^{1}

^{1}

^{*}

Welding operation of metals, gives rise to high temperature that results in melting of mating parts. The final composition of the joints formed in terms of its microstructure and properties at the fusion zone depends greatly on the degree of dilution of the weld. With an expert prediction technique, it may be possible to predict even before weld, the integrity of weld joint from the proposed process parameter. The aim of this study is to predict the percentage dilution (%D) of TIG mild steel welds using fuzzy logic. In this study, the weld specimen was produced using the TIG welding process guided by the central composite experimental design and thereafter percentage dilution (%D) was measured and fed to the fuzzy logic software. The process parameters include the voltage, current, gas flow rate and welding speed. The results obtained showed that the fuzzy logic tool is a good predictive tool and the model developed has proven to be very efficient in handling works of this nature, thereby saving time, energy and money wasted in pre-welding procedures. It would be encouraging to compare other quality parameters with process parameters to see how it can further help in quality improvement.

[

The Tungsten Inert Gas (TIG) machine was used, thirty experimental runs were carried out, each experimental run comprising the current, voltage, welding speed and gas flow rate, used to join two pieces of mild steel plates measuring 60 mm × 40 mm × 10 mm. The percentage (%) dilution was measured respectively. The welding process parameters are shown in

The general structure of fuzzy inference systems is shown in

Parameters | Unit | Symbol | Coded value Low (−1) | Coded value High (+1) |
---|---|---|---|---|

Current | Amp | A | 140 | 160 |

Gas flow rate | Lit/min | F | 12 | 14 |

Voltage | Volt | V | 20 | 24 |

Welding speed | cm/min | S | 150 | 170 |

logic system (FLS) can be defined as the nonlinear mapping of an input data set to a scalar output data.

The process of fuzzy logic is explained as follows: Firstly, a crisp set of input data are gathered and converted to a fuzzy set using fuzzy linguistic variables, fuzzy linguistic terms and membership functions. This step is known as fuzzification. Afterwards, an inference is made based on a set of rules. Lastly, the resulting fuzzy output is mapped to a crisp output using the membership functions, in the defuzzification step. A Fuzzy Logic System consists of five main parts:

1) Define the inputs and output (linguistic variables) and terms (initialization);

2) Convert the crisp variable to fuzzy sets (Fis) (fuzzification);

3) Create membership function (initialization);

4) Construct the rule base (initialization);

5) Predicting Dilution using Fuzzy Logic.

In this study we developed a fuzzy logic system to predict the percent dilution based on four input variables namely: voltage, current, welding speed and gas flow rate.

Linguistic variables are the input or output variables of the system whose values are words or sentences from a natural language, instead of numerical values. A linguistic variable is generally decomposed into a set of linguistic terms. Consider a welding process aimed at predicting the dilution. Let voltage (v), current (c), welding speed (ws) and gas flow rate (gfr) be the linguistic variables which represents the weld factors. To qualify the voltage, current, welding speed and gas flow rate, terms such as (very low, low, moderate, high and very high) are used in real life. These are the linguistic values of the voltage, current, welding speed and gas flow rate. Then,

V (v) = {very low, low, moderate, high, very high};

C (c) = {very low, low, moderate, high, very high};

WS (ws) = {very low, low, moderate, high, very high};

GFR (gfr) = {very low, low, moderate, high, very high}.

In the same way, the output variable (Dilution) can be qualify in real term as: D (d) = {very low, low, moderate, high, very high}.

The terms in bracket represent the set of decompositions for the linguistic variable voltage, current, welding speed, gas flow rate and dilution. Each member of this decomposition is called a linguistic term. For this problem, the linguistic variables and their range of values include:

1) Voltage; this range from 20 to 24 volts.

2) Current; this range from 140 to 160 amps.

3) Welding speed; this range from 150 to170 mm/min.

4) Gas flow rate; this range from 12 to 14 L/min.

5) Dilution; this range from 43.12 to 98.22 mm.

The range of the input and output variable were extracted from the welding process parameters limits experimental design summary presented in

To convert the crisp variables (actual experimental data) into fuzzy sets, adaptive neuro fuzzy inference system (Anfis) was employed to generate a fuzzy inference system (FIS). To generate the FIS structure, the raw data were presented as input parameters in anfisedit tool box. A section of the raw data presented to MATLAB as input parameters is presented in

fuzzy form. To generate the fuzzy inference system (FIS), grid partition was selected and the generate FIS button was activated. Five membership functions were selected for each input variable. For this problem, the triangular membership function (trimf) was used. The simplicity and flexibility of the triangular membership function coupled with its ability to define wider range of decomposed sets of linguistic variables account for its selection. For the output variable, five membership functions were also used. Unlike the input variables, the constant membership function (conmf) was used to define the output variable owing to its simplicity as presented in

Membership functions are used in the fuzzification and defuzzification steps of a Fuzzy Logic Systems (FLS), to map the non-fuzzy input values to fuzzy linguistic terms and vice versa. A membership function is used in most cases to quantify a linguistic term. An important characteristic of fuzzy logic is that a numerical value does not have to be fuzzified using only one membership function. In other words, a value can belong to multiple sets at the same time.

