Due to the advances in the digitalization process of the manufacturing industry and the resulting available data, there is tremendous progress and large interest in integrating machine learning and optimization methods on the shop floor in order to improve production processes. Additionally, a shortage of resources leads to increasing acceptance of new approaches, such as machine learning to save energy, time, and resources, and avoid waste. After describing possible occurring data types in the manufacturing world, this study covers the majority of relevant literature from 2008 to 2018 dealing with machine learning and optimization approaches for product quality or process improvement in the manufacturing industry. The review shows that there is hardly any correlation between the used data, the amount of data, the machine learning algorithms, the used optimizers, and the respective problem from the production. The detailed correlations between these criteria and the recent progress made in this area as well as the issues that are still unsolved are discussed in this paper.

A review of machine learning for the optimization of production processes

Vulnerability assessment is one of the prerequisites for risk analysis in disaster management. Vulnerability to earthquakes, especially in urban areas, has increased over the years due to the presence of complex urban structures and rapid development. Urban vulnerability is a result of human behavior which describes the extent of susceptibility or resilience of social, economic, and physical assets to natural disasters. The main aim of this paper is to develop a new hybrid framework using Analytic Network Process (ANP) and Artificial Neural Network (ANN) models for constructing a composite social, economic, environmental, and physical vulnerability index. This index was then applied to Tabriz City, which is a seismic-prone province in the northwestern part of Iran with recurring devastating earthquakes and consequent heavy casualties and damages. A Geographical Information Systems (GIS) analysis was used to identify and evaluate quantitative vulnerability indicators for generating an earthquake vulnerability map. The classified and standardized indicators were subsequently weighed and ranked using an ANP model to construct the training database. Then, standardized maps coupled with the training site maps were presented as input to a Multilayer Perceptron (MLP) neural network for producing an Earthquake Vulnerability Map (EVM). Finally, an EVM was produced for Tabriz City and the level of vulnerability in various zones was obtained. South and southeast regions of Tabriz City indicate low to moderate vulnerability, while some zones of the northeastern tract are under critical vulnerability conditions. Furthermore, the impact of the vulnerability of Tabriz City on population during an earthquake was included in this analysis for risk estimation. A comparison of the result produced by EVM and the Population Vulnerability (PV) of Tabriz City corroborated the validity of the results obtained by ANP-ANN. The findings of this paper are useful for decision-makers and government authorities to obtain a better knowledge of a city’s vulnerability dimensions, and to adopt preparedness strategies in the future for Tabriz City. The developed hybrid framework of ANP and ANN Models can easily be replicated and applied to other urban regions around the world for sustainability and environmental management.

A Hybrid Analytic Network Process and Artificial Neural Network (ANP-ANN) Model for Urban Earthquake Vulnerability Assessment

In current remote sensing literature, the problems of sea-land segmentation and ship detection (including in-dock ships) are investigated separately despite the high correlation between them. This inhibits joint optimization and makes the implementation of the methods highly complicated. In this paper, we propose a novel fully convolutional network to accomplish the two tasks simultaneously, in a semantic labeling fashion, i.e., to label every pixel of the image into 3 classes, sea, land and ships. A multi-scale structure for the network is proposed to address the huge scale gap between different classes of targets, i.e., sea/land and ships. Conventional multi-scale structure utilizes shortcuts to connect low level, fine scale feature maps to high level ones to increase the network’s ability to produce finer results. In contrast, our proposed multi-scale structure focuses on increasing the receptive field of the network while maintaining the ability towards fine scale details. The multi-scale convolution network accommodates the huge scale difference between sea-land and ships and provides comprehensive features, and is able to accomplish the tasks in an end-to-end manner that is easy for implementation and feasible for joint optimization. In the network, the input forks into fine-scale and coarse-scale paths, which share the same convolution layers to minimize network parameter increase, and then are joined together to produce the final result. The experiments show that the network tackles the semantic labeling problem with improved performance.

