Production systems are currently under high constraints of availability, productivity, quality and flexibility. Therefore, it is a necessary to monitor and to keep operational the entities of the manufacturing process. In this paper, we are interested in solving some problems with the temporal component, like the periods to change used tools, in order to optimize the tasks on line. For this reason, a set-up of indirect predictive monitoring strategy online has been realized to followup the evolution of surface quality of the workpiece. In fact, the detection of the workpiece state after grinding in real time can help to avoid production downtime during the quality control, exhaustive damage of machined quality workpiece and machining system. In addition, a frequent change tool or plate not monitored induces additional costs. In this context, several studies have been conducted to propose methods and techniques for monitoring surface quality of the machined workpiece. In the most of cases, the developed approaches have used indirect measures of the state of the cutting tool. The measured signals will be analyzed later by the different techniques of signal processing to extract the information about the state of the cutting tool. In second stage, a correlation between the state of the cutting tool and the machined surface quality is established. However this double treatment can generate errors which can be at the origin of a divergence between the acquired signal by the sensor and the real state of the surface quality. It is in this context that the work presented in this paper is to develop a unique treatment to establish a direct correlation between the signals obtained by a sensor of cutting force in grinding and the surface quality of the workpiece. The wavelet decomposition is used in this paper to treat these signals.