Simulation evaluation of dynamic characteristic identification accuracy of sliding bearing considering test error

Aiming at the dynamic characteristics test bench of sliding bearings, the dynamic model is established. Based on the forward and inverse dynamic problems of the bearing, a simulation evaluation method for the identification accuracy of the sliding bearing dynamic characteristics is proposed and the algorithm is verified. The identification errors of dynamic characteristic coefficients under different excitation frequencies are analyzed, the sensitivities of single frequency excitation method and dual-frequency excitation method to test error are contrastively analyzed, and the influence laws of dynamic characteristic identification accuracy of sliding bearing are evaluated. Based on which the traditional single frequency excitation method has been improved. The dynamic characteristic test should be carried out respectively in the low frequency range and the high frequency range. The main stiffness and cross damping are the average of two tests, the main damping is the identification value in the high frequency, and the cross stiffness is the identification value in the low frequency. That will effectively reduce the impact of test error. The obtained data and laws could support the improvement of the dynamic characteristics test method of sliding bearings and the confirmation of test parameters, thereby the accuracy of dynamic characteristics identification is improved.

Experimental Investigation on the Influence of Ambient Temperature on the Test Accuracy for the Differential Pressure Hydrostatic Levelling System

Hydrostatic levelling system (HLS) is widely used to monitor the settlement of major projects, such as high-speed railways, bridges, tunnels, dams, and nuclear power plants; ambient temperature is the most important influencing factor in the actual engineering settlement detection process. In order to systematically study the influence of ambient temperature TA on the test accuracy of the HLS, a test platform was built in the ambient temperature laboratory, and the influence of factors, including the amount of TA change, the rate of increase/decrease of TA, the expansion coefficient of the connecting pipe, and the distance of the measuring point, on the HLS test accuracy was quantitatively analyzed. The test results show that the elevation of a single HSL case has a linear correlation with the ambient temperature; when the temperature rise rate is greater than 0.1°C/min, the measured data are distorted due to incomplete development of material expansion. The temperature influence coefficient of a single HSL case is linearly related to the expansion coefficient deviation between the refrigerant and pipe; the test error of the double HLS case caused by TA is attributed to the expansion coefficient deviation of the pipe and the refrigerant between the base station and the measuring point. The relative temperature influence coefficient increases as distance measurement increases, and the HLS test error caused by TA will maintain a constant value when the distance measurement exceeds a certain value.

Impedance-based forecasting of battery performance amid uneven usage

Accurate forecasting of lithium-ion battery performance is important for easing consumer concerns about the safety and reliability of electric vehicles. Most research on battery health prognostics focuses on the R&D setting where cells are subjected to the same usage patterns, yet in practice there is great variability in use across cells and cycles, making forecasting much more challenging. Here, we address this challenge by combining electrochemical impedance spectroscopy (EIS), a non-invasive measurement of battery state, with probabilistic machine learning. We generated a dataset of 40 commercial lithium-ion coin cells cycled under multistage constant current charging/discharging, with currents randomly changed between cycles to emulate realistic use patterns. We show that future discharge capacities can be predicted with calibrated uncertainties, given the future cycling protocol and a single EIS measurement made just before charging, and without any knowledge of usage history. Our method is data-efficient, requiring just eight cells to achieve a test error of less than 10%, and robust to dataset shifts. Our model can forecast well into the future, attaining a test error of less than 10% when projecting 32 cycles ahead. Further, we find that model performance can be boosted by 25% by augmenting EIS with additional features derived from historical capacity-voltage curves. Our results suggest that battery health is better quantified by a multidimensional vector rather than a scalar State of Health, thus deriving informative electrochemical `biomarkers' in tandem with machine learning is key to predictive battery management and control.

Development and experimental study of analyzer to enhance maritime safety

On the basis of empirical experimental data, relationships were identified indicating the influence of navigators' response to such vessel control indicators as maneuverability and safety. This formed a hypothesis about a non-random connection between the navigator's actions, response and parameters of maritime transport management. Within the framework of this hypothesis, logical-formal approaches were proposed that allow using server data of both maritime simulators and operating vessels in order to timely identify the occurrence of a critical situation with possible catastrophic consequences. A method for processing navigation data based on the analysis of temporal zones is proposed, which made it possible to prevent manifestations of reduced efficiency of maritime transport management by 22.5 %. Based on cluster analysis and automated neural networks, it was possible to identify temporary vessel control fragments and classify them by the level of danger. At the same time, the neural network test error was only 3.1 %, and the learning error was 3.8 %, which ensures the high quality of simulation results. The proposed approaches were tested using the Navi Trainer 5000 navigation simulator (Wärtsilä Corporation, Finland). The simulation of the system for identifying critical situations in maritime transport management made it possible to reduce the probability of catastrophic situations by 13.5 %. The use of automated artificial neural networks allowed defining critical situations in real time from the database of maritime transport management on the captain's bridge for an individual navigator.

