-
The present invention relates to a field of engineering of cement manufacturing, and more particularly relates to a method and system for optimizing fuel consumption in a cement manufacturing kiln.
-
A cement manufacturing process is a complex operation that requires precise control of numerous variables to optimize production efficiency, reduce costs, and maintain product quality. Traditionally, a performance evaluation of cement kilns relies on an analysis of various operational parameters such as kiln feed, temperature levels, and emission outputs. However, a process of gathering, analyzing, and making adjustments based on these parameters poses significant challenges. One of the main challenges in the cement industry has been the time-consuming nature of evaluating plant performance. With the myriad of parameters affecting the cement manufacturing kiln's stability and efficiency, it has historically been difficult to assess the current condition of plant operations rapidly and accurately. The traditional methods often require manual data collection and analysis, which not only consumes significant time but also increases the likelihood of human error.
-
Moreover, the ability to provide a quick and accurate Return on Investment (ROI) estimation based on the data from Exploratory Data Analysis (EDA) has been limited. Plant managers and engineers need to make informed decisions about investments in equipment upgrades, process modifications, and operational improvements. However, without efficient tools to analyze data and predict outcomes, these decisions can be suboptimal, leading to increased costs and missed opportunities for efficiency gains. Accordingly, there is a long-felt and unmet need for a method and a system which optimizes fuel consumption in a cement manufacturing kiln and thereby optimizing a return on investment on cement manufacturing kiln.
-
Conventional systems do not have an ability to continuously monitor and adjust operational parameters in real time. Thus, time is wasted on performance evaluation, human error, due to lack of a system that allows for rapid and accurate assessments of plant operations. Consequently, cement manufacturing plants are unable to achieve higher production efficiency and reduced operational costs.
-
From an environmental perspective, the problem of high CO2 emissions due to inefficient fuel consumption is persistent. In conventional systems, fuel is not burned efficiently, resulting in higher CO2 emissions. Thus, conventional systems are not aligned with global environmental goals and regulations, thus damaging a sustainability profile of the cement manufacturing plant.
-
Higher fuel usage increase the expenses associated with purchasing fuel, which is a major cost component in cement production. Additionally, by failing to maintain stable and efficient kiln operations, wear and tear on equipment is increased, leading to higher maintenance costs and lessened equipment lifespan. A lack of ability to predict and control operational parameters reduces changes for better planning and resource allocation, further reducing the plant's financial performance. Solving these economic challenges not only improves the environmental impact of cement manufacturing but also enhances the economic viability and return on investment for cement manufacturing plants.
-
Thus it is an object of the present invention to provide a method and system for optimizing fuel consumption in a cement manufacturing kiln.
-
The object is achieved according to a method as claimed in claim 1 or according to a system as claimed in claim 12. Embodiments result, for example, as claimed in claims 2 to 11 and 13 to 14. For example, the object of the present invention is achieved through a method of optimizing fuel consumption in a cement manufacturing kiln. The approach to optimize fuel consumption in the cement manufacturing kiln reduces operational costs and enhances a return on investment (ROI) in a cement manufacturing plant.
-
A cement manufacturing kiln is a large, cylindrical vessel which is used during a pyroprocessing stage of cement production. Inside the cement manufacturing kiln, a plurality of raw materials are pyroprocessed to generate clinker. Examples of the plurality of raw materials include limestone, clay, or shale. The pyroprocessing happens at very high temperatures and is thus fuel-intensive. Examples of fuel consumed includes coal, natural gas, and oil. The fuel consumed by the cement manufacturing kiln is expensive, and thus by optimizing fuel consumption, return of interest of the cement manufacturing plant can be optimized. Furthermore, a temperature of the cement manufacturing kiln is dependent on the fuel consumption of the cement manufacturing kiln. A stability of the cement manufacturing kiln is dependent on the temperature. Thus, by optimizing the fuel consumption, a stability of the cement manufacturing kiln can be maintained, and furthermore, a return of investment of the cement manufacturing kiln can be optimized. Furthermore, the fuel consumption is also related to an amount of emission of the cement manufacturing kiln, and an amount of combustion of a fuel in the cement manufacturing kiln.
-
The outputs of the cement manufacturing kiln are primarily the clinker and one or more waste gases. A quality of clinker has a significant impact on a final strength and quality of cement produced by the cement manufacturing plant. Since the quality of clinker is proportional to a stability of the cement manufacturing kiln, optimizing the fuel consumption becomes of paramount importance.
-
In a preferred embodiment, the method comprises receiving a plurality of operational parameters associated with the cement manufacturing kiln. The plurality of operational parameters is captured by one or more sensors in the cement manufacturing plant. The plurality of operational parameters comprises kiln feed rate, chain zone temperature, C3S (quality parameter), kiln inlet O2, and kiln inlet CO temperature.
-
The plurality of operational parameters are collected by the one or more sensors which are located within the cement manufacturing plant. The one or more sensors comprises flow sensors, thermocouplers, infrared sensors, gas analyzers, and others. In one example, flow sensors is configured to determine the cement manufacturing kiln feed rate by measuring the volume of raw materials entering the cement manufacturing kiln. Thermocouples or infrared sensors are configured to monitor temperatures, such as the chain zone temperature and the temperatures at the cement manufacturing kiln inlet. The gas analyzers are configured to measure concentration of gases like oxygen and carbon monoxide at the cement manufacturing kiln. The one or more sensors are configured to transmit the plurality of operational parameters to the processing unit via wired connections such as Ethernet or other communication cables for stable, continuous data transmission. The one or more sensors may also use wireless systems like Wi-Fi or Bluetooth to transmit the plurality of operational parameters to the processing unit. Furthermore, the plurality of operational parameters are also transmitted via industrial communication protocols like Modbus or Fieldbus, designed to handle large volumes of data and ensure reliable transmission even in harsh industrial environments.
