Data historians track and process production and operational data by time. Unfortunately, not all data historians are created equal. Operational field data should be easy to access, analyze, and share. Data historians must be easily integrated with other software solutions. As a result, data can feed formal analytics and machine learning initiatives and gain greater operational insights.
The eLynx Historian provides operators with a tool set that is designed for modern data initiatives. Operators can easily inbound and outbound data with other cloud solutions and software applications. Application integrations include solutions like Spotfire, ARIES, Excel, Informatica, Snowflake, and P2, just to name a few.
With the eLynx Historian solution, operators can trend data over time. This includes all asset trends, such as a well, pad, and gathering systems. Additionally, operators may query data based on metadata associated with each asset type.
Many operators are seeking to leverage machine learning and data analytics to obtain advanced warnings of production issues, i.e. predictive analytics. eLynx has discovered a new and critical tool set required for operators to obtain data for machine learning augmentation.
The eLynx Historian service provides users with mobile app access, meaningful dashboards, and modern data analysis and integration capabilities. It is a way to capture human intelligence and augment artificial intelligence.
To utilize machine learning with granular time series data sets, operators must label a dataset at a time series granularity. This is different from daily granularity. Most operators have, at best, daily well failure data. To feed time series data into time series forecasting, the start-time and end-time of the events you want to predict must be tracked.
Analyze time series data by crowdsourcing internal resources. With the eLynx Historian, engineers are empowered to label their time series database and create a dataset that is ready for data scientists to analyze.
The eLynx system allows users to label time series data manually. Data can also be labeled automatically by creating rules, which specify the start-time and end-time criteria. The eLynx Rules Engine is designed to reduce alarm fatigue, increase operator response time, and offer a real-time diagnostic tool.
As data is received by the eLynx Historian, the Rules Engine evaluates the data. If any rule criteria is met, an event is started or ended.
The Rules Engine allows engineers to specify criteria beyond traditional SCADA alarms. The rules can include multiple variables with different durations and math functions. Examples include: slope changes, independent or in relation to another variable (deviating/converging), sharp increase/decrease, gradual increase/decrease, etc. The rules can also scale across different wells, as you can modify the thresholds on a per-well basis.
The eLynx system allows engineers to run rules across historical data sets. This allows analysts to review the results prior to deploying the rule to operations. The ability to do this helps engineers verify the expected efficacy of a rule.
The eLynx system allows operators to validate results from each rule as valid or invalid. This provides a necessary feedback loop between the operators and the engineers. Rules can be modified as needed to improve the efficacy of the results. If a rule’s performance on a specific well is not providing meaningful results, then engineers can adjust the rule thresholds or remove the rule.
Rules created in the eLynx Rules Engine can ultimately replace alarm setpoints. The Rules Engine provides a diagnostic rather than sending an alarm notification for every individual symptom.
Traditional SCADA alarm management places a heavy burden on operators by sending individual symptoms over time. Operators are expected to aggregate symptoms together manually to determine a diagnosis. The eLynx Rules Engine aggregates symptoms for you and creates events based on the diagnosis.
Alarm notifications can be overwhelming, resulting in alarm fatigue and alarms getting missed. The ability to reduce notifications by any amount has a huge impact on operational efficiency. Empower your team with a toolset they can use to deploy data analytics initiatives faster.
The eLynx system has built-in data quality functions that can be integrated into the Rules Engine. If there is an issue with data quality, the system does not evaluate a rule against invalid data. The system will only send out valid results based on quality data.
The data quality functions include stuck sensors, out of range readings, and communications losses. Ensure your data scientists and data analysts are using quality data to create their statistical analysis.
The eLynx SCADA solution has a built-in production dashboard, which allows operators to view any subset of assets. Operators can view the Production Dashboard from a single pumper route up to an entire operating area. The Production Dashboard automatically displays producing wells, down wells, wells at risk of going down, and wells that are not communicating.
In addition, the associated target production for each well is specified. Meaning, operators can immediately identify the greatest production impact and prioritize accordingly. This view is also available in the mobile app.
The eLynx mobile app makes it easy for operators to capture contextual data, such as downtime codes and field notes. Operators can easily capture field notes by speaking into their phone using the voice to text option. The field notes are instantly captured in the eLynx system. Meaning, engineers can see the operator’s notes alongside the graphs they are viewing.
The eLynx Historian service enables your team to automate the detection, classification, and notification of well conditions. Stop manually aggregating symptoms to determine diagnostics. Engineer automated diagnostics with the eLynx Rules Engine. With the eLynx Historian, you will see immediate operational efficiency gains and achieve more analytical capabilities. Over time, you will have created a validated labeled time series data set that can be leveraged by machine learning and predictive analytics initiatives.