Analyzing angle crashes at unsignalized intersections using machine learning techniques

A recently developed machine learning technique, multivariate adaptive regression splines (MARS), is introduced in this study to predict vehicles’ angle crashes. MARS has a promising prediction power, and does not suffer from interpretation complexity. Negative Binomial (NB) and MARS models were fitted and compared using extensive data collected on unsignalized intersections in Florida. Two models were estimated for angle crash frequency at 3- and 4-legged unsignalized intersections. Treating crash frequency as a continuous response variable for fitting a MARS model was also examined by considering the natural logarithm of the crash frequency. Finally, combining MARS with another machine learning technique (random forest) was explored and discussed. The fitted NB angle crash models showed several significant factors that contribute to angle crash occurrence at unsignalized intersections such as, traffic volume on the major road, the upstream distance to the nearest signalized intersection, the distance between successive unsignalized intersections, median type on the major approach, percentage of trucks on the major approach, size of the intersection and the geographic location within the state. Based on the mean square prediction error (MSPE) assessment criterion, MARS outperformed the corresponding NB models. Also, using MARS for predicting continuous response variables yielded more favorable results than predicting discrete response variables. The generated MARS models showed the most promising results after screening the covariates using random forest. Based on the results of this study, MARS is recommended as an efficient technique for predicting crashes at unsignalized intersections (angle crashes in this study).     

Precision measurement and compensation of kinematic errors for industrial robots using artifact and machine learning

Industrial robots are widely used in various areas owing to their greater degrees of freedom (DOFs) and larger operation space compared with traditional frame movement systems involving sliding and rotational stages. However, the geometrical transfer of joint kinematic errors and the relatively weak rigidity of industrial robots compared with frame movement systems decrease their absolute kinematic accuracy, thereby limiting their further application in ultraprecision manufacturing. This imposes a stringent requirement for improving the absolute kinematic accuracy of industrial robots in terms of the position and orientation of the robot arm end. Current measurement and compensation methods for industrial robots either require expensive measuring systems, producing positioning or orientation errors, or offer low measurement accuracy. Herein, a kinematic calibration method for an industrial robot using an artifact with a hybrid spherical and ellipsoid surface is proposed. A system with submicrometric precision for measuring the position and orientation of the robot arm end is developed using laser displacement sensors. Subsequently, a novel kinematic error compensating method involving both a residual learning algorithm and a neural network is proposed to compensate for nonlinear errors. A six-layer recurrent neural network (RNN) is designed to compensate for the kinematic nonlinear errors of a six-DOF industrial robot. The results validate the feasibility of the proposed method for measuring the kinematic errors of industrial robots, and the compensation method based on the RNN improves the accuracy via parameter fitting. Experimental studies show that the measuring system and compensation method can reduce motion errors by more than 30%. The present study provides a feasible and economic approach for measuring and improving the motion accuracy of an industrial robot at the submicrometric measurement level.The full text can be downloaded at https://link.springer.com/article/10.1007/s40436-022-00400-6     

Acoustic signal based fault detection on belt conveyor idlers using machine learning

Belt conveyor systems are widely utilized in transportation applications. This research aims to achieve fault detection on belt conveyor idlers with an acoustic signal based method. The presented novel method uses Mel Frequency Cepstrum Coefficients and Gradient Boost Decision Tree for feature extraction and classification. Thirteen Mel Frequency Cepstrum Coefficients are extracted from acquired sound signal as features. A Gradient Boost Decision Tree model is developed and trained. After training, the model is applied to a testing dataset. Results show that the trained model can achieve diagnosis accuracy of 94.53%, as well as recall rate up to 99.7%. This study verifies the proposed method for acoustic signal based fault detection of belt conveyor idlers.     

The application of machine learning models based on particles characteristics during coal slime flotation

In this study, four different machine learning (ML) models were used to simulate the migration behavior of minerals during coal slime flotation based on particle characteristics (shape, size, compositions, and types): random forest (RF), logistic regression (LR), AdaBoosting (Ada), and k-nearest neighbors (KNN). For ML model development, 70% of the total data was used for the training phase, and 30% was used for the testing phase. F-score and area under the curve (AUC) were used as the most vital indicators for evaluating the different ML models. Compared to the other ML models, the RF model had the best accuracy for simulating particle migration behavior during flotation. Furthermore, the RF model avoided the drawback of having to be retrained when the feed conditions changed. The results revealed that particle size and particle composition play the most significant role in coal slime flotation.     