-
In the preferred embodiment, the method comprises determining, from the plurality of operational parameters, one or more operational parameters which affects a cement manufacturing kiln stability of the cement manufacturing plant. In one example, the processing unit is configured to determine the one or more parameter based on a user input received at a user interface. In another example, the processing unit is configured to determine the one or more operational parameters by application of a machine learning algorithm on the plurality of operational parameters. In one example, the machine learning algorithm is configured to correlate specific changes in the plurality of operational parameters with variations in a plurality of kiln stability indicators of the cement manufacturing kiln. The plurality of kiln stability indicators indicate a stability of the cement manufacturing kiln. Examples of the plurality of key stability indicators include a cement manufacturing kiln shell temperature, an axial thrust of the cement manufacturing kiln, a rotational speed of the cement manufacturing kiln, and a torque and a power consumption of the cement manufacturing kiln. The plurality of kiln stability indicators are measured by the one or more sensors in the cement manufacturing plant.
-
In one example, the machine learning algorithm is configured to analyze historical data to determine a plurality of interrelationships between the plurality of operational parameters and a plurality of kiln stability indicators. In one example, the machine learning algorithm is trained by application of a supervised learning algorithm on a labelled training dataset comprising information associated with interrelationships between the plurality of operational parameters and the plurality of kiln stability indicators. Examples of the machine learning algorithms include a random forest algorithm and a support vector machine algorithm.
-
The method further comprises receiving, by the processing unit, the historical data associated with the plurality of operational parameters and the plurality of kiln stability indicators. The method further comprises analyzing the historical data associated with the plurality of operational parameters and the plurality of kiln stability indicators to generate a correlation matrix. A correlation matrix is a statistical tool which is configured to determine a degree and a direction of correlation between the plurality of operational parameters and the plurality of kiln stability indicators.
-
The processing unit is configured to generate the correlation matrix by application of a statistical algorithm on the plurality of operational parameters and the plurality of kiln stability indicators. The correlation matrix comprises information associated with a first set of operational parameters which have a positive correlation with the plurality of kiln stability indicators. The correlation matrix further comprises information associated a second set of operational parameters which has a negative correlation with the plurality of kiln stability indicators. In one example, the correlation between kiln feed rate and kiln inlet CO temperature has a strong positive correlation, indicating that changes in the feed rate significantly impact the CO temperature. Examples of the statistical algorithms include Pearson correlation coefficient-based algorithm, Spearman's rank correlation coefficient-based algorithm, Kendall's Tau-based algorithm, Polychoric correlation-based algorithm, and Polyserial correlation-based algorithm. In yet another example, the correlation matrix is generated by application of a supervised training algorithm on the historical data comprising the plurality of operational parameters and the plurality of kiln stability indicators. In other words, the correlation matrix comprises information associated with a plurality of interrelationships between the plurality of operational parameters and the plurality of kiln stability indicators.
-
In one example, the method further comprises receiving a user input indicative of at least one parameter which is to be selected from one of the plurality of operational parameters. In another example, the method comprises determining, by the processing unit, the at least one parameter from the plurality of operational parameters by application of a maximizing algorithm on the plurality of operational parameters to determine the at least one parameters which has maximum impact on the plurality of kiln stability indicators. In another example, the processing unit is configured to apply a multilinear regression algorithm on the correlation matrix to determine the at least one parameter whose variation has maximum impact on values of the plurality of kiln stability indicators. Examples of the multilinear regression algorithms include Ordinary Least Squares (OLS)-based algorithm, Ridge Regression-based algorithm, Lasso Regression-based algorithm, Elastic Net Regression-based algorithm, and Principal Component Regression (PCR)-based algorithm. Thus, the at least one parameter has a highest correlation impact with the plurality of kiln stability indicators. In one example, the at least one parameter is determined to be a cement manufacturing kiln temperature.
-
The method further comprises determining, by the processing unit, one or more boundary ranges for the one or more operational parameters. The one or more boundary ranges are determined based on at least one value of at least one parameter which is captured in real-time from the one or more sensors. The at least one value of the at least one parameter is received from the one or more sensors in real time from the cement manufacturing plant. The one or more boundary ranges are indicative of a range of the one or more operational parameters which result in a specific set of values for the plurality of kiln stability indicators, for the at least one value of the at least one parameter. In other words, the one or more boundary ranges are indictive of the range of the one or more operational parameters, for which the cement manufacturing kiln remains stable. The one or more boundary ranges for the one or more operational parameters is directly dependent on the value of the at least one parameter of the plurality of operational parameters. In other words, the one or more boundary ranges are adjusted dynamically by the processing unit based on the value of the at least one parameter of the plurality of operational parameters.
