Building Gen AI-Powered Predictive Maintenance with MongoDB

Humza Akhtar and Jack Yallop
June 27, 2024 | Updated: July 31, 2024

In today’s fast-evolving industrial landscape, digital transformation has become a necessity. From manufacturing plants to connected vehicles, the push towards predictive maintenance excellence is driving organizations to embrace smarter, more efficient ways of managing operations. One of the most compelling advancements in this domain is predictive maintenance powered by generative AI, a cutting-edge approach that will revolutionize how industries maintain and optimize their equipment.

For manufacturers seeking maintenance excellence, a unified data store and a developer data platform are key enablers. These tools provide the foundation for integrating AI applications that can analyze sensor data, predict failures, and optimize maintenance schedules. MongoDB Atlas is the only multi-cloud developer data platform available that is designed to streamline and speed up developers' data handling.

With MongoDB Atlas, developers can enhance end-to-end value chain optimization through AI/ML, advanced analytics, and real-time data processing, supporting cutting-edge mobile, edge, and IoT applications. In this post, we’ll explore the basics of predictive maintenance and how MongoDB can be used for maintenance excellence.

Check out our AI resource page to learn more about building AI-powered apps with MongoDB.

Understanding the need for predictive maintenance

Predictive maintenance is about anticipating and addressing equipment failures before they occur, ensuring minimal disruption to operations. Traditional maintenance strategies, like time-based or usage-based maintenance, are less effective than predictive maintenance because they don’t account for the varying conditions and complexities of machinery. Unanticipated equipment breakdown can result in line stoppage and substantial throughput losses, potentially leading to millions of dollars in revenue loss.

Since the pandemic, many organizations have begun significant digital transformations to improve efficiency and resilience. However, a concerning gap exists between tech adoption and return on investment. While 89% of organizations have begun digital and AI transformations, only 31% have seen the expected revenue lift, and only 25% have realized the expected cost savings.

These numbers highlight the importance of implementing new technologies strategically. Manufacturers need to carefully consider how AI can address their specific challenges and then integrate them into existing processes effectively.

Predictive maintenance boosts efficiency and saves money

Predictive maintenance uses data analysis to identify problems in machines before they fail. This allows organizations to schedule maintenance at the optimal time, maximizing machine reliability and efficiency.

Indeed, according to Deloitte, predictive maintenance can lead to a variety of benefits, including:

  • 3-5% reduction in new equipment costs

  • 5-20% increase in labor productivity

  • 15-20% reduction in facility downtime

  • 10-30% reduction in inventory levels

  • 5-20% reduction in carrying costs

Since the concept was introduced, predictive maintenance has constantly evolved. We've moved beyond basic threshold-based monitoring to advanced techniques like machine learning (ML) models. These models can not only predict failures but also diagnose the root cause, allowing for targeted repairs.

The latest trend in predictive maintenance is automated strategy creation. This involves using AI to not only predict equipment breakdowns but also to generate repair plans, ensuring the right fixes are made at the right time.

Generative AI in predictive maintenance

To better understand how gen AI can be used to build robust predictive maintenance solutions, let's dig into the characteristics of organizations that have successfully implemented AI. They exhibit common traits across five key areas:

  • Identifying high-impact value drivers and AI use cases: Efforts should be concentrated on domains where artificial intelligence yields maximal utility rather than employing it arbitrarily.

  • Aligning AI strategy with data strategy: Organizations must establish a strong data foundation with a data strategy that directly supports their AI goals.

  • Continuous data enrichment and accessibility: High-quality data, readily available and usable across the organization, is essential for the success of AI initiatives.

  • Empowering talent and fostering development: By equipping their workforce with training and resources, organizations can empower them to leverage AI effectively.

  • Enabling scalable AI adoption: Building a strong and scalable infrastructure is key to unlocking the full potential of AI by enabling its smooth and ongoing integration across the organization.

Implementing predictive maintenance using MongoDB Atlas

When combined with a robust data management platform like MongoDB Atlas, gen AI can predict failures with remarkable accuracy and suggest optimal maintenance schedules. MongoDB Atlas is the only multi-cloud developer data platform designed to accelerate and simplify how developers work with data. Developers can power end-to-end value chain optimization with AI/ML, advanced analytics, and real-time data processing for innovative mobile, edge, and IoT applications.