机器学习分布式网络传输异常数据智能检测方法

对于链路状态数据库的网络传输异常数据检测存在检测数据不完整、较为敏感、检测效率差的问题,提出基于机器学习的分布式网络传输异常数据智能检测方法,通过K最近邻分簇算法对分布式网络节点实施分簇,利用贝叶斯分类算法检测簇头是否出现异常;确定异常簇后,选取小波阈值降噪方法对异常簇内数据进行降噪处理,在此基础上,采用遗传算法检测降...     

Energy and exergy analyses for a cement ball mill of a new generation cement plant and optimizing grinding process: A case study

Nowadays, ball mills are used widely in cement plants to grind clinker and gypsum to produce cement. In this work, the energy and exergy analyses of a cement ball mill (CBM) were performed and some measurements were carried out in an existing CBM in a cement plant to improve the efficiency of the grinding process. The first and second laws efficiency of the CBM was specified to be 80.5% and 19.9%, respectively. The electrical energy consumption of the CBM unit was specified to be 37.9 kWh/t. The effects of ball charge pattern, cement fineness and two additive materials (limestone and pozzolan) on the performance of the CBM unit and the quality of cement were investigated. The first and second laws efficiency of the CBM increased (81.8% and 20.6%) and the electrical energy consumption of CBM unit decreased (36.5 kWh/t) after modifying the ball charge pattern. Also, the results demonstrated that cement production rate increases (185–224 t/h) and the electrical consumption decreases (41.1–33.1 kWh/t) when cement fineness decreases (3250 –2820 cm²/g). However, the cement compressive strength (3, 7 and 28 days) decreases and the cement setting time (initial and final) increases by reducing the cement fineness. Besides, when the clinker was replaced by limestone or pozzolan, on the one side, the efficiency of the first and second laws of the CBM unit was increased, but on the other side the cement compressive strength was decreased and the cement setting time was increased.     

基于机器学习的热导率预测模型研究

传统的理论研究、实验研究及计算仿真已无法满足科学家对新材料的探索与设计。数据驱动的机器学习算法对材料的筛选与性能预测有着推动作用。将机器学习算法应用到材料信息学,基于现有材料热导率数据集,建立机器学习热导率预测模型,通过交叉验证来对机器学习回归模型进行评估。利用机器学习算法建立描述符与热导率属性之间的映射模型,可用于大规模的材料筛选,从而指导实验研究。     

Tailoring nanoprecipitates for ultra-strong high-entropy alloys via machine learning and prestrain aging

The multi-principal-component concept of high-entropy alloys(HEAs) generates numerous new alloys.Among them,nanoscale precipitated HEAs have achieved superior mechanical properties and shown the potentials for structural applications.However,it is still a great challe nge to find the optimal alloy within the numerous candidates.Up to now,the reported nanoprecipitated HEAs are mainly designed by a trialand-error approach with the aid of phase diagram calculations,limiting the development of structural HEAs.In the current work,a novel method is proposed to accelerate the development of ultra-strong nanoprecipitated HEAs.With the guidance of physical metallurgy,the volume fraction of the required nanoprecipitates is designed from a machine learning of big data with thermodynamic foundation while the morphology of precipitates is kinetically tailored by prestrain aging.As a proof-of-principle study,an HEA with superior strength and ductility has been designed and systematically investigated.The newly developed γ'-strengthened HEA exhibits 1.31 GPa yield strength,1.65 GPa ultimate tensile strength,and 15% tensile elongation.Atom probe tomography and transmission electron microscope characterizations reveal the well-controlled high γ' volume fraction(52%) and refined precipitate size(19 nm).The refinement of nanoprecipitates originates from the accelerated nucleation of the γ' phase by prestrain aging.A deeper understanding of the excellent mechanical properties is illustrated from the aspect of strengthening mecha nisms.Finally,the versatility of the current design strategy to other precipitation-hardened alloys is discussed.     

A machine learning system for identifying transmembrane domains from amino acid sequences

We present our machine learning system, that uses inductive logic programming techniques to learn how to identify transmembrane domains from amino acid sequences. Our system facilitates the use of operators such as ‘contains’, that act on entire sequences, rather than on individual elements of a sequence. The prediction accuracy of our new system is around 93%, and this compares favourably with earlier results. This work was carried out with the support of a research grant from ISIS, Fujitsu Laboratories.     

