Online prediction of the free lime content in the sintering zone and the use of neural networks for process optimization

The phase formation in clinker in the sintering zone is one of the critical operational processes in cement manufacture. The state of the art for chec king and optimizing the sintering process is thermography, i.e. measuring t he temperature distribution using infrared cameras. The "PIT Multisensor" d escribed in this article was developed specifically for applications in ind ustrial combustion systems with heavy dust burdens, and is based on an air- cooled two-channel endoscope. Video and thermographic images as well as var ious other combustion attributes are recorded using a video, glass-fibre, o r diode camera. The second optical output is used to take a glass-fibre cam era, which carries the kiln radiation directly to a special radiation recei ver in the field computer. The data which is generated can be used for onli ne prediction of the free lime content using a mathematical model. Links to various process control systems are available via the "PIT Cement" softwar e which, in addition to the thermographic display, creates various options for displaying the process dynamics. By using the described hardware and so ftware it is possible to achieve various optimization objectives simultaneo usly and online. Continuous online determination of the free lime content e nables the kiln to be fed with a continuous, constant and minimized supply of energy which is adjusted to suit the process; this leads to substantial savings in primary fuel and better control of the emission of harmful subst ances.