Model Predictive Control Coupled with Artificial Intelligence for Eddy Current Dynamometers

The recent studies on Artificial Intelligence(AI)accompanied by enhanced computing capabilities supports increasing attention into traditional control methods coupled with AI learning methods in an attempt to bringing adap-tiveness and fast responding features.The Model Predictive Control(MPC)tech-nique is a widely used,safe and reliable control method based on constraints.On the other hand,the Eddy Current dynamometers are highly nonlinear braking sys-tems whose performance parameters are related to many processes related vari-ables.This study is based on an adaptive model predictive control that utilizes selected AI methods.The presented approach presents an updated the mathema-tical model of an Eddy Current Dynamometer based on experimentally obtained system operational data.Finally,the comparison of AI methods and related learn-ing performances based on the assessment technique of mean absolute percentage error(MAPE)issues are discussed.The results indicate that Single Hidden Layer Neural Network(SHLNN),General Regression Neural Network(GRNN),Radial Basis Network(RBNN),Neuro Fuzzy Network(ANFIS)coupled MPC have quite satisfying performances.The presented results indicate that,amongst them,GRNN appears to provide the best performance.

Design and simulation of electrical dynamometer using improved DTC induction motor driver

AC motors, especially the squirrel cage induction motors have the advantages of simple structure, good reliability and low cost. They are more suitable to be used as electrical dynamometers to provide dynamic load for bench test systems. But, the speed and torque of induction motors are not easy to be controlled accurately. In this work, an electrical dynamometer based on the induction motor is proposed. In order to get better control performance of torque and speed of induction motor, an improved direct torque control method(DTC) is also developed based on the space vector modulation(SVM) technique. The performance of the proposed dynamometer system is validated in the Matlab/Simulink platform. The simulation results show that the new dynamometer has good torque and stator flux response. And the torque and stator current ripples of it are reduced significantly compared with using the conventional DTC method.

Test-retest strength reliability of the Electronic Push/Pull Dynamometer (EPPD) in the measurement of the quadriceps and hamstring muscles on a new chair

Background: Test-retest strength reliability of the Electronic Push/Pull Dynamometer (EPPD) in the measurement of the extensor and flexor muscles on a new constructed chair. The objective of the study was to assess reliability of Electronic Push/Pull Dynamometer in the measurement of the knee flexion and extension at 90° and 60° on a new constructed chair. The aims of the author: To assess reliability of Electronic Push/Pull Dynamometer in the measurement of the knee flexion and extension at 90° and 60° on a new constructed chair. Design: A test-retest reliability study. Subjects: One hundred healthy students male and female (mean age, 21y). Methods: Maximum isometric strength of the quadriceps and hamstring muscle groups was measured using the EPPD were recorded at 60° and 90° for 3 trials on 2 occasions. Reliability was assessed with the Intraclass correlation coefficient (ICC), mean and standard deviation (SD) of measurements, and smallest real differences were calculated for the maximum and for the mean and work of the 3 repetitions. Results: Mean strength ranged from 50.44 kg for knee flexion to 55.76 kg for knee extension 50.44 kg to 61.98 kg at 90° hip flexion. Test-retest reliability Intraclass correlation coefficients (ICCs) ranged from 0.85 to 0.99. ICCs for test-retest reliability ranged from 0.780 to 0.998. Conclusions: The results of the reliability study indicate that the EPPD in reliable dynamometer to use in determining lower limb muscle force production. It can be used to measure disease progression and to evaluate changes in knee extension and flexion strength at the individual patient level.

