In this study, an effective search methodology based on fuzzy logic is applied to narrow down search range for the possible breakdown causes. Moreover a genetic algorithm (GA) is employed to directly find the intervals of solution to the inverse fuzzy inference problem during diagnosis procedure. Through the assistance of the developed intelligent diagnosis system, an inspector can be easier and more effective to find various possible occurred breakdown causes by judging from the observed symptoms during manufacturing process. An application of the developed intelligent diagnosis system to tracing the breakdown causes occurred during spinning process is reported in this study. The results show that the accuracy and efficiency of the diagnosis system are as promising as expected.
It is crucial for a manufacturing process to be of an intelligent diagnosis system to help effectively find out the occurred problems and eliminate them in no time when breakdowns occur. However, nowadays the inspecting & tracing process for the breakdowns causes during producing product in manufacturing industry still heavily depends on the expertise of an experienced technician. In general a junior inspector is lacking in the knowledge or the experience needed for tracing out break down causes from the occurred problems. Results of inspection and diagnosis are exclusively influenced with mental and physical conditions of an inspector. It is not only time-consuming but also economically infeasible for an enterprise to retrain a new operator to expert at the specific technical knowledge of engineering, once the trained operator leaves the job. For the sake to help solve the above-mentioned problems, an intelligent diagnosis system is developed by using fuzzy logic and genetic algorithm (GA) in this study.
A good diagnosis system should have the capability to help find the possible causes incurring the defects of product. Fuzzy sets theory is a handy tool for expert information formalization while simulating cause-effect connections in technical and medical diagnostic problems [
The direct logical inference suggests finding diagnoses (output variables or effects) according to observable internal parameters of the object state (input variables or causes). At present, the majority of fuzzy logic applications to the diagnosis problems adopt the direct logical inference [
In the case of inverse logical inference some renewal of causes takes place (of the object state parameters) according to observable effects (symptoms). The inverse logical inference is used much less due to the lack of effective algorithms solving fuzzy logical equation system. It is required to develop a more effective approach to finding solution to inverse fuzzy logic problem during diagnosing breakdown causes. Although the effective algorithm for solving the inverse fuzzy logic problem has been researched [
Let the relationship between symptoms and causes in a diagnosis process be represented as rij. Thus, the relationship between cause i and symptom j in a diagnosis system can thus be illustrated as that between i and j in an diagnosis situation when a relationship exists between breakdown cause i and symptom j, the rij is shown as 1; otherwise it is 0. Assume that matrix R is composed of elements rij of size m × n, matrix A is a row matrix consisting of m elements, and matrix B is a row matrix consisting of n elements, respectively. The relationship between causes and symptoms in a diagnosis system can thus be shown as the following.
A ∘ R = B (1)
where
R = ( r 11 r 12 ⋯ r 1 n r 21 r 22 ⋯ r 2 n ⋯ ⋯ ⋯ ⋯ r m 1 r m 2 ⋯ r m n )
A = ( a 1 a 2 ⋯ a m )
B = ( b 1 b 2 ⋯ b n ) .
Calculated result from Equation (1) by max-min composition (Zadeh and Kacprzyk, 1992) yields
V i ( a i Λ r i j ) = b j (2)
where V: max, L: min, i = 1 , 2 , ⋯ , m , and j = 1 , 2 , ⋯ , n .
