Energy optimisation for the combination of turning and drilling features using differential evolution.

Cutting parameter optimisation is an effective way to realise energy-efficient machining. In previous studies, the cutting parameters of machining features of turning, milling, grinding, drilling, hobbing, and threading were optimised to decrease energy consumed by machine tools, and considerable energy savings were achieved. However, the energy consumption (EC) for each feature was separately optimised without systematic consideration of the negative effects on the EC for other features. The total EC for all features together probably increases. Hence, the trade-off amongst the reductions of EC for each feature needs to be jointly optimised. In our study, the external turning and drilling features are selected as examples to be combined. As a key novel contribution, we propose the integrated dimensional and cutting parameter optimisation problem about minimising the EC of Machine Tools for the combination of Turning and Drilling features (EMT-TD). In terms of optimisation, differential evolution (DE) is adopted to minimise the EMT-TD. According to case studies, DE obtained the optimal solutions within a computation time of 1 second. The optimal solutions achieved savings of 5.41%, 10.85%, and 7.19% of EMT-TD and savings of 2.23%, 5.90%, and 2.73% of machining time for three typical cases, respectively.

Energy benchmark for energy-efficient path planning of the automated guided vehicle.

The automated guided vehicle (AGV) is a piece of promising advanced transport equipment that has been widely used in flexible manufacturing systems to increase productivity and automation. Previous studies about the AGV focused on improving the capacities of perception, navigation, and anti-collision as well as reducing the transport time, cost, and distance, but insufficient attention was paid to the energy consumption (EC) reduction of AGV. The energy benchmark is recognised as an effective analytical methodology and management tool that can improve energy efficiency. Nonetheless, research on the energy benchmark for the AGV is lacking. To finish a transport task, many AGV path plans are feasible, and we develop an energy benchmark to evaluate each path plan and select the energy-saving one. We also establish a dynamic rating system of energy efficiency which is consistent with the energy-saving potentials of the transport task. The case study shows that the transport EC is reduced by 10.98 %, validating the proposed energy benchmark methodology. In addition, the effects of AGV path plans on the EC of machine tools at the workstations are analysed. Lastly, we explore the relationship between the energy efficiency of AGV path plans and the locations of workstations.

Locally Weighted Principal Component Analysis-Based Multimode Modeling for Complex Distributed Parameter Systems.

Global principal component analysis (PCA) has been successfully introduced for modeling distributed parameter systems (DPSs). In spite of the merits, this method is not feasible due to parameter variations and multiple operating domains. A novel multimode spatiotemporal modeling method based on the locally weighted PCA (LW-PCA) method is developed for large-scale highly nonlinear DPSs with parameter variations, by separating the original dataset into tractable subsets. This method implements the decomposition by making full use of the dependence among subset densities. First, the spatiotemporal snapshots are divided into multiple different Gaussian components by using a finite Gaussian mixture model (FGMM). Once the components are derived, a Bayesian inference strategy is then applied to calculate the posterior probabilities of each spatiotemporal snapshot belonging to each component, which will be regarded as the local weights of the LW-PCA method. Second, LW-PCA is adopted to calculate each locally weighted snapshot matrix, and the corresponding local spatial basis functions (SBFs) can be generated by the PCA method. Third, all the local temporal models are estimated using the extreme learning machine (ELM). Thus, the local spatiotemporal models can be produced with local SBFs and corresponding temporal model. Finally, the original system can be approximated using the sum form of each local spatiotemporal model. Unlike global PCA, which uses global SBFs to construct a global spatiotemporal model, LW-PCA approximates the original system by multiple local reduced SBFs. Numerical simulations verify the effectiveness of the developed multimode spatiotemporal model.