MongoDB Atlas offers a suite of features perfectly suited for building a predictive maintenance system, as shown in Figure 1 below. Its ability to handle both structured and unstructured data allows for comprehensive condition monitoring and anomaly detection. Here’s how you can build a generative AI-powered predictive maintenance software using MongoDB Atlas:

  • Machine prioritization: This stage prioritizes machines for the maintenance excellence program using a retrieval-augmented generation (RAG) system that takes in structured and unstructured data related to maintenance costs and past failures. Generative AI revolutionizes this process by reducing manual analysis time and minimizing investment risks. At the end of this stage, the organization knows exactly which equipment or assets are well-suited for sensorization.

    Utilizing MongoDB Atlas, which stores both structured and unstructured data, allows for semantic searches that provide accurate context to AI models. This results in precise machine prioritization and criticality analysis.

  • Failure prediction: MongoDB Atlas provides the necessary tools to implement failure prediction, offering a unified view of operational data, real-time processing, integrated monitoring, and seamless machine learning integration. Sensors on machines, like milling machines, collect data (e.g., air temperature and torque) and process it through Atlas Stream Processing, allowing continuous, real-time data handling. This data is then analyzed by trained models in MongoDB, with results visualized using Atlas Charts and alerts pushed via Atlas Device Sync to mobile devices, establishing an end-to-end failure prediction system.

  • Repair plan generation: To implement a comprehensive repair strategy, generating a detailed maintenance work order is crucial. This involves integrating structured data, such as repair instructions and spare parts, with unstructured data from machine manuals. MongoDB Atlas serves as the operational data layer, seamlessly combining these data types.

    By leveraging Atlas Vector Search and aggregation pipelines, the system extracts and vectorizes information from manuals and past work orders. This data feeds into a large language model (LLM), which generates the work order template, including inventory and resource details, resulting in an accurate and efficient repair plan.

  • Maintenance guidance generation: Generative AI is used to integrate service notes and additional information with the repair plan, providing enhanced guidance for technicians.

    For example, if service notes in another language are found in the maintenance management system, we extract and translate the text to suit our application. This information is then combined with the repair plan using a large language model. The updated plan is pushed to the technician’s mobile app via Atlas Device Sync. The system generates step-by-step instructions by analyzing work orders and machine manuals, ensuring comprehensive guidance without manually sifting through extensive documents.

Graphic displaying how end-to-end predictive maintenance with MongoDB Atlas is achieved. The process occurs in 4 stages. In stage 1, titled prioritization of assets, the input contains both structured and unstructured data including machine info, production data, expert interviews, and old work order. The output is machine priority. In stage 2, titled Failure Prediction, the input is structured data such as sensor data and maintenance logs. The output is machine failure. The third stage, titled maintenance plan generation, the input is structured and unstructured data such as failure info, inventory data, machine manual, and old work orders. The outpu is machine repair plan. The final stage, maintenance guidance generation, has structured data such as standard operating procedures and service notes as it's inputs. The output is repair instructions.
Figure 1: Achieving end-to-end predictive maintenance with MongoDB Atlas Developer Data Platform

In the quest for operational excellence, predictive maintenance powered by generative AI and MongoDB Atlas stands out as a game-changer. This innovative approach not only enhances the reliability and efficiency of industrial operations but also sets the stage for a future where AI-driven insights and actions become the norm. By leveraging the advanced capabilities of MongoDB Atlas, manufacturers can unlock new levels of performance and productivity, heralding a new era of smart manufacturing and connected systems.