As mentioned earlier, five membership functions were selected for each input and output variable namely; very low, low, moderate, high and very high. Figures 6-13 show the definition of the membership function for voltage, current, welding speed and gas flow rate.

Summary results of membership function and membership sets for voltage, current, weld speed, gas flow rate and percentage dilution are presented in

For the critical rules constructed for predicting dilution using fuzzy logic, the simplified form of

Membership Function | Membership Sets | ||||
---|---|---|---|---|---|

Voltage | Current | Welding Speed | GFR | Dilution | |

Very Low Low Moderate High Very high | (16 18 20) (18 20 22) (20 22 24) (22 24 26) (24 26 28) | (120 130 140) (130 140 150) (140 150 160) (150 160 170) (160 170 180) | (130 140 150) (140 150 160) (150 160 170) (160 170 180) (170 180 190) | (10 11 12) (11 12 13) (12 13 14) (13 14 15) (14 15 16) | (43.12) (56.89) (70.67) (84.44) (98.22) |

1) If voltage is low and current is high and welding speed is high and gas flow rate is high, dilution is very low.

2) If voltage is moderate and current is moderate and welding speed is moderate and gas flow rate is very high, dilution is low.

3) If voltage is high and current is high and welding speed is low and gas flow rate is low, dilution is moderate.

4) If voltage is high and current is low and welding speed is high and gas flow rate is high, dilution is high.

5) If voltage is very high and current is moderate and welding speed is moderate and gas flow rate is moderate, dilution is very high.

6) If voltage is low and current is high and welding speed is low and gas flow rate is low, dilution is moderate.

7) If voltage is low and current is low and welding speed is low and gas flow rate is low, dilution is low.

8) If voltage is low and current is low and welding speed is high and gas flow rate is high, dilution is low.

In a fuzzy logic system, a rule base is constructed to control the output variable. A fuzzy rule is a simple IF-THEN rule with a condition and a conclusion. Based on the result of

Figures 15-22 show the predictions that were made using fuzzy logic systems.

From the result of

From the result of

current of 150 Amp, welding speed 160 mm/min and gas flow rate of 15 L/min, the predicted dilution was 56.90 mm.

From the result of

From the result of

current of 140 Amp, welding speed 170 mm/min and gas flow rate of 14 L/min, the predicted dilution was 84.40 mm.

From the result of

From the result of

From the result of

current of 140 Amp, welding speed 150 mm/min and gas flow rate of 12 L/min, the predicted dilution was 56.90 mm.

From the result of

The surface plot which shows the relationship between the input and the output variable is presented in

Result of

The randomized selected performance evaluation of fuzzy logic and experimental means in predicting dilution are shown in

Learning parameters on the accuracy of weld predictions were studied along the variations of the input parameters for fuzzy logic and it was able to produce a model capable of predicting percentage weld dilution beyond the range of the given parameters. The randomized selected results obtained from fuzzy logic for minimized percentage weld dilution are presented in

Variable Combinations Dilution | |||||||
---|---|---|---|---|---|---|---|

R/N | Voltage | Current | W S | GFR | Exp (Dilution) | Fuzzy (Dilution) | % Error |

30 | 20 | 160 | 170 | 14 | 43.12 | 43.10 | 0.0464 |

12 | 22 | 150 | 160 | 15 | 57.66 | 56.90 | 1.3356 |

16 | 24 | 160 | 150 | 12 | 70.61 | 70.70 | 0.1273 |

18 | 24 | 140 | 170 | 14 | 84.31 | 84.40 | 0.1066 |

7 | 26 | 150 | 160 | 13 | 98.22 | 98.20 | 0.0203 |

24 | 20 | 160 | 150 | 12 | 67.79 | 70.70 | 4.1159 |

27 | 20 | 140 | 150 | 12 | 54.52 | 56.90 | 4.1827 |

26 | 20 | 140 | 170 | 14 | 58.17 | 56.90 | 2.2319 |

13 L/min, gave a percentage dilution of 98.20 using the fuzzy logic tool, which was very close to our experimental result. It provides enough room for process parameter simulation for optimum response, which would also save cost and material wastage that result from try and error experimentation.

This research work has thrived in developing an optimization and prediction of welds of extremely high quality of TIG welding process using fuzzy logic through which the effects of their various process parameters and their interactions were determined and predictions made on expected quality of the weld at known process parameters.

A novel concept of an intelligent model has been developed to predict welding process parameters (current, voltage, welding speed and gas flow rate) and bead parameters (%D) for improved quality welds using fuzzy logic. The results of this study will help reduce the cost of expensive analytical methods employed during welding operation and it will help fabrication industries to maximize the quality of their products with minimal stress and save them time normally applied to do a trial and error work pre to welding.

The authors declare no conflicts of interest regarding the publication of this paper.

Nweze, S. and Achebo, J. (2019) The Use of Fuzzy Logic in Predicting Percentage (%) Dilution of Weld during Tig Welding Process. Materials Sciences and Applications, 10, 406-422. https://doi.org/10.4236/msa.2019.105030