Research Article
A Hybrid Machine Learning and Optimization Model to Minimize
the Total Cost of BRT Brake Components
Saeed Najafi-Zangeneh ,
1
Naser Shams Gharneh ,
1
Ali Arjomandi-Nezhad ,
2
and Erfan Hassannayebi
3
1
Industrial Engineering Department, Amirkabir University of Technology, Tehran 15875-4413, Iran
2
Industrial Engineering and Productivity Research Center, Amirkabir University of Technology, Tehran 15875-4413, Iran
3
Department of Industrial Engineering, Sharif University of Technology, Tehran 14588-89694, Iran
Correspondence should be addressed to Erfan Hassannayebi; hassannayebi@sharif.edu
Received 3 March 2021; Revised 5 September 2021; Accepted 12 October 2021; Published 22 October 2021
Academic Editor: Dongjoo Park
Copyright©2021SaeedNajafi-Zangenehetal.isisanopenaccessarticledistributedundertheCreativeCommonsAttribution
License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is
properly cited.
Public transport is amongst critical infrastructures in modern cities, especially megacities, home to millions of people. e
reliability of these systems is highly crucial for both citizens and service providers. If service providers overlook system reliability, a
considerable amount of expenses will be wasted. Several factors such as vehicle failure, accident, lack of budget weather factors,
and traffic congestion cause unreliability, among which vehicle failure plays a prominent role. e brake system is the most
vulnerable and vital component of a public transportation bus. Brake reliability depends on driver’s expertise, component quality,
passenger loading, line situation, etc. Driver’s expertise and components’ quality are the most important factors for brake system
reliability. is study aims to implement a hybrid machine learning and optimization model to minimize the total investment and
reliability-related costs in a bus rapid transit (BRT) system. A regression analysis method is proposed to capture the main
attributes of a joint brake system, including the level of education, training, and drivers’ experience. e failure rate is modeled as a
linear function of ETE and the quality of brake system subcomponents using a Lasso regression model. MILP optimization is then
provided for optimizing the total expected costs for a bus rapid transit (BRT) system. Furthermore, a practical case is studied to
investigate whether this optimization can reduce costs. e results confirm the efficiency of the hybrid optimization approach.
1. Introduction
Nowadays, cities are growing in size, and their populations
are increasing rapidly. As citizens need to travel inside their
cities more frequently, public transportation systems are
getting ever-increasing importance in society. Many pas-
sengers travel by bus rapid transit (BRT), a left-side door bus
operating in a fully separated lane. BRTreliability studies are
pivotal because an interruption in such systems would result
in passenger dissatisfaction and stakeholders would have to
deal with vast economic losses. To overcome this challenge,
the reliability of this transportation system is analyzed and
then optimized. Reliability refers to the probability that a
device performs its purpose adequately for the period
intended under the operating conditions encountered [1]. A
high level of reliability would be an excellent incentive for
citizens to choose public transport [2]. Several works ana-
lyzed in detail in the next section aim to quantify and en-
hance the reliability of urban bus systems as a backbone to
public transport.
ere are several reasons for BRT system irregularity,
including suboptimal scheduling, accident, bus failure, etc.
Based on the analysis of historical data, the main reason for
BRT irregularity and latency is bus failures, which is due to
brake failure in most cases. Not only is brake failure the
primary reason for bus failure, but also it completely in-
terrupts the bus. e driver cannot even take the bus to the
repair shop. erefore, brake component reliability opti-
mization is vital in enhancing overall reliability. However,
system owners have limited financial resources; therefore,
Hindawi
Journal of Advanced Transportation
Volume 2021, Article ID 5590780, 11 pages
https://doi.org/10.1155/2021/5590780