Neural modelling, control and optimisation of an industrial grinding process

This paper describes the development of neural model-based control strategies for the optimisation of an industrial aluminium substrate disk grinding process. The grindstone removal rate varies considerably over a stone life and is a highly nonlinear function of process variables. Using historical grindstone performance data, a NARX-based neural network model is developed. This model is then used to implement a direct inverse controller and an internal model controller based on the process settings and previous removal rates. Preliminary plant investigations show that thickness defects can be reduced by 50% or more, compared to other schemes employed. (c) 2004 Elsevier Ltd. All rights reserved.

Artificial neural network modeling for surface roughness prediction in cylindrical grinding of Al‐SiCp metal matrix composites and ANOVA analysis

Metal matrix composites (MMC) having aluminium (Al) in the matrix phase and silicon carbide particles (SiCp) in reinforcement phase, ie Al‐SiCp type MMC, have gained popularity in the re‐cent past. In this competitive age, manufacturing industries strive to produce superior quality products at reasonable price. This is possible by achieving higher productivity while performing machining at optimum combinations of process variables. The low weight and high strength MMC are found suitable for variety of components

Use of plastic and textile media in polishing primary treated effluent

The majority of on-site sewage management systems in Australia fail to perform to expectations. About 60% to 80% of on-site systems reportedly fail to produce acceptable effluent quality, and there is an increaed concern about the risks associated with public health and environmental pollution. In Victoria, a large proportion of septic tank installations have been reported to discharge highly polluted waste to drains and streams. Users, often considered by regulators as operators, have to bear the costs of upgrade/replacement of their old systems to meet stringent water quality guidelines. Some of the common problems include clogging of the disposal fields due to solids and organic overloading and surfacing of highly polluted effluent. Large land application area is subsequently required for irrigating the effluent and/or installation of upgraded disposal fields.
This paper investigates the effectiveness of various types of textile and plastic media, in polishing primary tank effluent, downstream from a typical two-compartment septic tank system. Results to date show that high biochemical oxygen demand removal rates are achieved from the textile and plastic media (up to 86% and 83% respectively). At these removal levels, the performance of a combined conventional septic tank system and plastic/textile filters is comparable to that of an advanced aerated wastewater treatment system. This approach, subject to further investigation, could provide a less costly upgrade.

Preparation of silica abrasives from water glass and application in silicon wafer polishing

Chemical mechanical polishing technique is more frequently adopted for planarization in integrated circuit fabrication. The silica abrasives in colloidal state are fabricated with the sodium silicate solution as raw materials through the polymerization reaction among silicic acid molecules. By continuous injection of silicic acid into the preexisting silica solution, the diameter of silica nanoparticles increases. The different sized silica nanoparticles are imaged by scanning electron microscopy, and the dried silica are characterized by X-ray diffraction and thermal analysis. The polishing test on silicon wafer with as-fabricated silica abrasives shows that the surface flatness reaches 1.1 nm roughness, however, micro scratches are still present in the surface.

A corrosion inhibition study of steel grinding balls in an oxygen and alkaline environment

The corrosion of steel grinding balls is a major recurrent cost for mill operators concerned with the production gold. Subsequently, the use of corrosion inhibitors in production fluids, which is typically at pH >9, is an attractive and economical option. This study reports on the corrosion wear of steel grinding balls under alkaline/oxygen conditions and in presence of cyanide. A fundamental study on the influence of several inorganic-based inhibitors (i.e., nitrite, chromate, silicate, hexametaphosphate) on the corrosion rate of carbon steel was undertaken. Subsequently, the corrosion performances of various inhibitors were evaluated in stirred vessels. Corrosion rates were determined via mass loss and electrochemical methods (i.e., linear polarisation, Tafel). It was observed that inhibitors based upon chromate provide superior protection under the conditions investigated in this study. In lime treated, high chloride waters, chromate gave over 80% protection at levels of 10 100 ppm with no evidence of pitting.

