When planning and implementing a digital strategy, taking that important holistic approach means moving the process from typically siloed and discrete functions to one where all processes are connected, via developments in Internet of Things (IoT) technologies and then automated. Sandeep Ramprasad explains why these pandemic-stricken times are perhaps an opportune time for the cement industry to embrace digital technologies and harness big data.
________
Delivering high-quality products, while keeping production costs low and plant efficiency high, is an ongoing challenge in all process-driven industries. Traditional industries such as cement, face numerous challenges to reduce the cost of operations while also maximising the yield and ensuring quality. With the Covid-19 global pandemic creating major disruptions around the world, this is perhaps the best time for the cement industry to embrace digital technologies and harness big data to improve productivity, availability and quality across value chains. Several operators are already benefiting from this adoption.
Digital APC solutions help control, stabilise and optimise various cement processes, helping plant managers achieve profitability and drive towards sustainability targets. These solutions enable manufacturers to optimise coal, raw material and finished cement grinding by increasing throughput and securing consistent output quality, while also lowering energy consumption. Digital advanced data analytics offer tremendous opportunities to increase efficiency and further optimise the production processes. With the emergence of new digital technologies, machine learning models can provide productivity improvements in addition to APC solutions.
APC and analytics provide the ability to make predictions and estimations about process performance even in the absence of reliable measurement data. This could especially come in handy when real-world measurement would be too expensive or to increase the frequency of data input and provide backup for unreliable measurements.
In such cases, analytic models can be deduced from either first principles or process data. Analytic models include graphical (first principles), linear regression, non-linear regression, principal component analysis, artificial neural networks and support vector machines. Users can test various models and choose the one with either the best fit or performance statistic, thereby leveraging state-of-the-art advanced analytics.
Predictive quality analytics make it possible to accurately forecast cement quality in real-time at any point during production, thereby reducing the overspending to meet quality targets.
Blaine is measured in a laboratory at a frequency of every one to two hours and is used in the control system to maintain consistent quality and high levels of production. Although the data can be utilised for process control, it does not provide real-time insight into the process. This manual approach has limitations and ideally requires a predictive modelling technology that can predict Blaine every few minutes to maintain consistent quality, improve operational stability and reduce variability.
This can be accomplished through the collection of historical data from the control system for model training (production parameters and lab data), data cleansing (e.g., removal of data during mill stoppages, etc.), creating a fully automatic regression training model selecting the best fit from the library of models, deployment and testing of the model’s accuracy using the real-time online data, automatic data pull and retraining of the model if the accuracy is not met and using the predicted Blaine output to exercise control.
As a result, a prediction model transforms cement quality, Blaine, from an output process parameter to an input parameter that helps in sustaining the benefits via adaptive re-modelling and tuning. The efficiency of the process can be improved considerably through this approach since Blaine lacks continuous measurement in real-time and can be prone to infrequent sampling. Hence, operators can make more informed decisions using the information available.
Recent developments in advanced analytics have made machine learning models more easily accessible to users. But the true power of a machine learning algorithm can be harnessed only when domain knowledge is applied along with these algorithms. Data cleansing, anomaly removal, analysing the correlation of parameters and result interpretation can be carried out efficiently with expertise in domain knowledge.
Having served the cement industry for more than a century, building up knowledge and know-how of electrification and process control, ABB has the expertise and a proven track record in increasing plant performance and improving energy efficiency. Using ABB’s proven analytical and process modelling tools, along with our in-depth industry-specific knowledge, we can provide a clear path for plants to achieve operational excellence.
Author: Sandeep Ramprasad is the Global Service Product Manager for Cement at ABB. Actively involved in the fields of engineering, technology management, strategy and product management, he is responsible for driving product and portfolio management, business development and marketing in cement services.