Let us suppose a situation in which it is necessary to check the car before going on a journey, a situation in which breakdowns appear but also mysteriously disappear, a situation where solving problems with the vehicle is only possible by looking at the data obtained by reading sensors, routine vehicle checking (insight into data irregularity), "real-time" monitoring of car condition…The main goal of this paper is the early detection of erroneous readings of vehicle airflow systems in real time and constant monitoring of the subject vehicle, by coupling and using trained models based on machine learning tools of artificial intelligence and using "Infinity" device.

Inertia weight is a significant parameter of the particle swarm optimization (PSO) algorithm. Its controllers the search capabilities of PSO and provides a balance between exploration and exploitation. There are a plethora of studies on inertia weight variants of continuous PSO (CPSO). However, a few numbers of studies have been presented for binary PSO (BPSO). In existing BPSO variants, despite different positions of particles, every individual is treated equally by ignoring the dispersion of particles in the search space. To deal with each particle according to its fitness value, we have proposed a Rank-based Self-adaptive Inertia Weight to enhance the performance of the Novel BPSO (NBPSO). The proposed algorithm controls the movement of particles by defining the ranks of each particle based on their fitness. The performance of the proposed algorithm is evaluated on four benchmark test functions. The experimental results show that the proposed method performs better than the compared algorithms in terms of convergence speed.