e-Komoditi Indonesia to Boost Palm Oil Mills Automation Using AI and IoT
e-Komoditi Indonesia to Boost Palm Oil Mills Automation Using AI and IoT
Palm oil mill
HomeNewsYou are here
e-Komoditi Indonesia to Boost Palm Oil Mills Automation Using AI and IoT

21/07/2021 371 Readers

Today's business world is changing with the adoption of IoT and AI in order to modernize industrial aspects, making it more productive and efficient, while increasing business growth and value.

Several businesses have already adopted IoT (Internet of Things) and AI (Artificial Intelligence) as part of their processes and products. The convergence of IoT and AI can redefine the way that industries, businesses, and economies function.

AI-enabled IoT creates intelligent machines that simulate smart behavior and supports data-driven decision-making with minimal or no human interference.

Combining these two technology streams benefit and modernize businesses. Internet of Things deals with devices interacting using the internet, while Artificial Intelligence makes the devices learn from their data and experience.

In the case of palm oil mills, they must adapt and equip themselves with the latest technologies and innovations, specifically for process control based on automation.

Boosting Operational Efficiency

Internet of Things (IoT) is about sensors implanted into machines, which offer streams of data through internet connectivity. While Artificial Intelligence (AI) provides the power to unlock responses, offering both creativity and context to drive smart actions. Since the data delivered from the sensor can be analyzed with AI, businesses can make informed decisions.

Returning to palm oil mills example, FFB (Fresh Fruit Bunches) grading is normally performed manually by competent and experienced graders who collect samples and evaluate the FFB based on visual observation.

FFB grading is considered the front-line assessment in any palm oil mill to measure raw material ripeness and freshness. The quality of the raw material will determine the yield of oil produced at the end of the process, often referred as OER (Oil Extraction Rate) and Free Fatty Acid (FFA).

However, the sample size is only about 25-30% of the whole loads which means only 50 to 100 bunches are assessed per load. In other words, in terms of quantity, there are more ungraded FFB than there are graded ones for each load.

In addition, most of the samples are picked from the top part of each load. If the quality of the FFB at the bottom portion of the load is significantly different from the top, it means that the grading quality of the load may be inaccurate and can lead to misrepresentation towards the calculated OER of the day.

By utilizing a multi-spectral camera for image capture and a suitable machine learning algorithm, palm oil mills can teach the machine to identify the quality of each FFB which can then be sorted according to their quality. This would be beneficial during the sterilization process where the specific process can be chosen for the sterilization of FFB.

Palm oil mills are using mainly triple-peak sterilization. However, if the FFB can be segregated according to their quality, the sterilization process can be further optimized to operate at an energy-efficient setting, hence reducing the need for triple-peak sterilization operation.

Advance analysis such as this has the potential for better accuracy and can assess 100% of the FFB inside a moving scraper conveyor. By implementing this, manpower can be reduced, and fewer disputes regarding quality and quantity will take place between palm oil estates and mills.

Better Risks Management

Automation can help substantially reduce human error problems in palm oil mill operations which can improve the reliability of the current manual sampling process which because it is not representative can result in incorrect process management decisions.

Automation technology can be used in CPO storage tanks so that mill operators can know the volume of CPO inside accurately and can also be used in temperature control to prevent the oil from freezing or overheating. In addition, the automation system can help measure the water and oil levels in the CST (Clarifier Settling Tank).

Within the boiling station, the sterilizer used is generally a horizontal platform that can accommodate 10 lorries per unit or the equivalent of 25-27 tons of FFB. In the boiling process, FFB is heated with steam at a temperature of approximately 135 degrees Celsius and a pressure of 2.0-2.8 kg/cm2 for 80-90 minutes.

Boiling aims to stop the development of FFA releasing the loose fruit from the bunches, releasing the core adhesion to the palm shell, and reducing the water content.

For BPV (Back Pressure Vessel) stations that use conventional systems occasionally, there is a shortage of steam which means direct injection from the boiler is required. With a manual system, the operator keeps the BPV open even though the input from this boiler can be as high as 20 bars, while the BPV capacity is 5 bars. If not monitored correctly, it can result in an explosion at the BPV station.

Usually, the first to explode is a safety valve or valve that is no longer strong enough to withstand the pressure. In contrast to IoT pressure sensor automation where supervision can be carried out with a control panel so as to reduce risks that endanger the safety of workers.

In simple terms, the monitoring automation of palm oil mills will improve process efficiency, increasing yields, increasing productivity, reducing production costs, improving product quality, and increasing safety standards to meet industrial safety laws and regulations.

