Xiaochen Zheng

Xiaochen Zheng
École Polytechnique Fédérale de Lausanne | EPFL · Institute of Mechanical Engineering

Doctor of Engineering

About

71
Publications
23,405
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
824
Citations
Citations since 2016
66 Research Items
819 Citations
2016201720182019202020212022050100150200250300
2016201720182019202020212022050100150200250300
2016201720182019202020212022050100150200250300
2016201720182019202020212022050100150200250300

Publications

Publications (71)
Article
Chatter is a harmful self-excited vibration that commonly occurs during milling processes. Data-driven chatter detection and prediction is critical to achieve high surface quality and process efficiency. Most existing chatter detection approaches are based on external sensors, such as accelerometers and microphones, which require installation of ex...
Article
Full-text available
Human activity recognition (HAR) has received more and more attention, which is able to play an important role in many fields, such as healthcare and intelligent home. Thus, we have discussed an application of activity recognition in the healthcare field in this paper. Essential tremor (ET) is a common neurological disorder that can make people wit...
Article
Full-text available
The development of an aircraft industrial system faces the challenge of integrative requirements validation with de-correlated modelling languages and distributed proprietary formats. This paper specifies an ontology-centric industrial requirements validation based on a cognitive digital twin approach, aiming at addressing the potentials of utilizi...
Article
Full-text available
During the design phase of an aircraft manufacturing system, different industrial scenarios need to be evaluated according to key performance indicators to achieve the optimal system performance. It is a highly complex process involving multidisciplinary stakeholders, various digital tools and protocols. To address the digital discontinuity challen...
Article
Full-text available
Digital Twin technology has been widely applied in various industry domains. Modern industrial systems are highly complex consisting of multiple interrelated systems, subsystems and components. During the lifecycle of an industrial system, multiple digital twin models might be created related to different domains and lifecycle phases. The integrati...
Article
Full-text available
Gas path fault diagnosis of a gas turbine is a complex task involving field data analysis and knowledge-based reasoning. In this paper, a data-knowledge hybrid driven method for gas path fault diagnosis is proposed by integrating a physical model-based gas path analysis (GPA) method with a fault diagnosis ontology model. Firstly, a physical model-b...
Chapter
Full-text available
Aircraft assembly is a complex process associated with different stakeholders, which strongly impacts the R&D cost for the entire aircraft lifecycle management. Traditional aircraft assembly process is designed based on a document-centric approach which cannot provide graphical notations for engineers to understand the entire assembly process. More...
Chapter
Full-text available
Model-based System of Systems Engineering (MBSoSE) enables to improve the efficiency of the architecture design, and the performance analysis and modeling of highly complex system of systems (SoS). Introducing situational awareness into complex system of systems engineering (SoSE) can facilitate users to understand and analyze the SoS models and ma...
Article
Full-text available
Digital Twin is one of the fundamental enabling technologies for Industry 4.0 as it allows the convergence between a physical system and its digital representation. A proper modelling method is the prerequisite for successful digital twin implementation. The manufacturing process determines critically the quality of the manufactured products. The i...
Article
Full-text available
The Prognostic and Health Management (PHM) system of an aircraft has complex structures and diverse functions. It is highly coupled with other systems, such as the avionics system and flight management system. The Model-based Systems Engineering (MBSE) method is effective to support the design and verification of the aircraft PHM system. As a power...
Preprint
Full-text available
The development of an aircraft industrial system is a complex process which faces the challenge of digital discontinuity in multidisciplinary engineering due to various interfaces between different digital tools, leading to extra development time and costs. This paper proposes an ontology-based system, aiming at functionality integration and design...
Preprint
Model-based System of Systems Engineering (MBSoSE) enables to improve the efficiency of the architecture design, and the performance analysis and modeling of highly complex system of systems (SoS). Introducing situational awareness into complex system of systems engineering(SoSE) can facilitate users to understand and analyze the SoS models and mak...
