In the paper, the results of investigations on the properties of acoustic emission signals generated in a tested pressure vessel are presented. The investigations were performed by repeating several times the following procedure: an increase in pressure, maintaining a given pressure level, a further increase in pressure, and then maintaining the pressure at new determined level. During the tests the acoustic emission signals were recorded by the measuring system 8AE-PD with piezoelectric sensors D9241A. The used eight-channel measuring system 8AE-PD enables the monitoring, recording and then basic and advanced analysis of signals.

The results of basic analysis carried out in domain of time and the results of advanced analysis carried out in the discrimination threshold domain of the recorded acoustic emission signals are presented in the paper.

In the framework of the advanced analysis, results are described by the defined by the author descriptors with acronyms ADC, ADP and ADNC. Such description is based on identifying the properties of amplitude distributions of acoustic emission signals by assigning them the level of advancement. It is shown that for signals including continoues AE or single burst AE signals descriptions of such registered signals by means of ADC, ADP and ADNC descriptors and by Upp and Urms descriptors provide identical ordering of registered acoustic emission signals. For complex signals, the description using ADC, ADP and ADNC descriptors based on the analysis of amplitude distributions of recorded signals gives the order of signals with more accurate connection with deformational processes being sources of acoustic emission signals.

The prediction of machined surface parameters is an important factor in machining centre development. There is a great need to elaborate a method for on-line surface roughness estimation [1-7]. Among various measurement techniques, optical methods are considered suitable for in-process measurement of machined surface roughness. These techniques are non-contact, fast, flexible and tree-dimensional in nature.

The optical method suggested in this paper is based on the vision system created to acquire an image of the machined surface during the cutting process. The acquired image is analyzed to correlate its parameters with surface parameters. In the application of machined surface image analysis, the wavelet methods were introduced. A digital image of a machined surface was described using the one-dimensional Digital Wavelet Transform with the basic wavelet as Coiflet. The statistical description of wavelet components made it possible to develop the quality measure and correlate it with surface roughness [8-11].

For an estimation of surface roughness a neural network estimator was applied [12-16]. The estimator was built to work in a recurrent way. The current value of the Ra estimation and the measured change in surface image features were used for forecasting the surface roughness Ra parameter. The results of the analysis confirmed the usability of the application of the proposed method in systems for surface roughness monitoring.