Using machine learning to identify primary features in choosing electric vehicles based on income levels

An electric vehicle is becoming one of the popular choices when choosing a vehicle.People are generally impressed with electric vehicles’zero-emission and smooth drives,while unstable battery duration keeps people away.This study tries to identify the primary factors that affect the likelihood of owning an electric vehicle based on different income levels.We divide the dataset into three subgroups by household income from$50,000 to$150,000 or low-medium income level,$150,000 to$250,000 or medium-high income level,and$250,000 or above,the high-income level.We considered several machine learning classifiers,and naive Bayes gave us a relatively higher accuracy than other algorithms in terms of overall accuracy and F1 scores.Based on the probability analysis,we found that for each of these groups,one-way commuting distance is the most important for all three income levels.

High Specific Power Electrical Machines: A System Perspective

There has been a growing need for high specific power electrical machines for a wide range of applications.These include hybrid/electric traction applications,and aerospace applications.A lot of work has been done to accomplish significantly higher specific power electrical machines especially for aerospace applications.Several machine topologies as well as thermal management schemes have been proposed.Even though there has been a few publications that provided an overview of high-speed and high specific power electrical machines[1-3],the goal of this paper is to provide a more comprehensive review of high specific power electrical machines with special focus on machines that have been built and tested and are considered the leading candidates defining the state-of-the art.Another key objective of this paper is to highlight the key“system-level”tradeoffs involved in pushing electrical machines to higher specific power.Focusing solely on the machine specific power can lead to a sub-optimal solution at the system-level.

CUTTING REGULARITY AND DISCHARGE CHARACTERISTICS BY USING COMPOSITE COOLING LIQUID IN WIRE CUT ELECTRICAL DISCHARGE MACHINE WITH HIGH WIRE TRAVELING SPEED

The analysis of cutting regularity is provided through using and comparing two typical cooling liquids. It is proved that cutting regularity is greatly affected by cooling liquid＇s washing ability. Discharge characteristics and theoretic analysis between two electrodes are also discussed based on discharge waveform. By using composite cooling liquid which has strong washing ability, the efficiency in the first stable cutting phase has reached more than 200 mm^2/min, and the roughness of the surface has reached Ra〈0.8 μm after the fourth cutting with more than 50 mm^2/min average cutting efficiency. It is pointed out that cutting situation of the wire cut electrical discharge machine with high wire traveling speed （HSWEDM） is better than the wire cut electrical discharge machine with low wire traveling speed （LSWEDM） in the condition of improving the cooling liquid washing ability. The machining indices of HSWEDM will be increased remarkably by using the composite cooling liquid.

Implementation of Machine-to-Machine Solutions Using MQTT Protocol in Internet of Things (IoT) Environment to Improve Automation Process for Electrical Distribution Substations in Colombia

In order to incorporate smart elements into distribution networks at ITELCA laboratories in Bogotá-Colombia, a Machine-to-Machine-based solution has been developed. This solution aids in the process of low-cost electrical fault location, which contributes to improving quality of service, particularly by shortening interruption time spans in mid-voltage grids. The implementation makes use of MQTT protocol with an intensive use of Internet of things (IoT) environment which guarantees the following properties within the automation process: Advanced reports and statistics, remote command execution on one or more units (groups of units), detailed monitoring of remote units and custom alarm mechanism and firmware upgrade on one or more units (groups of units). This kind of implementation is the first one in Colombia and it is able to automatically recover from an N-1 fault.

Role of Advanced Materials in Electrical Machines

There has been a revived and growing role for electrical machines and drives across a wide range of applications.Such applications include,hybrid/electrical traction applications,aerospace applications,and renewable energy.All these applications present different set of requirements and challenges.The common trend is that there is a need for higher-performance electrical machines in terms of higher power/torque density,and higher efficiency while keeping cost under control.There has been a lot of work done around coming up with novel machine topologies,optimizing more conventional topologies as well as improved thermal management schemes.Like many other areas of engineering/research,advanced materials can play a key role in opening up the design space for electrical machines leading to a step improvement in their performance.This paper will present an overview of some of the key advanced materials that are either recently developed or are currently under development and their potential impact on electrical machines.