The diagnostic procedure seems quite simple using given matrix A and matrix R to find the solution of matrix B because there exists only one specific solution. Yet using matrix B and R to find matrix A, which can fit the requirement of Equation (1), will be rather more sophisticated because more than one solution exists. Such kind of vague relations existing between breakdown causes and symptoms are called fuzzy relations. A fuzzy set, defined originally by Zadeh [
Assuming that matrices A, B, and R in Equation (1) are all fuzzy set [
{ a * = b if b < r a * = [ b , 1 ] if b = r a * = ϕ if b > r (3)
Relationships between b, r, and a can be illustrated as in
Finding of fuzzy set A amounts to the solution of the fuzzy logical Equations system:
b 1 = ( a 1 Λ r 11 ) V ( a 2 Λ r 21 ) ⋯ V ( a m Λ r m 1 ) b 2 = ( a 1 Λ r 12 ) V ( a 2 Λ r 22 ) ⋯ V ( a m Λ r m 2 ) ⋯ ⋯ ⋯ ⋯ b n = ( a 1 Λ r 1 n ) V ( a 2 Λ r 2 n ) ⋯ V ( a m Λ r m n ) (4)
which is derived from Equation (2). The solution to the problem of fuzzy logical equations (i.e., Equation 2) is formulated in this way. Vector a = ( a 1 , a 2 , ⋯ , a n ) , which satisfies limitations of a i ∈ [ 0 , 1 ] , i = 1 , 2 , ⋯ , m , should be found and provides the least distance between expert and analytical measures of effects significances, that is between the left and the right parts of Equation (2).
Minimizing
∑ j = 1 n ( b j − ∨ i ( a i ∧ r i j ) ) 2 . (5)
In general, Equation (2) can have no solitary solution but a set of them. Therefore, according to Equation (5), a form of intervals can be acquired as the solution to the fuzzy logical equations system and illustrated as follows.
a i = [ a i 1 , a i u ] ⊂ [ 0 , 1 ] , i = 1 , 2 , ⋯ , m , (6)
where a i 1 ( a i u ) is the low (upper) boundary of cause a i significance measure.
Formation of intervals a i ( i .e . , [ a i 1 , a i u ] ) is done by way of multiple optimization problem solution to Equation (5) and it begins with the search for the null solution of it.
The null solution to optimization problem in Equation (5) is illustrated as
a ( 0 ) = ( a 1 ( 0 ) , a 2 ( 0 ) , ⋯ , a n ( 0 ) ) , where a i ( 0 ) ∈ [ a i 1 , a i u ] , i = 1 , 2 , ⋯ , m . The upper boun-
dary ( a i u ) is found in range [ a i ( 0 ) , 1 ] and the low ( a i 1 ) in range [ 0 , a i ( 0 ) ] .
Let a ( k ) = ( a 1 ( k ) , a 2 ( k ) , ⋯ , a n ( k ) ) be some kth solution of optimization problem in
Equation (5). While searching for upper boundaries ( a i u ) it is suggested that
a i ( k ) ≥ a i ( k − 1 ) , and while searching for low boundaries ( a i 1 ) it is suggested that
a i ( k ) ≤ a i ( k − 1 ) . It is shown in the
The upper and low boundary can be found as the following steps.
1) Randomly find an optimal solution (i.e., a ( 0 ) ) based on Equation (5).
2) Search dynamics of upper solutions boundaries (i.e., a i ( k ) ≥ a i ( k − 1 ) ).
{If a ( k ) ≠ a ( k − 1 ) , then a i u ( a i ) = a i ( k ) , i = 1 , 2 , ⋯ , m , k = 1 , 2 , ⋯ , p .
Else if a ( k ) = a ( k − 1 ) , then the search is stopped.}
3) Search dynamics of low solutions boundaries (i.e., a i ( k ) ≤ a i ( k − 1 ) ).
{If a ( k ) ≠ a ( k − 1 ) , then a i 1 ( a i ) = a i ( k ) , i = 1 , 2 , ⋯ , m , k = 1 , 2 , ⋯ , p .
Else if a ( k ) = a ( k − 1 ) , then the search is stopped.}
To solve a problem, the GA randomly generates a set of solutions for the first generation. Each solution is called a chromosome that is usually in the form of a binary string. According to a fitness function, a fitness value is assigned to each solution. The fitness values of these initial solutions may be poor; however, they will rise as better solutions survive in the next generation. A new generation is
produced through the following three basic operations [
1) Randomly generate an initial solution set (population) of N strings and evaluate each solution by fitness function.
2) If the termination condition does not meet, do
Repeat {Select parents for crossover.
Generate offspring.
Mutate some of the numbers
Merge mutants and offspring into population.