The use of an overall automation system in the palm oil mills will provide accurate and actual information on process and production reports. Automation prevents losses that occur in terms of energy, human resources, and production yields.

Keywords: IoT, AI, Internet of Things, Artificial Intelligence

Several businesses have already adopted IoT (Internet of Things) and AI (Artificial Intelligence) as part of their processes and products. The convergence of IoT and AI can redefine the way that industries, businesses, and economies function.

AI-enabled IoT creates intelligent machines that simulate smart behavior and supports data-driven decision-making with minimal or no human interference.

Combining these two technology streams benefit and modernize businesses. Internet of Things deals with devices interacting using the internet, while Artificial Intelligence makes the devices learn from their data and experience.

In the case of palm oil mills, they must adapt and equip themselves with the latest technologies and innovations, specifically for process control based on automation.

Boosting Operational Efficiency

Internet of Things (IoT) is about sensors implanted into machines, which offer streams of data through internet connectivity. While Artificial Intelligence (AI) provides the power to unlock responses, offering both creativity and context to drive smart actions. Since the data delivered from the sensor can be analyzed with AI, businesses can make informed decisions.

Returning to palm oil mills example, FFB (Fresh Fruit Bunches) grading is normally performed manually by competent and experienced graders who collect samples and evaluate the FFB based on visual observation.

FFB grading is considered the front-line assessment in any palm oil mill to measure raw material ripeness and freshness. The quality of the raw material will determine the yield of oil produced at the end of the process, often referred as OER (Oil Extraction Rate) and Free Fatty Acid (FFA).

However, the sample size is only about 25-30% of the whole loads which means only 50 to 100 bunches are assessed per load. In other words, in terms of quantity, there are more ungraded FFB than there are graded ones for each load.

In addition, most of the samples are picked from the top part of each load. If the quality of the FFB at the bottom portion of the load is significantly different from the top, it means that the grading quality of the load may be inaccurate and can lead to misrepresentation towards the calculated OER of the day.

By utilizing a multi-spectral camera for image capture and a suitable machine learning algorithm, palm oil mills can teach the machine to identify the quality of each FFB which can then be sorted according to their quality. This would be beneficial during the sterilization process where the specific process can be chosen for the sterilization of FFB.

Palm oil mills are using mainly triple-peak sterilization. However, if the FFB can be segregated according to their quality, the sterilization process can be further optimized to operate at an energy-efficient setting, hence reducing the need for triple-peak sterilization operation.

Advance analysis such as this has the potential for better accuracy and can assess 100% of the FFB inside a moving scraper conveyor. By implementing this, manpower can be reduced, and fewer disputes regarding quality and quantity will take place between palm oil estates and mills.

Better Risks Management

Automation can help substantially reduce human error problems in palm oil mill operations which can improve the reliability of the current manual sampling process which because it is not representative can result in incorrect process management decisions.

Automation technology can be used in CPO storage tanks so that mill operators can know the volume of CPO inside accurately and can also be used in temperature control to prevent the oil from freezing or overheating. In addition, the automation system can help measure the water and oil levels in the CST (Clarifier Settling Tank).

Within the boiling station, the sterilizer used is generally a horizontal platform that can accommodate 10 lorries per unit or the equivalent of 25-27 tons of FFB. In the boiling process, FFB is heated with steam at a temperature of approximately 135 degrees Celsius and a pressure of 2.0-2.8 kg/cm2 for 80-90 minutes.

Boiling aims to stop the development of FFA releasing the loose fruit from the bunches, releasing the core adhesion to the palm shell, and reducing the water content.

For BPV (Back Pressure Vessel) stations that use conventional systems occasionally, there is a shortage of steam which means direct injection from the boiler is required. With a manual system, the operator keeps the BPV open even though the input from this boiler can be as high as 20 bars, while the BPV capacity is 5 bars. If not monitored correctly, it can result in an explosion at the BPV station.

Usually, the first to explode is a safety valve or valve that is no longer strong enough to withstand the pressure. In contrast to IoT pressure sensor automation where supervision can be carried out with a control panel so as to reduce risks that endanger the safety of workers.

In simple terms, the monitoring automation of palm oil mills will improve process efficiency, increasing yields, increasing productivity, reducing production costs, improving product quality, and increasing safety standards to meet industrial safety laws and regulations.

The use of an overall automation system in the palm oil mills will provide accurate and actual information on process and production reports. Automation prevents losses that occur in terms of energy, human resources, and production yields.

Keywords: IoT, AI, Internet of Things, Artificial Intelligence

Editor: Joko Yuwono

Your Reliable Partner for Software Development and Solutions

www.ekomoditi.idwww.ekomoditi.id