Improving Semi-Supervised Learning for Remaining Useful Lifetime Estimation Through Self-Supervision

RUL estimation plays a vital role in effectively scheduling maintenance operations. Unfortunately, it suffers from a severe data imbalance where data from machines near their end of life is rare. Additionally, the data produced by a machine can only be labeled after the machine failed. Both of these points make using data-driven methods for RUL estimation difficult. Semi-Supervised Learning (SSL) can incorporate the unlabeled data produced by machines that did not yet fail into data-driven methods. Previous work on SSL evaluated approaches under unrealistic conditions where the data near failure was still available. Even so, only moderate improvements were made. This paper defines more realistic evaluation conditions and proposes a novel SSL approach based on self-supervised pre-training. The method can outperform two competing approaches from the literature and the supervised baseline on the NASA Commercial Modular Aero-Propulsion System Simulation dataset.

Overview of Machine Learning Methods for Lithium-Ion Battery Remaining Useful Lifetime Prediction

Lithium-ion batteries play an indispensable role, from portable electronic devices to electric vehicles and home storage systems. Even though they are characterized by superior performance than most other storage technologies, their lifetime is not unlimited and has to be predicted to ensure the economic viability of the battery application. Furthermore, to ensure the optimal battery system operation, the remaining useful lifetime (RUL) prediction has become an essential feature of modern battery management systems (BMSs). Thus, the prediction of RUL of Lithium-ion batteries has become a hot topic for both industry and academia. The purpose of this work is to review, classify, and compare different machine learning (ML)-based methods for the prediction of the RUL of Lithium-ion batteries. First, this article summarizes and classifies various Lithium-ion battery RUL estimation methods that have been proposed in recent years. Secondly, an innovative method was selected for evaluation and compared in terms of accuracy and complexity. DNN is more suitable for RUL prediction due to its strong independent learning ability and generalization ability. In addition, the challenges and prospects of BMS and RUL prediction research are also put forward. Finally, the development of various methods is summarized.

Statistical analysis of cutting tool wear in machining centers

Cutting tools have great use in the industry for their great effectiveness at the time of use, but it is important to know what the proper use is, because the misuse or constant use of such tools, can cause excessive wear and tear that will reduce tool life. There are different methods and equations to measure the useful life of the tool, it is important to know its state so that at the time of being used in a machining process does not cause irreversible damage to the part. One of the most well-known equations is the Taylor equation where they relate useful lifetime to cutting speed. This project was developed in order to demonstrate, by means of equations and graphs, the lifetime and wear of the cutting tools, as well as the application of statistical equations that allow the analysis of the results obtained in the laboratory; a statistical study was able to evaluate the wear on the cutting tool, obtaining statistically the useful life of the tool in each machining process and calculate in the same way the total useful life of the tool.

Postbiotics as Dynamic Biological Molecules for Antimicrobial Activity: A Mini-Review

Postbiotics, products, or metabolites secreted by living probiotic bacteria like teichoic acids, peptides, enzymes, peptidoglycans, polysaccharides, organic acids, and external cell proteins are said to be produced during the bacterial fermentation process. However, postbiotics may provide immunization, antioxidant, prevents inflammation, low cholesterolemic, antimicrobial, antagonistic obesity, contrast hypertensive, and diabetic retinopathy impacts. In the current review, we attempt to display the antimicrobial performance of postbiotics. In this regard, we considered microbial strains used as postbiotic sources and postbiotics as antimicrobial agents in food products. All databases such as Science Direct, Scopus, Pub Med, and Google Scholar were examined using the following keywords: “postbiotics”, “Antimicrobial activity”, “Anti-inflammatory”, and “Low cholesterolemic”. Further studies demonstrated that probiotics are fed special forms of fiber (prebiotic) molecules, indicating substances known as postbiotics. Furthermore, short-chain fatty acids (SCFAs) like acetate, propionate, and butyrate are among the comprehensively investigated postbiotics. The extraction and purification of these compounds are carried out by means of dialysis, centrifugation, and freeze-drying techniques. According to the gained results, postbiotics assist in improving host health by increasing certain physiological functions. Furthermore, postbiotics can be used to increment the useful lifetime of different foods, like dairy products. It has also been shown that manually adding postbiotics to such products prevents the growth and proliferation of molds and thus the spoilage caused by them. This inhibitory effect indicates the antimicrobial properties of these compounds. Finally, we will see significant advances in the biological preservation of products, especially in the food industry.