Cull some members of the population.}
3) Stop and return the best fitted solution.
In order to apply GAs to our problem, we firstly need to encode the elements of matrix A as a binary string. The domain of variable ai is [ d i 1 , d i u ] and the required precision is dependent on the size of encoded-bit. The precision requirement implies that the range of domain of each variable should be divided into at least ( d i u − d i 1 ) / ( 2 n − 1 ) size ranges. The required bits (denoted with n) for a variable is calculated as follows and the mapping from a binary string to a real number for variable ai is straightly forward and completed as follows.
a i = d i 1 + s i ( d i u − d i 1 ) / ( 2 n − 1 ) (7)
where si is an integer between 0 - 2 n and is called a searching index.
After finding an appropriate si to put into Equation (7) to have an ai, which can make fitness function to come out with a fitness value approaching to “1”, the desired parameters can thus be obtained. Combine all of the parameters as a string to be an index vector, i.e. A = ( a 1 , a 2 , ⋯ , a m ) , and unite all of the encoder of each searching index as a bit string to construct a chromosome shown as below.
P = p 11 ⋯ p 1 j p 21 ⋯ p 2 j ⋯ p i 1 ⋯ p i j p i j ∈ { 0 , 1 } ; i = 1 , 2 , ⋯ , m ; j = 1 , 2 , ⋯ , n ; (8)
Suppose that each ai was encoded by n bits and there was m parameters then the length of Equation (8) should be an N-bit (N = m × n) string. During each generation, all the searching index sis of the generated chromosome can be obtained by Equation (9).
s i = p i 1 × 2 n − 1 + p i 2 × 2 n − 2 + ⋯ + p i n × 2 n − n i = 1 , 2 , ⋯ , m ; (9)
Finally the real number for variable ai can thus be obtained from Equation (7) and Equation (9). The flow chart for the encoding and decoding of the parameter is illustrated in
A main difference between genetic algorithms and more traditional optimization search algorithms is that genetic algorithms work with a coding of the parameter set and not the parameters themselves [
The target is to minimize the distance between the observed values (i.e., bj) and the calculated ones (i.e., V i ( a i Λ r i j ) ) shown as Equation (5). The fitness of GA used in search mechanism can thus be set as Equation (10). This approach will allow the GA to find the minimum difference between them when the fitness function value is maximum (i.e., approaches to 1).
Fitness = 1 − ∑ j = 1 n ( b j − ∨ i ( a i ∧ r i j ) ) 2 (10)
where V: max, L: min, i = 1 , 2 , ⋯ , m , and j = 1 , 2 , ⋯ , n .
In order to develop a more effective diagnosis system, which is capable of tracing the possible breakdown causes from the categories of defects and providing an immediate response, it is necessary to sketch an effective searching algorithm for the diagnosis procedure. The methodology used in research [
A i = { a 1 , a 2 , ⋯ , a m } = cause set
B j = { b 1 , b 2 , ⋯ , b n } = symptom set
R i j = ( r i j ) mxn = fuzzy relation matrix of size m × n between a and b
where
a 1 − a m : m kinds of breakdown causes,
b 1 − b n : n kinds of symptoms, and
r i j : the fuzzy truth value between the ith kind of cause and the jth kind of symptom.
The fuzzy truth values of rijs are acquired empirically from experts of engineering using the following linguistic values [
1) completely true: Once ai occurs then bj appears.
2) very true: When ai occurs, bj will appear very definitely.
3) true: When ai occurs, bj will appear very probably.
4) rather true: When ai occurs, bj will appear probably.
5) rather rather true: When ai occurs, bj will appear seldom.
6) unknown: When ai occurs, bj will never appear.
Generally speaking, in a diagnosis problem, the symptoms can be divided into two kinds of categories, the positive symptom set (J1), consisting of those symptoms that have been observed by the operator, and the negative one (J2), consisting of those symptoms that have not yet been observed by the operator. When only certain symptoms have been observed by the operator, the diagnosis process can proceed. It is impossible for all the symptoms of the system to appear at one time, so that J1 ¹ f and J2 ¹ f.
