independently of the actual CSTR two main streams: the mathematical model approach and the
case. The CSTR is described by means of hierarchically ori- knowledge based approach. Within the knowledge based
ented objects. Each object has its own local FDD methods, approach two main directions can also be recognized: the
which are not prescribed in advance. A global FDD mecha- shallow-knowledge (heuristics) and the deep-knowledge
nism instructs objects in the hierarchical model to detect and (models) techniques [Tzafestas, 1989J.
diagnose their own faults. Our research is based upon the deep-knowledge based
In this study the following assumptions have been approach using hierarchical oriented submodels/objects.
made: This will be explained in §3 "Objects".
Only single faults are foreseen.
All possible faults are known and modelled. I. In this paper a fault is defined as the cause of an error and errors
Process operates in steady state. are detected through their symptoms,

73
mediately ask the correct object for its data and use it. Only sor faults . The FDD system has to wait for the maximum
when the model changes, the links must be updated. time to be sure that no other effects are visible. In that case
the detected fault is a sensor fault.
The FDD can handle a situation in which there is no external
To put in more general terms, in time more informa-
sens.or available. In fact, this principle is one of the big
tion appears. The FDD system is able to produce a more de-
advantages of this FDD method. It is easy to investigate what
tailed diagnosis in time and it knows how long to wait before
the effects will be if one or more sensors are removed from
final conclusions can be drawn. If the time that the system
the process. In that case, the equations which use these sen-
must wait for the conclusion of an object takes too long, the
sors are simply not used by the GE algorithm. The effect will
global algorithm suspends the FDD of that object and contin-
be a graceful degradation of the performance: the conclu-
ues with other suspects of the occurred fault.
sions become less specific (more possible faults) and fuzzier
(lower certainty). 2. Progressive reasoning/'any-time' algorithm.
The FDD system produces a set of possible faults at all
times. It starts with a maximum set of all possible faults. As
7 Fuzzy reasoning time passes, more elements of this set can be excluded using
the GE algorithm. Because of the way the global diagnosis
As mentioned before, thresholds are used to determine searches in the hierarchy of objects, it produces a continu-
whether or not the value of a variable is correct. So the ously improving diagnosis. This improving diagnosis means
thresholds give the maximum and minimum expected value that the FDD system reveals more detailed faults by limiting
of the variable. If these thresholds separate the range of the the set of possible faults .
value exactly into 'correct' and 'incorrect', an instable diagno- Also zooming takes place. In the beginning of the di-
sis occurs when one of the variables fluctuates around its agnosis, the possible faulty objects are high level objects. As
threshold (see Example 1) [Kramer, 1987J. The Boolean GE the diagnosis continues, lower level, more detailed suspect-
algorithm gives opposite diagnoses for values just above or objects are presented .
just below the threshold. 3. Unmodelled dynamics.
This problem is solved using fuzzy logic. Each thresh- Not all (fast) dynamics are modelled in the FDD sys-
old is fuzzified. That means that the result of the evaluation tem. If the FDD system is much faster than the modelled dy-
of an equation is no longer Boolean, but a real value from 0 namics of the process (i.e. the FDD system has to wait fot
to I which will be assigned to the conditions of the equation. certain effects to propagate), it may interpret phenomena due
The standard, non-fuzzy GE algorithm uses a Boolean dis - to fast dynamics and it must wait until such phenomena are
junction and conjunction operator to select the faulty condi- over. Therefore an estimation of these dynamics have to be
tion. When using fuzzy values, a new combined fuzzy included. If the FDD system is much slower than the dynam-
disjunction and conjunction operator had to be developed to ics of the process, certain effects of detected faults are invis-
handle the fuzzy logic in the GE algorithm. It is a complex ible for the system and it is impossible to make a diagnosis
operator which also uses the number of equations related to with these (fast) effects.
the condition . The result of the fuzzy GE algorithm is a set
4. An optimal set of scanned objects.
of possible faults with certainty factors (see Example 2).
In the detection phase, the FDD system must detect ab-
normalities as fast as possible. It can detect abnormalities at
8 Real-time aspects a high level and at a low level. Symptoms propagate from the
bottom of the hierarchy to the top. By evaluating only the
highest level object, all faults can be detected. Only one ob-
The FDD system is applied on-line and real-time. It must be
ject is evaluated in the scanning. Therefore the scanning will
able to monitor the CSTR process continuously. In the fol-
take less time, but the symptoms must propagate all to the
lowing ways time aspects are included:
top and this may take a long time. The alternative is to eval-
1. Fault propagation times. uate all low level objects. The propagation time will be as
The effects/symptoms of faults propagate through the low as possible. But then the scan-time increases, because
process. This propagation takes a certain time, depending on the maximum number of objects must be evaluated. The
the dynamics of the process, the value of the thresholds and worst detection time of an error is the propagation time + the
the magnitude of the fault. Thus the FDD system has to wait scan time (or cycle time). Therefore an optimum can be
for certain effects to take place after the occurrence of a fault. found in a selection of a set of objects in the middle of the
This waiting time is particularly important in the case of sen- hierarchy at which the fault-detection-time is minimal.