If you would like to learn more about generative AI-powered predictive maintenance, visit the following resources:

← Previous

Unlock PDF Search in Insurance with MongoDB & Superduper.io

As industries go, the insurance industry is particularly document-driven. Insurance professionals, including claim adjusters and underwriters, spend considerable time handling documentation with a significant portion of their workday consumed by paperwork and administrative tasks. This makes solutions that speed up the process of reviewing documents all the more important. Retrieval-augmented generation (RAG) applications are a game-changer for insurance companies, enabling them to harness the power of unstructured data while promoting accessibility and flexibility. This is especially true for PDFs, which despite their prevalence are difficult to search, leading claim adjusters and underwriters to spend hours reviewing contracts, claims, and guidelines in this common format. By combining MongoDB and Superduper.io you can build a RAG-powered system for PDF search, thus bringing efficiency and accuracy to this cumbersome task. With a PDF search application, users can simply type a question in natural language and the app will sift through company data, provide an answer, summarize the content of the documents, and indicate the source of the information, including the page and paragraph where it was found. In this blog, we will dive into the architecture of how this PDF search application can be created and what it looks like in practice. Why should insurance companies care about PDF Search? Insurance firms rely heavily on data processing. To make investment decisions or handle claims, they leverage vast amounts of data, mostly unstructured. As previously mentioned, underwriters and claim adjusters need to comb through numerous pages of guidelines, contracts, and reports, typically in PDF format. Manually finding and reviewing every piece of information is time-consuming and can easily lead to expensive mistakes, such as incorrect risk estimations. Quickly finding and accessing relevant content is key. Combining Atlas Vector Search and LLMs to build RAG apps can directly impact the bottom line of an insurance company. Behind the scenes: System architecture and flow As mentioned, MongoDB and Superduper.io underpin our information retrieval system. Let’s break down the process of building it: The user adds the PDFs that need to be searched. A script scans them, creates the chunks, and vectorizes them (see Figure 1). The chunking step is carried out using a sliding window methodology, which ensures that potentially important transitional data between chunks is not lost, helping to preserve continuity of context. Vectors and chunk metadata are stored in MongoDB, and an Atlas Vector Search index is created (see Figure 3). The PDFs are now ready to be queried. The user selects a customer, asks a question, and the system returns an answer, where it was found and highlights the section with a red frame (see Figure 3). Figure 1: PDF chunking, embedding creation, and storage orchestrated with Superduper.io Each customer has a guidelines PDF associated with their account based on their residency. When the user selects a customer and asks a question, the system runs a Vector Search query on that particular document, seamlessly filtering out the non-relevant ones. This is made possible by the pre-filtering field included in the search query. Atlas Vector Search also takes advantage of MongoDB’s new Search Nodes dedicated architecture, enabling better optimization for the right level of resourcing for specific workload needs. Search Nodes provide dedicated infrastructure for Atlas Search and Vector Search workloads, allowing you to optimize your compute resources and fully scale your search needs independent of the database. Search Nodes provide better performance at scale, delivering workload isolation, higher availability, and the ability to optimize resource usage. Figure 2: PDF querying flow, orchestrated with Superduper.io Superduper.io Superduper.io is an open-source Python framework for integrating AI models and workflows directly with and across major databases for more flexible and scalable custom enterprise AI solutions. It enables developers to build, deploy, and manage AI on their existing data infrastructure and data, while using their preferred tools, eliminating data migration and duplication. With Superduper.io, developers can: Bring AI to their databases, eliminate data pipelines and moving data, and minimize engineering efforts, time to production, and computation resources. Implement AI workflows with any open and closed source AI models and APIs, on any type of data, with any AI and Python framework, package, class or function. Safeguard their data by switching from APIs to hosting and fine-tuning your own models, on your own existing infrastructure, whether on-premises or in the cloud. Easily switch between embedding models and LLMs, to other API providers as well as hosting your own models, on HuggingFace, or elsewhere just by changing a small configuration. Build next-generation AI apps on your existing database Superduper.io provides an array of sample use cases and notebooks that developers can use to get started, including vector search with MongoDB, embedding generation, multimodal search, retrieval-augmented generation (RAG), transfer learning, and many more. The demo showcased in this post is adapted from an app previously developed by Superduper.io. Let's put it into practice To show you how this could work in practice, let’s look at, an underwriter handling a specific case. The underwriter is seeking to identify the risk control measures as shown in Figure 3 below but needs to look through documentation. Analyzing the guidelines PDF associated with a specific customer helps determine the loss in the event of an accident or the new premium in the case of a policy renewal. The app assists by answering questions and displaying relevant sections of the document. Figure 3: Screenshot of the UI of the application, showing the question asked, the LLM’s answer, and the reference document where the information is found By integrating MongoDB and Superduper.io, you can create a RAG-powered system for efficient and accurate PDF search. This application allows users to type questions in natural language, enabling the app to search through company data, provide answers, summarize document content, and pinpoint the exact source of the information, including the specific page and paragraph. If you would like to learn more about Vector Search powered apps and Superduper.io, visit the following resources: PDF Search in Insurance Github repository Search PDFs at Scale with MongoDB and Nomic Superduper.io Github, includes notebooks and examples