Design and Manufacture of a Mobile Dynamometer

DIT has competed for a number of years in the Formula Student competition with petrol engine propelled vehicles.Dynamometer testing on these engines was traditionally outsourced.In2017/2018a decision was made to commence the design of an electric vehicle.Access to a suitable dynamometer for regular testing became more important than ever in order to fully characterise the electric motors the gearbox combinations and optimise the performance of the formula student electric vehicle.This paper deals with the design and manufacture and component selection for a mobile dynamometer that can accurately simulate racetrack conditions and apply typical loading cycles to a motor producing torque,power and speed values from a typical drivetrain.The dynamometer described uses a particle brake to apply the loads,a datum M425torque transducer to measure torque and a National Instruments LabVIEW interface to display and store data during testing.Safety is of vital importance and this paper describes the high-safety standards applied during the design and manufacture phase.With the implementation of an electronic control circuit,motor characteristics charts are produced,analysed and utilised for calibration and benchmarking for future motor test runs.Aim:Design&Manufacture of a mobile dynamometer unit to produce torque,speed and power values from the drive train of a motor.

Working condition recognition of sucker rod pumping system based on 4-segment time-frequency signature matrix and deep learning

High-precision and real-time diagnosis of sucker rod pumping system(SRPS)is important for quickly mastering oil well operations.Deep learning-based method for classifying the dynamometer card(DC)of oil wells is an efficient diagnosis method.However,the input of the DC as a two-dimensional image into the deep learning framework suffers from low feature utilization and high computational effort.Additionally,different SRPSs in an oil field have various system parameters,and the same SRPS generates different DCs at different moments.Thus,there is heterogeneity in field data,which can dramatically impair the diagnostic accuracy.To solve the above problems,a working condition recognition method based on 4-segment time-frequency signature matrix(4S-TFSM)and deep learning is presented in this paper.First,the 4-segment time-frequency signature(4S-TFS)method that can reduce the computing power requirements is proposed for feature extraction of DC data.Subsequently,the 4S-TFSM is constructed by relative normalization and matrix calculation to synthesize the features of multiple data and solve the problem of data heterogeneity.Finally,a convolutional neural network(CNN),one of the deep learning frameworks,is used to determine the functioning conditions based on the 4S-TFSM.Experiments on field data verify that the proposed diagnostic method based on 4S-TFSM and CNN(4S-TFSM-CNN)can significantly improve the accuracy of working condition recognition with lower computational cost.To the best of our knowledge,this is the first work to discuss the effect of data heterogeneity on the working condition recognition performance of SRPS.

Speed control strategy for tractor assisted driving based on chassis dynamometer test

Realizing automation of the chassis dynamometer and the unmanned test workshop is an inevitable trend in the development of new tractor products.The accuracy of the speed control of the test tractor directly affects the accuracy of the test loading force.In order to meet the purpose of precise control of the test tractor speed on the chassis dynamometer,a fuzzy PID control strategy was developed according to the working principle of assisted driving.On the basis of traditional PID control,the parameters of fuzzy inference module were added for real-time adjustment to achieve faster response to tractor speed changes and more precise control of tractor speed.The Matlab-Cruise co-simulation platform was established for simulation,and the experiment was verified by the tractor chassis dynamometer using the NEDC working condition and tractor ploughing working condition.The results show that both PID control and fuzzy PID control can achieve tractor speed following accuracy of±0.5 km/h.Fuzzy PID control has higher tractor speed following accuracy,faster response when speed changes,less tractor speed fluctuation,and overall control effect is better than PID control.The research results can provide a reference for the realization of the chassis dynamometer unmanned test workshop.

Using the curve moment and the PSO-SVM method to diagnose downhole conditions of a sucker rod pumping unit

Downhole working conditions of sucker rod pumping wells are automatically identified on a computer from the analysis of dynamometer cards. In this process, extraction of feature parameters and pattern classification are two key steps. The dynamometer card is firstly divided into four parts which include different production information according to the ＂four point method＂ used in actual oilfield production, and then the moment invariants for pattern recognition are extracted. An improved support vector machine （SVM） method is used for pattern classification whose error penalty parameter C and kernel function parameter g are optimally chosen by the particle swarm optimization （PSO） algorithm. The simulation results show the method proposed in this paper has good classification results.