-
In one example, the processing unit is configured to determine the one or more boundary ranges for the one or more operational parameters by application of a linear regression algorithm on the correlation matrix. In another example, the processing unit is configured to determine the one or more boundary ranges based on historical data of the plurality of operational parameters and the plurality of kiln stability indicators. The one or more boundary ranges is determined based on one or more operational benchmarks to establish safe operational limits for the cement manufacturing kiln. The one or more boundary ranges have an upper boundary and a lower boundary limit for the one or more operational parameters. In other words, the one or more boundary ranges comprise a maximum value and a minimum value allowable for the one or more operational parameters for the at least one value of the at least one parameter. For instance, if the correlation matrix shows that a cement manufacturing kiln inlet O2 level below 2% typically leads to poor combustion efficiency, the processing unit is configured to set a lower boundary value of 2% for O2 . In one example, the one or more boundary ranges are determined based on one or more user assertions which are received from the user. The one or more user assertions are user generated textual descriptions of limits allowable for each operational parameter of the plurality of operational parameters. The one or more user assertions are analyzed by the processing unit by application of a natural language processing algorithms on the one or more user assertions.
-
The method further comprises determining whether a value of the one or more operational parameters is outside of the one or more boundary ranges associated with the one or more operational parameters. In one example, one or more values of the one or more operational parameters is below the minimum value indicated in the one or more boundary ranges. In another example, one or more values of the one or more operational parameters is greater than the maximum value indicated in the one or more boundary ranges.
-
The method further comprises generating, by the processing unit, alerts to kiln operators when a value of the one or more operational parameters is outside of the one or more boundary ranges. The method further comprises generating, one or more recommendations to the cement manufacturing kiln operators by application of a trained large language model on the one or more operational parameters. The LLMs used include a long term short term memory networks, a gated recurrent unit, a transformer model, a convolutional neural network, and autoencoders. The LLM is trained by the processing unit based on a training dataset comprising historic values of the plurality of operational parameters, the plurality of kiln stability indicators, a plurality of user defined labels, and a plurality of predefined user recommendations generated by one or more users.
-
The method further comprises predicting, by the processing unit, the fuel consumption of the cement manufacturing kiln for a time period in which the value of the one or more operational parameters are outside of the one or more boundary range. In one example, the processing unit is configured to predict the fuel consumption in the time period by analysis of the correlation matrix and the one or more values of the one or more operational parameters. In one example, the fuel consumption is predicted by application of a simulation algorithm on the one or more values of the one or more operational parameters and the correlation matrix. The simulation algorithm may be a monte carlo simulation algorithm, a finite element analysis algorithm, and a system dynamics modelling based algorithm. The processing unit is configured to predict the fuel consumption for the future time period in a case the value of the one or more operational parameters are outside of the one or more boundary ranges.
-
The method further comprises generating a graphical representation which is indicative of a variation of fuel consumption with respect to variations in the one or more operational parameters. In one example, the graphical representation is a three dimensional graphical representation. The processing unit is configured to generate the three dimensional graphical representation by application of a graphical algorithms such as a 3D Scatter Plot Algorithm, a surface Plot Algorithm and a Volume Rendering Algorithm. The method further comprises displaying the graphical representation to one or more users.
-
The method further comprises generating a control signal based on the determination that the one or more operational parameters is outside of the one or more boundary ranges. The control signal is configured to cause the cement manufacturing kiln to optimize the one or more operational parameters and thereby optimize the fuel consumption of the cement manufacturing kiln.
-
The method further comprises controlling, by the processing unit, the cement manufacturing kiln to optimize the one or more operational parameters such that the one or more operational parameters are within the determined one or more boundary ranges. The processing unit is configured to control the cement manufacturing kiln by application of the generated control signal on the cement manufacturing kiln. For example, in a case where a parameter is determined to deviate from the one or more boundary ranges, the processing unit is configured to initiate one or more corrective actions. The one or more corrective actions are executed based on a series of automated controls which is configured to adjust the one or more operational parameters of the cement manufacturing kiln. For example, if a temperature in the cement manufacturing kiln exceeds its upper boundary, the processing unit is configured to adjust a rate of the cooling fans or alter the feed rate of raw materials to reduce the temperature. Similarly, if a chemical composition of the exhaust gases indicates incomplete combustion, the processing unit is configured to increase an oxygen supply to optimize combustion efficiency.
-
In one example, the processing unit is configured to apply the generated control signal onto a plurality of control systems to control the cement manufacturing kiln and thereby optimize the one or more operational parameters. The plurality of control systems comprise automated feedback loop based systems, predictive control systems, and adaptive control systems. In one example, the Automated Feedback Loop based systems are software-driven control systems that continuously monitor the one or more operational parameters, such as temperature or pressure measurements, and adjust the one or more operational parameters by use of a proportional integral and derivative controller (PID controller). The predictive control systems refer to systems that utilize modeling and simulation software to forecast future values of the one or more operational parameters to preemptively mitigate potential deviations of the one or more operational parameters. The adaptive control systems are complex control frameworks that modify an operation in response to variations in the one or more operational parameters.
-
The method further comprises predicting an amount of combustion based on the one or more operational parameters by application of the simulation algorithm on the correlation matrix. The method further comprises generating the control signal based on the determination that the one or more operational parameters, is outside of the one or more boundary ranges. The control signal is further configured to cause the cement manufacturing kiln to optimize the one or more operational parameters and thereby optimize the amount of combustion of the fuel in the cement manufacturing kiln. The method further comprises displaying the determined amount of combustion in a user interface.
-
The method further comprises predicting an amount of emissions created by the cement manufacturing kiln based on the one or more operational parameters by application of the simulation algorithm on the correlation matrix. The method further comprises generating the control signal based on the determination that the one or more operational parameters, is outside of the one or more boundary ranges. The control signal is further configured to cause the cement manufacturing kiln to optimize the one or more operational parameters and thereby optimize the amount of emission of the cement manufacturing kiln. The method further comprises displaying the determined amount of emission in the user interface.