Maritime Semantic Labeling of Optical Remote Sensing Images with Multi-Scale Fully Convolutional Network

Waterjet machining has attracted great attention in the conditions of hard-to-machine materials, microstructures, or complicated industrial components, and it has become well-established in all major areas of theoretical researches and already been found across the broad spectrum of technical application areas especially in the specific sectors of scientific frontiers, including the mechanical precision component, advanced functional material, intelligent automotive engineering, aerospace equipment, renewable energy science, leading medical instruments, etc. This paper reviews the historical and latest research developments and integrated applications of waterjet machining in the domains of mechanism and performances, which covers a lot of key aspects such as waterjet machining optimization, dynamic simulation and process monitoring of machining process, and the influence mechanism of waterjet machining as well. Its machining mechanism, performance capability, functional advantages, and inherent disadvantages are characterized and assessed in detail, so that the integrated applications of multifield-assisted waterjet machining can be introduced and focused thereafter. Finally, various future development prospects in all the abovementioned aspects of waterjet machining are discussed systematically and explored subsequently, which contribute to the acquirement of a series of comprehensive conclusions. This review can be used as suitable and effective tools to study and summarize the complicated correlations between waterjet machining mechanism and its actual working performances in different environmental conditions; therefore, this proposed investigation facilitates the precision manufacture or characteristic improvements of industrial product with higher efficiency and better quality in return.

Waterjet machining and research developments: a review

Grinding is a multi-length scale material removal process that is widely employed to machine a wide variety of materials in almost every industrial sector. Surface roughness induced by a grinding operation can affect corrosion resistance, wear resistance, and contact stiffness of the ground components. Prediction of surface roughness is useful for describing the quality of ground surfaces, evaluate the efficiency of the grinding process and guide the feedback control of the grinding parameters in real-time to help reduce the cost of production. This paper reviews extant research and discusses advances in the realm of machining theory, experimental design and Artificial Intelligence related to ground surface roughness prediction. The advantages and disadvantages of various grinding methods, current challenges and evolving future trends considering Industry-4.0 ready new generation machine tools are also discussed.

New insights into the methods for predicting ground surface roughness in the age of digitalisation

In this paper, the working parameter optimization of strengthen waterjet grinding by employing the orthogonal-experiment-design-based ANFIS (Adaptive Neural Fuzzy Inference System), was conducted to obtain an optimal result of bearing ring machining. An improved ANFIS system based upon orthogonal experiment design, was proposed to optimize the working parameters in grinding practices, which increases the surface hardness of ring surface from 49.0 to 72.0 HRC, topography elasticity variance from 330.0 to 670.0, texture energy from 24.5 to 88.0, decreases the surface roughness from 0.65 to 0.25 $$\upmu $$m, and loading deviation from 1860.5 to 1320.0, thereafter an optimal grinding quality can be obtained. The optimization approach proposed involve the following steps: Preparation of experimental environment; Measure index determination for ring surface; Orthogonal experiment design for making fuzzy logic rules; Establishment of ANFIS system; Working parameter optimization for waterjet grinding; and Performance verification for actual grinding. Objective of this research is determining the optimal working parameters with fewer experimental iterations compared to other alternative approaches, such as Genetic parameter optimization, SA–GA parametric prediction, Taguchi parameter estimation, ANN–SA parametric selection, and GONNs parameter selection method. Statistical analysis and result comparisons support its efficiency and reliability in machining practices, a stable and reliable grinding process can be achieved for typical conditions by using waterjet pressure at around 310ṀPa, flow rates of water mass at about 5.8 kg/min, attack angle by 60–75$${^{\circ }}$$, mass rate of abrasive grit by about 0.4 kg/min, and traverse speed by 60 mm/min. It was concluded that this proposed ANFIS system can be used as a suitable and effective tool, to investigate the complicated influential correlation between waterjet working parameters and grinding effectiveness in bearing manufacturing, and to give a better machining performance compared to other experimental practices.

