Press "Enter" to skip to content

Performance Monitoring of Farm Equipment with Digital Twins and Improving Agricultural Productivity

Article Written By Karthik Trichur Sundaram

About Karthik Trichur Sundaram:

Karthik Sundaram

Karthik Sundaram is an expert in SAP solutions and has been working with SAP since 1997. Karthik has implemented many global SAP S/4 HANA transformation projects working with SAP America as a Platinum Architect. Karthik has multiple SAP certifications and has executed successful projects in North America, Australia, Asia Pacific, the UK, and the Middle East. Karthik has worked in domains like A&D, Metals and Mining, Oil & Gas, Specialty Tools, Chemicals, Semiconductor Manufacturing, Telecom, and Utility. Karthik has published scholarly articles in journals. Karthik got his Bachelor’s in Electrical & Electronics Engineering from the College of Engineering, Trivandrum, India, and his MBA from Boise State University with Summa Cum Laude.


Digital Twins are the virtual or digital representations of actual Physical Objects. The Physical or the real object can be analyzed for its performance measures using the digital twin. Tractors and associated equipment like tillers and backhoes are the leading agricultural equipment that is one of the backbones of the Agricultural and Farming industry. A digital twin can assess the performance of the Tractors and help with the logistics, spare parts planning, and calculating the total maintenance cost. Digital twins can also help monitor the health hazards like Noise pollution and aid in appropriate action. This article will analyze the requirements to build an efficient software system or a Digital Tractor hub and various advantages from Logistics, Performance, Compliance, and Ergonomic perspective. This paper will mainly focus on fuel Powered tractors. However, some of the benefits will apply to Electric Tractors as well.


The Digital Twin concept model contains three main parts:

Physical Asset in Real Space

Digital Asset in Virtual Space

The connections of data and information tie the virtual and real assets together.

The original Digital Twin concept model is not new. This concept is based directly on the works of Dr. Michael Grieves and John Vickers “in the book Virtually Perfect: Driving Innovative and Lean Products through Product Lifecycle Management (pg. 133).”

However, with emerging technologies such as IoT, Big Data, Edge Computing, Machine Learning, and Predictive Analytics, the Digital Twin concept model can provide more significant insights into “Live” real-time or near real-time data enabling manufacturers and asset operators to proactively improve, optimize and transform their businesses.

Farms increasingly must rely on digital technologies such as sensing and monitoring devices, advanced analytics, and smart equipment. Agricultural production is changing fast towards smart farming systems, driven by the rapid pace of technology development like cloud computing, the Internet of Things, big data, machine learning, augmented reality and robotics (Janssen et al., 2017Tzounis et al., 2017Wolfert et al., 2017Kamilaris and Prenafeta-Boldú, 2018Zhai et al., 2020). Smart Farming can be seen as the next phase of Precision Agriculture, in which management tasks not only are based on precise location data but also on context data, situational awareness and event triggers (Balafoutis et al., 2017Wolfert et al., 2017)

Digital twins are virtual models of physical things, products, vehicles, and systems and their data and information flow. Digital twins create a holistic view of products, vehicles, and processes and allow virtual simulations and modifications. The real power of a digital twin is close to the real-time linkage between the physical and digital worlds.

The building elements are sensors, data, integration layer, analytics, and the digital twin, the virtual model itself. Digital twins promise to improve situational awareness and enable better responses to changes, particularly for asset optimization and preventive Maintenance. They can help extend the lifetime of assets and optimize their performance. Digital twins are increasingly and successfully used for product prototyping, reducing development times and costs. The market is immature, and we are still observing relatively simple digital twins like virtual models of vehicles, oil platforms, prototypes, etc. The demand is increasing fast, and digital twin templates, media, and services will increase. Digital twins won’t stop at assets or things but will be expanded to operations, systems, people, business processes, and metadata structures over time. These digital representations will be connected more tightly to their real-world counterparts and infused with more sophisticated artificial intelligence. Obstacles are the heterogeneous and disconnected data sources and the projects’ complexity. Digital twins will start around asset monitoring, optimization, and rapid prototyping. Midterm operation of factories and companies will follow; in the long term, we will see insights around product and service use and business modeling.