-
The object of the present invention is further achieved by a system designed to optimize fuel consumption for a cement manufacturing kiln. This system includes a sensor array that measures a variety of operational parameters crucial for maintaining kiln stability. A processor is integral to the system, equipped to determine boundary ranges for these parameters based on historical data values collected during a first time period. It can also detect when a parameter's value falls outside these ranges and predict future fuel consumption for periods when the parameters deviate from established norms.
-
Additionally, the system features a display configured to present a three-dimensional graph that illustrates how fuel consumption varies in relation to the operational parameters. There is also a control unit designed to adjust the operation of the cement manufacturing kiln to ensure these parameters remain within the boundary ranges, optimizing overall performance.
-
Expanding on the system's capabilities, the processor is further configured to calculate the duration of a second time period based on how long the parameters stay outside the boundary ranges. This duration is then displayed alongside the three-dimensional graph, providing a comprehensive view of the system's performance over time.
-
Moreover, the processor is capable of calculating and displaying the amount of combustion and emissions based on these parameters, and it adjusts the kiln's air-to-fuel ratio to enhance combustion efficiency using real-time emissions data.
-
The system also comprises data storage for retaining historical data on the operational parameters and a user interface that allows a user to input optimal values for at least one parameter. Utilizing a correlation matrix derived from the historical data and user inputs, the processor determines the boundary ranges for the parameters. It also generates alerts and provides recommendations for adjustments when the parameters exceed these boundary ranges, ensuring efficient and environmentally friendly kiln operations.
-
Advantageously, determination of the fuel consumption in the future time period and controlling the cement manufacturing kiln, enhances an operational efficiency and cost-effectiveness of the cement manufacturing kiln. The processing unit is enabled to foresee deviations and potential impacts of such deviations during future operations. Thus, the prediction of the fuel consumption enables the processing unit to do anticipatory adjustments to the cement manufacturing kiln, rather than reactive ones. Thus, the cement manufacturing kiln operates within the most efficient parameters even when facing variable conditions.
-
Advantageously, the processing unit is configured to do continuous optimization of the cement manufacturing kiln's fuel efficiency. Furthermore, the processing unit determines how parameters like temperature, feed rate, and gas concentrations will affect fuel consumption. Thus, the processing unit minimizes fuel usage while maintaining a stability of the cement manufacturing kiln. Thus the processing unit reduces energy costs, lowers environmental impact and also improves a return of investment of the cement manufacturing kiln.
-
The object of the invention is further achieved through a computer program product for optimizing fuel consumption in a cement manufacturing kiln. The computer program product comprises a non-transitory computer-readable medium having program instructions stored thereon. When executed by a processor, the program instructions cause the processor to perform a method as claimed in claims 1 to 11.
-
The present invention is further described hereinafter with reference to illustrated embodiments shown in the accompanying drawings, in which the features of the individual objects claimed or described can readily be combined with one another. Hereinafter, the invention is illustrated and explained in more detail by way of example with reference to the figures. The features shown in the figures can be combined by a person skilled in the art to form new embodiments without departing from the scope of the invention. Elements of the same type are given the same reference character. It is shown in:
- FIG 1
- is a block diagram of a system for automatically optimizing fuel consumption in a cement manufacturing kiln, according to an embodiment of the present invention;
- FIG 2
- is a block diagram of an engineering system, such as those shown in FIG. 1, in which an embodiment of the present invention can be implemented;
- FIG 3
- is a process flowchart illustrating an exemplary method of automatically optimizing fuel consumption in a cement manufacturing kiln, according to an embodiment of the present invention; and
- FIG 4A-B
- is a graphical representation of a one or more values of a plurality of operational parameters and a plurality of kiln stability indicators associated with a cement manufacturing kiln in accordance with an embodiment of the present invention.
-
Various embodiments are described with reference to the drawings, wherein like reference numerals are used to refer the drawings, wherein like reference numerals are used to refer to like elements throughout. In the following description, for the purpose of explanation, numerous specific details are set forth in order to provide thorough understanding of one or more embodiments. It may be evident that such embodiments may be practiced without these specific details.
-
FIG 1 is a block diagram of a system 100 for automatically optimizing fuel consumption in a cement manufacturing kiln 102, according to an embodiment of the present invention. In FIG 1, the system 100 includes one or more sensors 104, a control system 106, and a human machine interface 108. The control system comprises a processing unit 202 such as a programmable logic controller. The processing unit 202 comprises an automation module 112 which is configured to automatically optimize the fuel consumption in the cement manufacturing kiln 102.
-
The cement manufacturing kiln 102 is a large, cylindrical vessel which is used during a pyroprocessing stage of cement production. Inside the cement manufacturing kiln 102, a plurality of raw materials are pyroprocessed to generate clinker. Examples of the plurality of raw materials include limestone, clay, or shale. The pyroprocessing happens at very high temperatures and is thus fuel-intensive. Examples of fuel consumed includes coal, natural gas, and oil. The fuel consumed by the cement manufacturing kiln is expensive, and thus by optimizing fuel consumption, return of interest can be optimized. Furthermore, a temperature of the cement manufacturing kiln is dependent on the fuel consumption of the cement manufacturing kiln. A stability of the cement manufacturing kiln is dependent on the temperature. Thus, by optimizing the fuel consumption, a stability of the cement manufacturing kiln can be maintained, and furthermore, a return of investment of the cement manufacturing kiln can be optimized.
