Condition Monitoring of Variable Speed Machinery

Aug 12, 2012Download as PPTX, PDF0 likes515 views

This document proposes methods for novelty detection in variable speed machinery. It summarizes that: 1) Monitoring machinery is limited by changes in speed and load, termed "nuisance parameters". 2) A novel method called "multi-modal novelty detection" is proposed to employ intuition from "statistical parameterization" without its limitations by adding modal parameters like speed to feature vectors. 3) An experimental methodology is described involving sensors, data acquisition, and segmentation to generate feature vectors from variable speed tests with simulated faults, and results show standard techniques fail without speed adaptation while multi-modal novelty detection compares well.

Advancing the Online Monitoring
of Variable Speed Machinery
Jordan McBain, P.Eng.
mcbainjj@gmail.com
Sudbury, Ontario

Condition Monitoring of Variable Speed Machinery

Introduction
• Monitoring of machinery
largely limited to constant
conditions
• Changes in speed and load
termed ‘nuisance
parameters’
• Variable speed/load
machinery ubiquitous Ref: Stack

• Resonances/vibration
power

Novelty Detection
• Limited data
characterizing normal
state
– Little or no data for
abnormal states
• Compute feature
vectors of vibration
(e.g. AR model)
• Methods
– SVDD and Statistical
Boundaries

Statistical Parameterization
• Vibration strongly tied to temp (speed)
• Advanced by Keith Worden (Structural health
monitoring)
– Segment feature vectors into small groups of modal value
– Compute statistics for each group (bin)
– Trend with regression or interpolation
• Suffers from
– Double curse of dimensionality
• Describe healthy state for all
segments of modal parameter
– Gaussian distribution
• Good heuristic

Multi-Modal Novelty Detection
• Employ intuition from Statistical Parameterization
– Don’t flatten data into bins
– Add modal parameter (speed) to feature vector
– Use any novelty detection technique
– One parameter only
• Gaussian Distribution
– eliminated
• Curse of dimensionality
– Dependent on underlying
novelty detection technique

Experimental Methodology
• Sensors
– 2500 ppr Tach
– 4 accel (10 kHz)
– AE
– Hall effect sensors
– Inline torque meter
• Variable Speed/Fixed Load (10 Nm)
• DAQ and Control
– NI FPGA and Accel Card

• Vibration data
– Segmentation: 30 shaft rotations, 70% overlap, Gaussian window
– Feature vectors: Auto-Regressive (AR) Models and Statistics
– Training: 20% of data for training, 80% for validation
• Faults
– Gears (96:32 and 80:48): missing tooth, root crack, chipped pinion
– Bearings: rough ball, outer race, inner race, chopped ball

Classification Results
• No speed adaptation (SVDD)

Classification Results
• Statistical Parameterization

Conclusions
• No speed adaptation = poor results
• Statistical Parameterization
– Good results
– Double Curse of Dimensionality
– Gaussian Distribution
• Multi-Modal Novelty Detection
– Comparable Results
– More to come

Future Work
• Novelty Detection Augmented for Fault
Detection with Variable Speed Machinery
(MSSP)
• Multi-Modal Novelty Detection for Variable
Load and Speed Machinery
• Other multi-modal novelty detection
techniques
– No modal sensors

References
• [1] J McBain, M Timusk. Fault detection in variable
speed machinery: Statistical parameterization, Journal
of Sound and Vibration 327 (2009) 623-646.
• [2] K Worden, H Sohn, CR Farrar. Novelty detection in a
changing environment: Regression and interpolation
approaches, J.Sound Vibrat. 258 (2002) 741-761.
• [3] JR Stack, TG Habetler, RG Harley. Effects of machine
speed on the development and detection of rolling
element bearing faults, IEEE Power Electronics Letters.
1 (2003) 19-21.

IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology.

SIGNAL PROCESSING TECHNIQUES USED FOR GEAR FAULT DIAGNOSISJungho Park

��

Software Architecture For Condition Monitoring Of Mobile UndergroundJordan McBain

��

CBM Variable Speed MachineryJordan McBain

��

The document discusses condition monitoring of machinery using artificial intelligence techniques. It presents: 1) Condition monitoring and artificial intelligence can help automate monitoring of steady and unsteady equipment by analyzing variable parameters like loads, speeds and temperatures. 2) The theory of condition monitoring and artificial intelligence is explained, along with experimental work on methodology and results. 3) Monitoring multi-modal machinery requires techniques spanning sensing, segmentation, feature extraction, classification and post-processing to determine machinery health from noisy parameter data.