Preprint
2 The Prognostic and Health Management (PHM) system of an aircraft has complex structures 3 and diverse functions. It is highly coupled with other systems, such as avionics system and 4 flight management system. The model-based systems engineering (MBSE) method is effective 5 to support the design and verification of PHM systems of an aircraft. As...
Method
Full-text available
This document introduces how to import an existing ontology to Neo4j graph database and edit it by adding new classes and relationships. It is executed with Cypher language and enabled by the neosemantics package.
Code
This document introduces the general logic of the Python script for automatically generating Orbital Junction Process and the source code is attached in the end.
Article
Full-text available
Production scheduling enables a production system to allocate resources for the efficient and low-cost production. However, pure mathematical methods are typically utilized for production scheduling, which are not understandable and practical for different domain engineers. Moreover, heterogeneous information during production scheduling may result...
Article
Introduction There are some validated rating scales to assess severity of Essential tremor (ET), the most common cause of action tremor. Clinical evaluation through telematic consultations has been expanding in the last decade. Patients' self-assessment of tremor severity at home could constitute a useful tool in telemedicine. This paper aims to as...
Article
Full-text available
The development of an aircraft industrial system is a complex process which faces the challenge of digital discontinuity in multidisciplinary engineering due to various interfaces between different digital tools, leading to extra development time and costs. This paper proposes an ontology-based system, aiming at functionality integration and design...
Article
Full-text available
As a key enabling technology of Industry 4.0, Digital Twin (DT) has been widely applied to various industrial domains covering different lifecycle phases of products and systems. To fully realize the Industry 4.0 vision, it is necessary to integrate multiple relevant DTs of a system according to a specific mission. This requires integrating all ava...
Conference Paper
Full-text available
During the early phase of an aircraft program, industrial architects need to evaluate different industrial scenarios and perform trade-offs to optimize the future industrial architecture according to different key performance indicators. Expert knowledge accumulated during previous programs provides the foundation for the new one. It is a challengi...
Article
Full-text available
Actionable Cognitive Twins are the next generation Digital Twins enhanced with cognitive capabilities through a knowledge graph and artificial intelligence models that provide insights and decision-making options to the users. The knowledge graph describes the domain-specific knowledge regarding entities and interrelationships related to a manufact...
Method
Full-text available
This document explains how to install and configure a Neo4j graph database on an Azure cloud Ubuntu Virtual Machine (VM). Target readers are beginners of Azure cloud and Neo4j database. Following this instruction, you can create a VM on Azure cloud running Ubuntu system and then install and configure a Neo4j database which can be accessed remotely...
Preprint
With the continuous improvement of system scale and complexity, model-based system engineering (MBSE) is of great importance in the practice of system engineering (SE). MBSE has been widely concerned in industry, especially in the field of complex equipment. At the same time, in academia, research articles about MBSE come into being and grow rapidl...
Article
Full-text available
Model-based systems engineering (MBSE) provides an important capability for managing the complexities of system development. MBSE empowers the formalism of system architectures for supporting model-based requirement elicitation, specification, design, development, testing, fielding, etc. However, the modeling languages and techniques are heterogene...
Chapter
Full-text available
Digital twin (DT) provides a solution for supporting the interconnection between the physical world and the virtual world. When implementing DT integration, it is challenging to implement interface definition, information and service integration across DTs. This paper proposes a semantic modeling approach with a High-Level Architecture (HLA) to sup...
Preprint
Full-text available
During the early phase of an aircraft program, industrial architects need to evaluate different industrial scenarios and perform trade-offs to optimize the future industrial architecture according to different key performance indicators. Expert knowledge accumulated during previous programs provides a foundation for the new one. It is a challenging...
Conference Paper
Full-text available
The quality of a product is highly dependent on manufacturing processes. The recent development of industrial information technologies, such as Cyber-Physical Production Systems, Industrial Internet of Things, and Big Manufacturing Data Analytics has empowered the digitalization of manufacturing processes and promoted the concept of Digital Twin (D...