Actually during tracing a certain kind of breakdown cause through the observed symptoms, the reliability of diagnostic results should be very high as long as all possible symptoms for this kind of breakdown are all observed [
We can thus conclude that the diagnostic range can be narrowed effectively by neglecting those breakdown causes seldom noticed ai. For instance, breakdown causes that are in accordance with the circumstance of
V j ∈ J 2 R i j < rather rather true
should firstly be investigated. That is, the searching range of the diagnosis can be narrowed from i ∈ I ( = { i | i = 1 , 2 , ⋯ , m } ) down to
i ∈ I 1 ( = { i | V j ∈ J 2 R i j < rather rather true } ) .
A relationship should occur between the breakdown causes searched ai and the observed symptoms bj. In other words, the condition of
V j ∈ J 1 R i j > unknown
should be true. Therefore the searching range of diagnosis I1 can be reconstructed as
I 1 = { i | V j ∈ J 2 R i j < rather rather true , V j ∈ J 1 R i j > unknown } .
In a practical diagnostic procedure in the real world, the members in I1 are much fewer than those in cause set I (consisting of m members). Thus, an efficient searching method can be obtained.
Nevertheless, in a practical diagnostic procedure, while searching for the members of the set searching range I1, the circumstance of I1 = f can happen. Then a wider searching range should be reset to search once again. Yet the wider the searching range is set, the less reliable the breakdown cause found through this diagnostic procedure is. In order to achieve both effectively narrowing the diagnostic searching range and specific reliability of the diagnostic result, the extension of the searching range in a diagnosis procedure should have a proper limitation. Therefore, there are three kinds of searching range selected in this study. These sets and their reliability are represented as
I 1 ( = { i | V j ∈ J 2 R i j < rather rather true , V j ∈ J 1 R i j > unknown } ) ,
which has the greatest reliability and from which the diagnostic result that is found can be regarded as the actual “cause”;
I 2 ( = { i | V j ∈ J 2 R i j < rather true , V j ∈ J 1 R i j > unknown } ) ,
which is less reliable than I1 and from which the diagnostic result that is found can be regarded as “very probable”; and
I 3 ( = { i | V j ∈ J 2 R i j < true , V j ∈ J 1 R i j > unknown } ) ,
which is the least reliable, and from which the diagnostic result that is found can be regarded as “probable”.
The flow chart of the system’s diagnostic procedures is illustrated in
L i = ∑ j ∈ J 1 R i j (11)
where
Rij: the fuzzy truth value between the ith kind of breakdown cause and the jth kind of symptom.
J1: the positive symptom set.
An application of the intelligent diagnosis system to tracing the breakdown causes occurred during spinning was reported in this study. There were 6 kinds of defects that are most likely found during spinning and 20 possible occurrence causes of these defects all chosen from and referred to the reports [
1) Symptom Set and Cause Set
The cause set A and the symptom set B consist of the above-mentioned 20 causes and 6 kinds of defects respectively and the elements of each of the two are illustrated as below.
