Machine learning algorithm selection for windage alteration fault diagnosis of mine ventilation system

Machine learning algorithms have been widely used in mine fault diagnosis. The correct selection of the suitable algorithms is the key factor that affects the fault diagnosis. However, the impact of machine learning algorithms on the prediction performance of mine fault diagnosis models has not been fully evaluated. In this study, the windage alteration faults (WAFs) diagnosis models, which are based on K-nearest neighbor algorithm (KNN), multi-layer perceptron (MLP), support vector machine (SVM), and decision tree (DT), are constructed. Furthermore, the applicability of these four algorithms in the WAFs diagnosis is explored by a T-type ventilation network simulation experiment and the field empirical application research of Jinchuan No. 2 mine. The accuracy of the fault location diagnosis for the four models in both networks was 100%. In the simulation experiment, the mean absolute percentage error (MAPE) between the predicted values and the real values of the fault volume of the four models was 0.59%, 97.26%, 123.61%, and 8.78%, respectively. The MAPE for the field empirical application was 3.94%, 52.40%, 25.25%, and 7.15%, respectively. The results of the comprehensive evaluation of the fault location and fault volume diagnosis tests showed that the KNN model is the most suitable algorithm for the WAFs diagnosis, whereas the prediction performance of the DT model was the second-best. This study realizes the intelligent diagnosis of WAFs, and provides technical support for the realization of intelligent ventilation.     

The formed surface characteristics of SiCf/SiC composite in the nanosecond pulsed laser ablation

For the advantages of high-temperature resistance, corrosion resistance and ultra-high hardness, SiC_f/SiC composite is becoming a preferred material for manufacturing aero-engine parts. However, the anisotropy and heterogeneity bring great challenges to the processing technology. In this study, a nanosecond pulsed laser is applied to process SiC_f/SiC composite, where the influence of the scanning speed and laser scanning direction to the SiC fibers on the morphology of ablated grooves is investigated. The surface characteristics after ablation and the involved chemical reaction of SiC_f/SiC are explored. The results show that the increased laser scanning speed, accompanied by the decreasing spot overlap rate, leads to the less accumulation of energy on the material surface, so the ablation effect drops. In addition, for the anisotropy of the SiC_f/SiC material, the obtained surface characteristics are closely dependent on the laser scanning direction to the SiC fibers, resulting in different groove morphology. The element composition and phase analysis of the machined surface indicate that the main deposited product is SiO₂ and the carbon substance. The results can provide preliminary technical support for controlling the machining quality of ceramic matrix composites.     

Study on the non-uniform contact during ELID groove grinding

This paper introduces the potential feasibility that ELID (electrolytic in-process dressing) grinding replaces superfinishing in bearing manufacturing, but ELID grinding will bring new challenges. Different regions present distinguish surface profile due to the non-uniform contact in ELID groove grinding. However, few reports explaining the non-uniform contact are available. This article explores the mechanisms of the non-uniform contact during ELID groove grinding. Experiments on the non-uniform contact between bearing raceway and grinding wheel have been carried out under different conditions. The results show that non-uniform contact exists in ELID groove grinding process and it exerts influence on the profile of the raceway surface. Non-uniform contact influences the Rsk and Rku value all the time, but it influences the Ra value occasionally. Improvement strategies of eliminating the non-uniform contact are also discussed based on the experimental study.     

Influence of surface topography evolution of grinding wheel on the optimal material removal rate in grinding process of cemented carbide

Most of the reported studies on the optimization of grinding parameters do not consider the evolution of the surface topography of grinding wheels, and the established empirical models will no longer apply when the surface conditions of the grinding wheel changes. In this paper, an integrated model based on the surface topography of grinding wheel is established. The grinding process of cemented carbide is simulated using the established model, and the simulation results are analyzed to obtain the surface roughness model and the specific grinding energy model based on the undeformed chip thickness distribution. Subsequently, the grinding constraint models are defined according to the two grinding constraints—surface roughness and specific grinding energy. Through inversion analysis, the maximum material removal rate of the given grinding wheel surface conditions satisfying the defined grinding constraints are obtained, and the influence rules of the grinding wheel surface conditions on the maximum material removal rate are analyzed. Then the grinding wheel surface conditions are adjusted by changing the radial dressed height of the grinding wheel and the arrangement distance of the grains in wheel circumferential direction to improve the maximum material removal rate of the grinding wheel. Finally, the optimization results are verified through grinding tests of cemented carbide.     

Assessment of spray quality from an external mix nozzle and its impact on SQL grinding performance

Spray quality is the critical factor which decides the efficacy of Small Quantity Lubrication (SQL) technology in a high specific energy involved machining process like grinding. Yet, the understanding about spray quality, the actual process mechanics and its effect on machining performance is inadequate. The present work is an attempt to establish a correlation between the spray input variables, quality of the spray and machining performance of SQL grinding through modelling and experiments. Using computational fluid dynamic techniques, the variation of droplet size, droplet velocity, number of droplets and heat transfer coefficient have been analysed at different input parameters and the computed trends have been verified and validated. CFD modelling of spray indicates that it is possible to produce aerosol medium with high heat dissipation ability at moderately high air pressure and low flow rate. It also shows that any increase in atomising air pressure favourably leads to notable increase in wetting area and also results in substantial enhancement in heat dissipation ability. Reduction of residual stress is thus remarkably good. On the other hand, grinding fluid flow rate, if increased, offers significantly better lubricity and reduces the grinding force which also reduces tensile residual stress. Short spell grinding test results are found to be in good agreement with CFD results.     