June 24, 2024
Next →

Hanabi Technologies Uses MongoDB to Power AI Assistant, Hana

For all the hype surrounding generative AI, cynics tend to view the few real-world implementations as little more than “fancy chatbots.” But for Abhinav Aggarwal, CEO of Hanabi Technologies, the idea of a generative AI-powered bot that is more than just an assistant was intriguing. “I’d been using ChatGPT since it launched,” said Aggarwal. “That got me thinking: How could we make a chatbot that was like a team member?” And with that concept, Hana was born. The problem with bots “Most generative AI chatbots do not act like people; they wait for a command and give a response,” said Aggarwal. “We wanted to create a human-like chatbot that would proactively help people based on what they wanted—automating reminders, for example, or fetching time zones from your calendar to correctly schedule meetings.” Hanabi’s flagship product, Hana, is an AI assistant designed to enhance team collaboration within Google Chat, working in concert with Google Workspace and its suite of products. “Our target customers are smaller companies of between 10 and 50 people. At this size you’re not going to build your own agent from scratch,” he said. Hana integrates with Google APIs to deliver a human-like assistant that chimes in with helpful interventions, such as automatically setting reminders and making sure meetings are booked in the right time zone for each participant. “Hana is designed to bring AI to smaller companies and help them collaborate in a space where they are already working—Google Workspace,” Aggarwal explained. The MongoDB Atlas solution For Hana to act like a member of the team, Hanabi needed to process massive amounts of data to support advanced features like retrieval-augmented generation (RAG) for better information retrieval across Google Docs and many other sources. And with a rapidly growing user base of over 600 organizations and 17,000+ installs, Hanabi also required a secure, scalable, and high-performing data storage solution. MongoDB Atlas provided a flexible document model, built-in vector database, and scalable cloud-based infrastructure, freeing Hanabi engineers to build new features for Hana rather than focusing on rote tasks like data extract, transform, and load processes or manual scaling and provisioning. Now, MongoDB Atlas handles a variety of responsibilities: Scalability and security: MongoDB Atlas’s auto-scaling and automatic backup features have enabled Hanabi to seamlessly grow its user base without the need for manual database management. RAG: MongoDB Atlas plays a critical role in Hana’s RAG functionality. The platform enables Hanabi to split Google Docs into small sections, create embeddings, and store these sections in Atlas’s vector database. Development Processes: According to Aggarwal, MongoDB’s flexibility in managing changing schemas has been essential to the company’s fast-paced development cycle. Data Visualization: Using MongoDB Atlas Charts has enabled Hanabi to create comprehensive dashboards for real-time data visualization. This has helped the team track usage, set reminders, and optimize performance without needing to build a manual dashboard. Impact and results With MongoDB Atlas, Hanabi can successfully scale Hana to meet the demands of its rapidly expanding user base. The integration is also enabling Hana to offer powerful features like automatic interactions with customers, advanced information retrieval from Google Docs, and manually added memory snippets, making it an essential tool for teams around the world. Next steps Hanabi plans to continue integrating more tools into Hana while expanding its reach to personal Gmail users. The company is also rolling out a new automatic-interaction feature, further enhancing Hana’s ability to proactively assist users without direct commands. MongoDB Atlas remains a key component of Hanabi’s stack, alongside Google Kubernetes Engine, NestJS, and LangChain, enabling Hanabi to focus on innovating to improve the customer experience. Tech Stack MongoDB Atlas Google Kubernetes Engine NestJS LangChain Are you building AI apps? Join the MongoDB AI Innovators Program today! Successful participants gain access to free MongoDB Atlas credits, technical enablement, and invaluable connections within the broader AI ecosystem. If your company is interested in being featured, we’d love to hear from you. Connect with us at ai_adopters@mongodb.com.

November 21, 2024