Preprint
Full-text available
Digital twin (DT) provides a solution for supporting the interconnec-tion between the physical world and the virtual world. When implementing DT integration, it is challenging to implement interface definition, information and service integration across DTs. This paper proposes a semantic modeling approach with a High-Level Architecture (HLA) to su...
Article
Full-text available
Nowadays, the manufacturing industry is constantly changing. Production systems must operate in a highly dynamic environment where unexpected events could occur and create disruption, making rescheduling inevitable for manufacturing companies. Rescheduling models are fundamental to the robustness of production processes. This paper proposes a model...
Preprint
Full-text available
Actionable Cognitive Twins are the next generation Digital Twins enhanced with cognitive capabilities through a knowledge graph and artificial intelligence models that provide insights and decision-making options to the users. The knowledge graph describes the domain-specific knowledge regarding entities and interrelationships related to a manufact...
Article
Full-text available
Rush orders are common events in enterprises that are utilizing make-to-order production strategy. They have multiple negative impacts to the production system such as higher product defect rate which corresponds to product quality drop, not meeting the due dates and cause customers’ dissatisfaction, higher production costs, waste of materials and...
Article
Full-text available
The strategic design of organizations in an environment where complexity is constantly increasing, as in the cyber-physical systems typical of Industry 4.0, is a process full of uncertainties. Leaders are forced to make decisions that affect other organizational units without being sure that their decisions are the right ones. Previously to this wo...
Preprint
Full-text available
Model-based systems engineering (MBSE) provides an important capability for managing the complexities of system development. MBSE empowers the formalisms of system architectures for supporting model-based requirement elicitation, specification, design, development, testing, fielding, etc. However, the modeling languages and techniques are quite het...
Preprint
Full-text available
During the entire lifecycle of system development, various digital twins could be developed to support different systems engineering activities, such as verification and validation. The increasing complexity of digital twins leads to a challenge to manage the consistency, changes and traceability across the entire lifecycle. In this paper, a semant...
Article
Full-text available
In contemporary manufacturing systems, re-scheduling of the production has become an unavoidable and critical phenomenon. There are many types of unexpected events, which can disrupt the normal operation of manufacturing systems. Therefore, the current research work focuses on identifying the critical reaction time for such events in order to keep...
Chapter
Full-text available
Digital Twins (DT) are proposed in industries to support the entire lifecycle of services with different perspectives. Lack of systematic analysis of DT concepts leads to various definitions and services which challenges the DT developers for data integration and integrated service delivery. In this paper, a systems engineering approach is proposed...
Chapter
Full-text available
The wide application of Internet of Things (IoT) has fostered the development of Industry 4.0. In manufacturing domain, Industrial IoT (IIoT) are key components of the Factories of the Future (FoF). The big IIoT data are the foundation of implementing data-driven strategies. In current industrial practice, most of these IIoT data are wasted or frag...
Article
Full-text available
Information-intensive transformation is vital to realize the Industry 4.0 paradigm, where processes, systems, and people are in a connected environment. Current factories must combine different sources of knowledge with different technological layers. Taking into account data interconnection and information transparency, it is necessary to enhance...
Preprint
Model-based Systems Engineering (MBSE) has been widely utilized to formalize system artifacts and facilitate their development throughout the entire lifecycle. During complex system development, MBSE models need to be frequently exchanged across stakeholders. Concerns about data security and tampering using traditional data exchange approaches obst...
Conference Paper
Full-text available
With the increasing complexity of the highly engineered products, Model-based Systems Engineering (MBSE) is proposed to support the complexity management of the product development using models. As the basic of complexity management, complexity analysis is used to measure the system complexity for product solution trade-off. Using traditional MBSE...
