Development of an Automated System for Material Management at the RMC plant using Computer Vision

Development of an Automated System for Material Management at the RMC plant using Computer Vision

Miss. Kalyani Y. Patil

Research Scholar, Department of Civil Engineering, Pimpri Chinchwad College of Engineering, Pune, India

Dr. Rahul S. Chaudhari

Associate Professor, Department of Civil Engineering, Pimpri Chinchwad College of Engineering, Pune, India

Dr. Manish N. Narkhede

Assistant Professor Department of Electronics and Telecommunication, Pimpri Chinchwad College of Engineering, Pune, India

Abstract – Ready Mix Concrete (RMC) plants are critical components of modern construction, yet their operational efficiency is often compromised by reliance on traditional, manual material management practices. These outdated methods introduce significant challenges, including inventory inaccuracies, the risk of stockouts or overstocking, procurement delays, and increased operating costs. To address these systemic inefficiencies, this research explores the implementation of Computer Vision (CV) an advanced application of Artificial Intelligence for automated and intelligent material monitoring within RMC facilities. The proposed CV system is designed to provide real-time, accurate data on key operational aspects, such as raw material levels in storage bins, vehicle movement tracking, and the precise flow of materials throughout the plant. By automating these monitoring functions, the system eliminates the need for constant human checks, thereby minimizing errors and enhancing process control. The adoption of computer vision offers a scalable, robust, and reliable solution to ensure immediate inventory precision and a consistent material supply, ultimately leading to significant improvements in the overall accuracy, efficiency, and cost-effectiveness of RMC production.

Key words: Ready Mix Concrete (RMC), Computer Vision (CV)

important to use automation and smart monitoring systems. Using computer vision is a modern way to improve how accurate, efficient, and reliable material management is.

Computer vision, which is part of artificial intelligence, allows machines to understand and analyze visual data from images or videos. In RMC plants, computer vision can monitor how much material is in storage bins, spot when vehicles move, track how materials flow, and guarantee a steady supply without needing people to constantly check. RMC plants are a key part of today’s construction world, providing concrete that is carefully controlled in composition and consistent in quality. How well these plants work relies heavily on managing raw materials correctly, including cement, fine and coarse aggregates, water, and chemical additions. Traditionally, most RMC plants depend on manual checks and record- keeping for managing materials and keeping track of inventory. These traditional ways can easily lead to mistakes made by people, which can cause problems like not estimating materials correctly, unexpected shortages, building up too much stock, and delays in production. The construction business increasingly needs automation and digital changes. An automated system can guarantee accuracy, openness, and real-time monitoring of materials. Using computer vision tech seems promising. Computer vision is part of artificial intelligence that allows computers to analyze visual information from cameras and sensors.

1. Introduction

   Ready Mix Concrete (RMC) plants are essential for modern construction, providing large quantities of consistent, high- quality concrete. The efficient operation of these plants largely depends on how well they manage materials like cement, sand, aggregates, water, and chemical admixtures. Many RMC plants still use mostly manual methods for material management, relying on people to watch and keep records. This often causes problems like not knowing exactly how much material is on hand, running out of materials or having too much, delays in getting materials,

   Data Capture by Camera

   Cement

   GGBS

   Fly ash

   Admixture

   Quantity

   Sand

   20 MM

   10 MM

   Water

   Grade of the Concrete

   and higher costs. To deal with these problems, its

   Interface (Setup)

   Output (Material Management)

   Fig.1.1 Process followed by using Computer Vision

2. Objective of Study

   1. To understand the current process of material handling and its challenges in RMC plants.

   2. To identify information needed to manage materials more accurately and in real time.

   3. To design an automated system using computer vision to track and manage materials like cement, aggregates, water, and admixtures.

   4. To validate the system for improvement in efficiency, reduces waste, at RMC plant operations.

3. Methodolgy

   1. Detailed of Methodology:

4. Process followed in RMC plant

   In RMC Plant the Cement, GGBS, Fly ash, Sand, Aggregate (20MM, 10MM), Water, Admixture and Grade of Concrete this value mention in batch report. And RMC plant followed up the daily material used.

   manually work using this value create an excel sheet for daily update of how much material used. They tracking material manually like Storage and Order for material. In manually daily consumption can take to much time and sometimes mistakes will happen due to quantity of production in high.