Working parameter optimization of strengthen waterjet grinding with the orthogonal-experiment-design-based ANFIS

For the purpose of improving the working performance of AWJ (Abrasive waterjet) grinding in actual machining, and revealing the unknown influence mechanism of waterjet machining prediction, this re...

https://tandfonline.com/doi/pdf/10.1080/19942060.2016.1277556

Fuzzy prediction of AWJ turbulence characteristics by using typical multi-phase flow models

In this paper, the component parameter optimization of strengthen waterjet grinding slurry, by using the orthogonal-experiment-design-based adaptive neural fuzzy inference system (ANFIS), was conducted to obtain an optimal grinding performance for bearing ring. An improved ANFIS system based upon orthogonal experiment design was proposed to optimize the component parameters of multi-phase waterjet slurry in grinding practices and gives better grinding quality on objective ring surface. This approach involves the following steps: preparation of experimental environment, determination of measure indexes for surface grinded, orthogonal experiment design with fuzzy logic rules, establishment of ANFIS system, parameter optimization for waterjet slurry, and actual improvement verification of waterjet grinding on ring surface. The objective of this research is determining the optimal component parameters of waterjet slurry with fewer experimental iterations compared to other alternative approaches. Statistical analysis and result comparisons support its efficiency and reliability in practical machining operations; therefore, a more stable grinding process and better finished surface can be obtained. It was concluded that the proposed ANFIS system can be used as a suitable and effective tool to investigate the complicated influential correlations between slurry components and grinding effectiveness in bearing manufacturing conditions, which makes an optimal machining performance compared to other experimental practices in return.

Component parameter optimization of strengthen waterjet grinding slurry with the orthogonal-experiment-design-based ANFIS

Video tracking of drug tablet exerts important influences on the efficiency and reliability of its mass production; this topic also becomes a difficult and targeted focus for pharmaceutical production monitory in the past several years due to the high similarity and random distribution of those objectives to be searched for. By measuring the reflective lightness intensity of illumination lightness on tablet surface, reflective lightness intensity matrix was established and demonstrated in the form of grey image, presenting its shape topology and topography details in return. On this basis, a series of mathematical properties for describing reflective lightness intensity images were proposed, thereafter a set of fuzzy recognition system and its identification rules can be employed to classify those moving tablets with inputted image properties, which facilitates the determination of their instantaneous coordinate positions on given image frame accordingly. By repeating identical operations on the next frame, the real-time motions of tablet objectives were traced successfully. Orthogonal tracking experiment and performance comparisons verified the accuracy and reliability of this new method in pharmaceutical industry. With original suggestions concerning imaging arrangements, tablet descriptions and video tracking, this article provides reliable references and new research ideas for tablet tracking performance in high-yielding production domain.

Video tracking for high-similarity drug tablets based on reflective lightness intensity and fuzzy recognition system:

The utility model discloses an adjustable ground that sprays area and range buries formula automatic rising shower nozzle, including casing, flexible pipe and shower nozzle, casing upper end and sealed lid are threaded connection, and the shower nozzle is the refraction formula, and the shower nozzle is including reflecting the awl, adjusting spiral cover, adjusting bolt and nozzle base frame. The utility model discloses an advantage lie in: can control the range that thereby the shower nozzle was adjusted to the water yield through being equipped with adjusting bolt, through being equipped with the refraction awl and adjusting the spiral cover, can adjust the fan -shaped area of sprinkling irrigation under the same range circumstances, can prevent through being equipped with holding ring and recess track that flexible pipe and shower nozzle from rocking under the hydraulic drive, through be equipped with the sealing washer, the connecting pipe can be guaranteed the leakproofness and maintain necessary water pressure.

Yiheng Wen

Papers

Working parameter optimization of strengthen waterjet grinding with the orthogonal-experiment-design-based ANFIS

Fuzzy prediction of AWJ turbulence characteristics by using typical multi-phase flow models

Component parameter optimization of strengthen waterjet grinding slurry with the orthogonal-experiment-design-based ANFIS

Video tracking for high-similarity drug tablets based on reflective lightness intensity and fuzzy recognition system:

Adjustable ground that sprays area and range buries formula automatic rising shower nozzle