Article
Full-text available
Recent advances in technology have empowered the widespread application of cyber–physical systems in manufacturing and fostered the Industry 4.0 paradigm. In the factories of the future, it is possible that all items, including operators, will be equipped with integrated communication and data processing capabilities. Operators can become part of t...
Preprint
Full-text available
Digital Twins (DT) are proposed to provide services for internal services and customers by industries from different perspectives. Lack of systematic analysis of DT concepts leads to various definitions and services which challenges the DT developers for data integration and integrated service delivery. In this paper, a systems engineering approach...
Preprint
Full-text available
Cognitive Twins (CT) are proposed as Digital Twins (DT) with augmented semantic capabilities for identifying the dynamics of virtual model evolution, promoting the understanding of interrelationships between virtual models and enhancing the decision-making based on DT. The CT ensures that assets of Internet of Things (IoT) systems are well-managed...
Article
Full-text available
Indoor air pollution has been ranked among the top five environmental risks to public health. Indoor Air Quality (IAQ) is proven to have significant impacts on people's comfort, health, and performance. Through a systematic literature review in the area of IAQ, two gaps have been identified by this study: short-term monitoring bias and IAQ data-mon...
Conference Paper
Full-text available
Research in quantifying the influence of biophilic design in a limited quality working space is sparse. The study examines knowledge about biophilic design effects on cognitive performance, productivity and creativity through 12 participants in a dissatisfactory workspace. The study demonstrated generally biophilic design improves people's performa...
Article
Full-text available
Industry 4.0 leaders solve problems all of the time. Successful problem-solving behavioral pattern choice determines organizational and personal success, therefore a proper understanding of the problem-solving-related neurological dynamics is sure to help increase business performance. The purpose of this paper is two-fold: first, to discover relev...
Article
Full-text available
Background: Huge amounts of health-related data are generated every moment with the rapid development of Internet of Things (IoT) and wearable technologies. These big health data contain great value and can bring benefit to all stakeholders in the health care ecosystem. Currently, most of these data are siloed and fragmented in different health car...
Preprint
Full-text available
BACKGROUND Huge amount of health-related data are generated every moment with the rapid development of Internet of Things (IoT) and wearable technologies. These big health data contain great value and can bring benefit to all stakeholders in the healthcare ecosystem. Currently, most of these data are siloed and fragmented in different healthcare sy...
Article
Full-text available
Cloud manufacturing (CMfg) can manage mass manufacturing (MM) resources and capabilities, and provide them as services via the Internet. Undoubtedly, multiple manufacturing clouds will have abundant services in terms of function, price, reliability, location, etc. The implementation of such concept in a wider structure than a single MC requires to...
Article
This paper explores the effects of enforced Chinese policies regarding environmental matters at the provincial level. The paper proposes several features and explores datasets from the last four Five-Year Plans, which extensively covered the period from 1995 to 2015. As the datasets are multidimensional, dimensional reduction is applied with a cont...
Article
Background: Essential tremor (ET), one of the most common neurological disorders is typically evaluated with validated rating scales which only provide a subjective assessment during a clinical visit, underestimating the fluctuations tremor during different daily activities. Motion sensors have shown favorable performances in both quantifying trem...
Article
Full-text available
According to the Industry 4.0 paradigm, all objects in a factory, including people, are equipped with communication capabilities and integrated into cyber-physical systems (CPS). Human activity recognition (HAR) based on wearable sensors provides a method to connect people to CPS. Deep learning has shown surpassing performance in HAR. Data preproce...
Data
This is the instruction video for the evaluation of Essential Tremor. The patients are asked to follow the actions with the same speed as the neurologist performed in video. All the actions are rated by at least two neurologists on a scale from 0 to 4. The smartwatch records the acceleration data from the patients' wrist.
Data
Data preprocessing is an important part of deep learning projects. In this paper we present four preprocessed acceleration datasets which can be used to train and test deep learning models for Human Activity Recognition (HAR) tasks. The raw acceleration data collected from sensors were segmented and transformed into image format. These images can b...