Implementation of Machine-to-Machine Solutions to Improve Quality of Service for Electrical Energy Distribution Networks in Colombia

In order to incorporate smart elements into distribution networks at ITELCA laboratories in Bogotá-Colombia, a Machine-to-Machine-based solution has been developed. This solution aids in the process of low-cost electrical fault location, which contributes to improving quality of service, particularly by shortening interruption time spans in mid-voltage grids. The implementation makes use of a GENEKO modem that exploits its digital inputs together with a full coverage of certain required auxiliary services so as to generate proper detection signals whenever failure currents occur;which allows incorporating the latest failure detection technology into the system.

Overview of the Rectangular Wire Windings AC Electrical Machine

The rectangular wire winding AC electrical machine has drawn extensive attention due to their high slot fill factor,good heat dissipation,strong rigidity and short end-windings,which can be potential candidates for some traction application so as to enhance torque density,improve efficiency,decrease vibration and weaken noise,etc.In this paper,based on the complex process craft and the electromagnetic performance,a comprehensive and systematical overview on the rectangular wire windings AC electrical machine is introduced.According to the process craft,the different type of the rectangular wire windings,the different inserting direction of the rectangular wire windings and the insulation structure have been compared and analyzed.Furthermore,the detailed rectangular wire windings connection is researched and the general design guideline has been concluded.Especially,the performance of rectangular wire windings AC machine has been presented,with emphasis on the measure of improving the bigger AC copper losses at the high speed condition due to the distinguished proximity and skin effects.Finally,the future trend of the rectangular wire windings AC electrical machine is prospected.

Quantitative Comparison of Electromagnetic Performance of Electrical Machines for HEVs/EVs

In this paper,various types of sinusoidal-fed electrical machines,i.e.induction machines(IMs),permanent magnet(PM)machines,synchronous reluctance machines,variable flux machines,wound field machines,are comprehensively reviewed in terms of basic features,merits and demerits,and compared for HEV/EV traction applications.Their latest developments are highlighted while their electromagnetic performance are quantitatively compared based on the same specification as the Prius 2010 interior PM(IPM)machine,including the torque/power-speed characteristics,power factor,efficiency map,and drive cycle based overall efficiency.It is found that PM-assisted synchronous reluctance machines are the most promising alternatives to IPM machines with lower cost and potentially higher overall efficiency.Although IMs are cheaper and have better overload capability,they exhibit lower efficiency and power factor.Other electrical machines,such as synchronous reluctance machines,wound field machines,as well as many other newly developed machines,are currently less attractive due to lower torque density and efficiency.

Effective Electrical Submersible Pump Management Using Machine Learning

Artificial lift plays an important role in petroleum industry to sustain production flowrate and to extend the lifespan of oil wells. One of the most popular artificial lift methods is Electric Submersible Pumps (ESP) because it can produce high flowrate even for wells with great depth. Although ESPs are designed to work under extreme conditions such as corrosion, high temperatures and high pressure, their lifespan is much shorter than expected. ESP failures lead to production loss and increase the cost of replacement, because the cost of intervention work for ESP is much higher than for other artificial lift methods, especially for offshore wells. Therefore, the prediction of ESP failures is highly valuable in oil production and contributes a lot to the design, construction and operation of oil wells. The contribution of this study is to use 3 machine learning algorithms, which are Decision Tree, Random Forest and Gradient Boosting Machine, to build predictive models for ESP lifespan while using both dynamic and static ESP parameters. The results of these models were compared to find out the most suitable model for the prediction of ESP life cycle. In addition, this study also evaluated the influence factor of various operating parameters to forecast the most impact parameters on the duration of ESP. The results of this study can provide a better understanding of ESP behavior so that early actions can be realized to prevent potential ESP failures.

