Explore the vast range of titles available.

Tool remaining useful life prediction is important to guarantee processing quality and efficient continuous production. Tool wear is directly related to the working conditions, showing a complex correlation and timing correlation, which makes it difficult to predict the tool remaining useful life under variable conditions. In this paper, we seek to overcome this challenge. First, we establish the unified representation of the working condition, then extract the wear characteristics from the processing signal. The extracted wear features and corresponding working conditions are combined into an input matrix for predicting tool wear. Based on this, the complex spatio-temporal relationship under variable working conditions is captured. Finally, using the unique advantages of the long short-term memory (LSTM) model to solve complex correlation and memory accumulation effects, the tool remaining useful life prediction model under variable working conditions is established. An experiment illustrates the effectiveness of the proposed method.

To better handle temporal data and delve into learning the features of the data, a turbofan engine residual life prediction method is proposed, which integrates a dual-squeeze-excitation attention mechanism with a multi-scale temporal convolutional network. Firstly, utilizing a sliding window, the extracted multi-dimensional sensor features undergo overlapping sampling to enhance the model’s perception of temporal data. Secondly, a hybrid network prediction model based on DSE-MTCN is constructed, employing multi-scale convolutional kernels to expand the receptive field of convolution, assigning different weights to features, and adaptively allocating weights to hidden layer units. Lastly, the DSE-MTCN prediction model is globally optimized using the RAdam algorithm. The results demonstrate that this method effectively enhances the accuracy and generalization ability of the prediction model.

It is beneficial to maintain the normal operation of machines by conducting remaining useful life (RUL) prediction. Recently, graph data-driven machine RUL prediction methods have made a great success, since graph can model spatial and temporal dependencies of signals. However, the constructed graphs still have some limitations: (1) In the practical industrial production, the installation of multi-sensor networks is expensive and hard to achieve, so the single sensor is commonly used for data monitoring. However, most of these methods constructed graphs by establishing relationships between the different sensors, which are completely unsuitable for prediction tasks in single-sensor scenarios. (2) The quality of constructed graph is low, where the graph structure is fixed, failing in representing the machine degradation process. To overcome these limitations, a dynamic spatial–temporal (ST) graph-driven machine RUL prediction method using graph data augmentation (GDA) is proposed. The ST graph is constructed using short-time Fourier transform, capturing the frequency-domain and time-domain information hidden in the signals. Then, a GDA framework is designed to generate dynamic ST graphs, enlarging the structural differences of subgraphs. Subsequently, a GDA-based graph deep learning prediction model is constructed for dynamic ST graph-based RUL prediction, where an autoencoder-based graph embedding module is designed to replace simple Readout. Verification experiments are conducted on two case studies, and the results show that the proposed prediction method achieves a competitive performance.

Nowadays, new challenges around increasing production quality and productivity, and decreasing energy consumption, are growing in the manufacturing industry. In order to tackle these challenges, it is of vital importance to monitor the health of critical components. In the machine tool sector, one of the main aspects is to monitor the wear of the cutting tools, as it affects directly to the fulfillment of tolerances, production of scrap, energy consumption, etc. Besides, the prediction of the remaining useful life (RUL) of the cutting tools, which is related to their wear level, is gaining more importance in the field of predictive maintenance, being that prediction is a crucial point for an improvement of the quality of the cutting process. Unlike monitoring the current health of the cutting tools in real time, as tool wear diagnosis does, RUL prediction allows to know when the tool will end its useful life. This is a key factor since it allows optimizing the planning of maintenance strategies. Moreover, a substantial number of signals can be captured from machine tools, but not all of them perform as optimum predictors for tool RUL. Thus, this paper focuses on RUL and has two main objectives. First, to evaluate the optimum signals for RUL prediction, a substantial number of them were captured in a turning process and investigated by using recursive feature elimination (RFE). Second, the use of bidirectional recurrent neural networks (BRNN) as regressive models to predict the RUL of cutting tools in machining operations using the investigated optimum signals is investigated. The results are compared to traditional machine learning (ML) models and convolutional neural networks (CNN). The results show that among all the signals captured, the root mean squared (RMS) parameter of the forward force (Fy) is the optimum for RUL prediction. As well, the bidirectional long-short term memory (BiLSTM) and bidirectional gated recurrent units (BiGRU), which are two types of BRNN, along with the RMS of Fy signal, achieved the lowest root mean squared error (RMSE) for tool RUL, being also computationally the most demanding ones.

Cooked cured ham is a ready-to-eat food that is popular among consumers. Stored temperature has a key effect on the quality and shelf life of ham. In this work, the quality changes and shelf-life prediction of cooked cured ham stored at different temperatures were investigated. Sensory evaluation, physical and chemical indicators, and aerobic plate count were determined. Results showed that high storage temperature of cooked ham accelerates quality deterioration. Partial least squares (PLS) regression analysis based on the variable importance for projection identified nine important variables for predicting the shelf life of cooked cured ham. Compared with either PLS or back-propagation artificial neural network, the hybrid PLS-back-propagation artificial neural network model better predicts the shelf life of cooked cured ham by using the nine variables. This study provides a theoretical basis and data support for the quality control of cooked cured ham and a new idea for research on the shelf-life prediction of cooked cured ham.

