Citation: Ning, F.; Qu, H.; Shi, Y.; Cai,
M.; Xu, W. Feature-Based and
Process-Based Manufacturing Cost
Estimation. Machines 2022, 10, 319.
https://doi.org/10.3390/
machines10050319
Academic Editors: Kelvin K.L. Wong,
Dhanjoo N. Ghista, Andrew W.H. Ip
and Wenjun (Chris) Zhang
Received: 24 March 2022
Accepted: 25 April 2022
Published: 28 April 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
Feature-Based and Process-Based Manufacturing
Cost Estimation
Fangwei Ning, Hongquan Qu *, Yan Shi, Maolin Cai and Weiqing Xu
School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China;
nfangwei@163.com (F.N.); yesoyou@163.com (Y.S.); caimaolin@buaa.com.cn (M.C.);
weiqing.xu@buaa.edu.cn (W.X.)
* Correspondence: qhongquan@buaa.edu.cn
Abstract:
The demand for mass custom parts is increasing, estimating the cost of parts to a high degree
of efficiency is a matter of great concern to most manufacturing companies. Under the premise of
machining operations, cost estimation based on features and processes yields high estimation accuracy,
but it necessitates accurately identifying a part’s machining features and establishing the relationship
between the feature and the cost. Accordingly, a feature recognition method based on syntactic pattern
recognition is proposed herein. The proposed method provides a more precise feature definition and
easily describes complex features using constraints. To establish the relationships between geometric
features, processing modes, and cost, this study proposes a method of describing the features and
the processing mode using feature quantities and adopts deep learning technology to establish the
relationship between feature quantities and cost. By comparing a back propagation (BP) network
and a convolutional neural network (CNN) it can be concluded that a CNN using the “RMSProp”
optimizer exhibits higher accuracy.
Keywords:
manufacturing cost; feature recognition; cost estimation; machine learning; computer
aided manufacturing
1. Introduction
With the formation of the global economic market and the rapid development of the
internet, various new technologies have continued to emerge, and competition in the field
of machinery manufacturing has become increasingly fierce. This is mainly manifested in
the acceleration of product research and development, shortening of product life cycles,
dynamic changes and diversifications of customer demand, continuous innovation of
complex and new technologies, and frequent renewal of products. To adapt to the current
competitive market environment, parts manufacturers must save time, starting from cost
estimation until the completion of the entire process of parts manufacturing, and strive to
produce products that meet the needs of customers in the shortest possible time. However,
most of the existing methods for estimating costs of parts consider only the geometric
features of the parts or have low accuracy, which leads to errors or even complete mistakes
in the cost estimation results. In this study, we aimed to introduce feature quantities into
the machining process to describe the features of a part and achieve efficient and accurate
cost estimation of parts. The method first identified features based on syntactic patterns
and described complex features through the feature constraints of the part, thus allowing
for more accurate feature definition and more efficient identification. Thereafter, feature
quantities were established to describe features and machining patterns to determine the
relationship among geometric features, machining patterns, and the cost of a part.
Machines 2022, 10, 319. https://doi.org/10.3390/machines10050319 https://www.mdpi.com/journal/machines
