Pattern Analysis Framework With Graphical Indices for Condition-Based Monitoring

Verma, Nishchal K.; Sevakula, Rahul Kumar; Thirukovalluru, Raghuveer

doi:10.1109/tr.2017.2729465

Cited by 22 publications

(4 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6: end for 7: Result: student network (weight matrix: W stu , b stu ). 8: Fine-tune the Network: Update the weight and bias using equations ( 10) and (11) to get the optima weight matrix. 9: end 3) Padeborn university dataset [30] ).…”

Section: Resultsmentioning

confidence: 99%

“…But, these approaches become ineffective if there is a contamination of extraneous frequencies and there is a change in the dynamic behavior of the machine. The recent advancement in machine learning techniques overcomes these problems and is capable to learn highly non-linear and complex characteristics of a data pattern and diagnose the machine health condition [11]- [15].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Quick Learning Mechanism With Cross-Domain Adaptation for Intelligent Fault Diagnosis

Sharma

Verma

2022

IEEE Trans. Artif. Intell.

View full text Add to dashboard Cite

This paper presents a quick learning mechanism for intelligent fault diagnosis of rotating machines operating under changeable working conditions. Since real case machines in industries run under different operating conditions, the deep learning model trained for a laboratory case machine fails to perform well for the fault diagnosis using recorded data from real case machines. It poses the need of training a new diagnostic model for the fault diagnosis of the real case machine under every new working condition. Therefore, there is a need for a mechanism that can quickly transform the existing diagnostic model for machines operating under different conditions. we propose a quick learning method with Net2Net transformation followed by a fine-tuning method to cancel/minimize the maximum mean discrepancy of the new data to the previous one. This transformation enables us to create a new network with any architecture almost ready to be used for the new dataset. The effectiveness of the proposed fault diagnosis method has been demonstrated on the CWRU dataset, IMS bearing dataset, and Paderborn university dataset. We have shown that the diagnostic model trained for CWRU data at zero load can be used to quickly train another diagnostic model for the CWRU data at different loads and also for the IMS dataset. Using the dataset provided by Paderborn university, it has been validated that the diagnostic model trained on artificially damaged fault dataset can be used for quickly training another model for real damage dataset.Impact Statement-Industrial rotating machines require continuous monitoring and analysis of the experimentation data. Since operating conditions of real case machines differ from the laboratory case machines. Therefore, the diagnostic model trained using recorded signals from laboratory case machines fails to perform well on the real case machines under the changeable conditions. Training of the deep learning-based diagnostic model for every new working condition of the real case machines is uneconomical and time-consuming. The quick learning mechanism proposed in this paper solves this problem by transforming the existing diagnostic model from laboratory case machines to real case machines running under any load conditions. This method enables us to quickly transform the deep learning model trained for a machine under one condition to another condition or for one machine to another. Therefore, the proposed methodology can be very useful for the realtime monitoring of the industrial machines operating under changeable operating conditions.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Quick Learning Mechanism With Cross-Domain Adaptation for Intelligent Fault Diagnosis

Sharma

Verma

2022

IEEE Trans. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…Several signals and combinations of signals serve to identify the patterns, which separate fault-free and faulty data. Acoustic and vibration data [52][53][54] or parameters such as pressure, temperature and stroke [55] provide features for classification. Furthermore, novelty detection algorithms are applied to identify changes in valve behavior.…”

Section: Application and Discussion Of The Proposed Metric And Visual...mentioning

confidence: 99%

A Metric and Visualization of Completeness in Multi-Dimensional Data Sets of Sensor and Actuator Data Applied to a Condition Monitoring Use Case

Weiss

Vogel‐Heuser

2021

Applied Sciences

View full text Add to dashboard Cite

The so-called ‘Industrie 4.0′ provides high potential for data-driven methods in automated production systems. However, sensor and actuator data gathered during normal operation of the system is often limited to a narrow range of single, specific operating points. This limitation also restricts the significance of condition-based maintenance models, which are trained to the narrow data. In order to reveal the structure of such multi-dimensional data sets and detect deficiencies, this paper derives a data quality metric and visualization. The metric observes the feature space and evaluates the completeness of data. In the best case, the observations utilize the whole feature space, meaning all different combinations of the variables are present in the data. Low metric values indicate missing combinations, reducing the representativeness of the data. In this way, appropriate countermeasures can be taken if relevant data is missing. For evaluation, a data set of an industrial test bed for condition monitoring of control valves is used. It is shown that the state-of-the-art metrics and visualizations cannot detect deficiencies of completeness in multi-dimensional data sets. In contrast, the proposed heat map enables the expert to locate limitations in multi-dimensional data sets.

show abstract

“…Condition-Based Monitoring (CBM): is a preventive maintenance approach, which analyses various parameters of a system to identify and report any fault. CBM is thereby a need-based maintenance technique, where maintenance is done when need arises [16]. 8.…”

Section: Organizational Sustainability and The Maintenance Functionmentioning

confidence: 99%

A Maintenance-Based Project Management Approach towards Organizational Sustainability Goals

García-García,

Gallego-García,

Ren

et al. 2023

Advances in Science and Technology

View full text Add to dashboard Cite

The paper presents an integral project management model based on organizational maintenance applied to all its functions. The motivation of the paper is to fill the existing gap in literature to enhance the function of maintenance as a driver for sustainability as it identifies improvement potentials and secures its efficient deployment and operation during any asset lifecycle. For that purpose, the key factor mediating and enabling it, is the quality function that allows the management and measurement of asset performance. As a result, a quality toolbox is the core set of tools to design, manage, and control any project and their related aspects. Moreover, the project management approach is oriented towards the sustainability goals of the organization and based on them, the selection of projects and activities are defined. Therefore, the approach enables to convert the maintenance function to a holistic function and basis for organizational viability thanks to tailored-made plans for organizational development.

show abstract

Pattern Analysis Framework With Graphical Indices for Condition-Based Monitoring

Cited by 22 publications

References 42 publications

Quick Learning Mechanism With Cross-Domain Adaptation for Intelligent Fault Diagnosis

Quick Learning Mechanism With Cross-Domain Adaptation for Intelligent Fault Diagnosis

A Metric and Visualization of Completeness in Multi-Dimensional Data Sets of Sensor and Actuator Data Applied to a Condition Monitoring Use Case

A Maintenance-Based Project Management Approach towards Organizational Sustainability Goals

Contact Info

Product

Resources

About