Search Results

High strength materials have desirable mechanical properties but often cannot be machined economically, which results in unacceptably high finished component cost. MADI™ (machinable austempered ductile iron) overcomes this difficultly and provides the highly desirable combination of high strength, excellent low temperature toughness, good machinability and attractive finished component cost. The Machine Tool Systems Research Laboratory at the University of Illinois at Urbana-Champaign performed extensive machinability testing and determined the appropriate tools, speeds and feeds for milling and drilling (https://netfiles.uiuc.edu/malkewcz/www/MADI.htm). This paper provides the information necessary for the efficient and economical machining of MADI™ and provides comparative machinability data for common grades of ductile iron (EN-GJS-400-18, 400-15, 450-10, 500-7, 600-3 & 700-2) for comparison.

Machinability of SAE 8620 hot rolled steel bare was evaluated. All samples were tested in the normalized condition. Machinability was determined using a CNC turning center with titanium nitride coated cutting inserts. Several heats from different steel suppliers were tested, some contained the machining enhancers calcium and tellurium as well as various sulphur levels. One heat did not contain enhancers for determination of a machinability baseline. Two machining parameters were used: 800 and 1200 c.s.f.m. (constant surface feet per minute), both at a feed rate of .015 i.p.r. (inches per revolution) and .075 in. d.o.c. (depth of cut). All the materials were chemically, mechanically, and metallurgically characterized. This report will show that these machining enhancers can produce less insert damage (flank and crater) than the same grades without machining enhancers.

Powder metallurgy (P/M) industry has been known for the capability of producing near-net-shape parts. Its specific characteristics have resulted in lower production costs and eliminating many secondary machining. However, more and more P/M parts do require additional operations to fulfil their complex geometry features and surface roughness. Many of the machining factors that influence the machinability of cast and wrought steel parts, such as cutting speed, feedrate, coolant, tool geometry and shape, are also considered in the machining of P/M parts. However, composition, structure, and porosity of P/M are additional factors to be considered. Porosity in the P/M structure can decrease the machinability and shorten the tool life. Different variables have been considered in the material composition. Material densities and the free-machining additive manganese sulphide (MnS) are the two main factors of material composition, which dominate the machining performance.

In almost all-manufacturing processes, there is a trade-off between cost and quality. Parameters that indicate quality include surface texture, dimensional accuracy, mechanical properties and uniformity of physical appearance. Unfortunately, parts with good surface finish, precise geometry and high mechanical strength are usually the most expensive to produce. In order to achieve high quality components at reasonable cost, optimisation of machining is essential. This is usually accomplished by judicious selection of proper cutting tool, cutting method, and the various cutting parameters that control the process. It is the intention of this paper to demonstrate research efforts aimed at characterizing and machining of CAPTAL‘90’, a hydroxyapatite (HA) material-suitable for human bone tissue replacement. It is expected that experimental knowledge gained and the results will form basis for modification of hydroxyapatite material for better machining performance.

Based on a previous paper of the author [1] an oil condition index OC is defined. The index is composed of the values of a set of normalized oil parameters weighted by their importance to the machine and the application. The concept of Dimensional Analysis is used to determine the relationships between machine, oil and operating parameters. This process leads to dimensionless groups, which characterize the oil condition monitored for a machine. Defining OC for a specific machine or machine type and including specifics of the use and the environment the machine is operated in, provides operators and managers with Statistical Process Control (SPC) tools to predict maintenance and prevent catastrophic failure. Data from a reliability experiment are presented which illustrates the relationship between the oil properties, machine operating parameters and oil contamination.

Continuous process manufacture, such as oil refineries and breweries, all employ monitoring techniques, based on sensors measuring critical parameters. S.C.A.D.A. software (Supervisory Control And Data Aquisition), is used to analyse data and provide information. This technique allows performance monitoring of equipment, both instantaneously and historically. Failure prediction, using known deterioration patterns, allow Maintenance to minimise production losses, by being able to forward plan corrective activities. Batch-manufacturing industry has been slow to use S.C.A.D.A. monitoring systems because of various incompatible requirements. Systems will often not interface to numerical controls used on, for example, fastening machines. The relatively slow S.C.A.D.A. data scan rates and cyclic machinery has restricted their introduction.