Principal Component Analysis For Novelty DetectionJordan McBain

��

This document summarizes a journal article that proposes using principal component analysis (PCA) for novelty detection in condition monitoring applications. It describes how PCA can be used to reduce the dimensionality of feature spaces while retaining most of the variation in the data. The authors modify the standard PCA technique to maximize the difference between the spread of normal data and the spread of outlier data from the mean of the normal data. They validate the approach on artificial and machinery vibration data and show it can effectively distinguish outliers. Future work could involve extending the technique to non-linear data using kernel methods.

Condition Monitoring Of Unsteadily Operating EquipmentJordan McBain

��

The document discusses techniques for condition monitoring of unsteadily operating equipment. It proposes a statistical parameterization approach involving segmenting vibration data based on steady speeds/loads, extracting statistical parameters from segments, and using novelty detection with support vectors to classify patterns as normal or faulted while accounting for changing operating conditions. Experimental results on gearbox data demonstrated superior fault detection performance compared to alternative approaches.

Condition Monitoring of Variable State MachineryJordan McBain

��

DataSource - Channels to monitor signals from various sources - Queues to store incoming samples - Registration allows components to subscribe to updates ProcessingEngine - Applies signal processing techniques - Subscribes to DataSource for raw signals - Processes and returns processed signals UserInterface - Allows selection of processing techniques - Displays processed signals for analysis - Notifies user of faults or anomalies The software architecture supports flexible routing of signals from multiple sources to processing techniques. Object-oriented design allows new processing techniques and data sources to be added dynamically. This enables online condition monitoring of variable state machinery using intelligent signal processing.

Dynamic Reactor Pattern for Distributed Systems in Control and MonitoringJordan McBain

��

Full Scale Data Handling in Shipping: A Big Data SolutionLokukaluge Prasad Perera

��

Various industrial challenges in full scale data handling situations in shipping are considered in this study. These large scale data handling approaches are often categorized as "Big Data" challenges; therefore various solutions to overcome such situations are identified. The proposed approach consists of a marine engine centered data flow path with various data handling layers to address the same challenges. These layers are categorized as: sensor fault detection, data classification, data compression, data transmission and receiver, data expansion, integrity verification, and data regression. The functionalities of each data handling layer with respect to ship performance and navigation information of a selected vessel are discussed and additional challenges that are encountered during this process are also summarized. Hence, these results can be used to develop data analytics that are related to energy efficiency and system reliability applications of shipping.

XMPLR Data Analytics in Power GenerationScott Affelt

��

This document discusses opportunities for using data analytics in power generation. It outlines how data analytics can help improve efficiency, reliability, emissions, and flexibility through approaches like predictive maintenance. Advanced pattern recognition and prognostics are highlighted as particularly useful methods. Predictive maintenance allows issues to be addressed before failures occur, reducing downtime and maintenance costs. Implementing these approaches faces challenges regarding data collection, expertise, accuracy, and security. Overall, data analytics can help operators better manage assets and improve generation reliability through early fault detection and useful life predictions.

A practical approach to predictive asset management ehm data driven modellingMayur Dvivedi

��

62 friesen field_data_requirements_for_the_validation_of_pv_module_performanc...Sandia National Laboratories: Energy & Climate: Renewables

��

This document discusses the field data requirements for validating PV module performance models. It outlines that field testing is needed to understand module performance under real operating conditions compared to standardized lab tests. Key requirements for field testing include carefully selecting and characterizing modules, using high-precision calibrated equipment, properly characterizing the test site, and processing data with harmonized methods that include calculating measurement uncertainties. Meeting all these requirements allows for more comparable data across studies and better validation of models. Typical uncertainties in field performance ratio measurements are around 4.5%, while uncertainties can be reduced to around 1.5% by standardizing testing practices.

Track 4 session 3 - st dev con 2016 - pedestrian dead reckoningST_World

��

The document provides an overview of ST Microelectronics' Pedestrian Dead Reckoning (PDR) solution for indoor positioning. The PDR system uses MEMS sensors and algorithms to continuously track a user's position without needing connectivity. It consists of components for sensor calibration, step detection, stride length modeling, attitude filtering, carry position determination, and more. The PDR solution provides APIs to output location, activity mode, and other data to applications and can integrate with Android's location services.