Digital Twin enablement with Software Systems.

Physical product data, virtual product data, and connected data that tie physical and virtual product are needed to support product design, manufacturing, and service.(Tao et al., 2018)

Relevant Apps or Applications 

Apps for collaborative processing of Tractor information. Apps can enable Tractor virtual creation, administration of Tractor data, display of Tractor transactional data, and Tractor fleet monitoring.


A cloud portal of standardized content that defines and documents Tractor details will be shared and stored for a consistent definition between business partners.


A secure network to connect multiple business partners for inter and intra-company information exchange and collaboration.

Digital Tractor Hub: To optimize and enable Business Processes throughout the value chain.

Karthik Trichur Sundaram

The Digital Twin system designed for Tractor and Farm equipment monitoring should be hosted on the Cloud for collaboration and data exchange.

Figure 1 – Representative Schema Showing a Typical system Architecture for Monitoring Tractor Performance with a Digital Twin.

Design considerations from the Data Perspective.

Tractor data provided by the Manufacturer or Dealer will be stored in a system Database. Digital Twin creation in the Cloud system should be able to access and replicate the data from the Database, or Database data can be pushed into the Digital Twin system seamlessly.

Manufacturers or Dealers can also provide details like Registration, Insurance, and other legal data associated with the Digital Twin.A (Sørensen et al., 2010) comprehensive Farm Information system can be leveraged for Data analysis

Performance details can be monitored against the Digital Tractor by continuously updating the data for the Digital Twin. Any changes to Performance or Maintenance can also be updated Automatically through collaboration with External Service providers over the Cloud.

The Bill of Materials, Assembly, and Components of the Tractor and associated equipment can be maintained for a Digital Twin. The Bill of material version can also be updated regularly with collaboration from OEM over the Cloud.

All the Documents about Logistics like Repairs, Corrective and Preventive Maintenance, Replacement of Parts, Calibration, etc., along with Purchase orders and Invoices, can be synchronized against a Digital Tractor from the system of records regularly.

Any Specific documents of Ergonomics, Operation Manual along with other Essential details can be stored as an attachment against the digital twin or should be readily available as a URL link.

Design Consideration from Usage Perspective.

Tractor GPS or operator Handheld device should be continuously able to provide the Tractor’s location.

Engine status should be updated with IoT technology, and essential threshold values and breaches can be configured for corrective action. Typical status can include temperature, Oil level, Vibration, Fluid levels, etc.

The Tractor’s speed can also be sent across the Digital Twin to Monitor the performance and Fuel consumption.

Battery Charge Level can also be monitored with feedback from sensors through the IoT Layer. (K. Shaw, J. Fruhlinger)

Tire Pressure can be monitored with a Tire Pressure Monitoring System and should be available for a Digital Tractor.

Tractor Emissions, as applicable, can also be monitored along with Noise levels which can help with safe operation and ergonomics.

Benefits Of Digital Tractor Twin.

The Tractor’s overall performance can be monitored, and corrective and preventive actions can promptly increase the productivity of a Farmer. The various sensors feeding data through IoT Layer can also reduce noise levels and monitor emissions. Sensors like Tire Pressure monitoring can help with Fuel economy. The overall cost of Maintenance and reasons for breakdown can be analyzed against a Digital Tractor Twin. Furthermore, the reasons can be shared with Manufacturers, dealers, and other Stakeholders for improved design and Maintenance. The Tractor maintenance and operating cost can be calculated with Logistics data like Invoices and Purchase orders and will help the farmers with efficient product costing. The Test Data for

a tractor can be shared with Government agencies like NTTL. The University of Nebraska Tractor Test Laboratory (NTTL) is the officially designated tractor testing station for the United States and tests tractors according to the Organization for Economic Co-operation and Development (OECD) codes OECD codes. Tractors are tested in the country of manufacture. Twenty-nine countries adhere to the tractor test codes (including non-OECD members: China, India, the Russian Federation, and Serbia), with active tractor test stations in approximately 25 countries. Reciprocity agreements with the codes require that once an OECD test report is officially approved, it must be accepted by all participating countries.


