applying fuzzy inference system tsukamoto for decision ...ieomsociety.org/ieom_2016/pdfs/667.pdf ·...

Proceedings of the 2016 International Conference on Industrial Engineering and Operations Management Kuala Lumpur, Malaysia, March 8-10, 2016

Identify applicable sponsor/s here. If no sponsors, delete this text box (sponsors).

Applying Fuzzy Inference System Tsukamoto for Decision Making in Crude Palm Oil Production Planning

Abdul Talib Bon Department of Production and Operations Management

Universiti Tun Hussein Onn Malaysia 86400 Parit Raja, Johor, Malaysia

[email protected]

Silvia Firda Utami Department of Production and Operations Management

Universiti Tun Hussein Onn Malaysia 86400 Parit Raja, Johor, Malaysia

[email protected]

Abstract— This paper discusses the application of Fuzzy Inference System Tsukamoto for decision making in production planning at crude palm oil (CPO) company. In this study, the optimal amount of CPO production in year 2014 are available. The objective is to help the production manager’s for determine the optimal number of CPO production, so that can be effective and efficient in production planning. Data demand, inventory and production in 2014 as the input for FIS Tsukamoto to determine the optimal number of productions. There are three steps of FIS Tsukamoto to generate the inputs. Firstly is the Fuzzification, in this step the data input that call crisp set are transformed to the fuzzy set using the fuzzy theory. Secondly is the Inference, in this step all the fuzzy set must be sent to knowledge base that contains n fuzzy rule in the form of IF-THEN. Fire strength (antecedent membership values or α) will be sought at each rule. If more than one rule, it will be an aggregation of all the rules there are nine rules used in this study. Lastly is the defuzzification, the results of the second step above which still in fuzzy sets, then recovered into the crisp sets as an output by using the Center of Gravity Method. In conclusion, the result of the calculation shows that the FIS Tsukamoto can be optimized in terms of the amount of production and profits at Palm Oil Mill Company.

Keywords—Production Planning, crude palm oil, FIS Tsukamoto, demand, inventory

I. INTRODUCTION

Operation management has three fundamental works, namely planning, implementation of the plan, and monitoring the process. Planning is the first step in the production management. Planning is a prerequisite for execution and control. Without a plan, there is no basis for action and no basis for evaluating the results achieved [3]. The operation managers have the responsibility to make a plan and have important position in every company. Some of the tasks an operations manager was making decisions about planning, how many products will be produced, how much material will be used, how many workers and many more [7].

Every day an operations manager, especially production managers make decisions [6]. Not easy for a production manager to make decisions because they are constantly faced with uncertainty and a variety of other complex production issues [5]. These problems include the decline in the number of productions which cause a decrease in the profit of the company. As is the case in crude palm oil firm, the problems of vagueness on the number of productions also always happen because of many factors caused. Required methods effective and efficient to alleviate these problems. For this research, methods of Fuzzy Inference System Tsukamoto were applied to the production planning, CPO to determine the amount of optimal production.

Fuzzy Inference System Tsukamoto method is also one of a method for decision making. Especially in many uncertainties and vagueness situations, this method is very flexible and has a tolerance for any data existing [1][2]. The Fuzzy Inference System uses reasoning monotony in the process of solving problems. The workings of this method is to use the data production, inventory and demand data as input and then processed through the three stages of process to optimize the amount of the input of the third. The first phase, i.e. the transformation of Fuzzification input data be fuzzy sets. The second stage is the fuzzy inference process by entering the sets that has been formed into the rule. Finally, Defuzziification is the process of aggregation of fuzzy sets, fuzzy sets and changed into a crisp sets.