Relation between wear and tooth width modification in spur gears

In this experimental study, width modification of a spur gear was investigated to fix instantaneous pressure changes along single meshing area on the gear profile. In this gear, variable pressure distribution caused by the single and double teeth meshing and the radius of curvature along the active gear profile was approximately kept constant by maintaining a constant ratio of applied load to the tooth width (F/b) on every point. Hence, Hertz pressure distribution along the gear profile was approximately equally achieved. Other factors affecting wear were kept constant during the experiment. The specimen used was made from AISI 4140 steel. Finally, the amount of wear in the teeth profiles between the modified and unmodified gears was compared. And wear depth of modified gear along the meshing area was almost uniform.     

Digital Twin Enhanced Dynamic Job-Shop Scheduling

For dynamic scheduling, which is daily decision-making in a job-shop, machine availability prediction, disturbance detection and performance evaluation are always common bottlenecks. Previous research efforts on addressing the bottlenecks primarily emphasize on the analysis of data from the physical job-shop, but with little connection and convergence with its virtual models and simulated data. By introducing digital twin (DT), further convergence between physical and virtual spaces of the job-shop can be achieved, which greatly enables dynamic scheduling. DT fuses both real and simulated data to provide more information for the prediction of machine availability on one hand; and on the other hand, it helps to detect disturbances through comparing the physical machine with its continuously updated digital counterpart in real time, triggering timely rescheduling when needed. It also enables comprehensive performance evaluation for rescheduling using multiple-dimension models, which can describe geometric properties, physics parameters and behaviors of the machines. In the paper, a five-dimension DT for a machine in the job-shop is introduced first, then the DT-based machine availability prediction, disturbance detection and performance evaluation methods are explored. Based on this, a DT-enhanced dynamic scheduling methodology is proposed. A scheduling process of making hydraulic valves in a machining job-shop is taken as a case study to illustrate the effectiveness and advantages of the proposed method.     

Intelligent tool wear monitoring based on parallel residual and stacked bidirectional long short-term memory network

Effective tool wear monitoring (TWM) is essential for accurately assessing the degree of tool wear and for timely preventive maintenance. Existing data-driven monitoring methods mainly rely on complex feature engineering, which reduces the monitoring efficiency. This paper proposes a novel TWM model based on a parallel residual and stacked bidirectional long short-term memory (PRes–SBiLSTM) network. First, a parallel residual network (PResNet) is used to extract the multi-scale local features of sensor signals adaptively. Subsequently, a stacked bidirectional long short-term memory (SBiLSTM) network is used to obtain the time-series features related to the tool wear characteristics. Finally, the predicted tool wear value is outputted through a fully connected network. A smoothing correction method is applied to improve the prediction accuracy. The proposed model is experimentally verified to have a high prediction accuracy without sacrificing its generalization ability. A TWM system framework based on the PRes–SBiLSTM network is proposed, which has a certain reference value for TWM in actual industrial environments.     

Accurate positioning of a drilling and riveting cell for aircraft assembly

Modern aircraft assembly demands assembly cells or machines with higher machining efficiency and accuracy. Thus, a dual-machine drilling and riveting cell is developed in this paper. We firstly discuss its physical design, as well as the automatic drilling and riveting process. With the automatic drilling and riveting cell, drilling and riveting production line of aircraft panels can be expected. The frame chain of the drilling and riveting cell is constructed to link the assembly cell to its task space, which is the kinematics base. System calibrations, including task space calibration, the sensor calibration of an orientation alignment unit, the floating calibration of the implicit hand-eye relationship, are explored. For high positioning accuracy, a multi-sensor servoing method is proposed for cell positioning. An orientation-based laser servoing strategy, which uses the feedback of the orientation errors measured by laser displacement sensors, is used to align drilling direction and camera shooting direction. Besides, A single-camera-based visual servoing is applied to align the tool center point (TCP) to reference holes, to obtain their coordinates for drilling position modification. Experiments of multi-sensor servoing for cell positioning are performed on an automatic drilling and riveting machine developed for the panel assembly of an aircraft in China. With the cell positioning method, the automatic drilling and riveting cell can approximately achieve an accuracy of 0.05 mm, which can adequately fulfill the requirement for the assembly of the aircraft.     

New software developments for quality mesh generation and optimization from biomedical imaging data

In this paper we present a new software toolkit for generating and optimizing surface and volumetric meshes from three-dimensional (3D) biomedical imaging data, targeted at image-based finite element analysis of some biomedical activities in a single material domain. Our toolkit includes a series of geometric processing algorithms including surface re-meshing and quality-guaranteed tetrahedral mesh generation and optimization. All methods described have been encapsulated into a user-friendly graphical interface for easy manipulation and informative visualization of biomedical images and mesh models. Numerous examples are presented to demonstrate the effectiveness and efficiency of the described methods and toolkit.