-
The outputs of the cement manufacturing kiln 102 are primarily the clinker and waste gases. A quality and one or more properties of clinker has a significant impact on a final strength and a quality of cement produced by the cement manufacturing plant. Since the quality of clinker is proportional to a stability of the cement manufacturing kiln, optimizing the fuel consumption becomes of paramount importance.
-
The one or more sensors 104 are configured to capture a plurality of operational parameters from the cement manufacturing kiln 102. Examples of the one or more sensors 104 includes but is not limited to temperature sensors that monitor the cement manufacturing kiln's heat to prevent overheating, vibration sensors on grinding equipment to detect imbalances or potential failures, and gas analyzers that measure emissions and adjust operations to meet environmental regulations.
-
The control system 106 is configured to coordinate and optimize one or more stages of cement production. The control system 106 is configured to process inputs from the one or more sensors 104 to manage activities such as precise mixing of raw materials, control of kiln temperature for clinker production, and timing of cooling processes to ensure quality of the final cement.
-
The human machine interface 108 is configured to enable operators to interact directly with the control system 106. Operators can use HMI panels to monitor process variables like kiln temperature and motor speeds, adjust operational parameters, and troubleshoot issues from a centralized location. For instance, the HMI is configured to display diagnostics from the cement manufacturing kiln 102, to allow operators to make immediate adjustments or shutdowns to prevent damage or inefficiencies in the cement manufacturing kiln.
-
The processing unit 202, is typically a Programmable Logic Controller (PLC), which is crucial for executing complex control algorithms. In cement production, the PLC can automate repetitive tasks such as the sequential operation of valves for loading and unloading materials or the regulation of the grinding and baking processes. The processing unit 202 is further configured to analyze the plurality of operational parameters and control the cement manufacturing kiln 102 based on the analysis.
-
The automation Module 112 is pivotal for enhancing fuel efficiency, which is crucial for both economic and environmental aspects of production. The automation module 112 incorporates software that, when executed by the processing unit 202, optimizes fuel consumption in the cement manufacturing kiln 102. For instance, the automation module 112 is configured to continuously analyze data from the one or more sensors 104 to monitor temperatures, pressures, and flow rates of gases and materials in the cement manufacturing kiln. By processing the data, the automation module 112 adjusts a fuel feed rate and an air supply to maintain optimal combustion conditions, thereby reducing waste and lowering emissions
-
When executed by the processing unit 202, the automation module 112 causes the processing unit 202 to receive a plurality of operational parameters associated with the cement manufacturing kiln 102. The plurality of operational parameters may be captured by the one or more sensors 104 in the cement manufacturing kiln 102. The plurality of operational parameters comprises kiln feed rate, chain zone temperature, C3S (quality parameter), kiln inlet O2, and kiln inlet CO temperature.
-
In one example, the one or more sensors 104 comprises flow sensors, thermocouplers, infrared sensors, gas analyzers, and others. In one example, flow sensors is configured to determine the cement manufacturing kiln feed rate by measuring the volume of raw materials entering the cement manufacturing kiln. Thermocouples or infrared sensors are configured to monitor temperatures, such as the chain zone temperature and the temperatures at the cement manufacturing kiln inlet. The gas analyzers are configured to measure concentration of gases like oxygen and carbon monoxide at the cement manufacturing kiln inlet. The one or more sensors 104 are configured to transmit the plurality of operational parameters to the processing unit 202 via wired connections such as Ethernet or other communication cables for stable, continuous data transmission. The one or more sensors 104 may also use wireless systems like Wi-Fi or Bluetooth to transmit the plurality of operational parameters to the processing unit 202. Furthermore, the plurality of operational parameters are also transmitted via industrial communication protocols like Modbus or Fieldbus, designed to handle large volumes of data and ensure reliable transmission even in harsh industrial environments.
-
The automation module 112 further causes the processing unit 202 to determine, from the plurality of operational parameters, one or more operational parameters which affects a cement manufacturing kiln stability of the cement manufacturing plant. In one example, the processing unit 202 is configured to determine the one or more parameter based on a user input received at a user interface. In another example, the processing unit 202 is configured to determine the one or more operational parameters by application of a machine learning algorithm on the plurality of operational parameters. In one example, the machine learning algorithm is configured to correlate specific changes in the plurality of operational parameters with variations a cement manufacturing kiln performance. In one example, the machine learning algorithm is configured to analyze historical data to determine a plurality of interrelationship between the plurality of operational parameters and a plurality of kiln stability indicators. The plurality of kiln stability indicators indicate a cement manufacturing kiln stability of the cement manufacturing kiln. Examples of the plurality of key stability indicators include a cement manufacturing kiln shell temperature, an axial thrust of the cement manufacturing kiln, a rotational speed of the cement manufacturing kiln, and a torque and a power consumption of the cement manufacturing kiln.
-
The automation module 112 further causes the processing unit 202 to receive the historical data associated with the plurality of operational parameters and the plurality of kiln stability indicators. The automation module 112 further causes the processing unit 202 to analyze the historical data associated with the plurality of operational parameters and the plurality of kiln stability indicators to generate a correlation matrix. A correlation matrix is a statistical tool which is configured to determine a degree and a direction of correlation between the plurality of operational parameters and the plurality of kiln stability indicators.