Fuzzy Logic was first introduced in 1965 by Professor Lotfi Asker Zadeh a professor at the University of California, Berkeley, USA. In the Tsukamoto method, the implication of each rule shaped implications "Cause and Effect" / Implications " Input - Output " in which the antecedent and the consequent need something to do. Each rule is represented using fuzzy sets, the membership functions are monotone. Then, to determine the outcome of firm (Crisp Solution) used in the formula assertion

2206© IEOM Society International



978-1-4673-7762-1/16/$31.00 ©2016 IEEE

(defuzifikation) called " centered average method ". [10] Fuzzy set theory can be applied in the fields of economics , decision support systems , engineering and science [10]. Many previous studies related to the determination of the amount of production based on fuzzy logic, among others: research by Afiat Triyuniarta, et al (2009) obtained a fuzzy logic application software with four fuzzy sets for decision support system of determining a poor family in the city of Yogyakarta, which can assist the government in knowing the percentage of poor families based on years of data collection. Then, research by Fajaar Silikin (2011) compared the amount of production by Mamdani and Sugeno method using 3 variables with two fuzzy set towards the data of Genta Mas cigarette production in January 2011. In addition, research on the application of the Tsukamoto method (fuzzy logic) in a decision support system to determine the amount of production of goods based on inventory data and the number of requests [11].

II. RESEARH METHODOLOGY

In obtain the optimal amount of production in order to remain stable so that it can increase the profit of the company. The following three stages of FIS Tsukamoto, which are Fuzzification, Inference and Defuzzification:

A. Fuzzification

Fuzzification is the process of converting a non-fuzzy variables (numerical variables) into a fuzzy variables (linguisticvariables) [4]. The variables that will be used must be defined first such as variable demand, inventory and production. Each variable has a fuzzy set. As an example, for variable inventory, the used fuzzy set is down, Moderate, and Up. Then, after that seek membership value of each set of fuzz, on each variable. Membership value obtained by representing each fuzzy set with a membership function. There are six functions that can be used which are, representation of Linear, triangular curve, the curve shape of the shoulder, s-curve, trapezoidal curve, and the curve of the oval shape

B. Inference

Inference is the process of combining many rules based on available data. Fuzzy inference system receives input crisp. Thisinput is then sent to a knowledge base that contains n fuzzy rules in the form of IF-THEN. After determining the rules that will be used, then find the value of the antecedent membership or fire strenght (α), and the estimated value of goods to be manufactured (z) of each rule, using the membership value of each fuzzy set.

C. Defuzzyfication

Determine the crisp output value will be the number of goods produced (Z), by changing the input (in the form of fuzzysets derived from the composition of fuzzy rules) into a number of fuzzy sets in the domain. Defuzzyfication method used in the Tsukamoto method is centered average method. This formulation is to determine the crisp output value that will be the number of goods produced (Z), by changing the input (in the form of fuzzy sets derived from the composition of fuzzy rules) into a number of fuzzy sets in the domain. This is the centered average method equation :

=

==n

i

n

i

i

zii

Z

1

1

.

α

α (1)

III. RESEARCH AND DISCUSSIONS

After running the FIS Tsukamoto, the result is shown the different results of the calculation between the companies with the FIS Tsukamoto method. Significant differences can be seen more clearly Figure 1 below, shows that the company produces the goods is unstable, sometimes there are high and low. As for the total inventory is also the same as the total production, which is unstable, sometimes the amount of residual CPO produced very little, so that if it happens then to the next month, the company had to work hard to produce higher CPO. This happens because the company only has a little reserve to meet the next higher demand. As you know that the raw material of CPO is a perishable. Materials can only survive within 24 hours after being picked from the fields. Raw materials are also imported from the fields far away from the mill, thus becoming a long production lead time. In addition, the amount of raw materials is uncertain, because of factors such as weather, pests and others. Therefore, the company produces CPO to taste according to the number of customer orders.




978-1-4673-7762-1/16/$31.00 ©2016 IEEE

Figure 1. Plot Data for Production & Inventory Crude Palm Oil 2014 (Company). Source: The result of analysis, 2015

While the results of optimization using FIS Tsukamoto is much different with the results of the calculation of the

company. Seen in Figure 2, the plot shows results fairly stable production data and the amount of inventory that is high enough. The resulting total production is the optimal amount of production, which can be a standard amount of production to meet customer orders. So that later the company remains productive and earn a profit. The amount of inventory that has been optimized by FIS Tsukamoto is a high number. However, it is appropriate for the crude palm oil company, because with such a high number of inventory, the company had reserves of CPO for sale for the next month.