Machine Learning Mapping of Soil Apparent Electrical Conductivity on a Research Farm in Mississippi

Open-source and free tools are readily available to the public to process data and assist producers in making management decisions related to agricultural landscapes. On-the-go soil sensors are being used as a proxy to develop digital soil maps because of the data they can collect and their ability to cover a large area quickly. Machine learning, a subcomponent of artificial intelligence, makes predictions from data. Intermixing open-source tools, on-the-go sensor technologies, and machine learning may improve Mississippi soil mapping and crop production. This study aimed to evaluate machine learning for mapping apparent soil electrical conductivity (ECa) collected with an on-the-go sensor system at two sites (i.e., MF2, MF9) on a research farm in Mississippi. Machine learning tools (support vector machine) incorporated in Smart-Map, an open-source application, were used to evaluate the sites and derive the apparent electrical conductivity maps. Autocorrelation of the shallow (ECas) and deep (ECad) readings was statistically significant at both locations (Moran’s I, p 0.001);however, the spatial correlation was greater at MF2. According to the leave-one-out cross-validation results, the best models were developed for ECas versus ECad. Spatial patterns were observed for the ECas and ECad readings in both fields. The patterns observed for the ECad readings were more distinct than the ECas measurements. The research results indicated that machine learning was valuable for deriving apparent electrical conductivity maps in two Mississippi fields. Location and depth played a role in the machine learner’s ability to develop maps.

Hardware,Machines & Electrical Equipment From Wenzhou

Scissors and locks are famous products from Wenzhou. Now scissors from the city including multi-purpose, tailoring, tourist and special-purpose ones and exquisite fruit and artistic knives have entered the world market. At the

The Principle and Architecture of a Hybrid System of a Neural Network and an Expert System in Intelligent CAD of Electrical Machines

Using expert systems in intelligent CAD of electrical machines have limitations such as knowledge acquisition bottlenecks and matching conflict, combinatorial explosion, and endless recursion in the reasoning process. This paper discusses the principle of a hybrid system of a neural network and an expert system (HNNES), i.e., knowledge representation, reasoning mechanism, and knowledge acquisition based on neural networks. An architecture of HNNES is presented in consideration of the feature of the design of electrical machines.

Partial Discharge Measurement of OCP-Tapes in Rotating Electrical Machines

Nowadays, PD （partial discharge） measurements are a crucial part of the preventive maintenance of electrical equipment within high voltage engineering. Especially for electrical machines, both the supplier and the user are interested in the results of PD measurements. However, PDs hardly represent the cause of the failure, more likely they are claimed as the outcome of a failure. This paper deals with the insulation of a 6 kV electrical machine, whereas PD measurements were carried out at a single stator from wound coils. During manufacturing, these coils were equipped with different materials for the OCP （outer corona protection）. Using different PD measurement systems and different bandwidths, investigations of the PD behavior of the coils were carried out. Additionally, the surface resistivity of the corona protection was determined. As a result, conclusions for the correlations between the resistance of the OCP as well as the PD behavior are stated. Furthermore, the influence of using different measurement systems, different measuring circuits, and different bandwidths is shown.

Optimization of micro milling electrical discharge machining of Inconel 718 by Grey-Taguchi method

The optimization of micro milling electrical discharge machining（EDM） process parameters of Inconel 718 alloy to achieve multiple performance characteristics such as low electrode wear,high material removal rate and low working gap was investigated by the Grey-Taguchi method.The influences of peak current,pulse on-time,pulse off-time and spark gap on electrode wear（EW）,material removal rate（MRR） and working gap（WG） in the micro milling electrical discharge machining of Inconel 718 were analyzed.The experimental results show that the electrode wear decreases from 5.6×10-9 to 5.2×10-9 mm3/min,the material removal rate increases from 0.47×10-8 to 1.68×10-8 mm3/min,and the working gap decreases from 1.27 to 1.19 μm under optimal micro milling electrical discharge machining process parameters.Hence,it is clearly shown that multiple performance characteristics can be improved by using the Grey-Taguchi method.