SYMPTOMS
b1 smash
b2 stick-out on the edge of cone
b3 ribbon-shaped defects around cone’s surface
b4 ring-shaped defects
b5 spindle-shaped defects
b6 too much happening in yarn’s cut-off
CAUSES
a1 mal-set for Bobbin holder
a2 mal-functioned pulley tension caused by neps or cotton trash
a3 bobbin slipping from slot
a4 gap occurred between bobbin and sketch
a5 improper setting of skeleton
a6 improper yarn’s adjunction
a7 big gap on top of cone
a8 lack of yarn tension
a9 defects in cylinder-slot
a10 too big gap between bottom of bobbin and cylinder
a11 forward shifting during bobbin’s circulation
a12 un-smooth spindle-spinning
a13 too big gap on top of cone
a14 over-heavy tension pulley
a15 mal-positioned tension device
a16 mal-functioned back-forth motion
a17 too much yarn tension
a18 mal-positioned empty bobbin
a19 mal-positioned de-knotter
a20 mal-positioned plug base of bobbin
2) Fuzzy Relation Matrix
All the truth values of members of fuzzy relation matrix R are illustrated as
After the operator examines the defects (breakdown causes) occurred on the yarns, “ring-shaped defects” (i.e., b4) formed during winding process is found so that symptom “b4” is input into the system to proceed with the diagnosis. According to the diagnosis procedure shown in
ai bj | b1 | b2 | b3 | b4 | b5 | b6 |
---|---|---|---|---|---|---|
a1 | A | A | A | B | ||
a2 | B | |||||
a3 | B | |||||
a4 | C | |||||
a5 | C | |||||
a6 | D | |||||
a7 | A | |||||
a8 | B | A | A | |||
a9 | C | D | ||||
a10 | A | D | D | |||
a11 | A | A | A | B | ||
a12 | A | |||||
a13 | B | |||||
a14 | C | |||||
a15 | E | B | D | |||
a16 | E | B | C | |||
a17 | A | A | ||||
a18 | A | A | B | |||
a19 | A | |||||
a20 | C |
I 1 ( = { i | V j ∈ J 2 R i j < rather rather true , V j ∈ J 1 R i j > unknown } ) ( i . e . , I 1 = { i | V j ∈ J 2 R i j < 0.2 , V j ∈ J 1 R i j > 0 } ) and
I 2 ( = { i | V j ∈ J 2 R i j < rather true , V j ∈ J 1 R i j > unknown } ) ( i . e . , I 2 = { i | V j ∈ J 2 R i j < 0.4 , V j ∈ J 1 R i j > 0 } ) .
There is no breakdown cause ai, which lives up to the I1 and I2 conditions (Lin et al., 1995). Thus the situation ( i . e . , I 1 = I 2 = ϕ ) is found. Next, the searching range is more broadened up to
I 3 ( = { i | V j ∈ J 2 R i j < true , V j ∈ J 1 R i j > unknown } ) ( i . e . , I 3 = { i | V j ∈ J 2 R i j < 0.6 , V j ∈ J 1 R i j > 0 } )
to investigate the possible breakdown causes. There is a suspected one (i.e., a15), which regarded as “probable”, found under the searching range I 3 ( ≠ ϕ ) after checking fuzzy relation matrix shown in
J 1 ( = { b 4 } ) and J 2 ( = { b 1 , b 2 , b 3 , b 5 , b 6 } ) . Following the suggestion of the “probable” breakdown cause a15 (i.e., mal-positioned tension device) from the system, the operator can immediately check it up. It is found nothing wrong with a15 after the operator’s inspection. Excluding the “probable” breakdown cause a15, the system provides the operator with five suspected breakdown causes shown as follows.
SUGGEST again CHECK
a 1 − b 1 , b 3 , | b 4 | , b 5 ( L 1 = 3.8 , J 1 = { y 4 } )
a 11 − b 1 , b 3 , | b 4 | , b 5 ( L 11 = 3.8 , J 1 = { y 4 } )
a 16 − b 3 , | b 4 | , b 6 ( L 16 = 1.6 , J 1 = { y 4 } )
a 15 − b 2 , | b 4 | , b 6 ( L 15 = 1.4 , J 1 = { y 4 } )
where the symptoms with lines to both sides denote the already-recognized ones. The operator re-inspects the product defects in relation to the suspected causes and their related symptoms suggested by the system, and he/she find that there is another two more “stick-out on the edge of cone” (i.e., b2) and “too much happening in yarn’s cut-off” (i.e., b6). Therefore he can re-input b2, b4 and b6 into the system to proceed with the further diagnosis. According to the observed symptoms, the positive and negative symptom are obtained as J 1 = { b 2 , b 4 , b 6 } and J 2 = { b 1 , b 3 , b 5 } respectively. Firstly, the searching range is set to
I 1 ( = { i | V j ∈ J 2 R i j < rather rather true , V j ∈ J 1 R i j > unknown } ) to investigate the po- ssible break down causes. The found diagnostic result can be regarded as the actual “cause”. There are five suspected breakdowns (i.e., a9, a10, a15, a19, a20) found based on the searching range I 1 ( ≠ ϕ ) after checking fuzzy relation matrix shown in
A _ = ( a 9 , a 10 , a 15 , a 19 , a 20 ) , R _ = ( 0.6. 0 0.4 0.4 0 0.4 0.2 0.8 0.4 0 0 1 0 0 0.6 )
Let the obtained relation matrix R has the following form.
