RESEARCH ARTICLE Arunachalam VELMURUGAN, Marimuthu LOGANATHAN, E. James GUNASEKARAN Prediction of performance, combustion and emission char- acteristics of diesel-thermal cracked cashew nut shell liquid blends using artificial neural network © Higher Education Press and Springer-Verlag Berlin Heidelberg 2016 Abstract This paper explores the use of artificial neural networks (ANN) to predict performance, combustion and emissions of a single cylinder, four stroke stationary, diesel engine operated by thermal cracked cashew nut shell liquid (TC-CNSL) as the biodiesel blended with diesel. The tests were performed at three different injection timings (21°, 23°, 25°CA bTDC) by changing the thickness of the advance shim. The ANN was used to predict eight different engine-output responses, namely brake thermal efficiency (BTE), brake specific fuel consumption (BSFC), exhaust gas temperature (EGT), carbon monoxide (CO), oxide of nitrogen (NO x ), hydrocarbon (HC), maximum pressure (P max ) and heat release rate (HRR). Four pertinent engine operating parameters, i.e., injection timing (IT), injection pressure (IP), blend percentage and pecentage load were used as the input parameters for this modeling work. The ANN results show that there is a good correlation between the ANN predicted values and the experimental values for various engine performances, combustion parameters and exhaust emission characteristics. The mean square error value (MSE) is 0.005621 and the regression value of R 2 is 0.99316 for training, 0.98812 for validation, 0.9841 for testing while the overall value is 0.99173. Thus the developed ANN model is fairly powerful for predicting the performance, combustion and exhaust emissions of internal combustion engines. Keywords cashew nut shell liquid (CNSL), artificial neural networks (ANN), thermal cracking, mean square error (MSE) 1 Introduction Automobiles are the prime movers of the economic growth of any country. With the rapid industrialization of many of the third world countries, the requirement for conventional source of oil has increased enormously. Coupled with this, the inability of the oil producers to meet the demand has evived the interest in non-conventional oil resources such as non-edible oil such as Pungamia oil, cotton seed oil, Jatropha oil, and etc. Of these non-conventional sources, the least explored oil resource is cashew nut shell liquid (CNSL). Even though CNSL undergoes all the conserva- tive responses of phenols, CNSL aldehyde concentration products and CNSL-based phenolic resins are used in applications such as surface coatings, and adhesives. It can also be used as an alternative fuel in internal combustion engines after suitable treatment. One of the very simple methods is to directly use the CNSL in the engine by pre- heating it. But this method is afflicted with problems of gum formation and corrosion of cylinder liner due to the sulfur content in the fuel. Some researchers [1] have used the concept of mixing CNSL with diesel in varying proportions and preheating the oil before injecting directly in the engine cylinder. With these modifications, they reported improvements in brake thermal efficiency (BTE). Efforts are made to utilize CNSL as the raw material for producing biodiesel is rare, compared to other non-edible oils which have gained much popularity. Vedharaj et al. [2] have stated that it is very essential to use the renewable source of energy from CNSL which is extracted from cashew nut shell biomass and to utilize it as another fuel for diesel engine. CNSL, a valuable raw material for the petrochemical industries, has been used as a potential source for producing biodiesel and has also been directly used in diesel engine without any modification of the engine [3]. The research in IC engines has been conducted over the many years by using various methods to find the engine performance for different fuels and operating Received April 24, 2015; accepted August 28, 2015 Arunachalam VELMURUGAN (✉), Marimuthu LOGANATHAN, E. James GUNASEKARAN Department of Mechanical Engineering, Annamalai University, Anna- malainagar 608002, India E-mail: velathi.lec@gmail.com, vel_lec@rediffmail.com Front. Energy 2016, 10(1): 114–124 DOI 10.1007/s11708-016-0394-x