The market for industrial AMRs is experiencing significant growth, driven by the increasing demand for automation and efficiency in manufacturing and logistics. According to a report by MarketsandMarkets, the global AMR market is projected to reach $6.8 billion by 2025, growing at a CAGR of 14.28% during the forecast period. This presents a significant opportunity for companies to optimize their operations and reduce costs associated with downtime and maintenance.
As AI and machine learning capabilities continue to evolve, they are playing an increasingly important role in the manufacturing industry. In addition to driving robotics and automation, these technologies are also being used to improve overall equipment effectiveness, optimize processes, and enable predictive maintenance. McKinsey reports that AI’s greatest value in manufacturing can be realized through predictive maintenance, generating an estimated $0.5 trillion to $0.7 trillion in potential value impact across the world’s businesses.
By developing a software agent for predictive maintenance of AMRs, our project seeks to address the growing demand for advanced automation and optimization tools in the manufacturing industry. By leveraging machine learning algorithms to analyze data from sensors and other sources, our software will help identify potential issues before they occur, reducing downtime, improving efficiency, and ultimately driving cost savings for manufacturers.
Botshare has been at the forefront of developing Autonomous Mobile Robots (AMRs) for several years, and has made significant investments in R&D to develop state-of-the-art solutions for industrial automation. The company has a strong focus on leveraging cutting-edge technologies to create innovative and effective solutions that meet the needs of its customers.
Botshare uses a software platform based on the Robot Operating System 2 (ROS2), which provides a powerful framework for developing and running complex robotic applications. This platform allows Botshare to leverage the latest advancements in artificial intelligence and machine learning to create sophisticated algorithms that power its robots.
The company also uses advanced sensor processing technologies based on the STM32f4 microcontroller and C++ firmware. This enables Botshare’s AMRs to quickly and accurately process large amounts of data from their sensors, which are essential for tasks such as navigation, obstacle avoidance, and predictive maintenance.
To manage and control its AMRs, Botshare uses a user interface (UI) and control tools based on the Open Robot Management Framework (RMF). This open-source platform provides a flexible and customizable way to manage and monitor AMRs, allowing Botshare to quickly adapt to the needs of its customers.
Overall, Botshare’s commitment to R&D and use of cutting-edge technologies has enabled it to develop some of the most advanced and capable AMRs on the market today, and the company is well-positioned to continue leading the way in industrial automation for years to come.
The Autonomous Mobile Robot (AMR) used in this project for predictive maintenance testing is a Multipurpose Botshare Platform. This robot has a range of technical characteristics that make it suitable for a variety of industrial applications.
With a navigation accuracy of 0.05m and a maximum speed of 2 m/s, the AMR can quickly and accurately move around the warehouse or manufacturing facility. Its ability to detect obstacles at a minimum distance of 5 cm and a maximum distance of 20 m ensures safe and efficient operation.
The AMR has a carrying capacity of up to 120 kg and can operate on a slope of up to 5 degrees. Its intelligent self-charging feature, which uses positioning via QR code at the charging station, ensures that the robot is always charged and ready for use. The robot also has a web interface for easy control, setting modes, and adjusting settings.
For this project, the AMR will be equipped with predictive maintenance software that uses artificial intelligence and machine learning algorithms to analyze data from sensors and other sources. By detecting potential issues before they occur, the software will help reduce downtime, improve efficiency, and save costs associated with repairs and replacements.
The AMR’s compatibility with various attachments makes it a versatile platform for a range of industrial applications. In addition to its potential for predictive maintenance testing, the AMR can be used as a robot for disinfection, delivery in a restaurant or hotel, sorting in a warehouse, placing goods on shelves in a store, and moving goods between production areas, among other options.
Robot Preventative Maintenance techniques:
- Increased robot longevity and reliability: Regular preventative maintenance helps in increasing the robot’s longevity and reliability, ensuring that it functions optimally for an extended period.
- Identify potential failures before they result in unexpected downtime: By identifying potential issues early on, preventative maintenance helps in preventing unexpected downtime, thereby saving time and resources.
- Maintenance program can be tailored for each robot: Preventative maintenance can be tailored for each robot, based on its specific requirements and usage patterns. This ensures that the robot receives the necessary care and attention, leading to improved performance and reliability.
- Data to support scheduling future maintenance work: Preventative maintenance generates valuable data, which can be used to schedule future maintenance work and plan for any necessary repairs or upgrades.
- Planned quantity of spare parts in stock for quick repairs: Regular preventative maintenance ensures that any necessary repairs can be carried out quickly, as there is a planned quantity of spare parts in stock. This helps in reducing the risk of unexpected downtime and ensures that repairs can be carried out efficiently without overstocking unnecessary parts. By planning the spare parts inventory, the maintenance team can ensure that they have the required parts available when needed, avoiding delays in repairs and reducing the overall costs associated with maintenance.
- Predictive maintenance using machine learning: Some advanced robotics systems have the ability to learn from data generated by multiple robots and use this information to predict the maintenance needs of each individual robot. By analyzing data such as usage patterns, environmental conditions, and other relevant factors, machine learning algorithms can predict when maintenance is required for each robot with greater precision. This helps in optimizing maintenance schedules, reducing downtime, and improving the overall efficiency and performance of the robots. Predictive maintenance can also help in reducing costs by avoiding unnecessary maintenance and extending the lifespan of the robots.
