A Survey of HMM-based Algorithms in Machinery Fault Prediction

Ramezani, Somayeh Bakhtiari; Killen, Brad; Cummins, Logan; Rahimi, Shahram; Amirlatifi, Amin; Seale, Maria

doi:10.1109/ssci50451.2021.9659838

Cited by 9 publications

(8 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A generalized HMM is composed of a state model of Markov process z t , linked to an observation model P(x t |z t ), which contains the observations x t of the state model. While HMMs are considered agnostic of the duration of the states, the HSMMs can take the duration of each state into consideration [192], which makes HSMMs suitable for prognosis [193], [194]. Neither HMM nor HSMM can capture the inter-dependencies of observations in temporal data, which is a key factor in determining the state of the system.…”

Section: Bayesian Deep Learning and Variational Inferencementioning

confidence: 99%

Deep Representation Learning: Fundamentals, Technologies, Applications, and Open Challenges

Payandeh,

Baghaei,

Fayyazsanavi

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

Machine learning algorithms have had a profound impact on the field of computer science over the past few decades. The performance of these algorithms heavily depends on the representations derived from the data during the learning process. Successful learning processes aim to produce concise, discrete, meaningful representations that can be effectively applied to various tasks. Recent advancements in deep learning models have proven to be highly effective in capturing high-dimensional, non-linear, and multi-modal characteristics. In this work, we provide a comprehensive overview of the current state-of-the-art in deep representation learning and the principles and developments made in the process of representation learning. Our study encompasses both supervised and unsupervised methods, including popular techniques such as autoencoders, self-supervised methods, and deep neural networks. Furthermore, we explore a wide range of applications, including image recognition and natural language processing. In addition, we discuss recent trends, key issues, and open challenges in the field. This survey endeavors to make a significant contribution to the field of deep representation learning, fostering its understanding and facilitating further advancements.

show abstract

Section: Bayesian Deep Learning and Variational Inferencementioning

confidence: 99%

Deep Representation Learning: Fundamentals, Technologies, Applications, and Open Challenges

Payandeh,

Baghaei,

Fayyazsanavi

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…[17,18,19] reviewed data-driven algorithms for PdM in automotive systems. More recently, [20] discussed the different probabilistic techniques used in PdM and noted that finding all possible states of long multivariate temporal data is computationally expensive. To overcome this problem, they suggested discretization of the continuous data prior to applying the probabilistic techniques.…”

Section: Related Workmentioning

confidence: 99%

“…An HMM relates the observation model P (x t |z t ) to their underlying Markov processes state model z t , and their observations x t . Figure 10 shows an example of a basic HMM model for a four-state degradation of a system [20].…”

Section: ) Kernel-based Learning Algorithmsmentioning

confidence: 99%

Scalability, Explainability and Performance of Data-Driven Algorithms in Predicting the Remaining Useful Life: A Comprehensive Review

et al. 2023

View full text Add to dashboard Cite

Early detection of faulty patterns and timely scheduling of maintenance events can minimize risk to the underlying processes and increase a system's lifespan, reliability, and availability. Two main data-driven approaches are used in the literature to determine the Remaining Useful Life (RUL): direct calculation from raw data and indirect analysis by revealing the transitions from one latent state to another and highlighting degradation in a system's Health Indices. The present study discusses the state-of-theart data-driven methods introduced for RUL prediction in predictive maintenance, by looking at their capabilities, scalability, performance, and weaknesses. We will also discuss the challenges faced with the current approaches and the future directions to tackle the current limitations.

show abstract

“…[ 13 ] Numerous works have been published that provide a comprehensive review of algorithms for employing data‐driven models for battery life prediction and analyze the scalability of these algorithms. [ 13c,14 ] However, ECM and data‐driven models lack physical significance and disregard microscopic information within the battery; therefore, they offer limited insight into the physical underlying cause of material and cell‐level aging. Differently, the Pseudo‐two‐dimensions (P2D) electrochemical model, [ 15 ] which is based on porous electrode theory, describes the thermodynamics, chemical reaction kinetics, and transport mechanisms occurring within the battery in terms of the physicochemical processes.…”

Section: Introductionmentioning

confidence: 99%

“…Until now, a number of reviews on battery degradation mechanisms, [ 7,26 ] electrochemical model modeling, [ 17 ] model parameter identification, [ 27 ] and ML techniques [ 13c,14 ] have been published; however, each of these reviews has primarily focused on a single aspect. Oriented toward establishing a workflow for accurate prediction of battery aging, this review scrutinizes the essential elements for precise LIB aging prediction, including chemical and material‐level battery degradation mechanisms in different usage scenarios, electrochemical modeling cases combined with internal battery degradation reactions, and recent advances in model parameter identification methods, with a concentration on battery electrode balance.…”

Section: Introductionmentioning

confidence: 99%

Accurate Model Parameter Identification to Boost Precise Aging Prediction of Lithium‐Ion Batteries: A Review

Ding,

Li,

Dai

et al. 2023

Advanced Energy Materials

View full text Add to dashboard Cite

Precise prediction of lithium‐ion cell level aging under various operating conditions is an imperative but challenging part of ensuring the quality performance of emerging applications such as electric vehicles and stationary energy storage systems. Accurate and real‐time battery‐aging prediction models, which require an exact understanding of the degradation mechanisms of battery components and materials, could in turn provide new insights for materials and battery basic research. Furthermore, the primary barrier to meaningful artificial intelligence/machine learning for accelerating the prediction period is the exploitation of accurate aging mechanistic descriptors. This review comprehensively summarizes the evolution of deterioration mechanisms at the material and cell level in different environments and usage scenarios, including the intricate relationships between aging mechanisms, degradation modes, and external influences, which are the cornerstones of modeling simulation and machine learning techniques. Recent advances in electrochemical models coupled with internal battery degradation mechanisms as well as identification and tracking of aging parameters are shown, with particular emphasis on electrode balance and the anticipated trend of machine learning‐assisted reliable remaining useful life prediction. Precise simulation prediction of cell level aging will continue to play an essential role in advanced smart battery research and management, enhancing its performance while shortening experimental sequences.

show abstract

A Survey of HMM-based Algorithms in Machinery Fault Prediction

Cited by 9 publications

References 58 publications

Deep Representation Learning: Fundamentals, Technologies, Applications, and Open Challenges

Deep Representation Learning: Fundamentals, Technologies, Applications, and Open Challenges

Scalability, Explainability and Performance of Data-Driven Algorithms in Predicting the Remaining Useful Life: A Comprehensive Review

Accurate Model Parameter Identification to Boost Precise Aging Prediction of Lithium‐Ion Batteries: A Review

Contact Info

Product

Resources

About