Soft sensors are key solutions in predicting importance process variables. In process industries,rnimportant parameters which are difficult or cost a lot to measure online can be predicted usingrnsoft sensors. In this thesis a data driven soft sensor is developed using neural network to predictrnimportant clinker quality parameters.rnThe developed predictor is significant and can be categorized to the class of neural networkrnbased soft sensors. The significance of the thesis is that it avoids measurement delay incurredrnwhile analyzing clinker samples. As a result, quick control actions can be taken and clinkerrnquality can be further improved. This is one of the solutions provided by soft sensors. Many softrnsensors have been developed in different application areas and cement factory is the one. Somernpapers report neural network based predictors that are developed on rotary cement kiln. Thesernworks are related to the thesis. However, the thesis has its own new contribution. The first newrnfeature is that it has developed data synthesis strategy. Besides, multiple and advanced neuralrnnetwork architectures are used to get improved result. Moreover, it is of the first kind for thernselected case, which is the third line of Mugher cement factory.rnThe thesis is developed stage wise and a desired result is obtained. First, cement productionrnspecific to the case is studied. Then, data of all the recorded variables in the factories database isrncollected. This data collection is accompanied by variable selection and data encoding. The datarnis processed prior to using it for training the neural networks. This data preprocessing treatedrnmissing and outlier values. Based on the cleaned data, new data is synthesized to have enoughrndataset to work on. Finally, neural network models are developed and trained on this dataset. Asrna result, neural network models are obtained that can predict LSF, SM, AM and C3S values ofrnclinker with mean square error values of 4.3482, 0.0027, 0.0011 and 10.8759 respectively.rnIn conclusion, in this thesis a neural network based data driven clinker quality predictor isrndeveloped. While developing the predictor, Mugher cement factory is used as a case study. Therndeveloped predictor estimates LSF, SM, AM and C3S valuesrnKey words: Soft sensor, neural network, clinker quality prediction.rnSoft sensors are key solutions in predicting importance process variables. In process industries,rnimportant parameters which are difficult or cost a lot to measure online can be predicted usingrnsoft sensors. In this thesis a data driven soft sensor is developed using neural network to predictrnimportant clinker quality parameters.rnThe developed predictor is significant and can be categorized to the class of neural networkrnbased soft sensors. The significance of the thesis is that it avoids measurement delay incurredrnwhile analyzing clinker samples. As a result, quick control actions can be taken and clinkerrnquality can be further improved. This is one of the solutions provided by soft sensors. Many softrnsensors have been developed in different application areas and cement factory is the one. Somernpapers report neural network based predictors that are developed on rotary cement kiln. Thesernworks are related to the thesis. However, the thesis has its own new contribution. The first newrnfeature is that it has developed data synthesis strategy. Besides, multiple and advanced neuralrnnetwork architectures are used to get improved result. Moreover, it is of the first kind for thernselected case, which is the third line of Mugher cement factory.rnThe thesis is developed stage wise and a desired result is obtained. First, cement productionrnspecific to the case is studied. Then, data of all the recorded variables in the factories database isrncollected. This data collection is accompanied by variable selection and data encoding. The datarnis processed prior to using it for training the neural networks. This data preprocessing treatedrnmissing and outlier values. Based on the cleaned data, new data is synthesized to have enoughrndataset to work on. Finally, neural network models are developed and trained on this dataset. Asrna result, neural network models are obtained that can predict LSF, SM, AM and C3S values ofrnclinker with mean square error values of 4.3482, 0.0027, 0.0011 and 10.8759 respectively.rnIn conclusion, in this thesis a neural network based data driven clinker quality predictor isrndeveloped. While developing the predictor, Mugher cement factory is used as a case study. Therndeveloped predictor estimates LSF, SM, AM and C3S valuesrnKey words: Soft sensor, neural network, clinker quality prediction.rnSoft sensors are key solutions in predicting importance process variables. In process industries,rnimportant parameters which are difficult or cost a lot to measure online can be predicted usingrnsoft sensors. In this thesis a data driven soft sensor is developed using neural network to predictrnimportant clinker quality parameters.rnThe developed predictor is significant and can be categorized to the class of neural networkrnbased soft sensors. The significance of the thesis is that it avoids measurement delay incurredrnwhile analyzing clinker samples. As a result, quick control actions can be taken and clinkerrnquality can be further improved. This is one of the solutions provided by soft sensors. Many softrnsensors have been developed in different application areas and cement factory is the one. Somernpapers report neural network based predictors that are developed on rotary cement kiln. Thesernworks are related to the thesis. However, the thesis has its own new contribution. The first newrnfeature is that it has developed data synthesis strategy. Besides, multiple and advanced neuralrnnetwork architectures are used to get improved result. Moreover, it is of the first kind for thernselected case, which is the third line of Mugher cement factory.rnThe thesis is developed stage wise and a desired result is obtained. First, cement productionrnspecific to the case is studied. Then, data of all the recorded variables in the factories database isrncollected. This data collection is accompanied by variable selection and data encoding. The datarnis processed prior to using it for training the neural networks. This data preprocessing treatedrnmissing and outlier values. Based on the cleaned data, new data is synthesized to have enoughrndataset to work on. Finally, neural network models are developed and trained on this dataset. Asrna result, neural network models are obtained that can predict LSF, SM, AM and C3S values ofrnclinker with mean square error values of 4.3482, 0.0027, 0.0011 and 10.8759 respectively.rnIn conclusion, in this thesis a neural network based data driven clinker quality predictor isrndeveloped. While developing the predictor, Mugher cement factory is used as a case study. Therndeveloped predictor estimates LSF, SM, AM and C3S valuesrnKey words: Soft sensor, neural network, clinker quality prediction.rnSoft sensors are key solutions in predicting importance process variables. In process industries,rnimportant parameters which are difficult or cost a lot to measure online can be predicted usingrnsoft sensors. In this thesis a data driven soft sensor is developed using neural network to predictrnimportant clinker quality parameters.rnThe developed predictor is significant and can be categorized to the class of neural networkrnbased soft sensors. The significance of the thesis is that it avoids measurement delay incurredrnwhile analyzing clinker samples. As a result, quick control actions can be taken and clinkerrnquality can be further improved. This is one of the solutions provided by soft sensors. Many softrnsensors have been developed in different application areas and cement factory is the one. Somernpapers report neural network based predictors that are developed on rotary cement kiln. Thesernworks are related to the thesis. However, the thesis has its own new contribution. The first newrnfeature is that it has developed data synthesis strategy. Besides, multiple and advanced neuralrnnetwork architectures are used to get improved result. Moreover, it is of the first kind for thernselected case, which is the third line of Mugher cement factory.rnThe thesis is developed stage wise and a desired result is obtained. First, cement productionrnspecific to the case is studied. Then, data of all the recorded variables in the factories database isrncollected. This data collection is accompanied by variable selection and data encoding. The datarnis processed prior to using it for training the neural networks. This data preprocessing treatedrnmissing and outlier values. Based on the cleaned data, new data is synthesized to have enoughrndataset to work on. Finally, neural network models are developed and trained on this dataset. Asrna result, neural network models are obtained that can predict LSF, SM, AM and C3S values ofrnclinker with mean square error values of 4.3482, 0.0027, 0.0011 and 10.8759 respectively.rnIn conclusion, in this thesis a neural network based data driven clinker quality predictor isrndeveloped. While developing the predictor, Mugher cement factory is used as a case study. Therndeveloped predictor estimates LSF, SM, AM and C3S valuesrnKey words: Soft sensor, neural network, clinker quality prediction.