-
The automation module 112 further causes the processing unit 202 to generate the correlation matrix by application of a statistical algorithm on the plurality of operational parameters and the plurality of kiln stability indicators. The correlation matrix comprises information associated with a first set of operational parameters which have a strong positive correlation with the plurality of kiln stability indicators. The correlation matrix further comprises information associated a second set of operational parameters which has a strong negative correlation with the plurality of kiln stability indicators. In one example, the correlation between kiln feed rate and kiln inlet CO temperature has a strong positive correlation, indicating that changes in the feed rate significantly impact the CO temperature. Examples of the statistical algorithms include Pearson correlation coefficient-based algorithm, Spearman's rank correlation coefficient-based algorithm, Kendall's Tau-based algorithm, Polychoric correlation-based algorithm, and Polyserial correlation-based algorithm. In yet another example, the correlation matrix is generated by application of a supervised training algorithm on the historical data comprising the plurality of operational parameters and the plurality of kiln stability indicators.
-
The automation module 112 further causes the processing unit 202 to receive a user input to select at least one parameter from one of the plurality of operational parameters and the plurality of kiln stability indicators. In another example, the automation module 112 further causes the processing unit 202 to determine at least one parameter from the plurality of operational parameters which has maximum impact on the plurality of kiln stability indicators. The processing unit is configured to apply a multilinear regression algorithm on the correlation matrix to determine the at least one parameter whose variation has maximum impact on values of the plurality of kiln stability indicators. Examples of the multilinear regression algorithms include Ordinary Least Squares (OLS)-based algorithm, Ridge Regression-based algorithm, Lasso Regression-based algorithm, Elastic Net Regression-based algorithm, and Principal Component Regression (PCR)-based algorithm. Thus, the at least one parameter has a highest correlation impact with the plurality of kiln stability indicators. In one example, the at least one parameter is determined to be a cement manufacturing kiln temperature.
-
The automation module 112 further causes the processing unit 202 to determine one or more boundary ranges for the one or more operational parameters. The one or more boundary ranges are determined based on at least one value of at least one parameter which is captured in real-time from the one or more sensors. The at least one value of the at least one parameter is received from the one or more sensors in real time from the cement manufacturing plant. The one or more boundary ranges are indicative of a range of the one or more operational parameters which result in a specific set of values for the plurality of kiln stability indicators, for the at least one value of the at least one parameter. In other words, the one or more boundary ranges are indictive of the range of the one or more operational parameters, for which the cement manufacturing kiln remains stable.
-
The processing unit 202 is configured to determine the one or more boundary ranges for the one or more operational parameters by application of a linear regression algorithm on the correlation matrix. In one example, the processing unit 202 is configured to determine the one or more boundary ranges based on historical data of the plurality of operational parameters and the plurality of kiln stability indicators. and operational benchmarks to establish safe operational limits. For instance, if the data shows that a cement manufacturing kiln inlet O2 level below 2% typically leads to poor combustion efficiency, the processing unit 202 would set this as a lower boundary value. The one or more boundary ranges have an upper boundary and a lower boundary limit for the one or more operational parameters. In other words, the one or more boundary ranges comprise a maximum value and a minimum value allowable for the one or more operational parameters for the at least one value of the at least one parameter.
-
The automation module 112 further causes the processing unit 202 to determine that a value of the one or more operational parameters is outside of the one or more boundary ranges associated with the one or more operational parameters. In one example, one or more values of the one or more operational parameters is below the minimum value indicated in the one or more boundary ranges. In another example, one or more values of the one or more operational parameters is greater than the maximum value indicated in the one or more boundary ranges.
-
The automation module 112 further causes the processing unit 202 to generate alerts to kiln operators when the one or more operational parameters is outside of the one or more boundary ranges. The automation module 112 further causes the processing unit 202 to generate one or more recommendations to the cement manufacturing kiln operators by application of a trained large language model on the one or more operational parameters. The LLMs used include a long term short term memory networks, a gated recurrent unit, a transformer model, a convolutional neural network, and autoencoders. The LLM is trained by the processing unit 202 based on a training dataset comprising historic values of the plurality of operational parameters, the plurality of kiln stability indicators, a plurality of user defined labels, and a plurality of predefined user recommendations generated by one or more users.
-
The automation module 112 further causes the processing unit 202 to predict the fuel consumption of the cement manufacturing kiln for a future time period in which the value of the one or more operational parameters are outside of the one or more boundary range. The processing unit 202 is configured to predict the fuel consumption in the future time period by analysis of the correlation matrix and the one or more values of the one or more operational parameters. In one example, the fuel consumption is predicted by application of a simulation algorithm on the one or more values of the one or more operational parameters and the correlation matrix. The simulation algorithm may be a monte carlo simulation algorithm, a finite element analysis algorithm, and a system dynamics modelling based algorithm. The processing unit 202 is configured to predict the fuel consumption for the future time period in a case the value of the one or more operational parameters are outside of the one or more boundary ranges.
-
The automation module 112 further causes the processing unit 202 to generating a three-dimensional graphical representation which is indicative of a variation of fuel consumption with respect to variations in the one or more operational parameters. The processing unit 202 is configured to generate the three dimensional graphical representation by application of a graphical algorithms such as a 3D Scatter Plot Algorithm, a surface Plot Algorithm and a Volume Rendering Algorithm.