High-throughput simulation combined machine learning search for optimum elemental composition in medium entropy alloy

In medium/high entropy alloys, their mechanical properties are strongly dependent on the chemicalelemental composition. Thus, searching for optimum elemental composition remains a critical issue to maximize the mechanical performance. However, this issue solved by traditional optimization process via "trial and error" or experiences of domain experts is extremely difficult. Here we propose an approach based on high-throughput simulation combined machine learning to obtain medium entropy alloys with high strength and low cost. This method not only obtains a large amount of data quickly and accurately,but also helps us to determine the relationship between the composition and mechanical properties.The results reveal a vital importance of high-throughput simulation combined machine learning to find best mechanical properties in a wide range of elemental compositions for development of alloys with expected performance.     

The state-of-the-art on Intellectual Property Analytics (IPA): A literature review on artificial intelligence,machine learning and deep learning methods for analysing intellectual property (IP) data

Big data is increasingly available in all areas of manufacturing and operations, which presents an opportunity for better decision making and discovery of the next generation of innovative technologies. Recently, there have been substantial developments in the field of patent analytics, which describes the science of analysing large amounts of patent information to discover trends. We define Intellectual Property Analytics (IPA) as the data science of analysing large amount of IP information, to discover relationships, trends and patterns for decision making. In this paper, we contribute to the ongoing discussion on the use of intellectual property analytics methods, i.e artificial intelligence methods, machine learning and deep learning approaches, to analyse intellectual property data. This literature review follows a narrative approach with search strategy, where we present the state-of-the-art in intellectual property analytics by reviewing 57 recent articles. The bibliographic information of the articles are analysed, followed by a discussion of the articles divided in four main categories: knowledge management, technology management, economic value, and extraction and effective management of information. We hope research scholars and industrial users, may find this review helpful when searching for the latest research efforts pertaining to intellectual property analytics.     

小波包分形与支持向量机在水声目标识别中的应用研究

水声目标分类识别是公认的水声信号处理难题,船舶辐射噪声是一种非线性非平稳信号,具有一定的混沌特性,更好地认识船舶辐射噪声的非线性性质,有助于更好地寻找有效的水声目标检测及识别算法。为了解决水声目标的分类识别问题,提出了利用小波包分形和支持向量机组合进行水声目标识别。利用小波包分解得到目标辐射噪声不同频带内信号分形维数作为特征矢量,并输入到支持向量机实现目标分类,实验结果表明,小波包分形和支持向量机的结合有比较好的分类识别效果,有一定的实际应用价值。     

基于数字孪生与深度学习技术的制造加工设备智能化方法研究

针对传统制造加工设备在生产加工过程中存在设备与数据信息联系不紧密,设备使用维护多依赖于人工经验等问题,提出了一种新的设备智能化方法。首先,在信息层建立能反映制造加工设备真实状态的数字孪生体;其次,基于历史加工大数据,通过数字孪生体对加工过程的行为进行建模及深度学习和训练,并利用训练好的人工神经网络根据采集到的实时数据来预测制造加工设备下一时刻的状态,使制造加工设备实现物理层与信息层数据的深度融合,拥有自我感知、自我预测的能力,最终实现智能化;最后,以浆料微流挤出成型设备挤出结构系统的智能化实施过程为例,验证了所提出方法的可行性。实例结果表明该设备智能化方法可有效地对挤出结构系统的运行状态进行监测及预测,为后续提高挤出成型精度提供了有效的数据信息。研究表明数字孪生和深度学习技术能够提升制造加工设备的智能化程度,可为未来智能制造的发展提供理论支撑。     

Motion parameter tuning for servomotor packs based on learning automata method

Abstract

In this paper, we investigate the use of the learning automata method in tuning the motion parameters of servomotor packs with implicit control structures. For commercial servomotor packs, it is difficult to design motion parameters using systematic approaches. However, tuning these motion parameters is very important. Here, the tuning process is automated using a learning automata method that operates through interactions with unknown environments using a stochastic trial and error process; it also provides additional convergence information through probability density functions. Moreover, a tuning method that matches the dynamic responses of all synchronous motion axes is developed for increasing the contouring accuracy of multi‐axis systems. The obtained experimental results indicate that the proposed method can effectively tune the motion parameters. As compared to tuning methods that do not consider matched dynamic responses, the proposed method achieves a reduction of 46.6% in the roundness error.     