   Image.4.1 Batch Report

   Image 4.2 Quantity of Material in Batch report

   Image 5.1 Design of the Box with dimension

   Image 5.2 Expected Model of the Box

   Image 4.3 Consumption report of Cement, GGBS, Fly ash and Admixture

   6 Experimental Work

   Computer vision, which is part of artificial intelligence, allows machines to understand and analyze visual data from images or videos. How well these plants work relies heavily on managing raw materials correctly, including cement, fine and coarse aggregates, water, and chemical additions. Traditionally, most RMC plants depend on manual checks and record-keeping for managing materials and keeping track of inventory. These traditional ways can easily lead to mistakes made by people, which can cause problems like not estimating materials correctly, unexpected shortages, building up too much stock, and delays in production. The construction business increasingly needs automation and digital changes.

   Image 4.4 Consumption report of Sand, 20MM, 10MM and Water

5. Proposed Setup for Computer

Vision

Ready Mix Concrete (RMC) plants are important in current construction because they supply a lot of consistent, good concrete. How well these plants run depends a lot on how well materials like cement, sand, aggregates, water, and chemical admixtures are managed. Many RMC plants still use hand monitoring and record keeping. This can cause wrong inventory data, not enough or too much material, late procurement, and higher costs. To fix these problems, it is key to add automation and smart monitoring. Computer vision is a current and helpful way to make material management in RMC plants more correct, efficient, and reliable.

Image 6.1 ctual model for Computer vision

Image 6.2 Actual Model of the Box

An automated system can guarantee accuracy, openness, and real-time monitoring of materials. Using computer vision tech seems promising. Computer vision is part of artificial intelligence that allows computers to analyze visual information from cameras and sensors. By adding this tech to an RMC plant, material levels can be automatically tracked, vehicle or equipment movements can be followed, and stockpile levels can be checked using images or videos. Creating an automated material management system using computer vision tries to reduce the need for people to be involved and make RMC plants work better. By using image processing methods, getting real-time data, and creating analytical models, the system can continuously track material levels, produce precise inventory reports, and send alerts for getting new material. This keeps production running smoothly, cuts down on waste, and controls resources.

Image 6.2.2 Document Uploading

Image 6.2.3 Document Processing

6.3 Output:

Image 6.3 Software Processing

6.2 Input:

Image 6.3.1 Upload Document Result

Image 6.2.1 Input Window

Variation in Materials Weekly

Image 6.3.2 Capture Document Result

6.4 Material Variations:

0

Variation in Materials Daily

Cement (Tone) GGBS (Tone)

Fly ash (Tone) Admixture (Tone)

80 Image 6.4.3 Weekly Material Variation in Cement,

60 Fly Ash, GGBS and Admixture

Cement (Tone) Fly ash (Tone) GGBS (Tone) Admixture (Tone)

Image 6.4.1 Daily Material Variation in Cement, Fly Ash, GGBS and Admixture

Variations in Material Daily

Variation in Materials Weekly

Sand (Tone)

10 MM Aggragate (Tone)

20 MM Aggragate (Tone)

50 Image 6.4.4 Weekly Material Variation in Sand, 10 MM

0 and 20 MM

Sand (Tone)

10 MM Aggragate (Tone)

20 MM Aggragate (Tone)

Image 6.4.2 Daily Material Variation in Sand, 10MM and 20MM

1. Conclusion

   1. Consumption of materials is high in RMC plants, where cement is consumed up to 66 tons per day, while aggregate can be up to 185 tons per day.

   2. Material management through human intervention causes time wastage and makes humans prone to errors and incorrect material management.

   3. A proposed computer vision system allows for data acquisition and tracking of materials automatically.

   4. Automating activities results in increased efficiency by 8-10% as well as minimizing wastage of materials by 1- 2%.

   5. The system minimizes human involvement by almost 80- 90%, thus ensuring accuracy.

   6. It helps to plan material inventories and prevents shortage and excess of materials.

   7. Facilitates decision-making based on daily consumption of materials.

2. References

1. Patel, K. V., & Vyas, C. M. (2011, May). Construction materials management on project sites. In National Conference on Recent Trends in Engineering & Technology (Vol. 31, No. 6, pp. 2932-2941).