Hl = {al ,a2} Hl = {al ,a2}


H2 = {al} H2 = {al}
Suppose: al a2 Suppose: al a2
El = fault 1~ Hl : 1 1 El = probabl~ fault 0.8~ Hl : 0.8 0.8
E2 = fault 1~ H2: 1 E2 = maybe ault 0.6~ H2: Q6
Result of GE: 1 0 Result of GE: 0.6 0.32
Suppose: al a2 Suppose: al a2
El = fault 1~ Hl : 1 1 El = probably fault 0 . 8~ Hl : 0.8 0.8
E2 = not fault O~ H2: Q E2 = maybe not fault 0.4~ H2: M
Result of GE: 0 Result of GE: 0.4 0.48

Example 1 The standard Boolean GE method. Example 2 The fuzzy GE method.


Also a major disadvantage of the Boolean GE When E2 flu(;tuates, it has only small effects
is illustrated: when E2 fluctuates round its in the diagnosis result: stable diagnosis.
threshold, the GE algorithm concludes that
either al or a2 is faulty: instable diagnosis.

76
9 Simulating the CSTR process A B

The CSTR process that is used to evaluate the FDD system


is given in Fig. I . In the Continuou s Stirred Tank Reactor, an
exothermic chemical reaction takes place: feed materia l is
converted into a product. The produced heat is removed by a
cooling medium in the cooling jacket of the reactor. The feed
of the CSTR and the cooling fluid are brought into the reac-
tor via a circuit consisting of a pump, a controlled val ve
(using a PI algorithm in the flow -controller) and a connec-
tion.
The CSTR process can be described with three (non-
linear) differential equations for the state variables of the ® result of diagnosis: faulty object
process: the temperature of the reactor, the concentration of
~ evaluated but non-faulty object
material A and the temperature of the cooling fluid . Further-
more there are several equations that describe the flows in o non-evaluated, non-faulty object
the system and the influence of the flow-controller. Fig. 5 Search trees in case of fault models (A) and in
It is possible to introduce faults in several components case of no fault models (8) .
of the simulated process, according to a certain (chosen) set sec.). Diagnosing small, slow changes of parameters takes
of faults that can occur in such a process. For instance, it is more time (150-2700 sec.). The calculation times of this
possible to introduce different kinds of sensor faults, step or implementation of the FDD system are about 5-20 sec.
ramp shaped disturbances on all kinds of parameters or in- Because the main parts of the CSTR process are slow, the
puts. diagnosis time mainly depends on fault propagation times.