血管网光声成像的机器学习抗散射仿真研究

乳腺癌已成为全球女性发病率最高的肿瘤疾病,微血管成像对乳腺癌的治疗方案和预后有重要意义。光声层析成像术(Photoacoustic Tomography, PAT)可有效对乳腺癌内微血管网进行成像,但肿瘤组织内部的异质微结构和钙化点的散射对成像质量影响较大。针对该问题,文章基于U-Net的卷积神经网络对不同颗粒散射条件下软组织中血管网图像散斑开展仿真研究。仿真结果表明,该神经网络可以学习光声散斑图像和成像目标之间的映射关系,提取出隐藏在噪声中的血管光声信号,并重建出轮廓清晰、背景清晰的高质量血管图像,表明U-Net网络可以从高度模糊的散射图像中提取出有效的光声信息,实现目标图像的高清重建,在乳腺癌的诊断成像中具有广阔的应用前景。     

A case study on energy and exergy analyses for an industrial-scale vertical roller mill assisted grinding in cement plant

In this study, the analyses of energy and exergy were implemented for an industrial-scale vertical roller mill (VRM) of Kerman Momtazan Cement Company (KMCC) of Iran. The energy and exergy analyses demonstrated the first law efficiency of the VRM is 62.1%, while the second law efficiency of the VRM is 34.6%. Comparing to the widely applied ball milling, the second law efficiency is 16.4% higher for the VRM than the ball mill. Results also showed when the classifier rotor speed increases from 53 to 65 rpm, the particle size of the product decreases from P_90µm = 18.2% to P_90µm = 10.8%, but the power consumption of the VRM unit increases from 19.7 to 22.3 kWh/t of raw materials. Finally, the power consumption of the VRM unit compared with 14 raw mill units around Iran and the international best available technology (IBAT). The results demonstrated that the VRM unit consumes around 81% (9.75 kWh/t of raw materials), and 36% (5.8 kWh/t of raw materials) more energy to grind raw material than the IBAT unit and domestic best raw mill (DBRM), respectively.     

Extreme learning machine based approach for diagnosis and analysis of breast cancer

Due to the heterogeneous and complex nature of clinical data, the need to use sophisticated diagnosis techniques has increased significantly in recent years. The proposed approach for diagnosis of breast cancer exploits the potential of an extreme learning machine (ELM) and analyzes its performance after classification into benign and malignant cases. To optimize the ELM network in terms of computation time and memory resources, weight pruning is used without performance compromise. Using real data sets, numerical experiments have been conducted. With an accuracy of 93%, the optimum numbers of node layers for breast cancer diagnosis has been found to be 20. Comparative results demonstrate over-performance of the proposed ELM approach.     

基于机器学习的轨道角动量光束模式探测技术研究进展

轨道角动量(OAM)复用和编码技术可有效提高光通信系统信道容量。近些年研究者提出将机器学习(ML)技术用于OAM模式探测以提高OAM光通信系统性能。本文对基于机器学习的OAM模式探测方案进行了综述,包括误差反向传播(BP)神经网络、自组织神经网络(SOM)、支持向量机(SVM)、卷积神经网络(CNN)、光束变换辅助的识别技术以及全光衍射深度神经网络(D2NN),分析了各类机器学习OAM探测器在对抗大气、水下信道带来的干扰时展现出的性能差异以及各自优势。

     

A gingivitis identification method based on contrast-limited adaptive histogram equalization,gray-level co-occurrence matrix,and extreme learning machine

The diagnosis of gingivitis often occurs years later using a series of conventional oral examination, and they depended a lot on dental records, which are physically and mentally laborious task for dentists. In this study, our research presented a new method to diagnose gingivitis, which is based on contrast-limited adaptive histogram equalization (CLAHE), gray-level co-occurrence matrix (GLCM), and extreme learning machine (ELM). Our dataset contains 93 images: 58 gingivitis images and 35 healthy control images. The experiments demonstrate that the average sensitivity, specificity, precision, and accuracy of our method is 75%, 73%, 74% and 74%, respectively. This method is more accurate and sensitive than three state-of-the-art approaches.     

Detection of interferences in an additive manufacturing process: an experimental study integrating methods of feature selection and machine learning

Additive manufacturing becomes a more and more important technology for production, mainly driven by the ability to realise extremely complex structures using multiple materials but without assembly or excessive waste. Nevertheless, like any high-precision technology additive manufacturing responds to interferences during the manufacturing process. These interferences – like vibrations – might lead to deviations in product quality, becoming manifest for instance in a reduced lifetime of a product or application issues. This study targets the issue of detecting such interferences during a manufacturing process in an exemplary experimental setup. Collection of data using current sensor technology directly on a 3D-printer enables a quantitative detection of interferences. The evaluation provides insights into the effectiveness of the realised application-oriented setup, the effort required for equipping a manufacturing system with sensors, and the effort for acquisition and processing the data. These insights are of practical utility for organisations dealing with additive manufacturing: the chosen approach for detecting interferences shows promising results, reaching interference detection rates of up to 100% depending on the applied data processing configuration.