检索结果-内蒙古大学图书馆

FAILURE DETECTION AND REMAINING LIFE ESTIMATION FOR ION MILL ETCHING process THROUGH DEEP-LEARNING BASED MULTIMODAL DATA FUSION 14

引用

14th ASME International Manufacturing Science and Engineering conference

作者： He, Anqi Jin, Xiaoning Northeastern Univ Dept Mech & Ind Engn Boston MA 02115 USA

ISBN: (纸本)9780791858745

Ion Mill Etching (IME) is an advanced process technology that uses ion-beam sources to remove materials by atomic sandblasting in order to reveal a specific pattern on the substrate. The high precision capability requires stringent process monitoring and control of the flowcool system which is critical to prevent thermal deformation for temperature sensitive materials from the heat generated from the ion beam irradiation. This study focuses on a multi-sensor data analytics to monitoring the IME process condition enabling diagnostics and prediction of three main failure mechanisms of the IME flowcool system. A generalizable framework of engineering-based data-driven failure diagnostics and prediction is developed using random forest-based classification and a Deep Long Short-Term Memory (LSTM)-based failure prediction. The proposed framework and methods are demonstrated and validated in an ion mill etching process using multi-sensor data collected from multiple run-to failure cycles. Three different failure modes related to the flowcool system are detected, identified in real time and the time to the next failure is accurately predicted. The proposed method provides a systematic and generalizable approach for process monitoring and early prediction of failures by using heterogeneous sensor measurements and operational data when under various operating conditions and settings.

关键词： Ion mill etching multi-sensor fusion diagnostics remaining useful life prediction classification deep learning

来源：评论

学校读者我要写书评

暂无评论

Using Network Traces to Generate Models for Automatic Network Application Protocols diagnostics 16

Using Network Traces to Generate Models for Automatic Networ...

引用

16th International Joint conference on E-Business and Telecommunications (ICETE)

作者： Holkovic, Martin Rysavy, Ondrej Polcak, Libor CESNET Ale Zikova 1903-4 Prague 16000 Czech Republic Brno Univ Technol Fac Informat Technol Bozetechova 1-2 Brno 61266 Czech Republic

ISBN: (纸本)9789897583780

Network diagnostics is a time-consuming activity that requires an administrator with good knowledge of network principles and technologies. Even if some network errors have been resolved in the past, the administrator must spend considerable time removing these errors when they reoccur. This article presents an automated tool to learn the expected behavior of network protocols and possible variations. The created model can be used to automate the diagnostic process. The model presents a finite automaton containing protocol behavior for different situations. diagnostics of unknown communication is performed by checking the created model and searching for error states and their descriptions. We have also created a proof-of-concept tool that demonstrates the practical potential of this approach.

关键词： Network diagnostics Automatic diagnostics Protocol Model from Traces

来源：评论

学校读者我要写书评

暂无评论

Towards Basic Design Principles of Next Generation Human-Operator Decision Support Systems

Towards Basic Design Principles of Next Generation Human-Ope...

引用

International conference on control, Decision and Information Technologies (CoDIT)

作者： Elena Ph. Jharko Kirill R. Chernyshov V.A. Trapeznikov Institute of Control Sciences Moscow Russia

ISBN: (数字)9781728159539

ISBN: (纸本)9781728159546

Providing of insight into an approach to creation of information human-operator decision support systems (IHODSS) for complex process plants as exemplified by nuclear power unit control. IHODSS functional basis is determined by accomplishing the following tasks essentially forming a triune task: prediction of power unit parameters behavior and process progress aspects, in-mode diagnostics, and early in-process recognition of anomalies; generation of recommendations on optimal process conditions. An overview of basic principles of development and function of IHODSS, software and hardware selection, as well as characterization of software and hardware suite for IHODSS tasks refinement are presented..

关键词： control systems Task analysis process control Reliability Personnel Trajectory Mathematical model

来源：评论

学校读者我要写书评

暂无评论

Temperature analysis of electronic devices for reliability design based on process neural network

Temperature analysis of electronic devices for reliability d...