-
The automation module 112 further causes the processing unit 202 to control the cement manufacturing kiln 102 to optimize the one or more operational parameters such that the one or more operational parameters are within the determined one or more boundary ranges. For example, in a case where a parameter is determined to deviate from the one or more boundary ranges, the processing unit 202 is configured to initiate one or more corrective actions. The one or more corrective actions are executed based on a series of automated controls which is configured to adjust the one or more operational parameters of the cement manufacturing kiln. For example, if a temperature in the cement manufacturing kiln exceeds its upper boundary, the processing unit 202 is configured to adjust a rate of the cooling fans or alter the feed rate of raw materials to reduce the temperature. Similarly, if a chemical composition of the exhaust gases indicates incomplete combustion, the processing unit 202 is configured to increase an oxygen supply to optimize combustion efficiency.
-
In one example, the processing unit 202 is configured to use a plurality of control systems to control the one or more operational parameters. The plurality of control systems comprise automated feedback loop based systems, predictive control systems, and adaptive control systems. In one example, the Automated Feedback Loop based systems are software-driven control systems that continuously monitor the one or more operational parameters, such as temperature or pressure measurements, and adjust the one or more operational parameters by use of a proportional integral and derivative controller (PID controller). The predictive control systems refer to systems that utilize modeling and simulation software to forecast future values of the one or more operational parameters to preemptively mitigate potential deviations of the one or more operational parameters. The adaptive control systems are complex control frameworks that modify an operation in response to variations in the one or more operational parameters.
-
Advantageously, determination of the fuel consumption in the future time period and controlling the cement manufacturing kiln 102, enhances an operational efficiency and cost-effectiveness of the cement manufacturing kiln 102. The processing unit 202 is enabled to foresee deviations and potential impacts of such deviations during future operations. Thus, the prediction of the fuel consumption enables the processing unit 202 to do anticipatory adjustments to the cement manufacturing kiln, rather than reactive ones. Thus, the cement manufacturing kiln 102 operates within the most efficient parameters even when facing variable conditions.
-
Advantageously, the processing unit 202 is configured to do continuous optimization of the cement manufacturing kiln 102 fuel efficiency. Furthermore, the processing unit 202 determines how parameters like temperature, feed rate, and gas concentrations will affect fuel consumption. Thus, the processing unit 202 minimizes fuel usage while maintaining a stability of the cement manufacturing kiln. Thus the processing unit 202 reduces energy costs, lowers environmental impact and also improves a return of investment of the cement manufacturing kiln.
-
FIG 2 is a block diagram of a control system 106, such as those shown in FIG 1, in which an embodiment of the present invention can be implemented. In FIG 2, the control system 106 includes a processor(s) 202, an accessible memory 204, a storage unit 206, a communication interface 208, an input-output unit 210, a network interface 212 and a bus 214.
-
The processor(s) 202, as used herein, means any type of computational circuit, such as, but not limited to, a microprocessor unit, microcontroller, complex instruction set computing microprocessor unit, reduced instruction set computing microprocessor unit, very long instruction word microprocessor unit, explicitly parallel instruction computing microprocessor unit, graphics processing unit, digital signal processing unit, or any other type of processing circuit. The processor(s) 202 may also include embedded controllers, such as generic or programmable logic devices or arrays, application specific integrated circuits, single-chip computers, and the like.
-
The memory 204 may be non-transitory volatile memory and non-volatile memory. The memory 204 may be coupled for communication with the processor(s) 202, such as being a computer-readable storage medium. The processor(s) 202 may execute machine-readable instructions and/or source code stored in the memory 204. A variety of machine-readable instructions may be stored in and accessed from the memory 204. The memory 204 may include any suitable elements for storing data and machine-readable instructions, such as read only memory, random access memory, erasable programmable read only memory, electrically erasable programmable read only memory, a hard drive, a removable media drive for handling compact disks, digital video disks, diskettes, magnetic tape cartridges, memory cards, and the like. In the present embodiment, the memory 204 includes an integrated development environment (IDE) 216. The IDE 216 includes an automation module 112 stored in the form of machine-readable instructions on any of the above-mentioned storage media and may be in communication with and executed by the processor(s) 202.
-
The storage unit 206 may be a non-transitory storage medium configured for storing a database (such as database 118) which comprises server version of the plurality of programming blocks associated with the set of industrial domains.
-
The communication interface 208 is configured for establishing communication sessions between the one or more client devices 120A-N and the engineering system 102. The communication interface 208 allows one or more control applications running on the HMI 108 to import/export project files into the control system 106. In an embodiment, the communication interface 208 interacts with the interface at the HMI 108 for allowing one or more plant operators to control the cement manufacturing kiln 102.
-
The input-output unit 210 may include input devices a keypad, touch-sensitive display, camera (such as a camera receiving gesture-based inputs), etc. capable of receiving one or more input signals, such as user commands to control the plurality of operational parameters. Also, the input-output unit 210 may be a display unit for displaying a graphical user interface which visualizes the plurality of operational parameters. The bus 214 acts as interconnect between the processor 202, the memory 204, and the input-output unit 210.
-
The network interface 212 may be configured to handle network connectivity, bandwidth and network traffic between the control system 106, the HMI 108, the one or more sensors 104 and the cement manufacturing kiln 102.
-
Those of ordinary skilled in the art will appreciate that the hardware depicted in FIG 2 may vary for particular implementations. For example, other peripheral devices such as an optical disk drive and the like, Local Area Network (LAN), Wide Area Network (WAN), Wireless (e.g., Wi-Fi) adapter, graphics adapter, disk controller, input/output (I/O) adapter also may be used in addition or in place of the hardware depicted. The depicted example is provided for the purpose of explanation only and is not meant to imply architectural limitations with respect to the present disclosure.