Use of sensors to monitor dynamic performance of machine tools at Ford’s powertrain machining plants has proven to be effective. The traditional approach to convert sensor data to actionable intelligence consists of identifying single features from cycle based signatures and setting thresholds above acceptable performance limits based on trials. The thresholds are used to discriminate between acceptable and unacceptable performance during each cycle and raise alarms if necessary. This approach requires a significant amount of resource & time intensive set up work up-front and considerable trial and error adjustments. The current state does not leverage patterns that might be discernible using multiple features simultaneously. This paper describes enhanced methods for processing the data using supervised and unsupervised machine learning methods. The objective of using these methods is to improve the prediction accuracy and reduce up-front set up.

This paper presents the results of a study using computer human modeling to examine machine appendage speed. The objective was to determine the impact of roof bolter machine appendage speed on the likelihood of the operator coming in contact with. A contact means two or more objects intersecting or touching each other, e.g., appendage makes contact with the operator’s hand, arm, head or leg. Incident investigation reports do not usually contain enough information to aid in studying this problem and laboratory experiments with human subjects are also not feasible because of safety and ethical issues. As an alternative, researchers developed a computer model approach as the primary means to gather data. By simulating an operator’s random behavior and machine’s appendage velocity, researchers can study potential hazards of tasks where it is not possible to perform experiments with human subjects.

Computer-Aided Engineering Systems are interactive computer based systems for application to a wide variety of engineering and manufacturing functions. Volumetric models and a structured data base are two key components of these systems. This paper presents the concept of a Product Structured Data Base and its use in combination with volumetric models, in the layout phase of a machine design. This combination provides for automatic analysis of interference and fit between parts of a machine.

Automotive collision avoidance system is a measure of enhanced safety. Car collisions have claimed the lives of many, and the advancement of science and technology has made collision avoidance a reality. Traditionally, collision avoidance systems are designed with the aim to avoid rear end collision, but in this paper, we are going to look at the collision avoidance with respect to fast approaching automobiles from a blind turn, making use of the navigation system. Here, we reviewed two levels of probability for collision. The first case is with high probability of probable collision and another case is with high probability of imminent collision. If the probability of probable collision is high, the driver is warned and requested to control the speed of the car. If the probability of imminent collision is high, the driver is warned, and autonomous braking takes effect.

Combustion stability is a key contributor to engine shake at idle speed and can impact the overall perception of vehicle quality. The sub-firing harmonics of the combustion torque are used as a metric to assess idle shake and are, typically, measured at different levels of engine break mean effective pressure (BMEP). Due to the nature of the combustion phenomena at idle, it is clear that predicting the cycle-to-cycle and cylinder-to-cylinder combustion pressure variations, required to assess the combustion uniformity, cannot be achieved with the state of the art simulation technology. Inspired by the advancement in the field of machine learning and artificial intelligence and by the availability of a large amount of measured combustion test data, this paper explores the performance of various machine learning algorithms in predicting the idle combustion uniformity.

Performance predictions of advanced turbocharged engines are becoming difficult because conventional engine models are built using performance map data of turbochargers with a proportional integral derivative (PID) controller. Improving prediction capabilities under transient test cycles or real driving conditions is a challenging task. This study applies a machine learning technique to predict turbocharger performances with high accuracy under steady-state and transient conditions. The manipulated signals of engine speed and torque created based on Compressed High-Intensity Radiated Pulse (Chirp signal) and Amplitude-modulated Pseudo-Random Binary Signal (APRBS) are used as inputs to the engine testbed. Data from the engine experiments are used as training data for the AI-based turbocharger model. High prediction accuracy of the AI turbocharger model is achieved with the co-efficient of determination in the model, and cross-validation results are higher than 0.8.

A wet clutch is an established component in a conventional powertrain. It also finds a new role in electrified systems. For example, a wet clutch is utilized to couple or decouple an internal combustion engine from an electrically-driven drivetrain on demand in hybrid electric vehicles. In some electrical vehicle designs, it provides a means for motor speed reduction. Wet clutch control for those new applications may differ significantly from conventional strategy. For example, actuator pressure may be heavily modulated, causing the clutch to exhibit pronounced hysteresis. The clutch may be required to operate at a very high slip speed for unforeseen behaviors. A linear transfer function is commonly utilized for clutch control in automating shifting applications, assuming that clutch torque is proportional to actuator pressure. However, the linear model becomes inadequate for enabling robust control when the clutch behavior becomes highly nonlinear with hysteresis.