引用

2019 International conference on Sensing, diagnostics, Prognostics, and control, SDPC 2019

作者： Ding, Chen Niu, Zhiling Yu, Muchun Zhang, Zijun Li, Bingwei China Academy of Launch Vehicle Technology Beijing China

ISBN: (纸本)9781728101996

Aiming at reliability design for electronic devices, process neural networks are proposed to predict the temperature of electronic devices. To avoid errors caused by discrete input data fitting or difference, only discrete data is used when solving orthogonal transformation coefficients. To accelerate the learning speed of the gradient descent algorithm, a parameter- independent adaptive learning algorithm is developed. The results show that this model has better accuracy and generalization ability compared with artificial neural networks and linear regression method, and the parameter-independent adaptive learning algorithm has quicker convergence rate compared with parameter-fixed algorithm and adaptive learning algorithm. © 2019 IEEE.

关键词： Orthogonal functions

来源：评论

学校读者我要写书评

暂无评论

diagnostics of Electrical Wires and Cables

Diagnostics of Electrical Wires and Cables

引用

International conference on Industrial Engineering, Applications and Manufacturing (ICIEAM)

作者： Bryakin, Ivan, V Bochkarev, Igor, V Khramshin, Vadim R. Natl Acad Sci Kyrgyz Republ Bishkek Kyrgyzstan Kyrgyz State Tech Univ Bishkek Kyrgyzstan South Ural State Univ Chelyabinsk Russia

ISBN: (纸本)9781538681190

The authors have developed a new method of diagnostics of cable conductivity elements (CE), which helps determine the type and location of their defect. This method relies on a physical phenomenon never used in the non-destructive testing systems before. It consists in polarizing the spin magnetic moments of free electrons in conductive structures when exposed to an external elec-tric field. This process is recorded by an induction sensor, which generates a measuring pilot signal in the form of the induction EMF, the parameters of which are determined based on the cable CE parameters in the area of this sensor location. A diagnostics is carried out through comparing the re-ceived signal with a reference signal obtained in advance in a similar way. In this case, the process of the reference signal generation depends on the control objectives that were set. When it is only necessary to confirm the cable CE defect and identify its type without specifying its parameters, the reference signal is obtained using a standard cable section without defects. When a categorization of the revealed defects is required along with their specific parameters determination, it is necessary to create a reference signal database acquired based upon measurements in the cable samples with in-tentionally planted set defects.

关键词： cable conductivity elements spin capacitor induction sensor electron spin traveling polarization wave of spin magnetic moments of free electrons harmonic oscillator EMF of induction

来源：评论

学校读者我要写书评

暂无评论

Operational State Evaluation and Maintenance Decision-making Method for Multi-state CNC Machine Tools based on Partially Observable Markov Decision process

Operational State Evaluation and Maintenance Decision-making...

引用

International conference on Sensing, diagnostics, Prognostics, and control (SDPC)

作者： Fang Zixuan Wang Xiaodong Wang Lifang Systems Engineering Research lnstitute Beijing China

ISBN: (数字)9781728170503

ISBN: (纸本)9781728170510

With the development of science and technology, the manufacturing technology of computer numerical control (CNC) has been one of the irreplaceable important technologies in the manufacturing industry. However, due to the lack of sufficient data, the existing evaluation methods cannot accurately evaluate the operational state of CNC machine tools, and an effective maintenance scheduling strategy cannot be proposed. Aiming at the lack of monitoring data and the unclear understanding of the degradation mechanism of CNC machine tools, an operational state evaluation and maintenance decision-making method of multi-state CNC machine tools based on partially observable Markov decision process (POMDP) was proposed. On the one hand, considering the imperfect operational information of CNC machine tools and the influence of different maintenance activities on the degradation process of NC machine tools, a dynamic evaluation model for the operational state was constructed. On the other hand, a maintenance decision model for CNC machine tools was established with the goal of minimizing the total cost of losses (including maintenance costs and potential failures costs). The proposed method is applied to CNC machine tools of cylinder to verify the effectiveness and advancement of the method.

关键词： Degradation Decision making Maintenance engineering Markov processes Machine tools Computer numerical control Optimization

来源：评论

学校读者我要写书评

暂无评论

Reliability analysis based on dependent competing risk model of imperfect shock model considering changing threshold and degradation process

Reliability analysis based on dependent competing risk model...