Figure 2. Plot Data for Production & Inventory Crude Palm Oil 2014 (FIS Tsukamoto)

JAN FER MAR APR MAY JUN JUL AUG SEPT OCT NOV DEC

INVENTORY (Tonnes) 1379,5 247,95 391,16 317,42 1181,9 338,25 643,26 1416,9 530,37 389,42 1005,2 492,36

PRODUCTION (Tonnes) 3874,1 3552,7 3974,3 3469,4 3672,1 3780,0 4043,8 4404,5 4563,6 4238,4 4153,0 4115,7

0,00

1000,00

2000,00

3000,00

4000,00

5000,00

6000,00

7000,00To

tal

Plot Data Production & Inventory 2014 (Company)

JAN FER MAR APR MAY JUN JUL AUG SEPT OCT NOV DEC

INVENTORY (Tonnes) 1391,0 900,82 1140,7 1530,7 2630,2 2167,1 2409,7 2616,7 1275,9 1061,6 1417,6 918,30

PRODUCTION (Z) (Tonnes) 3886,2 4194,1 4071,0 3933,1 3907,1 4160,6 3981,4 3837,9 4109,4 4165,0 3893,2 4129,3

0

1000

2000

3000

4000

5000

6000

7000

Tota

l

Plot Data Production & Inventory 2014 (FIS Tsukamoto)




978-1-4673-7762-1/16/$31.00 ©2016 IEEE

In detail, the comparison of the products and profits of the company and FIS Tsukamoto calculation, as shown in Table 4.20 below:

Table 1. Total Product and profit from the company 2014.

Source: (Researcher, 2015 & MPOC, 2014)

MONTH PRICES (RM/Tonnes) TOTAL PRODUCT (Tonnes) PROFIT (RM)

JAN 2.534 5253.62 13,312.67FER 2.635 3800.74 10,014.95MAR 2.862 4365.47 12,493.98APR 2.696 3786.88 10,209.43MAY 2.605 4854.10 12,644.93JUN 2.436 4118.33 10,032.25JUL 2.404 4687.08 11,267.74AUG 2.174 5821.52 12,655.98SEPT 2.059 5094.00 10,488.55OCT 2.179 4627.87 10,084.13NOV 2.219 5158.32 11,446.31DEC 2.155 4608.14 9,930.54

56176.07 134,581.46TOTAL

COMPANY

Table 2. Total Product and profit from the results of calculation of FIS Tsukamoto 2014.

Source: (Researcher, 2015 & MPOC, 2014)

MONTH PRICES (RM/Tonnes) TOTAL PRODUCT (Tonnes) PROFIT (RM)JAN 2.534 5277.27 13,372.60 FER 2.635 5094.93 13,425.14

MAR 2.862 5211.84 14,916.29 APR 2.696 5463.94 14,730.78 MAY 2.605 6537.36 17,029.82 JUN 2.436 6327.73 15,414.35 JUL 2.404 6391.11 15,364.23 AUG 2.174 6454.76 14,032.65 SEPT 2.059 5385.38 11,088.50 OCT 2.179 5226.68 11,388.94 NOV 2.219 5310.81 11,784.69 DEC 2.155 5047.67 10,877.73

67729.48 163,425.71 TOTAL

FUZZY INFERENCE SYSTEM TSUKAMOTO

As seen from Table 2 and 3, there is a very significant difference between the results of the calculation of the company and the FIS Tsukamoto. Total company's products for one year is 56176.07 tonnes, with profits when sold for RM 134, 581.46. Meanwhile, FIS Tsukamoto produced a total of 67729.48 tonnes as much product and profit around RM 134, 581.46. There is a difference from the results, because the calculation result FIS Tsukamoto slightly more compared to the results of the calculation of the company. The difference is as much as 11553.41 tonnes and approximately RM 28, 844.25. The result of the calculation shows that the FIS Tsukamoto can be optimized in terms of the amount of production and profits at companies Sindora Palm Oil Mill.