Multiple fault diagnosis of down-hole conditions of sucker-rod pumping wells based on Freeman chain code and DCA

It is important to achieve continuous, stable and efficient pumping well operation in actual oilfield operation. Down-hole pumping well working conditions can be monitored in real-time and a reasonable production scheme can be designed when computer diagnosis is used. However, it is difficult to make a comprehensive analysis to supply efficient technical guidance for operation of the pumping well with multiple faults of down-hole conditions, which cannot be effectively dealt with by the common methods. To solve this problem, a method based on designated component analysis （DCA） is used in this paper. Freeman chain code is used to represent the down-hole dynamometer card whose important characteristics are extracted to construct a designated mode set. A control chart is used as a basis for fault detection. The upper and lower control lines on the control chart are determined from standard samples in normal working conditions. In an incompletely orthogonal mode, the designated mode set could be divided into some subsets in which the modes are completely orthogonal. The observed data is projected into each designated mode to realize fault detection according to the upper and lower control lines. The examples show that the proposed method can effectively diagnose multiple faults of down-hole conditions.

Approach to the Design Calculation of Sucker Rod Pumping Systems in Coalbed Methane Wells

The existing design of the pumping systems mainly focuses on the approximate computational formulae and procedures,which are developed based on the analytic approaches of conventional oil/gas fields.The calculation of polished rod loads usually just concerns about the static and inertial loads.And the computation of gearbox torque generally uses empirical formulae and correction factors.The above modeling procedures,if applied to the coalbed methane（CBM） wells,can not give the desired accuracy of the system design and its pertinent analysis.In this paper,based on the kinematic and dynamic analysis of the pumping system,the kinematic relation of polished rod is analyzed,and the variation of the total loads of polished rod is developed with the limits of CBM well conditions along the string.The gearbox torque calculation model is established by combining the counterbalance effect with the calculated dynamometer cards and torque factors.The application characteristics of this model are demonstrated by the example of ZH002-4 well in Qinshui basin.The interpretations of results show that the cranks of beam units should rotate in a counter clockwise direction viewed with the wellhead to the right.Compared with oil？gas fields,the dynamic and friction to polished rod load ratios are relatively high and the computation of polished rod loads should involve the static and inertial loads,as well as vibration and friction loads.And the dynamic load ratio decreases rapidly during the production.Besides,the total deformation of the string is small in CBM wells.As for balanced operation,the gearbox torque load usually has two approximately equal peaks and the magnitudes of instantaneous torque are just within 50% of unbalanced gearbox loadings.The proposed research improves efficiency of the pumping system,loads the pumping unit more uniformly,and provides the reasonable basis for selecting the units.

Experimental study on the temperature evolution in the railway brake disc

Increasing operating speed of modern passenger railway vehicles leads to higher thermal load onthe braking system. Organic composite brake pads are poor thermal conductors, hence frictionalheat is absorbed mainly by the disc. In this study three brake pad types were tested on thedynamometer. Metallic fibres, steel and copper, were introduced to the formulation of twomaterials. The third was a non-metallic material - a reference case. Dynamometer test comprisedemergency brake applications to determine the frictional characteristics of the materials andconstant-power drag braking to analyse the effect of metal fibres on temperature evolution,measured by six thermocouples embedded in the brake disc. Mean friction coefficient is analysedand discussed. It is concluded that conductive fibre in the friction material formulation mayinfluence its tribological characteristics. Despite high thermal conductivity, metal fibres in theconcentration tested in this study, did not reduce temperature of the brake disc.