引用

2019 International conference on Sensing, diagnostics, Prognostics, and control, SDPC 2019

作者： Liu, Yiwen Bai, Chunlei China Aero-Polytechnology Establishment Beijing China

ISBN: (纸本)9781728101996

In this paper, a dependent competing risk model for a system with two-type failures is studied. Most scholars in present research consider that every shock can cause damage on the degradation process, however, because of the system resistance, only shock loads which are larger than a certain level can cause damage on the degradation. Consider that degradation failure due to degradation process and catastrophic failure due to random shocks will both make the system failed. Assume further that the degradation process and random shocks are not independent. Random shocks resulted in additional degradation. Meanwhile, degradation process affected the hard failure threshold of random shocks. In this case, reliability model of system was built. Furthermore, reliability analysis (independent verses dependent) and sensitivity analysis with different arrival rate were shown. Finally, this paper gave a numerical example. When a component experiences both degradation process and random shocks, this paper not only considers the influence of the random shocks on degradation, but also the impact of degradation on the shocks. On the other hand, this paper considered the situation of incomplete impact and established a competing model of degradation failure and traumatic failure. © 2019 IEEE.

关键词： Reliability analysis

来源：评论

学校读者我要写书评

暂无评论

Reliability evaluation of instrument-control power distribution system

Reliability evaluation of instrument-control power distribut...

引用

2019 International conference on Sensing, diagnostics, Prognostics, and control, SDPC 2019

作者： Qiao, Xingyu Liu, He North China Electric Power University School of Control and Computer Engineering Beijing China

ISBN: (纸本)9781728101996

To meet the needs of nuclear power plant instrument-control power distribution system, and to follow the trend of rapid development of technology, it is necessary to carry out the comprehensive reliability evaluation for the nuclear power plant instrument-control power distribution system. This paper introduces a multi-level index system model based on improved analytic hierarchy process and the CRITIC method to evaluate the reliability of instrument-control power distribution system. By combining the subjective weights and objective weights calculated by the improved AHP method and the CRITIC method, a comprehensive weight of selected index is obtained and applied to establish the final evaluation model. Finally, two design schemes of the instrument-control power distribution system are used to verify the validity of the evaluation model. The result shows that the model is reliable and effective. It can provide the reference for the design and improvement for the reliability. © 2019 IEEE.

关键词： Nuclear power plants

来源：评论

学校读者我要写书评

暂无评论

control of railroad track irregularities based on the use of axlebox acceleration sensors in automatic systems for prescriptive diagnostics of the technical condition of high-speed electric trains

引用

AIP conference Proceedings 2023年第1期2476卷

作者： Oleg Suslov Alexander Adadurov Andrey Lesnikov Elena Sidorova Yana Grekhova Scientific Research Institute of Railway Transport Russian Federation

The main result of the work of all participants in the transportation process in the railway transport is the delivery of cargo and passengers in a timely manner and ensuring traffic safety. Achieving this result is impossible without constant monitoring of the state of the transportation infrastructure and, first of all, without monitoring the condition of the track, which is especially important when high-speed rolling stock is moving, when a track failure can lead to disruption of passenger comfort and premature wear of expensive elements of electric trains. The most promising solution for ensuring the continuity of monitoring the state of the track is the introduction of track irregularities monitoring systems that are integrated into the high-speed rolling stock circulating on the network. Such solutions, in addition to the existing technologies for monitoring the state of mobile track measuring devices, will allow to identify sections of the track with an unacceptable condition more quickly. This article discusses the issue of developing a technology for monitoring the values of horizontal and vertical irregularities of the track based on micromechanical acceleration sensors installed on the axleboxes of the rolling stock, as an integral part of the on-board automatic system for prescriptive diagnostics of the technical condition of high-speed electric trains.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development and Design of the Intellectual Bionic Robotic Arm control System

Development and Design of the Intellectual Bionic Robotic Ar...

引用

International conference on Industrial Engineering, Applications and Manufacturing (ICIEAM)

作者： Pribluda, Bogdan Uglovskiy, Artem Korol, Valery South Russian State Tech Univ NPI MI Platov Novocherkassk Russia

ISBN: (纸本)9781538681190

Dynamically developing technologies in the modern world impose their requirements on digital and analog devices and devices used in various industries such as aviation, space, medical, etc. The advantage is mainly given to the devices with a high degree of automation and not requiring control operations performed by man in the process of their work. One of the most important tasks is the design of robotic systems. The authors propose a control system for a bionic robotic arm based on the neural network control. Neural network control is a special case of intelligent control that uses artificial neural networks to solve problems of controlling dynamic objects. This approach will ensure high speed and accuracy of application.

关键词： control system neural networks intellectual bionic robotic arm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：