10 Example of fault detection and


diagnosis. 12 Unknown faults

The present FDD system can only manage known, modelled


As an example, the detection and diagnosis of a fault in the
faults. Within the concept presented in this paper, the exten-
temperature sensor attached to the reactor is described .
sion to add unknown faults is quite simple. In general an
If a fault is introduced in the temperature sensor of the
object can fail in several ways (called fault modes) and in an
reactor (e.g. the temperature is fixed at a certain value out-
unknown way. This unknown way can be modelled just as an
side the range between the thresholds of the temperature of
extra fault mode. In respect to the object hierarchy, this
the reactor) the FDD system detects an error in the tempera-
means that an object gets an extra child-object which repre-
ture of the reactor (in the object CSTR). The equation 'tem-
sents the unknown fault. The unknown-fault-child-object
perature is normal' is evaluated abnormally and in the set of
has no children because it can ' t specify the fault any further.
conditions of that equation, one of these conditions must be
The unknown fault is defined as a possible cause of an
false .
error with respect to the normative behaviour. The normative
The object CSTR now has to decide whether it is an in-
behaviour can be described by means of a set of parity equa-
ternal or external fault. If the T-sensor is correct and the tem-
tions. The normative behaviour equations have at least one
perature of the vessel is too high , this shall have its effects on
condition: the condition which represents the unknown fault.
the concentration of the outflow . This is a slow process, as to
Next to these, other equations can be used to add information
prevent premature conclusions, the FDD must wait to u s~ ~he
about the known faults . Because every symptom can be ex-
equations which use the concentration sensor. The waItmg
plained by the presence of an unknown fault, every equation
time for this equation is 600 seconds. That means that, if af-
has the unknown-fault-condition. Therefore even if a known
ter a maximum of 600 seconds no changes occur in the con-
fault can be found which explains all symptoms, also the un-
centration, apparently the real temperature did not change.
known fault is presented as a possible cause of the error.
Therefore the conclusion is: the sensor must be broken.
This definition of the unknown fault differs from the
Real changes in the temperature can be caused only by
definition in which only modelled components can fail (like
external objects (e.g. the feed or coolant supply). Because
for instance in the GDE [de Kleer, 1987]). In the last defini-
the waiting time is very high, the FDD decides to evaluate
tion errors which are not caused by the components which
the feed - and coolant supply first. Those two conclude that
are explicitly modelled (which describe only the normative
they are functioning correctly . Therefore the fault must lie
behaviour), can not be diagnosed. These can be external in-
inside the CSTR: hence it must be the sensor. It can draw this
fluences or components which have normally no influence
conclusion without having to wait for the information from
on the normative behaviour and which are therefore not
the output-concentration sensor because all other possible
modelled (e.g. a failing isolator). This definition demands
faults have been eliminated.
implicitly a kind of fault-modelling, whereas our definition
does not.
In practice, allowing unknown faults and the advan-
11 Results
tage of not having to model faults means that the FDD will
stop diagnosing on one level higher in the hierarchy com-
The FDD system has been implemented in G2. It monitors a pared with the FDD which uses only known fault models.
dynamic simulation of a CSTR process, which is also imple- Also, if in an object only its normative behaviour is given, it
mented in G2. Large, fast faults are quickly diagnosed (5-35 cannot diagnose an internal fault. That implies that it cannot