General Structure of a Robot - V2David Bensoussan

��

DataScience-101Karthikeyan VK

��

Discover the fascinating world of data science with this beginner-friendly introduction to the field. This presentation covers key concepts and skills, making it perfect for those who are new to data science or looking to refresh their knowledge. You'll learn about the role of a data scientist, the data science process, and popular tools and techniques used in the industry. Content Overview: Introduction to Data Science Key Components and Terminology Data Types and Sources Data Cleaning and Preprocessing Exploratory Data Analysis Feature Engineering and Selection Machine Learning Algorithms Model Evaluation and Validation Data Visualization Techniques Essential Tools and Libraries Real-World Applications and Use Cases Building a Data Science Career Tags: #DataScience #MachineLearning #BigData #Analytics #DataVisualization #AI #Python #DataEngineering #Statistics

Manoj ahire resumeManoj Ahire

��

Manoj Ahire-ResumeManoj Ahire

��

Manoj Ahire is a lead engineer with over 10 years of experience designing and implementing SCADA systems for solar power plants and other industries. His responsibilities include designing control system architectures, configuring communication between devices, developing HMI displays, configuring alarms and reports, and performing testing and commissioning. He has extensive experience designing SCADA systems for solar plants ranging from 1MW to 35MW in size.

Xmplr power gen natgas 2016 wo animationScott Affelt

��

This document discusses opportunities for using data analytics in power generation. It outlines key areas where data analytics can help with efficiency, reliability, emissions, and flexibility. The main focus is on using data analytics and prognostics to predict equipment failures. Different prognostic approaches are described, including physics-based, data-based, and experience-based models. Power generation applications for advanced pattern recognition and prognostics are also discussed. Challenges in implementing these techniques include ensuring access to clean, relevant data from multiple sources and gaining confidence in prediction accuracy. Overall, data analytics can help power generators improve reliability by detecting anomalies early and predicting remaining useful life for equipment.

Akhilesh Pandey_RF Optimization EngAkhilesh Pandey

��

The document is a resume for Akhilesh Kumar Pandey summarizing his qualifications and experience as an RF Optimization Engineer with over 9 years of experience in GSM, WCDMA, and LTE networks. It provides details of his current role as a Senior Network Engineer with Ericsson India along with previous roles and responsibilities handling RF optimization, planning, and performance monitoring. Technical skills and tools used are also listed.

maninewSubramanian mariappan

��

M. Subramanian has over 8 years of experience in electrical and instrumentation. He currently works as an Electrical and Instrumentation Superintendent for MEFSCO in Saudi Arabia. Previously, he worked as an Electrical and Instrumentation Supervisor for DHARANI SUGARS AND CHEMICALS LTD in India. He has expertise in electrical systems, PLCs, DCS, process control systems and various field instruments including transmitters, valves, and flow meters.

VCE ppt .pptxSiddheshJadhav84

��

This document discusses new trends in vibration-based structural health monitoring. It describes how vibration-based SHM works by detecting changes in the modal parameters of a structure caused by damage. The key modal parameters used are frequencies, mode shapes, and damping. A baseline reading of an undamaged structure is used for comparison to detect damage. It also discusses challenges in vibration-based SHM including developing more sensitive damage indicators and methods to distinguish damage from environmental effects.

Resume_Sushil Kumar Kushwahasushil kuamr kushwaha

��

Opportunities for data analytics in power generation affelt 2016Scott Affelt

��

This document discusses opportunities for using data analytics in power generation. It outlines key areas where data analytics can provide benefits, such as improving efficiency, reliability, emissions compliance, and flexibility. The focus is on using data analytics and prognostics to predict equipment failures. Several approaches to prognostics are described, including experience-based, data-based, and physics-based models. Power generation equipment that could benefit from advanced pattern recognition and prognostics includes turbines, pumps, generators, compressors, gearboxes, and bearings. Challenges to implementing these techniques include ensuring access to relevant data, validating prediction accuracy, and addressing data security concerns.

Manoj Ahire-ResumeManoj Ahire

��

The document provides a resume for Manoj N. Ahire, who has experience as a Project Manager for SCADA systems used in solar power plants and other industries. It summarizes his responsibilities for various SCADA projects in India and the United States, which included designing control systems, configuring communication protocols, developing HMI displays, and performing testing and commissioning. It also lists his educational qualifications and previous work experience with automation companies.

