Utilizing Firefly Algorithm-Optimized ANFIS for Estimating Engine Torque and Emissions Based on Fuel Use and Speed

In this study, a method for predicting engine torque and emissions considering fuel consumption and engine speed parameters is presented. An adaptive neuro-fuzzy inference system (ANFIS) optimized with the Firefly algorithm is used. This strategy uses the global optimization capabilities of the Firefly algorithm, an algorithm inspired by biological phenomena, in combination with the ability of ANFIS to describe complicated non-linear relationships between inputs and outputs. The ANFIS system was trained on a dataset containing various engine operating conditions, with the Firefly algorithm fine-tuning the model parameters to ensure optimal effectiveness. The input parameters of the model consisted of fuel quantity and engine speed, while engine torque and nitrogen oxide emissions formed the output parameters. The results obtained showed high accuracy in predicting engine torque and emissions, confirming the effectiveness of the Firefly-optimized ANFIS model. This model makes an important contribution to engine performance monitoring and emissions management. It provides a powerful tool for real-time regulation and has the potential to improve fuel efficiency while reducing environmental impact. Future research efforts should extend the applicability of this model to a wider range of engine shapes and operating conditions.