Adaptive fault diagnosis of sucker rod pump systems based on optimal perceptron and simulation data

A highly precise and timely diagnosis technology can help effectively monitor and adjust the sucker rod production system(SRPS)used in oil wells to ensure a safe and efficient production.The current diagnosis method is pattern recognition of a dynamometer card(DC)based on feature extraction and perceptron.The premise of this method is that the training and target data have the same distribution.However,the training data are collected from a field SRPS with different system parameters designed to adapt to production conditions,which may significantly affect the diagnostic accuracy.To address this issue,in this study,an improved model of the sucker rod string(SRS)is derived by adding faultparameter dimensions,with which DCs under 16 working conditions could be generated.Subsequently an adaptive diagnosis method is proposed by taking simulated DCs generated near the working point of the target SRPS as training data.Meanwhile,to further improve the accuracy of the proposed method,the DC features are improved by relative normalization and using additional features of the DC position to increase the distance between different types of samples.The parameters of the perceptron are optimized to promote its discriminability.Finally,the accuracy and real-time performance of the proposed adaptive diagnosis method are validated using field data.

Joining Force of Heterogeneous Titanium Alloy in Linear Friction Welding Process

A dynamometer was designed and manufactured to measure the joining force in the linear friction welding process.The error percentages of the dynamometer in the upset(x)and vibration(y)directions were 0.9% and 0.75%,respectively.The cross-sensitivity range of the dynamometer was 1.2%—3.3% in the two directions.The precision level satisfies the requirements of the dynamometer test.The joining force of the TC17 and TC11 heterogeneous titanium alloys in the linear friction welding process was used to test the manufactured dynamometer.The test results showed that the upset force was large,but the vibration force showed a smaller change in TC11 during the linear friction welding process.In addition,the upset and vibration forces of the linear friction welding were greater with a short welding time than those with a long welding time.

An Intelligent Diagnosis Method of the Working Conditions in Sucker-Rod Pump Wells Based on Convolutional Neural Networks and Transfer Learning

In recent years,deep learning models represented by convolutional neural networks have shown incomparable advantages in image recognition and have been widely used in various fields.In the diagnosis of sucker-rod pump working conditions,due to the lack of a large-scale dynamometer card data set,the advantages of a deep convolutional neural network are not well reflected,and its application is limited.Therefore,this paper proposes an intelligent diagnosis method of the working conditions in sucker-rod pump wells based on transfer learning,which is used to solve the problem of too few samples in a dynamometer card data set.Based on the dynamometer cards measured in oilfields,image classification and preprocessing are conducted,and a dynamometer card data set including 10 typical working conditions is created.On this basis,using a trained deep convolutional neural network learning model,model training and parameter optimization are conducted,and the learned deep dynamometer card features are transferred and applied so as to realize the intelligent diagnosis of dynamometer cards.The experimental results show that transfer learning is feasible,and the performance of the deep convolutional neural network is better than that of the shallow convolutional neural network and general fully connected neural network.The deep convolutional neural network can effectively and accurately diagnose the working conditions of sucker-rod pump wells and provide an effective method to solve the problem of few samples in dynamometer card data sets.

Measurement of Emissions from a Passenger Truck Fueled with Biodiesel from Different Feedstocks

Biodiesel has generated increased interest recently as an alternative to petroleum-derived diesel. Due to its high oxygen content, biodiesel typically burns more completely than petroleum diesel, and thus has lower emissions of hydrocarbons (HC), carbon monoxide (CO), and particulate matter (PM). However, biodiesel may increase or decrease nitrogen oxide (NOx) and carbon dioxide (CO2) emissions, depending on biodiesel feedstock, engine type, and test cycle. The purpose of this study was to compare emissions from 20% blends of biodiesel made from 4 feedstocks (soybean oil, canola oil, waste cooking oil, and animal fat) with emissions from ultra low sulfur diesel (ULSD). Emissions of NOx and CO2 were made under real-world driving conditions using a Horiba On-Board Measurement System OBS-1300 on a highway route and arterial route;emissions of NOx, CO2, HC, CO, and PM were measured in a controlled setting using a chassis dynamometer with Urban Dynamometer Drive Schedule. Dynamometer test results showed statistically significant lower emissions of HC, CO, and PM from all B20 blends compared to ULSD. For CO2, both on-road testing (arterial, highway, and idling) and dynamometer testing showed no statistically significant difference in emissions among the B20 blends and ULSD. For NOx, dynamometer testing showed only B20 from soybean oil to have statistically significant higher emissions. This is generally consistent with the on-road testing, which showed no statistically significant difference in NOx emissions between ULSD and the B20 blends.

