Citation: Wen, Y.-C.; Chen, W.-H.
Service Innovation and Quality
Assessment of Industry 4.0
Microservice through Data Modeling
and System Simulation Evaluation
Approaches. Appl. Sci. 2022, 12, 4718.
https://doi.org/10.3390/app12094718
Academic Editors: João Carlos de
Oliveira Matias and Paolo Renna
Received: 24 March 2022
Accepted: 6 May 2022
Published: 7 May 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Service Innovation and Quality Assessment of Industry 4.0
Microservice through Data Modeling and System Simulation
Evaluation Approaches
Yen-Chun Wen * and Wun-Hwa Chen
Technology Management, Department of Business Administration, National Taiwan University,
Taipei City 106, Taiwan; andychen@ntu.edu.tw
* Correspondence: d07741007@ntu.edu.tw; Tel.: +886-2-2642-8999 (ext. 7259)
Abstract:
This study proposes a system construction approach under Industry 4.0 infrastructure
that is validated by the proposed framework of microservice quality assessment with framework
with data modeling and simulation methodology to achieve innovation and value cocreation goals.
The framework, which combines a dynamic process flow with service-dominant logic design and
reliability assessment using a multilayer perceptron (MLP) prediction model can assist decision
makers in optimizing their service innovation and decision-making processes. The service inno-
vation and evaluation approaches have implications for optimizing the corporation cooperation.
The corporation can form a much more comprehensive manufacturing infrastructure or system by
considering the requirements and assessment results of third parties. To help the corporation redefine
its value proposition and system structure, we must examine the system interaction between different
hierarchical layers within the Industry 4.0 system infrastructure. This study used a production dataset
from the NASDAQ-listed electronics corporation and two top German and Japanese automobile
firms. The proposed system framework had already been validated and introduced to improve 12%
of service quality. The system integrated with anticipated functions will accelerate service innovation
and optimization by combining MLP and Kaplan–Meier estimation methodologies by extracting the
characteristics of realistic datasets.
Keywords:
smart manufacturing; service-dominant logic; reliability; service system; artificial intelli-
gence; neural networks
1. Introduction
Decision makers of organizations will encounter various integration problems during
decision-making and troubleshooting processes [
1
] owing to the limitation in the devel-
opment of a complex manufacturing system. Enterprises and firms should define relative
frameworks to address the challenges of information imbalance and cognition bias posed
by the evolution of internet of things (IoT) techniques and telecommunication technology.
Several enterprise systems, such as product lifecycle management, manufacturing execu-
tion system (MES) and enterprise resource planning systems [
2
,
3
], assist firms in achieving
Industry 4.0 criteria by tackling integration issues. However, customers prefer specific
customized functions rather than generalized functions to tackle the integration issues [
4
].
Most of the firms collect research and development (R&D) information or relevant business
development datasets to analyze the requirements of customers to reduce rework costs
associated with transferring various systems to the final phase. In contrast to the monolithic
system, an application-specific microservice architecture can assist firms in expanding their
services and defining new value propositions [
5
]. In this study, the service was modularized
into several microservices with an integrated application programing interface (API) after
adopting a microservice architecture. Furthermore, service providers can split or combine
different applications based on the requirements of their customers (Figure 1). However,
Appl. Sci. 2022, 12, 4718. https://doi.org/10.3390/app12094718 https://www.mdpi.com/journal/applsci
