Abstract:Non-traditional machining (NTM) has gained significant attention in the last decade due to its ability to machine conventionally hard-to-machine materials. However, NTMs suffer from several disadvantages such as higher initial cost, lower material removal rate, more power consumption, etc. NTMs involve several process parameters, the appropriate tweaking of which is necessary to obtain economical and suitable results. However, the costly and time-consuming nature of the NTMs makes it a tedious and expensive task to manually investigate the appropriate process parameters. The NTM process parameters and responses are often not linearly related and thus, conventional statistical tools might not be enough to derive functional knowledge. Thus, in this paper, three popular machine learning (ML) methods (viz. linear regression, random forest regression and AdaBoost regression) are employed to develop predictive models for NTM processes. By considering two high-fidelity datasets from the literature on electro-discharge machining and wire electro-discharge machining, case studies are shown in the paper for the effectiveness of the ML methods. Linear regression is observed to be insufficient in accurately mapping the complex relationship between the process parameters and responses. Both random forest regression and AdaBoost regression are found to be suitable for predictive modelling of NTMs. However, AdaBoost regression is recommended as it is found to be insensitive to the number of regressors and thus is more readily deployable.Keywords: machine learning; linear regression; predictive models; response surface; machining
Mechanical energy based non-traditional machining (NTM) processes directly utilize mechanical energy to gradually remove material from the workpiece primarily by erosion. Examples of such processes include abrasive jet machining (AJM), water jet machining (WJM), abrasive water jet machining (AWJM) and ultrasonic machining (USM). In abrasive jet machining, abrasive particles are first mixed with the compressed gas at a pre-defined mixing ratio. This mixture is then directed towards the workpiece in the form of a high velocity jet by means of a nozzle. The small diameter nozzle converts the pressure energy of the air-abrasive mixture into kinetic energy, and thus high velocity jet is obtained. This nozzle also maintains appropriate stand-off distance (SOD) and discharge angle. This high velocity jet erodes material from the work surface at a controlled rate and thus material removal is obtained. Here only abrasive particles participate in erosion of workpiece material; compressed air has no role in it.
Non Traditional Machining Processes Pk Mishra Pdf Free
DOWNLOAD: https://urllio.com/2vDCI9
Unconventional machining processes are used only when no other traditional machining process can meet the necessary requirements efficiently and economically. Abrasive Waterjet Machining (AWJM) is one of the most recently developed mechanical type unconventional hybrid manufacturing technologies. It is superior to many other cutting techniques in processing various materials, particularly in processing difficult to cut materials. This technology is being increase used in various industries. Therefore, optimum choice of the process parameters is essential for the economic, efficient, and effective utilization of these processes. Process parameters of AWJM are generally selected either based on the experience, and expertise of the operator or from the propriety machining handbooks. In most of the cases, selected parameters are conservative and far from the optimum. This hinders optimum utilization of the process capabilities. Selecting optimum values of process parameters without optimization requires elaborate experimentation which is costly, time consuming, and tedious. Process parameters optimization of AWJM essential for exploiting their potentials and capabilities to the fullest extent economically. This paper presents a Fuzzy Logic (FL) - based modeling of AWJM process and optimization of its rule base, data base and consequent part utilizing a Genetic Algorithm (GA). A binary coded GA has been used for the said purpose. While modeling with FL, the output parameters, namely Material Removal Rate (MRR) and Surface Finish (Ra) have been predicted for different combinations of process parameters, such as water jet pressure at the nozzle exit diameter of abrasive-water jet nozzle traverse or feed rate of the nozzle mass flow rate of water and mass flow rate of abrasives between nozzle and the work piece.
The best of AJM and WJM processes have been combined to create a process known as AWJM. AWJM technology was first commercialized in the late 1980"s as a pioneering breakthrough in the area of non-traditional processing technologies. It is used to cut the target materials with a fine high pressure water abrasive slurry jet. AWJM is superior to many other cutting techniques in processing various materials. Such as no thermal distortion on the work piece, omni-directional cutting capability, high machining versatility to cut virtually any material and small cutting forces. This technology has found extensive applications in industry, particularly in contouring or profile cutting and in processing difficult to cut materials such as ceramics and marbles, and layered composites.
In this work, the optimal machining parameters for aluminum silicon carbide material for the multi performance characteristic in AWJM machining were determined by Fuzzy-Genetic approach. The formulated optimization models are multi- variable non-linearly constrained single and multi-objective optimization problems. For AWJM processes, the formulated objective functions and constraints are very complicated and implicit functions of the decision variables. An attempt has been made to carry out the forward modeling of the AWJM process by using an FLC. A batch mode of training is adopted which requires a large amount of data. The training data has been generated artificially (at random) by using the response equations obtained through response surface methodology. The optimal FLC is evolved with the help of a genetic algorithm. The accuracy in prediction of the responses is tested for ten different test cases and found a reasonably good prediction for both the outputs. The optimization results were confirmed graphically with the help of the graphs showing dependence of the objective function and constraint on the decision variables. Only single objective optimization was done to check the suit ability and validity of the material removal models, on the basis of which optimization models were formulated. Hence by properly adjusting the control factors, work efficiency and product quality can be increased.
2ff7e9595c
Comments