Machine learning models have been widely used in the field of cutting tool wear identification, achieving favorable results. However, in actual industrial scenarios, obtaining sufficient labeled samples is time consuming and costly, while unlabeled samples are abundant and easy to collect. This situation significantly affects the model’s performance. To address this challenge, a novel semi-supervised method, based on long short-term memory (LSTM) networks, is provided. The proposed method leverages both small labeled and abundant unlabeled data to improve tool wear identification performance. The proposed method trains an initial tool wear regression model using LSTM, using a small amount of labeled samples. It then uses manifold regularization to generate pseudo-labels for the unlabeled samples. These pseudo-labeled samples are combined with the original labeled samples to retrain the MR–LSTM model iteratively to improve its performance. This process continues until a termination condition is met. The method considers the correlation between sample labels and feature structures, as well as the correlation between global and local sample labels. Experiments involving milling tool wear identification demonstrate that the proposed method significantly outperforms support vector regression (SVR) and recurrent neural network (RNN)-based methods, when a small amount of labeled samples and abundant unlabeled samples are available. The average R² values in terms of the proposed method’s predicted results can reach above 0.95. The proposed method is a potential technique for low-cost tool wear identification, without the need to collect a large number of labeled samples.

To reduce the experimental costs associated with tool condition monitoring (TCM) under new cutting conditions, a finite element modeling (FEM)-assisted deep subdomain adaptive network (DSAN) approach is proposed. Initially, an FEM technique is employed to construct a cutting tool model for the new cutting condition (target domain), and the similarity between simulated and experimental data is assessed to obtain valid simulated samples for the target domain. Subsequently, the time–frequency Markov representation method is utilized to extract imaging features from the simulated samples, which serve as input features for the monitoring model. Then, a DSAN model is established to facilitate the transfer from simulation to reality, with the source domain comprising a simulated sample set under new cutting conditions that includes various types of tool conditions obtained through FEM, and the target domain containing only a limited number of normal tool condition samples under new cutting conditions. The application analysis has demonstrated the effectiveness of the proposed method, achieving a classification accuracy of 99%. The proposed approach can significantly reduce experimental costs and obtain high-precision diagnostics of tool conditions with a small sample size.

Industrial effluents often contain azeotropic mixtures that are difficult to separate by conventional distillation. An illustrative case is the methanol/methyl acetate/ethyl acetate (MA/ME/EA) mixture. To address these challenges, this work studies the conceptual design and optimization of the reactive distillation-based hybrid processes for separating the MA/ME/EA mixture with an EA-rich feed composition (0.25/0.20/0.55 mol fraction). An improved triple-column extractive–reactive distillation with a side-draw product (TCERD-SP) and its heat-integrated variant (TCERD-SP-HI) have been developed. In the TCERD-SP process, EA is strategically withdrawn as a side product, reconfiguring the extractive column into integrated pre-separation and entrainer-recovery sections, thereby reducing entrainer and energy demands. A four-step process design methodology is applied, including thermodynamics analysis, conceptual design, rigorous optimization via Aspen Plus integrated with the genetic algorithm to minimize total annual cost (TAC), and comparative evaluation of economic and environmental performance. The results show that the basic double-column pre-separation-reactive distillation (DCPSRD) process, optimal for a previous feed composition, exhibits unsatisfactory TAC performance for this EA-rich feed composition. Among the configurations studied, the TCERD-SP process exhibits superior performance, saving TAC by 8.4% and 14.4% compared to the TCERD and DCPSRD processes, respectively. In addition, based on the advantage of convenient heat integration between the side reboiler and the reactive distillation column condenser, the heat-integrated TCERD-SP-HI process achieves a further 10.7% TAC reduction. Thus, for this EA-rich feed examined in this work, the TCERD-SP and TCERD-SP-HI processes are demonstrated as effective solutions for recovering these valuable chemicals.