CBM Sensing by Carl Byington of PHM DesignCarl Byington

��

Translate physical phenomena and fault symptoms into measurable quantities (“The equipment is trying to tell us something.”) System State Observables Process variables (Flow, Temp, Press, Speed, Torque,etc) Energy Event Observables Acoustic and Vibration (Accelerometers, Velocity & Proximity Probes, Microphones) High Frequency (Ultrasonics, Acoustic Emission) Electrical and Magnetics Physical Observables Oil properties and debris Human perceptible Challenge: How to choose, locate and process all the sensors?

Seminar Nima Yousefi 2015 Engineering University of Alberta Nima Yousefi, PEng, PMP

��

OPTIMIZING DRILLING & WELLBORE POSITIONING THROUGH AUTOMATION AND DIGITALIZATIONiQHub

��

This document discusses optimizing drilling and wellbore positioning through automation and digitalization. It outlines how guidance, control, navigation, sensors, and true system dynamics work together in an integrated automated system. Key benefits of such a system include improved productivity, accuracy, and consistency through features like high-definition wellbore trajectory projection, automated data validation, algorithmic drilling guidance, and integration with control systems. The system aims to improve rate of penetration, torque and drag, weight transfer, and slide efficiency. The goal is to consistently place wellbores as planned and avoid problems that can occur from excessive sliding.

Measurement System Analysis - A new ApproachIlinaRoy1

��

Condition Monitoring of Variable Speed Machinery

1. Advancing the Online Monitoring of Variable Speed Machinery Jordan McBain, P.Eng. mcbainjj@gmail.com Sudbury, Ontario

3. Introduction • Monitoring of machinery largely limited to constant conditions • Changes in speed and load termed ‘nuisance parameters’ • Variable speed/load machinery ubiquitous Ref: Stack • Resonances/vibration power

4. Novelty Detection • Limited data characterizing normal state – Little or no data for abnormal states • Compute feature vectors of vibration (e.g. AR model) • Methods – SVDD and Statistical Boundaries

5. Statistical Parameterization • Vibration strongly tied to temp (speed) • Advanced by Keith Worden (Structural health monitoring) – Segment feature vectors into small groups of modal value – Compute statistics for each group (bin) – Trend with regression or interpolation • Suffers from – Double curse of dimensionality • Describe healthy state for all segments of modal parameter – Gaussian distribution • Good heuristic

6. Multi-Modal Novelty Detection • Employ intuition from Statistical Parameterization – Don’t flatten data into bins – Add modal parameter (speed) to feature vector – Use any novelty detection technique – One parameter only • Gaussian Distribution – eliminated • Curse of dimensionality – Dependent on underlying novelty detection technique

7. Experimental Methodology

8. Experimental Methodology • Sensors – 2500 ppr Tach – 4 accel (10 kHz) – AE – Hall effect sensors – Inline torque meter • Variable Speed/Fixed Load (10 Nm) • DAQ and Control – NI FPGA and Accel Card • Vibration data – Segmentation: 30 shaft rotations, 70% overlap, Gaussian window – Feature vectors: Auto-Regressive (AR) Models and Statistics – Training: 20% of data for training, 80% for validation • Faults – Gears (96:32 and 80:48): missing tooth, root crack, chipped pinion – Bearings: rough ball, outer race, inner race, chopped ball

9. Classification Results • No speed adaptation (SVDD)

10. Classification Results • Statistical Parameterization

11. Classification Results

12. Conclusions • No speed adaptation = poor results • Statistical Parameterization – Good results – Double Curse of Dimensionality – Gaussian Distribution • Multi-Modal Novelty Detection – Comparable Results – More to come

13. Future Work • Novelty Detection Augmented for Fault Detection with Variable Speed Machinery (MSSP) • Multi-Modal Novelty Detection for Variable Load and Speed Machinery • Other multi-modal novelty detection techniques – No modal sensors

14. References • [1] J McBain, M Timusk. Fault detection in variable speed machinery: Statistical parameterization, Journal of Sound and Vibration 327 (2009) 623-646. • [2] K Worden, H Sohn, CR Farrar. Novelty detection in a changing environment: Regression and interpolation approaches, J.Sound Vibrat. 258 (2002) 741-761. • [3] JR Stack, TG Habetler, RG Harley. Effects of machine speed on the development and detection of rolling element bearing faults, IEEE Power Electronics Letters. 1 (2003) 19-21.

�ݺ�ߣ

Condition Monitoring of Variable Speed Machinery

Recommended

More Related Content

Similar to Condition Monitoring of Variable Speed Machinery (20)

Condition Monitoring of Variable Speed Machinery