Time prediction models of grapple skidder HSM 904 using multiple linear regressions (MLR) and adaptive neuro-fuzzy inference system (ANFIS)

The majority of productivity studies in forest operations use the ordinary least square regression in order to calculate time prediction models. Objective of this paper was to compare two methods, the adaptive neuro fuzzy inference system (ANFIS) and the multiple linear regression (MLR) pertaining to the modeling the loading time with the grapple skidder HSM 904. In order to investigate the influence of changes in membership functions (MF), inference system (IS) and optimization methods on the performance of the ANFIS model, four types of MF, two types of IS and two types of optimization methods were applied. Two stepwise (forward and backward) techniques were applied in the development of the MLR models. The data originated from a time study of 35 truckloads including 238 loading cycles with the specific forest machine. The comparison of the various modeling approaches indicated that the generated ANFIS with constant IS, Backpropagation training algorithm, and Gaussian membership function had a greater predictive power (R2 = 0.84) and higher performance than all calculated MLR models (R2 = 0.61). The results also showed that ANFIS could predict with a relatively high accuracy (R2 = 0.74) the loading time by adopting the “number of loaded logs” as the single input variable.

[1]  Mattias Eriksson,et al.  Productivity of harvesters and forwarders in CTL operations in northern Sweden based on large follow-up datasets , 2014 .

[2]  Rolf Björheden.  New work study methods help to decide processing technique in logging , 1988 .

[3]  Dillip K. Ghose,et al.  Prediction and optimization of runoff via ANFIS and GA , 2013 .

[4]  Mohammad Reza Ghaffariyan,et al.  Time Prediction Models and Cost Evaluation of Cut-To-Length (CTL) Harvesting Method in a Mountainous Forest , 2012, Small-scale Forestry.

[5]  M. Sugeno,et al.  Structure identification of fuzzy model , 1988 .

[6]  Kevin Boston,et al.  An Adaptive Network-based Fuzzy Inference System for Rock Share Estimation in Forest Road Construction , 2012 .

[7]  B. Talbot,et al.  Good practice guidelines for biomass production studies , 2012 .

[8]  Sergio Bermejo,et al.  Oriented principal component analysis for large margin classifiers , 2001, Neural Networks.

[9]  Meghdad Jourgholami.  Small-Scale Timber Harvesting: Mule Logging in Hyrcanian Forest , 2011, Small-scale Forestry.

[10]  Rudolf Kruse,et al.  Obtaining interpretable fuzzy classification rules from medical data , 1999, Artif. Intell. Medicine.

[11]  Akbar Najafi,et al.  TIME STUDY OF SKIDDER HSM 904 , 2007 .

[12]  Rien Visser,et al.  Determining the shape of the productivity function for mechanized felling and felling-processing , 2012, Journal of Forest Research.

[13]  M. Razack,et al.  Modeling daily discharge responses of a large karstic aquifer using soft computing methods: Artificial neural network and neuro-fuzzy , 2010 .

[14]  Rostam Mousavi.  Comparison of productivity, cost and environmental impacts of two harvesting methods in Northern Iran: short-log vs. long-log , 2009 .

[15]  Jyh-Shing Roger Jang,et al.  Self-learning fuzzy controllers based on temporal backpropagation , 1992, IEEE Trans. Neural Networks.

[16]  Raffaele Spinelli,et al.  Performance Modelling in Forest Operations Through Partial Least Square Regression , 2012 .

[17]  Seyed Rostam Mousavi Mirkala,et al.  Comparison of productivity, cost and environmental impacts of two harvesting methods in Northern Iran: short-log vs. long-log , 2009 .

[18]  M. W Gardner,et al.  Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences , 1998 .

[19]  Akbar Najafi,et al.  Productivity and cost of farm tractor skidding. , 2018 .

[20]  Kenan Melemez,et al.  A Comparison of Productivity in Five Small-Scale Harvesting Systems , 2013, Small-scale Forestry.