Analysis of the different forms of application and types of cutting fluid used in plunge cylindrical grinding using conventional and superabrasive CBN grinding wheels

The work reported here involved an investigation into the grinding process, one of the last finishing processes carried out on a production line. Although several input parameters are involved in this process, attention today focuses strongly on the form and amount of cutting fluid employed, since these substances may be seriously pernicious to human health and to the environment, and involve high purchasing and maintenance costs when utilized and stored incorrectly. The type and amount of cutting fluid used directly affect some of the main output variables of the grinding process which are analyzed here, such as tangential cutting force, specific grinding energy, acoustic emission, diametrical wear, roughness, residual stress and scanning electron microscopy. To analyze the influence of these variables, an optimised fluid application methodology was developed (involving rounded 5, 4 and 3 turn diameter nozzles and high fluid application pressures) to reduce the amount of fluid used in the grinding process and improve its performance in comparison with the conventional fluid application method (of diffuser nozzles and lower fluid application pressure). To this end, two types of cutting fluid (a 5% synthetic emulsion and neat oil) and two abrasive tools (an aluminium oxide and a superabrasive CBN grinding wheel) were used. The results revealed that, in every situation, the optimised application of cutting fluid significantly improved the efficiency of the process, particularly the combined use of neat oil and CBN grinding wheel. (c) 2005 Elsevier Ltd. All rights reserved.

Studies on the cooling minimum quantity and conventional cooling at hardened steels in grinding process

The purpose of this work is to explain the concept of cutting fluids reasonable usage through the fluid minimum quantity in grinding processes. on that purpose, the development of a new nozzle and an own and adequate methodology should be required in order to obtain good results and compare them to the conventional methods. The analysis of the grinding wheel/cutting fluid performance was accomplished from the following input parameters: flow rate variation by nozzle diameter changes (three diameters values: 3mm, 4mm and 5mm), besides the conventional round nozzle already within the machine. Integral oil and a synthetic emulsion were used as cutting fluids and a conventional grinding wheel was employed. The workpieces were made of steel VC 131, tempered and quenched with 60HRc. Thus, as the flow rate and the nozzle diameter changes, keeping steady fluid jet velocity (equal to cutting velocity), attempted to find the best machining conditions, with the purpose to obtain a decrease on the cutting fluid volume, taking into consideration the analysis of the process output variables such as cutting strength, cutting specific energy, grinding wheel wear and surface roughness. It was verified that the 3mm diameter optimized nozzle and the integral oil, in general, was the best combination among all proposed.

Evaluation of the thermal damages in inlet engine valves varying the grinding wheels and the cutting fluids

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Performance of aerodynamic baffles in cylindrical grinding analyzed on the basis of air layer pressure and speed

Over the years, grinding has been considered one of the most important manufacturing processes. Grinding is a high precision process, and the loss of a single workpiece in this stage of the production is unacceptable, fir the value added to the material is very high due to many processes it has already undergone prior to grinding. This study aims to contribute toward the development of an experimental methodology whereby the pressure and speed of the air layer produced by the high rotation of the grinding wheel is evaluated with and without baffles, i.e., in an optimized grinding operation and in a traditional one. Tests were also carried out with steel samples to check the difference in grinding wheel wear with and without the use of baffles.

Evaluation of grinding fluids in the grinding of a martensitic valve steel with CBN and alumina abrasives

In this paper the performances of different cutting fluids and grinding wheel types were analysed in the grinding of SAE HVN-3 workpieces. The resulting residual stress, wheel wear and roughness were evaluated. The influence of the cutting fluid jet velocity v(j) was also analysed. As a conclusion, the lubrication ability seems to be the governing factor in the cutting fluid performance. The use of CBN wheels can significantly reduce the thermal damage in grinding, leading to compressive residual stresses. The CBN wheel and the cutting oil give an optimum combination for performing this grinding operation.

Production grinding burn detection using acoustic emission and electric power signals

This work uses a monitoring system based on a PC platform, where the acoustic emission and electric power signals generated during the grinding process are used to investigate superficial burning occurrence in a surface grinding operation using two types of steel, three grinding conditions and an Al203 vitrified grinding wheel. Acoustic emission signals on the workpiece and grinding power were measured during a surface plunge operation until the grinding burn happened. From the results the standard deviation of the acoustic emission signal and the maximum electric power were calculated for each grinding pass. The proposed DPO parameter is the product between the power level and acoustic emission standard deviation. The results show that both signals can be used for burning detection, and the parameter DPO is the best indicator for the burning studied in this work. This can be explained by the high dispersion of the acoustic emission RMS level associated to the high power consumption when the grinding wheel lose its sharpness.