Semiconductor devices in electric vehicle (EV) motor drive systems are considered the most fragile components with a high occurrence rate for open circuit fault (OCF). Various signal-based and model-based methods with explicit mathematical models have been previously published for OCF diagnosis. However, this proposed work presents a model-free machine learning (ML) approach for a single-switch OCF detection and localization (DaL) for a two-level, three-phase inverter. Compared to already available ML models with complex feature extraction methods in the literature, a new and simple way to extract OCF feature data with sufficient classification accuracy is proposed. In this regard, the inherent property of active thermal management (ATM) based model predictive control (MPC) to quantify the conduction losses for each semiconductor device in a power converter is integrated with an ML network.

Implementing stringent emission norms and fuel economy requirement in the coming decade will be very challenging to the whole automotive industry. Aerodynamic losses contribute up to 13% to 22 % of overall fuel economy and aerodynamicists will be challenged to have optimum content on the vehicle to reduce this loss. Improving Aerodynamic performance of ground vehicles has already reached its peak and the industry is moving towards active mechanisms to improve performance. Calibrating or simulating these active mechanisms in the wind tunnel or in Computational Fluid Dynamics (CFD) would be very challenging as the model complexity increases. Computationally expensive CFD models are required to predict the transient behaviors of model complexity.

Wire Arc Additive Manufacturing (WAAM) is a type of 3D printing technology which build up layer by layer material using welding to create a finished product. To this extent, we have developed the machine learning approach using the KNN regression model to predict the bead’s height and width of the E71T1 mild steel sample by wire arc additive manufacturing (WAAM). We have conducted a systematic experimental study by varying the process parameters such as Voltage (V), Current (A) and wire feed rate (f), and the corresponding output value: height, and width of the bead are recorded. A total of 195 experiments were conducted, and the corresponding output values were noted. From the experimental data, 80% data was used to train the model, and 20% was used for testing the model. Further, the model’s accuracy was predicted using an independent set of test samples.

Lithium-ion batteries (LIBs) have become a focus of research interest for electric vehicles (EVs) due to their high volumetric and gravimetric energy storage capability, lower self-discharge rate, and excellent rechargeability coupled with high operational voltage as compared with the lead-acid batteries. This paper presents different machine learning approaches to predict health indicators & usable cycle life of LIBs. Here, we focus on two important battery health indicators i.e., battery discharge capacity and Internal resistance (IR). We used publicly available multi-cycled data of the Lithium Iron Phosphate (LFP), Lithium-Nickel-Manganese-Cobalt-Oxide (NMC) and Lithium Cobalt Oxide (LCO) cells. The approach proposed for predicting health indicators involves using a time-series model in the areas where the actual data i.e., from the Beginning of life (BOL) to the End of life (EOL) is not available.

Computer Aided Engineering (CAE) simulations are an integral part of the product development process in an automotive industry. The conventional approach involving pre-processing, solving and post-processing is highly time-consuming. Emerging digital technologies such as Machine Learning (ML) can be implemented in early stage of product development cycle to predict key performances without need of traditional CAE. Oil Canning loadcase simulates the displacement and buckling behavior of vehicle outer styling panels. A ML model trained using historical oil canning simulation results can be used to predict the maximum displacement and classify buckling locations. This enables product development team in faster decision making and reduces overall turnaround time. Oil canning FE model features such as stiffness, distance from constraints, etc., are extracted for training database of the ML model. Initially, 32 model features were extracted from the FE model.

Cellular solids are excellent energy absorbers and widely applied in the automotive passive safety area. Their microstructures offer the ability to undergo large plastic deformation at nearly constant nominal stress and thus can absorb a large amount of kinetic energy before collapsing to a more stable configuration or fracture. To further improve their performance, it is imperative to develop a systematic design method, to tailor microstructures’ behavior by adjusting their geometric parameters, especially for those with irregular, random shapes. In this research, we proposed a machine learning based method, which combines the finite element (FE) analysis to design open cell foams for crash energy absorption. The foam geometry is generated utilizing a large number of core points and convex polygons, known as the Voronoi diagram, and then converted to the FE model to compute the plateau stress under crush loading.

Unmanned Aerial Vehicles (UAVs) encounter various uncertainties, including unfamiliar environments, signal delays, limited control precision, and other disturbances during task execution. Such factors can significantly compromise flight safety in complex scenarios. In this paper, to enhance the safety of UAVs amidst these uncertainties, a control accuracy prediction model based on ensemble learning abnormal state detection is designed. By analyzing the historical state data, the trained model can be used to judge the current state and obtain the command tracking control accuracy of the UAV at that instant. Ensemble learning offers superior classification capabilities compared to weak learners, particularly for anomaly detection in flight data. The learning efficacy of support vector machine, random forest classifier is compared and achieving a peak accuracy of 95% for the prediction results using random forest combined with adaboost model .