Intelligent switching control for cement raw meal calcination process

Abstract

In raw meal calcination process, since boundary conditions of raw meal change frequently, the decomposition rate of raw meal (RMDR) cannot guarantee the desirable ranges. Therefore, C5 feeding tube was blocked and the load of rotary kiln will increase. To solve above problem, an intelligent switching control method is proposed to control the calciner temperature into their setpoints. This method for raw meal calcination process consists of four modules, namely a easy calcination controller, a difficult calcination controller, a abnormal condition controller, and a switching mechanism. The proposed approach can select right controller according to the change of the working conditions and has been successfully applied to the raw meal calcination process of Jiuganghongda Cement Plant in China and its efficiency has been validated by the practical application results.

Intelligent Setting Control for Clinker Calcination Process

“…In Fig. , an intelligent switching control method is used to realize the loop control, which is described in . The loop controller consists of four controllers, namely calciner temperature controller based on Takagi–Sugeno, preheater C1 outlet temperature controller based on fuzzy self‐tuning proportion integration (PI), import and export differential pressure controller based on PI, and rotary kiln speed controller based on PI.…”

Hybrid intelligent control of substrate feeding for industrial fed-batch chlortetracycline fermentation process

“…Instead of using a deterministic feeding profile, the presetting feeding rate can also be dynamically determined by case-based reasoning (CBR) [63]. CBR is generally suitable for mining expert's empirical knowledge from the operation data and it has been successfully applied to industrial processes [40,42,43]. It is practical to use the CBR method for building presetting module since modern instrument and measurement techniques allow for large amounts of operational data to be collected, stored and analyzed.…”

“…In addition, ANFIS [44] is also a promising technique for extracting fuzzy rules from operation data due to its advantages of describing expert knowledge using fuzzy inference systems and strong learning capability of artificial neural networks. Some successful applications of data based fuzzy modeling have been reported in recent years [43,73].…”

“…Therefore, for complex industrial processes, it is an inevitable tendency to develop hybrid intelligent control schemes by integrating information from mechanism analysis, plant data mining, data-driven or semi-empirical modeling, and expert knowledge, etc. Application examples of such methods have been reported in literature [40][41][42][43].…”

Temperature Forecasting System of Cement Decomposing Furnace Based on Grey System Theory

“…Whether the carbonate is decomposed effectively or not is an important factor of the cement quality. Because the carbonate need a stable temperature to decompose effectively, to forecast the temperature of the decomposing furnace is very important for the thermal distribution and the thermal regulation of the whole predecomposing system, which is described in [2]. At present, forecasting the temperature of the decomposing furnace in many factories depends on the work experience of the operation crews, so the forecasting result is not accurate, which is described in [3].…”