Constant optimization and feature standardization in multiobjective genetic programming

This paper extends the numerical tuning of tree constants in genetic programming (GP) to the multiobjective domain. Using ten real-world benchmark regression datasets and employing Bayesian comparison procedures, we first consider the effects of feature standardization (without constant tuning) and conclude that standardization generally produces lower test errors, but, contrary to other recently published work, we find much less clear trend for tree sizes. In addition, we consider the effects of constant tuning – with and without feature standardization – and observe that (1) constant tuning invariably improves test error, and (2) usually decreases tree size. Combined with standardization, constant tuning produces the best test error results; tree sizes, however, are increased. We also examine the effects of applying constant tuning only once at the end a conventional GP run which turns out to be surprisingly promising. Finally, we consider the merits of using numerical procedures to tune tree constants and observe that for around half the datasets evolutionary search alone is superior whereas for the remaining half, parameter tuning is superior. We identify a number of open research questions that arise from this work.

Rethink the Connections among Generalization, Memorization, and the Spectral Bias of DNNs

Over-parameterized deep neural networks (DNNs) with sufficient capacity to memorize random noise can achieve excellent generalization performance, challenging the bias-variance trade-off in classical learning theory. Recent studies claimed that DNNs first learn simple patterns and then memorize noise; some other works showed a phenomenon that DNNs have a spectral bias to learn target functions from low to high frequencies during training. However, we show that the monotonicity of the learning bias does not always hold: under the experimental setup of deep double descent, the high-frequency components of DNNs diminish in the late stage of training, leading to the second descent of the test error. Besides, we find that the spectrum of DNNs can be applied to indicating the second descent of the test error, even though it is calculated from the training set only.

Materials property prediction for limited datasets enabled by feature selection and joint learning with MODNet

In order to make accurate predictions of material properties, current machine-learning approaches generally require large amounts of data, which are often not available in practice. In this work, MODNet, an all-round framework, is presented which relies on a feedforward neural network, the selection of physically meaningful features, and when applicable, joint-learning. Next to being faster in terms of training time, this approach is shown to outperform current graph-network models on small datasets. In particular, the vibrational entropy at 305 K of crystals is predicted with a mean absolute test error of 0.009 meV/K/atom (four times lower than previous studies). Furthermore, joint learning reduces the test error compared to single-target learning and enables the prediction of multiple properties at once, such as temperature functions. Finally, the selection algorithm highlights the most important features and thus helps to understand the underlying physics.

The success of AdaBoost and its application in portfolio management

We develop a novel approach to explain why AdaBoost is a successful classifier. By introducing a measure of the influence of the noise points (ION) in the training data for the binary classification problem, we prove that there is a strong connection between the ION and the test error. We further identify that the ION of AdaBoost decreases as the iteration number or the complexity of the base learners increases. We confirm that it is impossible to obtain a consistent classifier without deep trees as the base learners of AdaBoost in some complicated situations. We apply AdaBoost in portfolio management via empirical studies in the Chinese market, which corroborates our theoretical propositions.

Computing Expectiles Using k-Nearest Neighbours Approach

Expectiles have gained considerable attention in recent years due to wide applications in many areas. In this study, the k-nearest neighbours approach, together with the asymmetric least squares loss function, called ex-kNN, is proposed for computing expectiles. Firstly, the effect of various distance measures on ex-kNN in terms of test error and computational time is evaluated. It is found that Canberra, Lorentzian, and Soergel distance measures lead to minimum test error, whereas Euclidean, Canberra, and Average of (L1,L∞) lead to a low computational cost. Secondly, the performance of ex-kNN is compared with existing packages er-boost and ex-svm for computing expectiles that are based on nine real life examples. Depending on the nature of data, the ex-kNN showed two to 10 times better performance than er-boost and comparable performance with ex-svm regarding test error. Computationally, the ex-kNN is found two to five times faster than ex-svm and much faster than er-boost, particularly, in the case of high dimensional data.

Assessment of the Content of Dry Matter and Dry Organic Matter in Compost with Neural Modelling Methods

Neural image analysis is commonly used to solve scientific problems of biosystems and mechanical engineering. The method has been applied, for example, to assess the quality of foodstuffs such as fruit and vegetables, cereal grains, and meat. The method can also be used to analyse composting processes. The scientific problem lets us formulate the research hypothesis: it is possible to identify representative traits of the image of composted material that are necessary to create a neural model supporting the process of assessment of the content of dry matter and dry organic matter in composted material. The effect of the research is the identification of selected features of the composted material and the methods of neural image analysis resulted in a new original method enabling effective assessment of the content of dry matter and dry organic matter. The content of dry matter and dry organic matter can be analysed by means of parameters specifying the colour of compost. The best developed neural models for the assessment of the content of dry matter and dry organic matter in compost are: in visible light RBF 19:19-2-1:1 (test error 0.0922) and MLP 14:14-14-11-1:1 (test error 0.1722), in mixed light RBF 30:30-8-1:1 (test error 0.0764) and MLP 7:7-9-7-1:1 (test error 0.1795). The neural models generated for the compost images taken in mixed light had better qualitative characteristics.