Benefits of predictive maintenance for AMRs:
- Predictive maintenance can reduce maintenance costs by up to 40%: According to a report by McKinsey, predictive maintenance can reduce maintenance costs for industrial equipment by up to 40%. This is because predictive maintenance enables maintenance teams to schedule maintenance when it is actually required, avoiding unnecessary maintenance tasks and reducing the overall cost of maintenance. (Source: McKinsey, “The impact of predictive maintenance on reducing unplanned downtime”)
- Predictive maintenance can increase equipment uptime by up to 10%: A study by the International Journal of Engineering and Technology found that predictive maintenance can increase equipment uptime by up to 10%. This is because predictive maintenance enables maintenance teams to identify potential issues before they cause downtime, allowing for repairs to be scheduled at a convenient time. (Source: International Journal of Engineering and Technology, “Predictive Maintenance for Industrial Equipment: A Review”)
- Predictive maintenance can improve asset lifespan by up to 20%: A study by Frost & Sullivan found that predictive maintenance can improve the lifespan of assets by up to 20%. This is because predictive maintenance enables maintenance teams to identify potential issues before they cause major damage, allowing for repairs to be scheduled before the equipment fails. (Source: Frost & Sullivan, “The Economic Benefits of Predictive Maintenance”)
- Predictive maintenance can reduce emergency maintenance by up to 75%: A study by the US Department of Energy found that predictive maintenance can reduce emergency maintenance for industrial equipment by up to 75%. This is because predictive maintenance enables maintenance teams to identify potential issues before they cause equipment failure, reducing the need for emergency repairs. (Source: US Department of Energy, “Best Practices for Effective Predictive Maintenance”)
- Predictive maintenance can improve safety: Predictive maintenance can help in improving safety for workers and equipment by identifying potential issues before they cause accidents or injuries. For example, predictive maintenance can help in identifying worn or damaged components that could fail and cause equipment to malfunction, potentially leading to accidents. (Source: ARC Advisory Group, “Predictive Maintenance: The Art of Uptime”)
- Predictive maintenance can reduce downtime by up to 30%: According to a report by the Aberdeen Group, predictive maintenance can reduce unplanned downtime for AMRs by up to 30%. This is because predictive maintenance helps in identifying potential issues before they become major problems, allowing maintenance to be scheduled at a convenient time and minimizing the impact on production. (Source: Aberdeen Group, “Predictive Maintenance: Keeping Equipment Up and Running”)
- Predictive maintenance can increase productivity by up to 25%: The same Aberdeen Group report also found that predictive maintenance can increase productivity for AMRs by up to 25%. This is because maintenance can be carried out at a time when it does not disrupt production, and the robots are able to operate at optimal performance levels. In addition, by identifying and addressing potential issues before they cause downtime, predictive maintenance can help to keep production running smoothly. (Source: Aberdeen Group, “Predictive Maintenance: Keeping Equipment Up and Running”)
- Real-world examples: Real-world examples also support the idea that predictive maintenance can reduce downtime and increase productivity for AMRs. For example, a case study by Daifuku North America described how a predictive maintenance program helped to reduce unplanned downtime for a fleet of AMRs by 50%, resulting in a significant improvement in productivity. (Source: Daifuku North America, “Predictive Maintenance: A Case Study”)
Overall, these sources provide strong evidence that predictive maintenance can have a significant positive impact on the performance of AMRs, helping to reduce downtime, increase productivity, and maximize the value of automation investments.
Companies that offer predictive maintenance solutions for AMRs:
- InOrbit: InOrbit is a cloud-based platform that provides real-time monitoring and predictive maintenance for AMRs, enabling remote troubleshooting, maintenance planning, and data analysis.
- Brain Corp: Brain Corp offers an AI-driven platform for predictive maintenance of AMRs, allowing operators to monitor and analyze data from multiple robots to identify potential issues and optimize maintenance schedules.
- DiManEx: DiManEx provides a predictive maintenance solution for AMRs that uses machine learning algorithms to analyze sensor data and predict potential issues, enabling operators to take proactive maintenance actions and avoid downtime.
- MIRAI-Intelligence: MIRAI-Intelligence offers a predictive maintenance solution for AMRs that uses deep learning algorithms to analyze sensor data and predict potential issues, enabling operators to optimize maintenance schedules and reduce downtime.
- Bright Machines: Bright Machines offers a predictive maintenance solution for AMRs that uses machine learning algorithms to analyze sensor data and predict potential issues, enabling operators to take proactive maintenance actions and reduce downtime.
Recent investments in companies that provide predictive maintenance solutions for AMRs, according to Crunchbase:
- InOrbit: InOrbit raised $2.6 million in seed funding in September 2021 to expand its cloud-based platform for monitoring and managing AMRs, including predictive maintenance capabilities.
- Brain Corp: Brain Corp raised $36 million in Series D funding in July 2021 to continue developing its AI-powered platform for AMR management, including predictive maintenance features.
- DiManEx: DiManEx raised €2.5 million in seed funding in May 2021 to scale its predictive maintenance solution for AMRs, which uses machine learning algorithms to analyze sensor data and predict potential issues.
Predictive maintenance for AMRs based on a real-world case study:
Company: Boxed Wholesale, an American online retailer
Problem: Boxed Wholesale’s fleet of AMRs was experiencing frequent breakdowns, leading to downtime and delays in order fulfillment.
Solution: Boxed Wholesale implemented a predictive maintenance solution for its AMRs, using machine learning algorithms to analyze sensor data and predict potential issues. The solution was developed by DiManEx, a company that specializes in predictive maintenance for AMRs.
Results: By implementing the predictive maintenance solution, Boxed Wholesale was able to reduce the number of breakdowns in its AMR fleet by 50%. The solution also helped the company optimize maintenance schedules and reduce downtime, resulting in increased productivity and improved customer satisfaction.
Key Takeaways: The use of predictive maintenance can help companies like Boxed Wholesale reduce downtime, optimize maintenance schedules, and improve overall efficiency in their AMR operations. By analyzing sensor data and using machine learning algorithms to predict potential issues, companies can take proactive maintenance actions and avoid costly breakdowns and delays.