Lithium-ion batteries are ubiquitous in applications ranging from portable electronics to electric vehicles. Irrespective of the application, reliable real-time estimation of battery state of health (SOH) by on-board computers is crucial to the safe operation of the battery, ultimately safeguarding asset integrity. In this Article, we design and evaluate a machine learning pipeline for estimation of battery capacity fade—a metric of battery health—on 179 cells cycled under various conditions. The pipeline estimates battery SOH with an associated confidence interval by using two parametric and two non-parametric algorithms. Using segments of charge voltage and current curves, the pipeline engineers 30 features, performs automatic feature selection and calibrates the algorithms. When deployed on cells operated under the fast-charging protocol, the best model achieves a root-mean-squared error of 0.45%. This work provides insights into the design of scalable data-driven models for battery SOH estimation, emphasizing the value of confidence bounds around the prediction. The pipeline methodology combines experimental data with machine learning modelling and could be applied to other critical components that require real-time estimation of SOH.

@en

Electrochemical capacitors (ECs) have only recently been considered as an alternative power source for telemetry sensors of drilling equipment for geothermal or oil and gas exploration. The lifecycle analysis and modelling of ECs is underrepresented in literature in comparison to other storage devices e.g. Li-ion batteries. This paper investigates the degradation of ECs when cycled outside the manufacturer-specified operating temperature envelope and proposes a machine learning-based approach for modelling the degradation. Experimental results show that end of life, defined as a 30% decrease in capacitance, occurs at 1,000 cycles when the environmental temperature exceeds the maximum operating temperature by 30%. The life-cycle test data is then used as an input to a Gaussian process regression (GPR) algorithm to predict the capacitance fade trend. The GPR is validated on a total of nine commercial cells from two different manufacturers, achieving an average root mean squared percent error of less than 2% and a mean calibration score of 93% when referenced to a 95% confidence interval. The model can be utilized to determine the EC degradation rate at a range of operating temperature values.

@en

Lithium-ion batteries power numerous systems from consumer electronics to electric vehicles, and thus undergo qualification testing for degradation assessment prior to deployment. Qualification testing involves repeated charge–discharge operation of the batteries, which can take more than three months if subjected to 500 cycles at a C-rate of 0.5C. Accelerated degradation testing can be used to reduce extensive test time, but its application requires a careful selection of stress factors. To address this challenge, this study identifies and ranks stress factors in terms of their effects on battery degradation (capacity fade) using half-fractional design of experiments and machine learning. Two case studies are presented involving 96 lithium-ion batteries from two different manufacturers, tested under five different stress factors. Results show that neither the individual (main) effects nor the two-way interaction effects of charge C-rate and depth of discharge rank in the top three significant stress factors for the capacity fade in lithium-ion batteries, while temperature in the form of either individual or interaction effect provides the maximum acceleration.@en

In this paper, failure analysis of an electromagnetic relay is studied to inform embedded health monitoring for the prediction of Remaining Useful Life (RUL) of electromagnetic relays. A statistical design of experiment with online monitoring of voltage, current, temperature, resistance, duty cycle, and frequency is used to identify relay failure precursors. Examples of detected precursors include abnormal spikes in resistance and extension of the average closing time of the relay within the final 1.5 million actuations prior to failure. A detailed post-failure analysis utilising white light interferometry and energy dispersive X-ray (EDX) analysis reveals the relay failure modes associated with erosion, pit and crater formation, and material transfer. The results demonstrate that low resolution data can detect signatures of impending failure modes such as stuck open and closed failures as well as unacceptable long opening times. The findings within this paper demonstrate remote monitoring of the near real-time health of electromagnetic relays with low resolution data analysis.

@en

Subsea power cables are critical assets within the distribution and transmission infrastructure of electrical networks. Over the past two decades, the size of investments in subsea power cable installation projects has been growing significantly. However, the analysis of historical failure data shows that the present state-of-the-art monitoring technologies do not detect about 70% of the failure modes in subsea power cables. This paper presents a modeling methodology for predicting damage along the length of subsea cables due to environmental conditions (e.g., seabed roughness and tidal flows) which result in the loss of the protective layers on the cable due to corrosion and abrasion (accounting for over 40% of subsea cable failures). For a defined cable layout on different seabed conditions and tidal current inputs, the model calculates the cable movement by taking into account the scouring effect and then it predicts the rate at which the material is lost due to corrosion and abrasion. Our approach integrates accelerated aging data using a Taber test which provides abrasion wear coefficients for the cable materials. The models have been embedded into a software tool that predicts the life expectancy of the cable and demonstrated for narrow conditions, where the tidal flow is unidirectional and perpendicular to the power cable. The paper also provides discussion on how the developed models can be used with other condition monitoring data sets in a prognostics framework.

@en

As one of solid state lighting sources, wafer-level chip scale Light Emitting Diode (LED) packages has gained much attention, because of its compact size, high power and high optical performance. For this package to be effective, the solder layer plays the critical role in heat dissipation, mechanical support and electrical conductivity. Among all types of solder materials, Sn-3.0Ag-0.5Cu (SAC305) solder alloy is considered as one of best chip-attachment candidates due to its acceptable cost, good solderability, and favorable shear strength. However, such solder connections are prone to fatigue over time due to thermal or power cycling. This paper models the wafer level chip scale LEDs soldered on both aluminum oxide and aluminum substrates with SAC305 solder alloy. Thermal cycling conditions are simulated to assess the fatigue damage of the solder interconnection. Von Mises stress and plastic work density are utilized to represent the fatigue damage per cycle by using finite element analysis (FEA) method. Important design considerations include the effects of LED chip substrate, thickness of the solder interconnections, void ratio in the solder connections and PCB substrate. The result is a set of fatigue damage accumulation metrics.

@en