Atmospheric Carbon Dioxide and Nitrogen Oxides Emissions Data for 2003-2005 Model Year Trucks

Heavy-duty trucks account for a substantial portion of the atmospheric carbon dioxide (CO2) and nitrogen oxides (NOx) inventory. The data presented in this paper will help the research community be interested in developing models that predict the NOx and CO2 levels in real use. Continuous data of emissions were recorded from chassis dynamometer testing of five 2003-2005 model year (MY) heavy-duty trucks. The instantaneous emissions rate was plotted against axle power in all cases. The effect of vehicle test weight and the drive cycle employed on the relation between emissions rate (grams per sec) and axle power was studied. The NOx/CO2 ratio was found to be independent of the test cycle. The average NOx/CO2 ratio for the 2003-2005 MY trucks was found to be 0.0051, which agrees reasonably well with the estimated ratio of 0.0048, based on certification standards. The data were compared to those from 1994-2002 MY trucks;the average NOx/CO2 ratio for those trucks was 0.0141. For the 2003-2005 MY trucks, the distance specific NOx (grams per mile) and the fuel economy (miles per gallon) were less than those of 1994-2002 MY trucks.

Evaluation of regenerative braking based on single-pedal control for electric vehicles

More than 25%of vehicle kinetic energy can be recycled under urban driving cycles.A single-pedal control strategy for regenerative braking is proposed to further enhance energy efficiency.Acceleration and deceleration are controlled by a single pedal,which alleviates driving intensity and prompts energy recovery.Regenerative braking is theoretically analyzed based on the construction of the single-pedal system,vehicle braking dynamics,and energy conservation law.The single-pedal control strategy is developed by considering daily driving conditions,and a single-pedal simulation model is established.Typical driving cycles are simulated to verify the effectiveness of the single-pedal control strategy.A dynamometer test is conducted to confirm the validity of the simulation model.Results show that using the single-pedal control strategy for electric vehicles can effectively improve the energy recovery rate and extend the driving range under the premise of ensuring safety while braking.The study lays a technical foundation for the optimization of regenerative braking systems and development of single-pedal control systems,which are conducive to the promotion and popularization of electric vehicles.

Morphology and composition of particles emitted from a port fuel injection gasoline vehicle under real-world driving test cycles

Traffic vehicles, many of which are powered by port fuel injection(PFI) engines, are major sources of particulate matter in the urban atmosphere. We studied particles from the emission of a commercial PFI-engine vehicle when it was running under the states of cold start, hot start, hot stabilized running, idle and acceleration, using a transmission electron microscope and an energy-dispersive X-ray detector. Results showed that the particles were mainly composed of organic, soot, and Ca-rich particles, with a small amount of S-rich and metal-containing particles, and displayed a unimodal size distribution with the peak at 600 nm. The emissions were highest under the cold start running state, followed by the hot start, hot stabilized, acceleration, and idle running states. Organic particles under the hot start and hot stabilized running states were higher than those of other running states. Soot particles were highest under the cold start running state. Under the idle running state, the relative number fraction of Ca-rich particles was high although their absolute number was low. These results indicate that PFI-engine vehicles emit substantial primary particles,which favor the formation of secondary aerosols via providing reaction sites and reaction catalysts, as well as supplying soot, organic, mineral and metal particles in the size range of the accumulation mode. In addition, the contents of Ca, P, and Zn in organic particles may serve as fingerprints for source apportionment of particles from PFI-engine vehicles.