In this paper, a new method for fatigue life prediction under multiaxial stress-strain conditions is developed. The method applies machine learning with the Gaussian process for regression to build a fatigue model. The fatigue failure mechanisms are reflected in the model by the application of the physics-based stress and strain invariants as input quantities. The application of the machine learning algorithm solved the problem of assigning an adequate parametric fatigue model to given material and loading conditions. The model was verified using the experimental data on the CuZn37 brass subjected to various cyclic loadings, including non-proportional multiaxial strain paths. The performance of the machine learning-based fatigue life prediction model is higher than the performance of the well-known parametric models.

The current research on shot peening of metal surfaces is mainly concentrated in the field of single-sided shot peening, and fewer researchers have conducted in-depth studies on the mechanism of double-sided shot peening. In this paper, the influence of different shot peening parameters on the fatigue life of double-sided shot peening of SAE1070 alloy steel is investigated, and at the same time, a fatigue life prediction model after double-sided shot peening of metal surfaces is established innovatively. Firstly, the DE-FE (discrete element-finite element) random multi-shot analysis mode is used to simulate the double-sided shot peening processing of AE1070 alloy steel using different shot peening parameters, respectively, and then, the model after shot peening is imported into fe-safe software for fatigue simulation test, and the same conditions are used to carry out the double-sided shot peening test on the specimen pieces of SAE1070, and then, the fatigue life test is carried out for the shot peening processed parts. The simulation results are compared with the test results. It can be found through the results that double-sided shot peening can effectively improve the comprehensive mechanical properties of SAE1070 alloy steel and increase its fatigue life. The effect of different strengths of shot peening varies significantly, and the optimal shot peening effect is achieved by the optimized shot peening parameters. The simulation and test results are more consistent, indicating that the established fatigue life prediction model can predict the fatigue life results more accurately. Graphical Abstract

Due to their distinct physical, chemical, and mechanical features, high-entropy alloys have significantly broadened the possibilities of designing metal materials, and are anticipated to hold a crucial position in key engineering domains such as aviation and aerospace. The fatigue performance of high-entropy alloys is a crucial aspect in assessing their applicability as a structural material with immense potential. This paper provides an overview of fatigue experiments conducted on high-entropy alloys in the past two decades, focusing on crack initiation behavior, crack propagation modes, and fatigue life prediction models.

This study proposes a methodology for developing deterioration models and predicting the service lives of vertical assets of urban water systems (i.e., water storage tanks and pumping stations) using regression analysis. The main factors contributing to the deterioration of these assets are analyzed. Simple and multiple linear regression models of average and maximum deterioration are calculated for 22 water storage tanks and 17 wastewater pumping stations. Data on a set of four water storage tanks are used to validate the developed deterioration models. Service life prediction is carried out using the developed models and considering two maximum deterioration levels: the maximum recommended and admissible deterioration levels. Two water storage tanks are further studied to illustrate and discuss the effect of maintenance and rehabilitation interventions on asset service life by comparing the asset deterioration before and after the interventions. Results include simple linear regression models of average and maximum deterioration indices as a function of asset age and multiple linear regression models that incorporate other physical, operational and environmental factors. The results show that simple linear regression models of asset deterioration show a better predictive power than multiple regression models. Despite the higher data variability of multiple regression models, these models allow to include the random process of asset deterioration, through the calculation of the standard deviation. This study also shows that periodic interventions are a preferable maintenance and rehabilitation strategy over major sporadic rehabilitation interventions since it allows to maintain assets in good condition and to extend their service life almost indefinitely. Plain Language Summary Urban water assets are continuously deteriorating and more investments are necessary to maintain adequate levels of service. However, investment budgets are often limited and appropriate deterioration models and reliably predicted service lives are essential for planning and scheduling maintenance actions. This paper develops deterioration models for water storage tanks and wastewater pumping stations based on the identification and classification of anomalies through visual inspection. Additionally, service lives (i.e., the period from the installation until the asset or its components fulfill the service requirements) were obtained and compared with reference values. Finally, the effect of maintenance actions and rehabilitation interventions on the service life of vertical assets was discussed. In order to maintain a good asset condition and extend its service life quasi‐indefinitely, periodic and well‐established interventions are a preferable maintenance and rehabilitation strategy over major sporadic rehabilitation interventions. Key Points Physical, operational and environmental factors of asset deterioration are discussed and deterioration models are summarized Predicted service lives are obtained and the effect of maintenance and rehabilitation interventions on asset service life are analyzed The methodology for service life prediction can be applied to other water assets