Efficient Digital Twin systems for a Tractor and associated farm equipment can help the farmers and producers and contribute to the ecosystem and well-being. The potential for real-time data transfer with IoT (sundmaeker et al., 2010) or the Internet of things can be fully exploited to get real-time data and enhance the Design of Tractors for maximum efficiency. Digital Twin features can be accessed by multiple stakeholders over the Cloud with a tablet or mobile device and will define the future of the Farm Equipment Industry.


University of Nebraska Lincoln.

Johannes  Reichel

Sensors & Systems

John Deere Manuals

Joe Mullich  Dell Technologies.

Marr, 2017


What is Digital Twin technology – and why is it so important?

Forbes (2017)

Google Scholar

Janssen S.J.C. Janssen, et al.

Towards a new generation of agricultural system data, models and knowledge products: information and communication technology

Agric. Syst., 155 (2017), pp. 200-212

ArticleDownload PDFView Record in ScopusGoogle Scholar

A.T. Balafoutis, et al.

Smart farming technologies – Description, taxonomy and economic impact

Lind (Ed.), Pedersen S, Technology and Economic Perspectives. Progress in Precision Agriculture. Springer, Cham, Precision Agriculture (2017)

Google Scholar

Wolfert et al., 2017

Kritzinger et al., 2018

Kritzinger, M. Karner, G. Traar, J. Henjes, W. Sihn

Digital twin in manufacturing: a categorical literature review and classification

IFAC-PapersOnLine, 51 (11) (2018), pp. 1016-1022

ArticleDownload PDFView Record in ScopusGoogle Scholar

Wolfert, L. Ge, C. Verdouw, M.-J. Bogaardt

Big data in smart farming – a review

Agric. Syst., 153 (2017), pp. 69-80

ArticleDownload PDFView Record in ScopusGoogle Scholar

Wolfert et al., 2017

Wolfert, L. Ge, C. Verdouw, M.-J. Bogaardt

Big data in smart farming – a review

Agric. Syst., 153 (2017), pp. 69-80

ArticleDownload PDFView Record in ScopusGoogle Scholar

Tzounis et al., 2017

Tzounis, N. Katsoulas, T. Bartzanas, C. Kittas

Internet of things in agriculture, recent advances and future challenges

Biosyst. Eng., 164 (2017), pp. 31-48

ArticleDownload PDFView Record in ScopusGoogle Scholar

Kamilaris and Prenafeta-Boldú, 2018

Kamilaris, F.X. Prenafeta-Boldú

Deep learning in agriculture: a survey

Comput. Electron. Agric., 147 (2018), pp. 70-90

ArticleDownload PDFView Record in ScopusGoogle Scholar

Shaw and Fruhlinger, 2019

Shaw, J. Fruhlinger

What Is a Digital Twin and why it’s Important to IoT

Network World (2019)

Google Scholar

Sørensen et al., 2010

C.G. Sørensen, S. Fountas, E. Nash, L. Pesonen, D. Bochtis, S.M. Pedersen, B. Basso, S.B. Blackmore

Conceptual model of a future farm management information system

Comput. Electron. Agric., 72 (1) (2010), pp. 37-47

ArticleDownload PDFView Record in ScopusGoogle Scholar

sundmaeker et al., 2010

Sundmaeker, P. Guillemin, P. Friess, S. Woelfflé

Vision and Challenges for Realising the Internet of Things

European Union, Brussels (2010)

Google Scholar

Tao et al., 2018

Tao, J. Cheng, Q. Qi, M. Zhang, H. Zhang, F. Sui

Digital twin-driven product design, manufacturing and service with big data

Int. J. Adv. Manuf. Technol., 94 (9) (2018), pp. 3563-3576

View PDF

CrossRefGoogle Scholar