Amazon Lookout for Equipment enables you to detect abnormal equipment behavior using three simple steps. First, the service enables you to ingest historical data generated from sensors on industrial equipment. Second, it trains a custom machine learning (ML) model using that data to assess healthy patterns for your equipment (you can use data from up to 300 sensors to train one model). Third, it uses that model to infer abnormal patterns from incoming sensor data for continuous monitoring of your equipment. You are charged based on the amount of data ingested, the compute hours used to train your models using the ingested data, and the number of hours of inferencing run using your model.
With Amazon Lookout for Equipment, you pay only for what you use, and there are no minimum fees and no upfront commitments.
Get started with Amazon Lookout for Equipment for free.
For the first month after sign-up, you are offered the following when using Lookout for Equipment:
Data Ingestion: Up to 50 GB
Training: Up to 250 training hours
Recommendations: Up to 168 hours of scheduled inference
Pricing at a glance
You are charged per GB of data ingested into Amazon Lookout for Equipment. This data ingestion charge is for the historical data used to train your models. There is no ingestion charge for the data used for inferencing. Ingestion charges are prorated to the nearest MB.
Amazon Lookout for Equipment will train a custom model with your data. You pay for the number of hours it takes to train your model. Amazon Lookout for Equipment may provision more compute resources to quickly train multiple models and pick the best one. All model training jobs are charged for a minimum of one hour of elapsed time and then prorated to the nearest second.
After you train a model, you can use the trained model to get results on new data coming from your equipment (receiving results from your model on new data is also known as inferencing). Amazon Lookout for Equipment allows you to set a schedule so that inference results are generated automatically for continuous equipment monitoring. You can schedule the frequency of inferencing to be once every 5 minutes, 10 minutes, 15 minutes, 30 minutes or 60 minutes but you are charged by the hour regardless of the set frequency. If scheduled inferencing is stopped, then the inference charges will be rounded up to the nearest hour.
|$0.20 per GB
|$0.24 per training hour
|$0.25 per inference hour
You have a petrochemical facility and want to monitor the performance of a compressor that has 200 sensors. You have collected 5GB of data from the compressor. The model takes 10 hours to train and uses 9 compute resources for every hour of elapsed time. You set your scheduled inference frequency for continuous monitoring. You also retrain your model once every 3 months (four times per year). Shown below is the total cost for the first year of usage.
For simplicity, let’s assume you have already used your free tier allocation. You have a steam generator in a power plant with 50 sensors measuring different components of the steam generator. You also have multiple failures logged in your maintenance system over the past year. You would like to build a model that can detect the failures before they lead to major downtime. Your 50 sensors each take readings once per second and they have one year of historical data totaling approximately 3GB. The model takes 10 hours to train and uses 9 compute resources for every hour of elapsed time. You set your scheduled inference frequency for continuous monitoring. You also retrain your model once every 3 months (four times per year). Shown below is the total cost for the first year of usage.