77
point out one of its children as the cause of the error. That redundancy of information (e.g. sensors) the system can
doesn't mean that one of those children is not faulty . To in- make a more precise diagnosis of the fault.
vestigate this, each child has to be asked separately to evalu- The FDD system is independent of the model descrip-
ate its behaviour. This means that, compared to the known- tion as long as this description follows the hierarchical object
faults situation, search time increases (see Fig. 5). oriented modelling syntax.
The effects of removing a sensor from the process can
easily be investigated.
13 FDD in dynamic changing states The FDD produces certainty factors with its conclu-
sions and produces a stable diagnosis due to the use of fuzzy
To be able to diagnose a process which will not stay in a techniques.
steady state, it is impossible to use equations in which abso- The FDD system can be real-time implemented. It can
lute, steady state values (i.e. thresholds) are compared with handle the dynamics of the process. It produces a result
measured sensor data. There are two solutions to avoid this. which improves if more time is available for evaluation. The
The first solution is to make the thresholds dynamic. In detection phase is optimized with respect to the calculation-
this way the thresholds are defined relative to an expected, and fault propagation times.
correct state. Two problems arise: The main problem of this method is found in the mod-
What is a correct state? A simulator which runs in paral- elling, especially regarding the tuning of the thresholds. This
lel to the real process can be used as a reference. Problem problem occurs only when the symptoms of the faults are
is that even in a very good simulator the results will drift still small ; the signals are moving near their thresholds. If the
away from the real process measurements. Therefore the signals are large compared to their thresholds, the FDD sys-
simulator must be aligned with the process. The danger tem diagnoses correctly.
of this aligning is that slow errors will not be detected be- The execution time using G2 is rather slow, but com-
cause the simulator will try to follow the (faulty) process. pared to the time constants of the process, fast enough.
So the errors will be 'compensated ' . Some ideas on how to extend the FDD system to be
Non-linearities. In this case study, the CSTR exhibits a able to diagnose unknown faults and to diagnose in a dynam-
strong non-linear behaviour. This means that the posi- ical changing state are presented.
tions of the thresholds relative to the expected state can
not be a constant, but should be a function of the state.
The second solution is to use only equations which are
independent of the state of the process. Mass and energy bal - 16 References
ances are such equations. Multilevel Flow Modelling
(MFM) diagnosis uses those equations ISassen, 19911. Us-
ing only these kind of equations has two disadvantages. de Kleer, J. and B. C. Williams (1987). Diagnosing multiple
They contain less information than equations in which is faults . Artificial Intelligence, No. 32, 97-130.
referred to state values. That means that the diagnosis be- Kramer, M. A. (1987). Malfunction diagnosis using quanti-
comes less specific . tative models with non-Boolean reasoning in expert systems.
Those equations process more state variables than the AIChE Journal, Vol. 33, No. 1,130-140.
equations which compare only one state variable with a
Petti, T. F., J. Klein and P. S. Dhurjati (1990). Diagnostic
reference. Therefore the cumulative inaccuracies are
model processor: using deep knowledge for process fault
larger. That means that the FDD system can diagnose
diagnosis. AIChE Journal, Vol. 36, No. 4, 565-575 .
only larger errors and will diagnose those later.
Ree, R. v. d., H. Koppelaar and E. J. H. Kerckhoffs (to be
published). Knowledge management in process modelling.
EURISCON'91, The European Robotics and Intelligent Sys-
14 Future research tems Conference , Kanoni, Corfu, Greece.
Rich, S. H. and V. Venkatasubramanian (1987). Model-
At present research is going on to solve some problems and based reasoning in diagnostic expert systems for chemical
limitations of the FDD system. process plants. Computers & Chemical Engineering, Vol.
Important subjects are multiple faults , definition of a 11, No. 2,111 - 122.
fault, tuning of thresholds and the link to mathematical FDD Sassen, J. M. A., P. Riedijk and R. B. M. Jaspers (1991).
approaches. Those four topics are closely related and proba- Using multi level-flow models for fault-diagnosis of indus-
bly can't be solved independently. Another project is to use trial processes. 3th European Conference on Cognitive Sci-
the FDD concepts described in this paper on a sub-system of ence Approaches to Process Control, Cardiff, UK. 207-216.
an aeroplane. In that case, FDD in dynamic changing states
must be included. This also demands the use of trend-infor- Terpstra, V. J., H. B. Verbruggen and P. M . Bruijn (1991).
mation . Because this probably means that the models will Integrating information processing and knowledge represen-
become more and more complex, the automatic generation tation in an object-oriented way. IFAC Workshop on compu-
of equations, their conditions and thresholds from state and ter software structures integrating All KBS systems in
fault models will be investigated . process control, Bergen, Norway. IFAC. 19-29.
Tzafestas, S. G. (1989). System fault diagnosis using the
15 Conclusions knowledge-based methodology. Chapter 15 from: R. Patton
et al. (Ed.), Fault diagnosis in dynamic systems. Theory and
applications. Prentice Hall, London. p. 509-594.
The FDD system can detect and diagnose the faults that can
occur in the CSTR process simulation. Dependent on the

78

You might also like