As the result of product examination the inspector find out there are three defects (i.e., symptoms) occurred, i.e., b2 = 1, b4 = 1, b6 = 1. As mentioned above, there is no solution for b = a Λ r if the magnitude of r is less than b. Therefore the values of b2, b4, and b6 are adjusted to the maximum values of the respective columns in R _ matrix and shown as follows.
b 2 = max r i 2 = 0.6 , b 4 = max r i 4 = 0.8 , b 6 = max r i 6 = 1.0 ,
where i = 9,10,15,19, and 20.
Once the vectors, i.e., R _ and B _ , are obtained, we can proceed with the 3- step method mentioned in Section 3 to search for the upper and low boundaries.
Firstly, following the three steps mentioned in Section 4, we encode the unknown occurring possibility of breakdown causes (i.e., a9, a10, a15, a19, and a20) by using a binary coding method. The bit-size of each of them is set to 7 bits in this study. Thus a chromosome illustrated in
a 9 ( 0 ) = 0.60 , a 10 ( 0 ) = 0.00 , a 15 ( 0 ) = 0.99 , a 19 ( 0 ) = 0.98 , a 20 ( 0 ) = 0.25
Secondly, by means of the null solution, we can search for the upper and low boundaries.
[ d 9 1 ( 0 ) , d 9 u ( 0 ) ] , [ d 10 1 ( 0 ) , d 10 u ( 0 ) ] , [ d 15 1 ( 0 ) , d 15 u ( 0 ) ] , [ d 19 1 ( 0 ) , d 19 u ( 0 ) ] and [ d 20 1 ( 0 ) , d 20 u ( 0 ) ] ).
Through proceeding with the search mechanism of GA, we can find a solution, whose fitness approaches to 1, as the optimal one. An optimal solution after generations of GA search can be obtained as follows.
a 9 ( 1 ) = 0.66 , a 10 ( 1 ) = 0.80 , a 15 ( 1 ) = 0.99 , a 19 ( 1 ) = 0.99 , a 20 ( 1 ) = 0.43
By narrowing down the search range step by step, the upper boundaries of a 9 u , a 10 u , a 15 u , a 19 u and a 20 u can be acquired.
When search the low boundaries, the search ranges of variable a9, a10, a15, a19 and a20 are set different to each other as [0, 0.60], [0, 0], [0, 0.99], [0, 0.98], and [0, 0.25] (i.e., [ d i 1 ( 0 ) , d i u ( 0 ) ] , i = 9, 10, 15, 19, 20). Through proceeding with the search mechanism of GA, we can find a solution, whose fitness approaches to 1, as the optimal one. An optimal solution after generations of GA search can be obtained as follows.
a 9 ( 1 ′ ) = 0.46 , a 10 ( 1 ′ ) = 0.00 , a 15 ( 1 ′ ) = 0.78 , a 19 ( 1 ′ ) = 0.70 , a 20 ( 1 ′ ) = 0.11
By narrowing down the search range step by step, the low boundaries of a 9 1 , a 10 1 , a 15 1 , a 19 1 , and a 20 1 can be acquired.
a 9 = [ 0 , 1 ] , a 10 ∈ [ 0 , 1 ] , a 15 ∈ [ 0.36 , 1 ] , a 19 ∈ [ 0.44 , 1 ] , a 20 ∈ [ 0 , 1 ] .