2. Albert, I., Shakantu, W., & Ibrahim, S. (2021). The effect of poor materials management in the construction industry: A case study of Abuja, Nigeria. Acta Structilia, 28(1), 142-167.

3. Vipin, V. P., & Rahima Shabeen, S. (2019). Factors affecting material management in construction industry. International Journal of Recent Technology and Engineering, 8(3), 8445-8448.

4. Kulkarni, V., Sharma, R., Hote, M., & Civil, M. E. (2017). Factors affecting material managemen construction site. International Research Journal of Engineering and Technology, 4(1), 474-478.

5. Gulghane, A. A., & Khandve, P. V. (2015). Management for construction materials and control of construction waste in construction industry: a review. International Journal of Engineering Research and Applications, 5(4), 59-64.

6. Patil, A. R., & Pataskar, S. V. (2013). Analyzing material management techniques on construction project. International Journal of Engineering and Innovative Technology, 3(4), 96-100.

7. Madhavi, T. P., Mathew, S. V., & Sasidharan, R. (2013). Material management in constructiona case study. International journal of research in engineering and technology, 2(13), 400-403.

8. Donyavi, S., & Flanagan, R. (2009, September). The impact of effective material management on construction site performance for small and medium sized construction enterprises. In Proceedings of the 25th annual ARCOM conference, Nottingham, UK (pp. 11-20).

9. Ahmed, F. H. (2017). Improving construction materials management practices in construction sites (Doctoral dissertation, Universiti Tun Hussein Onn Malaysia).

10. Kasim, N. B., Anumba, C.J., & Dainty, A. R. J. (2005, September). Improving materials management practices on fast-track construction projects. In 21st Annual ARCOM Conference, SOAS, University of London (Vol. 2, pp. 793- 802).

11. Pande, A. A., & Sabihuddin, S. (2015). Study of material management techniques on construction project. International Journal of Informative & Futuristic Research, 2(9), 3476-3486.

12. Sila, J. N., & Gakobo, J. (2021). Material management and project performance of construction companies in Nairobi city county, Kenya. International Academic Journal of Information Sciences and Project Management, 3(6), 368- 391.

13. Pinagapani, A. K., Abhishek, G., Athipathi, S., RV, N. K., & Pragatheesh, G. B. (2024). Automated material handling for inventory management system. Acta IMEKO, 13(4), 1- 8

14. Nasir, H. (2009, January). A model for automated construction materials tracking. In Masters Abstracts International (Vol. 48, No. 03).

15. Burke, F. (1967). The application of automated techniques in the management and control of source materials. The American Archivist, 30(2), 255-278.

16. Victoire, M. (2015). Inventory management techniques and its contribution on better management of manufacturing companies in RWANDA case study: SULFO RWANDA Ltd. European Journal of Academic Essays, 2(6), 49-58.

17. Ashokkumar, D. (2014). Study of quality management in construction industry. International Journal of Innovative Research in Science, Engineering and Technology, 3(1), 36-43.

18. Neelamkavil, J. (2009, June). Automation in the prefab and modular construction industry. In 26th symposium on construction robotics ISARC.

19. Koriom, N. K., Brahim, J., Zakaria, I., Kaish, A. A., & Mohsen, M. (2019). The state of the art of materials management research in the construction industry. In MATEC Web of Conferences (Vol. 266, p. 05013). EDP Sciences.

20. Kasim, N. (2011). ICT implementation for materials management in construction projects: case studies. Journal of Construction Engineering and Project Management, 1(1), 31-36.

21. Navon, R. (2005). Automated project performance control of construction projects. Automation in construction, 14(4), 467-476.

22. Sardroud, J. M. (2012). Influence of RFID technology on automated management of construction materials and components. Scientia Iranica, 19(3), 381-392.

23. Dharmapalan, V., & OBrien, W. J. (2020). Benefits and challenges of automated materials technology in industrial construction projects. Proceedings of the Institution of Civil Engineers-Smart Infrastructure and Construction, 171(4), 144-157.