Improve CPG operational efficiency with integrated equipment monitoring with TensorIoT powered by AWS
Machine downtime has a dramatic impact on your operational efficiency. Unexpected machine downtime is even worse. Detecting industrial equipment issues at an early stage and using that data to inform proper maintenance can give your consumer products organization a significant boost in operational efficiency.
Consumer packaged goods (CPG) manufacturers are increasingly investing in methods to detect abnormal behavior in industrial equipment to improve maintenance lifecycles. However, implementing these advanced maintenance approaches has multiple challenges. One major challenge is managing the plethora of data recorded from sensors and log information in the manufacturing facility as well as equipment and site metadata. These different forms of data might be inaccessible or spread across disparate systems that can impede access and processing. After the data is consolidated, the next step is gaining insights to prioritize an operationally efficient maintenance strategy.
A range of data processing tools exist today, but many require significant manual effort to implement or maintain. This acts as a barrier to use. What’s more, advanced analytics, such as machine learning (ML), require either external or in-house data scientists (located in manufacturing facilities) to manage models for each equipment type. This can lead to a high cost of implementation and can be daunting for operators that manage hundreds or thousands of sensors in a product facility or an array of food-and-beverage lines across facilities.
Real-time data capture and monitoring of your IoT assets with TensorIoT
TensorIoT, an Amazon Web Services (AWS) Partner, is no stranger to the difficulties that CPG brands face when looking to harness their data and improve business practices. TensorIoT creates products and solutions to help companies benefit from the power of ML and Internet of Things (IoT).
“Regardless of size or industry, companies are seeking to achieve greater situational awareness, gain actionable insights, and make more confident decisions,” says John Traynor, TensorIoT VP of Products.
For CPG customers, TensorIoT is adept at integrating sensors and machine data with tools from AWS into a holistic system that keeps operators informed about the status of their equipment at all times. TensorIoT uses AWS IoT Greengrass, an open-source edge runtime and cloud service, with AWS IoT SiteWise—a managed service that simplifies collecting, organizing, and analyzing industrial equipment data—and other AWS services to help CPG brands collect data from both direct equipment measurements and add-on sensors. They use connected devices to measure factors such as humidity, temperature, pressure, power, and vibration, giving a complete view of machine operation.
To help businesses better understand their data and processes, TensorIoT created SmartInsights, a product that incorporates data from multiple sources for analysis and visualization. Clear visualization tools combined with advanced analytics means that the assembled data is easy to understand and actionable for users.
TensorIoT first builds the connectivity to ingest data into Amazon Lookout for Equipment, an industrial equipment monitoring service that detects abnormal equipment behavior, for analysis. It then uses SmartInsights as the visualization tool for users to act on the outcome. An operational manager can visualize the health of the asset or send an automated push notification to maintenance teams as an alarm or message through Amazon Simple Notification Service (Amazon SNS), a fully managed messaging service. SmartInsights keeps CPG manufacturing sites and factory floors operating at peak performance for some of the most complex device hierarchies. Powered by AWS, TensorIoT helps companies rapidly and precisely detect equipment abnormalities, diagnose issues, and take immediate action to reduce expensive downtime.
Simplify machine learning with Amazon Lookout for Equipment
ML offers CPG manufacturers the ability to automatically discover new insights from data collected across systems and equipment types. In contrast, past industrial ML-powered solutions, such as equipment condition monitoring, have been reserved for critical or expensive assets due to the high cost of developing and managing the required models. Traditionally, a data scientist needed to go through dozens of steps to build an initial model for industrial equipment monitoring that could detect abnormal behavior.
Amazon Lookout for Equipment automates these traditional data science steps to open more opportunities for a broader set of equipment than ever before. Amazon Lookout for Equipment reduces the heavy lifting to create ML algorithms so that you can take advantage of industrial equipment monitoring to identify anomalies. From there, you can gain new actionable insights that help you improve your operations and avoid downtime.
Historically, ML models could be complex to manage due to changes in operations. Amazon Lookout for Equipment is making it easier and faster to get feedback from the engineers closest to the equipment by facilitating direct feedback from and iteration of these models. Now maintenance engineers can prioritize which insights are important to detect based on current operations, such as process, signal, or equipment issues. Using Amazon Lookout for Equipment, engineers can label these events and continue to refine and prioritize so that the insights stay relevant over the life of the asset.
TensorIoT and Amazon Lookout for Equipment integration
Let’s delve deeper into the process of visualizing near-real-time insights gained from Amazon Lookout for Equipment. It’s important to have historic operational performance as well as failure data to train the model to learn what patterns occur before failure. When trained, the model can create inferences about pending events from the equipment’s new live data. Since each piece of equipment requires separate training due to its unique operation, this process was once a time-consuming barrier to adoption. Using Amazon Lookout for Equipment and SmartInsights, engineers can visualize and solve these challenges.
Using Amazon Lookout for Equipment consists of three stages: ingestion, training, and inference (or detection). After the model is trained with available historical data, inference can happen automatically on a selected time interval, such as every 5 minutes or 1 hour.
SmartInsights provides visualization of data from each asset and incorporates the events from Amazon Lookout for Equipment. SmartInsights can then pair the original measurements with anomalies identified by Amazon Lookout for Equipment using the common time stamp. This allows SmartInsights to show measurements and anomalies on a common timescale while giving the operator context for these events.
SmartInsights also supports initiating alerts in response to certain conditions. For example, you can configure SmartInsights to send a message to a Slack channel or send a text message. Because SmartInsights is built on AWS, the notification endpoint can be any destination that is supported by Amazon SNS.
Improve uptime, increase safety, and boost machine efficiency
Condition-based maintenance is beneficial to CPG manufacturers on several levels:
- Improve uptime—Once maintenance events are predicted, you decide the scheduling to reduce the impact on your operational efficiency.
- Increased safety—Condition-based maintenance helps your equipment remain in safe operating conditions, which protects your operators and your machinery by catching issues before they become problems.
- Improved machine efficiency—As your machines undergo normal wear and tear, their efficiency decreases. Condition-based maintenance keeps your machines in good condition and extends the life span of your equipment.
Even before the release of Amazon Lookout for Equipment, TensorIoT helped CPG manufacturers innovate their machinery through the implementation of modern architectures, sensors for legacy augmentation, and ML to make newly acquired data intelligible and actionable. With Amazon Lookout for Equipment and TensorIoT solutions, TensorIoT helps make your assets even smarter.
Details on how to start using Amazon Lookout for Equipment are available on the AWS webpage.
TensorIoT is a software solution provider and an accomplished AWS Partner with AWS Competency designations in Machine Learning, IoT Consulting, Travel and Hospitality, Industrial, and Retail. Its services include Internet of Things implementation, smart fleet management, enterprise strategy, machine learning, edge computing, and more.