The obtained solution allows making a diagnosis conclusion. The cause of the observed defects should be considered as a19 (i.e., mal-positioned de-knotter), because of which has a higher solution boundary than the other four. Excluding
N | a9 | a10 | a15 | a19 | a20 | increasing |
---|---|---|---|---|---|---|
0 | 0.60 | 0.00 | 0.99 | 0.98 | 0.25 | |
1 | 0.66 | 0.80 | 0.99 | 0.99 | 0.43 | |
2 | 0.87 | 0.93 | 1.00 | 1.00 | 0.66 | |
3 | 0.90 | 0.97 | 1.00 | 1.00 | 0.93 | |
4 | 0.92 | 0.99 | 1.00 | 1.00 | 0.95 | |
5 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
6 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
ai bj | b1 | b2 | b3 | b4 | b5 | b6 |
---|---|---|---|---|---|---|
a1 | A | A | A | B | ||
a2 | B | |||||
a3 | B | |||||
a4 | C | |||||
a5 | C | |||||
a6 | D | |||||
a7 | A | |||||
a8 | B | A | A | |||
a9 | C | D | ||||
a10 | A | D | D | |||
a11 | A | A | A | B | ||
a12 | A | |||||
a13 | B | |||||
a14 | C | |||||
a15 | E | B | D | |||
a16 | E | B | C | |||
a17 | A | A | ||||
a18 | A | A | B | |||
a19 | A | |||||
a20 | C |
the obtained solution, system supports five ais of greater Li value as the suspected breakdown causes for further diagnosis. They are illustrated as follows.
SUGGEST again CHECK
a 1 − b 1 , b 3 , | b 4 | , b 5 ( L 1 = 3.8 , J 1 = { y 2 , y 4 , y 6 } )
a 11 − b 1 , b 3 , | b 4 | , b 5 ( L 11 = 3.8 , J 1 = { y 2 , y 4 , y 6 } )
a 8 − | b 2 | , b 5 , | b 6 | ( L 8 = 2.8 , J 1 = { y 2 , y 4 , y 6 } )
a 17 − b 5 , | b 6 | ( L 17 = 2.0 , J 1 = { y 2 , y 4 , y 6 } )
a 10 − b 1 , | b 2 | , | b 6 | ( L 10 = 1.8 , J 1 = { y 2 , y 4 , y 6 } )
where the symptoms with lines to both sides denote the already-recognized ones.
Through the assistance of the diagnosis system, the operator can obtain three derived suspected breakdown causes a9, a10, a15, a19 and a20, which have a reliability of “cause” because the searching range is I1, to help him/her in troubleshooting and eliminating the breakdown. In this experimental case, after the technician for maintenance in the mill proceeding with the troubleshooting, the exact breakdown cause is confirmed to be a19 (i.e., mal-positioned de-knotter). From the diagnostic case illustrated as above, the accuracy of the implementation of this system is approvable. Even when the diagnostic result is not the exact break- down cause, nevertheless, the system will still provide the operator with some suspected ones for further check. This system can thus achieve the demand of providing with a solution in any circumstance during diagnosing in the real world.
The determination on the breakdown causes becomes more effective and efficient by adopting a GA-based diagnosis procedure proposed in the study. It was constructed that using the fuzzy set theory, which does not simply perform the routine calculations like those developed by the conventional programming algorithm, can be more flexible and effective to find the solution to fuzzy logical equation by genetic algorithm. The developed diagnosis model is of the nature of human capability in recognition and evaluation of uncertain linguistic description. Through the assistance of the developed diagnosis model, even a new inspector, who lacks in the expertise and experience in the spinning engineering field, can still easily find out the breakdown causes occurred during manufacturing process and then eliminate them. Furthermore, it is expected that the developed diagnosis model can be applied to other industries for the troubleshooting of machines or facilities as long as the relation matrix for the application in specific field is provided.
Lin, J.-J., Chuang, C.-J. and Ko, C.-F. (2017) Applying GA and Fuzzy Logic to Breakdown Diagnosis for Spinning Process. Intelligent Information Management, 9, 21-38. http://dx.doi.org/10.4236/iim.2017.91002