Module-Level TIM Degradation in HALT

In this study, TIM degradation is driven through HALT using temperature cycling and random vibration for two commercially available materials providing thermal conductivities of 6.5 and 8.0 W/m-K. HALT specimen were prepared by applying TIM through a 4-mil stencil over AlSiC baseplates in the shape of those used in Wolfspeed CAS325M12HM2 power electronics modules. Baseplates were mounted onto aluminum carrier blocks with embedded thermocouples to characterize the thermal resistance across the baseplate and TIM layer. Thermal dissipation into the top of the baseplates was provided by a custom heating block, which mimics the size and placement of the die junctions in CAS325 modules, applying power loads of 200, 300, and 400W. After initial characterization, samples were transferred to the HALT chamber with one set of samples exposed to temperature cycling only (TCO) and the other temperature cycling and vibration (TCV). Both sample sets were cycled between temperature extremes of −40 and 180 °C with random vibrations applied at a peak acceleration of 3.21 Grms. After hundreds of cycles, samples were reevaluated to assess changes in thermal resistance to provide an accelerated measure of TIM degradation. This will allow for reliability calculations of useful lifetime, provide a basis for developing accelerated testing method to related temperature cycling to faster methods of degradation, and additionally provide a means by which to develop a maintenance schedule for servicing the power modules which will enhance cooling and lifetime operation.

Predictive Maintenance: An Autoencoder Anomaly-Based Approach for a 3 DoF Delta Robot

Performing predictive maintenance (PdM) is challenging for many reasons. Dealing with large datasets which may not contain run-to-failure data (R2F) complicates PdM even more. When no R2F data are available, identifying condition indicators (CIs), estimating the health index (HI), and thereafter, calculating a degradation model for predicting the remaining useful lifetime (RUL) are merely impossible using supervised learning. In this paper, a 3 DoF delta robot used for pick and place task is studied. In the proposed method, autoencoders (AEs) are used to predict when maintenance is required based on the signal sequence distribution and anomaly detection, which is vital when no R2F data are available. Due to the sequential nature of the data, nonlinearity of the system, and correlations between parameter time-series, convolutional layers are used for feature extraction. Thereafter, a sigmoid function is used to predict the probability of having an anomaly given CIs acquired from AEs. This function can be manually tuned given the sensitivity of the system or optimized by solving a minimax problem. Moreover, the proposed architecture can be used for fault localization for the specified system. Additionally, the proposed method can calculate RUL using Gaussian process (GP), as a degradation model, given HI values as its input.

A Multi-Model-Particle Filtering-Based Prognostic Approach to Consider Uncertainties in RUL Predictions

While increasing digitalization enables multiple advantages for a reliable operation of technical systems, a remaining challenge in the context of condition monitoring is seen in suitable consideration of uncertainties affecting the monitored system. Therefore, a suitable prognostic approach to predict the remaining useful lifetime of complex technical systems is required. To handle different kinds of uncertainties, a novel Multi-Model-Particle Filtering-based prognostic approach is developed and evaluated by the use case of rubber-metal-elements. These elements are maintained preventively due to the strong influence of uncertainties on their behavior. In this paper, two measurement quantities are compared concerning their ability to establish a prediction of the remaining useful lifetime of the monitored elements and the influence of present uncertainties. Based on three performance indices, the results are evaluated. A comparison with predictions of a classical Particle Filter underlines the superiority of the developed Multi-Model-Particle Filter. Finally, the value of the developed method for enabling condition monitoring of technical systems related to uncertainties is given exemplary by a comparison between the preventive and the predictive maintenance strategy for the use case.