Carbonyl emissions from heavy-duty diesel vehicle exhaust in China and the contribution to ozone formation potential

Fifteen heavy-duty diesel vehicles were tested on chassis dynamometer by using typical heavy duty driving cycle and fuel economy cycle. The air from the exhaust was sampled by 2,4- dinitrophenyhydrazine cartridge and 23 carbonyl compounds were analyzed by high performance liquid chromatography. The average emission factor of carbonyls was 97.2 mg/km, higher than that of light-duty diesel vehicles and gasoline-powered vehicles. Formaldehyde, acetaldehyde, acetone and propionaidehyde were the species with the highest emission factors. Main influencing factors for carbonyl emissions were vehicle type, average speed and regulated emission standard, and the impact of vehicle loading was not evident in this study. National emission of carbonyls from diesel vehicles exhaust was calculated for China, 2011, based on both vehicle miles traveled and fuel consumption. Carbonyl emission of diesel vehicle was estimated to be 45.8 Gg, and was comparable to gasolinepowered vehicles （58.4 Gg）. The emissions of formaldehyde, acetaldehyde and acetone were 12.6, 6.9, 3.8 Gg, respectively. The ozone formation potential of carbonyls from diesel vehicles exhaust was 537 mg O3/km, higher than 497 mg O3/km of none-methane hydrocarbons emitted from diesel vehicles.

Characterizing human driver characteristics using an artificial neural network and a theoretical model

Human drivers seem to have different characteristics,so different drivers often yield different results from the same driving mode tests with identical vehicles and same chassis dynamometer.However,drivers with different experiences often yield similar results under the same driving conditions.If the features of human drivers are known,the control inputs to each driver,including warnings,will be customized to optimize each man–machine vehicle system.Therefore,it is crucial to determine how to characterize human drivers quantitatively.This study proposes a method to estimate the parameters of a theoretical model of human drivers.The method uses an artificial neural network(ANN)model and a numerical procedure to interpret the identified ANN models theoretically.Our approach involves the following process.First,we specify each ANN driver model through chassis dynamometer tests performed by each human driver and vehicle.Subsequently,we obtain the parameters of a theoretical driver model using the ANN model for the corresponding driver.Specifically,we simulate the driver’s behaviors using the identified ANN models with controlled inputs.Finally,we estimate the theoretical driver model parameters using the numerical simulation results.A proportional-integral-differential(PID)control model is used as the theoretical model.The results of the parameter estimation indicate that the PID driver model parameter combination can characterize human drivers.Moreover,the results suggest that vehicular factors influence the parameter combinations of human drivers.

Functionalization of alumina particles to improve the performance of eco-friendly brake-pads

Abrasives,such as oxides of alumina(Al),silica(Si),zirconia(Zr),chromium(Cr)etc.,are added to raise the friction level and also to remove the glaze on the disc so that surface will be rejuvenated continuously during braking and will contribute to maintain the desired friction level.However,these inorganic particles have less adhesion with the resin/binder and hence are easily dug out during wearing process contributing to higher wear.If efforts are made to enhance the filler‐matrix adhesion,not only the wear of friction material(FM)should reduce,the particles may stay for a longer time on the tribo‐surface of the pads to contribute fully towards controlling the coefficient of friction(μ).In the present study,alumina particles were selected for siloxane treatment to improve the filler‐matrix adhesion.Two types of eco‐friendly(free from asbestos and Cu)brake‐pads were developed using alumina as a theme ingredient(treated and untreated)keeping all the parent formulation identical.An additional type of brake‐pads without alumina particles was also developed to observe the effect of abrasive particles on the tribo‐performance.The performance properties(physical,mechanical,and tribological)of brake‐pads were compared when evaluated in identical conditions.The tribotesting was done on full‐scale brake inertia dynamometer following the procedure in Japanese automobile standard(JASO C 406).It was observed that siloxane treatment affected both friction and wear of brake‐pads in a beneficial way.Wear resistance got increased 35%for siloxane treated pads.Worn surfaces were analysed using scanning electron microscopy(SEM)and energy dispersive X‐ray(EDAX)technique.