Modeling and Monitoring of Performance Limiting Factors for Ball-screw Linear Motion Systems / (Record no. 610753)

000 -LEADER
fixed length control field 04099nam a22001577a 4500
082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER
Classification number 621
100 ## - MAIN ENTRY--PERSONAL NAME
Personal name Riaz, Naveed
245 ## - TITLE STATEMENT
Title Modeling and Monitoring of Performance Limiting Factors for Ball-screw Linear Motion Systems /
Statement of responsibility, etc. Naveed Riaz
264 ## - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE
Place of production, publication, distribution, manufacture Islamabad : SMME- NUST; Soft Copy
Name of producer, publisher, distributor, manufacturer Islamabad : SMME- NUST; Soft Copy
Date of production, publication, distribution, manufacture, or copyright notice 2022.
300 ## - PHYSICAL DESCRIPTION
Extent 143p.
Other physical details Islamabad : SMME- NUST; Soft Copy
Dimensions 30cm.
500 ## - GENERAL NOTE
General note Reliability of high precision linear motion systems is one of the main concerns in<br/>industrial and military systems. The performance and repeatability of these systems are<br/>influenced by their respective Ball Screw (BS) linear drives. A fault in these members severely<br/>affects positioning accuracy and safe working of overall system. BS linear drives perform flight /<br/>application critical job and are responsible to provide precise linear motion while carrying thrust<br/>loading. BS drives are specifically designed on the basis of desired operational parameters like<br/>power rating, drive torque, slew rate, efficiency, friction, and mechanical backlash etc. These<br/>operating parameters significantly affect the functional performance of linear electro-mechanical<br/>systems. At present, few techniques are available to monitor BS drives for aerospace and<br/>industrial systems.<br/>This research works to improve reliability of ball screw drive linear systems by modeling<br/>and monitoring the performance factors through analytical redundancy and intelligent deep<br/>learning. In the past, some traditional techniques have been employed to address these problems;<br/>however these techniques show limitations like insufficient data acquisition, requirement of<br/>dedicated model developer and poor domain adaptation. Recently, deep learning techniques have<br/>been introduced and are becoming more popular to detect and characterize various fault signal<br/>analysis problems due to their robustness and accuracy.<br/>The aim of this research is to provide solution of mechanical faults identification and<br/>classification problems for BS linear drives. A fault diagnostic algorithm is designed based on<br/>dynamic mathematical model and a remnant filter is implemented to detect signal errors. The<br/>remnant filter generates residual signal proportional to the error induced. Fault detection<br/>thresholds are set and decision logic is established based on position measurement corrections to<br/>compare residual signal with the lower and upper pre-defined threshold constants.<br/>Accuracy in faults identification is highly dependent on improved features extraction. For<br/>this purpose, a novel Residual Twin CNN (ResT-CNN) is proposed that uses combination of 1-D<br/>and 2-D CNN in parallel learning which improves features extraction performance; followed by<br/>knowledge base-Remnant-PCA (Kb-Rem-PCA) architecture in combination with multi-class<br/>support vector machine (Mc-SVM). Current and Position signal data was collected under<br/>different load domains. This novel hybrid combination proved very effective in accurate faults<br/>identification and classification.<br/>The performance of proposed intelligent technique was successfully tested and validated<br/>on different datasets including IMS-UC (Intelligent Maintenance Systems – University of<br/>Cincinnati) publically published bearing dataset, Paderborn published multi-stage bearing<br/>dataset, Current signal dataset for multiple fault modes of BS drive and Position measurement<br/>data for multi faults cases for BS linear drive.<br/>The actual Signal and Model Fit Simulated Data for BSD system was compared. The<br/>testing results proved the effectiveness and superiority of proposed model against different state<br/>of the art techniques. The proposed novel framework was also tested for system's stability under<br/>different load domains. The results reveal highly competitive values greater than 95% in terms of<br/>accuracy and precision for different faults cases
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element PhD in Mechanical Engineering
700 ## - ADDED ENTRY--PERSONAL NAME
Personal name Supervisor : Dr. Syed Irtiza Ali Shah
856 ## - ELECTRONIC LOCATION AND ACCESS
Uniform Resource Identifier <a href="http://10.250.8.41:8080/xmlui/handle/123456789/33985">http://10.250.8.41:8080/xmlui/handle/123456789/33985</a>
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Source of classification or shelving scheme
Koha item type Thesis
Holdings
Withdrawn status Permanent Location Current Location Shelving location Date acquired Full call number Barcode Koha item type
  School of Mechanical & Manufacturing Engineering (SMME) School of Mechanical & Manufacturing Engineering (SMME) E-Books 08/02/2024 621 SMME-Phd-21 Thesis
© 2023 Central Library, National University of Sciences and Technology. All Rights Reserved.