Statistical Description of Debris Particle Size Distribution in Electrical Discharge Machining

Gap debris as discharge product is closely related to machining process in electrical discharge machining（EDM）. A lot of recent researches have focused on the relationship among debris size, surfaces texture, remove rate, and machining stability. The study on statistical distribution of debris size contributes to the research, but it is still superficial currently. In order to obtain the distribution law of the debris particle size, laser particle size analyzer（LPSA） combined with scanning electron microscope（SEM） is used to analyze the EDM debris size. Firstly, the heating dried method is applied to obtain the debris particles. Secondly, the measuring range of LPSA is determined as 0.5–100 μm by SEM observation, and the frequency distribution histogram and the cumulative frequency distribution scattergram of debris size are obtained by using LPSA. Thirdly, according to the distribution characteristic of the frequency distribution histogram, the statistical distribution functions of lognormal, exponentially modified Gaussian（EMG）, Gamma and Weibull are chosen to achieve curve fitting of the histogram. At last, the distribute law of the debris size is obtained by fitting results. Experiments with different discharge parameters are carried out on an EDM machine designed by the authors themselves, and the machining conditions are tool electrode of red-copper material, workpiece of ANSI 1045 material and working fluid of de-ionized water. The experimental results indicate that the debris sizes of all experiment sample truly obey the Weibull distribution. The obtained distribution law is significantly important for all the models established based on the debris particle size.

Surface Modification Process by Electrical Discharge Machining with Ti Powder Green Compact Electrode

This paper describes a new method of surface modification by Electrical Discharge Machining (EDM). By using ordinary EDM machine tool and kerosene fluid, a hard ceramic layer can be created on the workpiece surface with Ti or other compressed powder electrode in a certain condition. This new revolutionary method is called Electrical Discharge Coating (EDC). The process of EDC begins with electrode wear during EDM,then a kind of hard carbide is created through the thermal and chemical reaction between the worn electrode material and the carbon particle decomposed from kerosene fluid under high temperature. The carbide is piled up on a workpiece quickly and becomes a hard layer of ceramic about 20 μm in several minutes. This paper studies the principle and process of EDC systemically by using Ti powder green compact electrode. In order to obtain a layer of compact ceramic film, it is very important to select proper electric pulse parameters, such as pulse width, pulse interval, peak current. Meantime, the electrode materials and its forming mode will effect the machining surface quality greatly. This paper presents a series of experiment results to study the EDC process by adopt different technology parameters. Experiments and analyses show that a compact TiC ceramic layer can be created on the surface of metal workpiece. The hardness of ceramic layer is more 3 times higher than the base body, and the hardness changes gradiently from surface to base body. The method will have a great future because many materials can be easily added to the electrode and then be coated on the workpiece surface. Gearing the parameters ceramic can be created with different thickness. The switch between deposition and removal process is carried out easily by changing the polarity, thus the gear to the thickness and shape of the composite ceramic layer is carried out easily. This kind of composite ceramic layer will be used to deal with the surface of the cutting tools or molds possibly, in order to lengthen their life. It also can be found wide application in the fields of surface repairing and strengthening of the ship or aircraft.

Extreme Learning Machine-Based Thermal Model for Lithium-Ion Batteries of Electric Vehicles under External Short Circuit

External short circuit(ESC)of lithium-ion batteries is one of the common and severe electrical failures in electric vehicles.In this study,a novel thermal modelis developed to capture the temperature behavior of batteries under ESC conditions.Experiments were systematically performed under different battery initial state of charge and ambient temperatures.Based on the experimental results,we employed an extreme learming machine(ELM)-based thermal(ELMT)model to depict battery temperature behavior under ESC,where a lumped-state thermal model was used to replace the activation function of conventional ELMs.To demonstrate the effectiveness of the proposed model,wecompared the ELMT model with a multi-lumped-state thermal(MLT)model parameterized by thegenetic algorithm using the experimental data from various sets of battery cells.It is shown that the ELMT model can achieve higher computa-tional efficiency than the MLT model and better fitting and prediction accuracy,where the average root mean squared error(RMSE)of the fitting is 0.65℃ for the ELMT model and 3.95℃ for the MLT model,and the RMES of the prediction under new data set is 3.97℃ for the ELMT model and 6.11℃ for the MLT model.