978-1-4673-7762-1/16/$31.00 ©2016 IEEE

IV. CONCLUSIONS

Fuzzy Inference System Tsukamoto is a method of decision making to determine the optimal amount of production. The conclusions of this study are the method can be applied to the FIS Tsukamoto CPO company and disappear and more effective compared to methods used at the company. FIS Tsukamoto is also more give you an advantage in terms of profit. Therefore the methods appropriate for the FIS Tsukamoto help operation managers in production planning.

ACKNOWLEDGMENT

This research is supported and sponsored by Fundamental Research Grant Scheme (FRGS) Phase 1/2014 Research Vot. 1469, under Ministry of Education, Malaysia

REFERENCES [1] Abdul Talib Bon & Silvia Firda Utami 2014. Analytical Hierarchy Process and Fuzzy Inference System Tsukamoto for Production

Planning. International Trade & Academic Research Conference (ITARC) 3rd -4th November 2014, London-UK.[2] Abdul Talib Bon & Silvia Firda Utami, 2015. An analytical hierarchy process and fuzzy inference system tsukamoto for production

planning: a review and conceptual research. International Journal of Business and Economic Development Vol. 3 Number 1 March2015. Pages: 1-11

[3] Fogarty, D,W, Blackstone, J.H., Hoffmann, T.R. 1991. Production and Inventory Management. 2nd Ed. USA: South-WesternPublishing Co.

[4] Frans Susilo, S.J. 2006. Association and Blurred Logic and Its Application. 2nd Ed. Yogyakarta: Graha Ilmu.[5] Grote, Gudela. 2009. Management of Uncertainty: Theory & Application In The Design of System and Operation, United Kingdom:

Springer.[6] Harvard Business School. 2006. Decision Making: 5 Step to Better Results. Boston: Harvard Business School Publishing Corporation.[7] Kamauff, Jhon. 2010. Managers Guide to Operations Management. USA: Mc. Graw Hill.[8] Malaysian Palm Oil Board. 2013. Production of Crude Palm Oil for December 2013: January-June 2012-2013. Retrieved 16 March,

2014.From http://bepi.mpob.gov.my/index.php/statistic/production/118-production-2013/603-production-of-crude-oil-palm-2013.html[9] Malaysian Palm Oil Council. 2014. Palm Oil Price 2014. Received 20 March, 2015. From www.mpoc.org.my.[10] Setiadji. 2009. Samar Association & Logic and Its Application. Graha Science Publishers : New York[11] Abdurrahman, Ginanjar. 2011. Journal Application Tsukamoto method (fuzzy logic) In a decision support system to determine the

amount of production of goods Based on inventory data and the number of requests.http://library.walisongo.ac.id/digilib/download.php?id=7385.Indonesia

BIOGRAPHY

Dr. Abdul Talib Bon is Professor of Technology Management in the Department of Production and Operations Management at the Universiti Tun Hussein Onn Malaysia. He has a PhD in Computer Science, which he obtained from the Universite de La Rochelle, France. His doctoral thesis was on topic Process Quality Improvement on Beltline Moulding Manufacturing. He studied Business Administration in the Universiti Kebangsaan Malaysia for which he was awarded the MBA. He’s bachelor degree and diploma in Mechanical Engineering which his obtained from the Universiti Teknologi Malaysia. He received his postgraduate certificate in Mechatronics and Robotics from Carlisle, United Kingdom. He had published more 150 International Proceedings and International Journals and 8 books. His research interests include manufacturing, forecasting, simulation, optimization, TQM and Green Supply Chain. He is a member of IEOM, IIE, IIF, TAM, MIM and council member’s of MSORSM.


applying fuzzy inference system tsukamoto for decision ...ieomsociety.org/ieom_2016/pdfs/667.pdf ·...

Documents