-
Those skilled in the art will recognize that, for simplicity and clarity, the full structure and operation of all data processing systems suitable for use with the present disclosure is not being depicted or described herein. Instead, only so much of an control system 106 as is unique to the present disclosure or necessary for an understanding of the present disclosure is depicted and described. The remainder of the construction and operation of the control system 106 may conform to any of the various current implementation and practices known in the art.
-
Those of ordinary skilled in the art will appreciate that the hardware depicted in FIG 2 may vary for particular implementations. For example, other peripheral devices such as an optical disk drive and the like, Local Area Network (LAN), Wide Area Network (WAN), Wireless (e.g., Wi-Fi) adapter, graphics adapter, disk controller, input/output (I/O) adapter also may be used in addition or in place of the hardware depicted. The depicted example is provided for the purpose of explanation only and is not meant to imply architectural limitations with respect to the present disclosure.
-
Those skilled in the art will recognize that, for simplicity and clarity, the full structure and operation of all data processing systems suitable for use with the present disclosure is not being depicted or described herein. Instead, only so much of the industrial control system 102 as is unique to the present disclosure or necessary for an understanding of the present disclosure is depicted and described. The remainder of the construction and operation of the industrial control system 102 may conform to any of the various current implementation and practices known in the art.
-
FIG 3 is a process flowchart illustrating an exemplary method 300 of automatically optimizing fuel consumption in a cement manufacturing kiln, according to an embodiment of the present invention. Fig. 3 is explained in conjunction with FIG. 1 and 2.
-
The method 300 includes several steps executed by the processing unit 202. At 302, from a plurality of operational parameters, one or more operational parameters which affects a cement manufacturing kiln stability are determined. At step 304, one or more boundary ranges are determined, by the processing unit 202, for the one or more operational parameters. The one or more boundary ranges are determined based on at least one value of at least one parameter of the one or more operational parameters in a first time period. The at least one value is captured by one or more sensors 104 in real-time. At step 306, a value of the one or more operational parameters is determined to be outside of the one or more boundary ranges associated with the one or more operational parameters. At step 308, a fuel consumption of the cement manufacturing kiln during a future time period is predicted by the processing unit 202. At the future time period, the value of the one or more operational parameters are outside of the one or more boundary range. The fuel consumption is predicted by application of a simulation algorithm on the value of the one or more operational parameters. At step 310, a graphical representation indicative of a variation of fuel consumption with the one or more operational parameters is displayed on an HMI 108. At step 312, the cement manufacturing kiln 102 is controlled by the processing unit 202 to optimize the one or more operational parameters such that the one or more operational parameters are within the determined one or more boundary range.
-
FIG 4A-B is a graphical representation of a one or more values of a plurality of operational parameters and a plurality of kiln stability indicators associated with a cement manufacturing kiln in accordance with an embodiment of the present invention. FIG. 4A depicts a two dimensional graph 400A of a temperature parameter of the plurality of operational parameters. FIG. 4B depicts a three dimensional graph 400B of the plurality of operational parameters.
-
The present invention can take a form of a computer program product comprising program modules accessible from computer-usable or computer-readable medium storing program code for use by or in connection with one or more computers, processors, or instruction execution system. For the purpose of this description, a computer-usable or computer-readable medium can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The medium can be electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system (or apparatus or device) or a propagation mediums in and of themselves as signal carriers are not included in the definition of physical computer-readable medium include a semiconductor or solid state memory, magnetic tape, a removable computer diskette, random access memory (RAM), a read only memory (ROM), a rigid magnetic disk and optical disk such as compact disk read-only memory (CD-ROM), compact disk read/write, and DVD. Both processors and program code for implementing each aspect of the technology can be centralized or distributed (or a combination thereof) as known to those skilled in the art.
-
While the present invention has been described in detail with reference to certain embodiments, it should be appreciated that the present invention is not limited to those embodiments. In view of the present disclosure, many modifications and variations would be present themselves, to those skilled in the art without departing from the scope of the various embodiments of the present invention, as described herein. The scope of the present invention is, therefore, indicated by the following claims rather than by the foregoing description. All changes, modifications, and variations coming within the meaning and range of equivalency of the claims are to be considered within their scope. All advantageous embodiments claimed in method claims may also be apply to system/apparatus claims.
a list of reference numerals :
-
- 1. 100 - System for automatically optimizing fuel consumption in a cement manufacturing kiln
- 2. 102 - Cement manufacturing kiln
- 3. 104 - One or more sensors
- 4. 106 - Control system
- 5. 108 - Human-machine interface (HMI)
- 6. 112 - Automation module
- 7. 202 - Processing unit (such as a Programmable Logic Controller, PLC)
- 8. 204 - Memory (non-transitory volatile and non-volatile memory)
- 9. 206 - Storage unit
- 10. 208 - Communication interface
- 11. 210 - Input-output unit
- 12. 212 - Network interface
- 13. 214 - Bus
- 14. 216 - Integrated Development Environment (IDE)
- 15. 300 - Method of automatically optimizing fuel consumption in a cement manufacturing kiln
- 16. 302 - Determining one or more operational parameters affecting kiln stability
- 17. 304 - Determining one or more boundary ranges for operational parameters
- 18. 306 - Determining if operational parameters are outside boundary ranges
- 19. 308 - Predicting fuel consumption during a future time period
- 20. 310 - Displaying graphical representation of fuel consumption variation
- 21. 312 - Controlling the kiln to optimize operational parameters
- 22. 400A - Two-dimensional graph of a temperature parameter
- 23. 400B - Three-dimensional graph of operational parameters