Micro Electrical Discharge Machining Deposition in Air for Fabrication of Micro Spiral Structures

Micro electrical discharge machining（EDM） deposition process is a new micro machining method for fabrication of metal micro structures. In this process, the high level of tool electrode wear is used to achieve the metal material deposition. Up to now, the studies of micro EDM deposition process focused mainly on the researches of deposition process, namely the effects of discharge parameters in deposition process on the deposition rate or deposition quality. The research of the formation of micro structures with different discharge energy density still lacks. With proper conditions and only by the z-axis feeding in vertical direction, a novel shape of micro spiral structure can be deposited, with 0.11 mm in wire diameter, 0.20 mm in outside diameter, and 3.78 mm in height. Then some new deposition strategies including angular deposition and against the gravity deposition were also successful. In order to find the forming mechanism of the spiral structures, the numerical simulation of the transient temperature distribution on the discharge point was conducted by using the finite-element method（FEM）. The results show that there are two major factors lead to the forming of the spiral structures. One is the different material removal form of tool electrode according with the discharge energy density, the other is the influenced degree of the movement of the removed material particles in the discharge gap. The more the energy density in single discharge is, the smaller the mass of the removed material particles is, and the easier the movements of which will be changed to form an order tendency. The fine texture characteristics of the deposited micro spiral structures were analyzed by the energy spectrum analysis and the metallographic analysis. It shows that the components of the deposited material are almost the same as those of the tool electrode. Moreover the deposited material has the brass metallic luster in the longitudinal profile and has compact bonding with the base material. This research is useful to understand the micro-process of micro EDM deposition better and helpful to increase the controllability of the new EDM method for fabrication of micro structures.

Experimental Research on Effects of Process Parameters on Servo Scanning 3D Micro Electrical Discharge Machining

Servo scanning 3D micro electrical discharge machining (3D SSMEDM) is a novel and effective method in fabricating complex 3D micro structures with high aspect ratio on conducting materials. In 3D SSMEDM process, the axial wear of tool electrode can be compensated automatically by servo-keeping discharge gap, instead of the traditional methods that depend on experiential models or intermittent compensation. However, the effects of process parameters on 3D SSMEDM have not been reported up until now. In this study, the emphasis is laid on the effects of pulse duration, peak current, machining polarity, track style, track overlap, and scanning velocity on the 3D SSMEDM performances of machining efficiency, processing status, and surface accuracy. A series of experiments were carried out by machining a micro-rectangle cavity (900 μm×600 μm) on doped silicon. The experimental results were obtained as follows. Peak current plays a main role in machining efficiency and surface accuracy. Pulse duration affects obviously the stability of discharge state. The material removal rate of cathode processing is about 3/5 of that of anode processing. Compared with direction-parallel path, contour-parallel path is better in counteracting the lateral wear of tool electrode end. Scanning velocity should be selected moderately to avoid electric arc and short. Track overlap should be slightly less than the radius of tool electrode. In addition, a typical 3D micro structure of eye shape was machined based on the optimized process parameters. These results are beneficial to improve machining stability, accuracy, and efficiency in 3D SSMEDM.

Machining performance on hybrid process of abrasive jet machining and electrical discharge machining

To develop a hybrid process of abrasive jet machining (AJM) and electrical discharge machining (EDM),the effects of the hybrid process parameters on machining performance were comprehensively investigated to confirm the benefits of this hybrid process.The appropriate abrasives delivered by high speed gas media were incorporated with an EDM in gas system to construct the hybrid process of AJM and EDM,and then the high speed abrasives could impinge on the machined surface to remove the recast layer caused by EDM process to increase the efficiency of material removal and reduce the surface roughness.In this study,the benefits of the hybrid process were determined as the machining performance of hybrid process was compared with that of the EDM in gas system.The main process parameters were varied to explore their effects on material removal rate,surface roughness and surface integrities.The experimental results show that the hybrid process of AJM and EDM can enhance the machining efficiency and improve the surface quality.Consequently,the developed hybrid process can fit the requirements of modern manufacturing applications.