Oil & gas
available to them from digital transmitters associated with a wide variety of devices installed throughout facilities. However, the vast amount of data now being collected requires intelligent software to deliver analytics solutions and allow end-users to make better use of the data which they own. For metrology purposes, and in particular flow
D
measurement, there are typically three key areas of interest to end-users:
1. Data analytics 2. Condition-based monitoring (CBM) 3. Predictive analytics
In data analytics, both historical and real-time data can be analysed to uncover complex patterns and trends in primary and secondary flow measurement instrumentation and related back to physical processes and events. Through data-driven modelling, a facility’s data can be used to replace inefficient ‘time- based’ calibration and maintenance schedules with CBM systems. These can remotely determine facility process conditions, as well as detect fraudulent activity (e.g., fuel theft) in custody transfer scenarios and meter drift, without the need for unnecessary manual intervention, which is costly, causes potential safety issues and results in loss of production, which in the current climate is undesirable. In addition, specialised flow visualisation devices, such as X-ray tomography-
igitalisation strategies are now commonplace throughout the oil and gas industry. A major driver for this has been the fact that end-users now have a wealth of diagnostic data
based systems, can output data to which models can be applied to provide end-users with detailed insights as to the flow conditions within their multi-sensor systems. Predictive analytics embraces and expands upon the machine learning algorithms developed for CBM. When fully realised and developed through the use of high-resolution data sets, it allows end-users to forecast meter calibration requirements and determine if erosion, waxing, hydrate formation or corrosion requires intervention to prevent unplanned downtime. However, every operator wishing to embrace such concepts will be different with respect to physical layout, sensor availability and data resolution. This means that in order to develop CBMs and predictive models, which are useful and reflective of reality, it is vital that experienced flow measurement engineers consult on model development and commissioning. In doing so, one effectively programmes into the model the collective experience of a facility’s operators and its individual components. Data acquisition in multi-sensor systems has
grown into a significant source for diverse research and industrial areas, where mainly non- invasive and non-destructive examinations are needed. The data-driven models fed by complex temporal features (i.e., data that represents a state in time) and spatial features (i.e., information that pertains to the location of sensors) can unleash different levels of information and aid in production optimisation. In addition, a high resolution of faulty records
allows the development of a reliable predictive model that can detect deviations from normal conditions, and if possible, identify the root cause of deviations. However, data-driven models with insufficient data will lead to poor predictive
performance, known as the data sparsity problem. To overcome these limitations, artificially created sets of data known as synthetic data are widely employed to produce data that have not been observed in reality. Although many machine learning approaches
have been used in multi-sensor systems, this field still faces many technical challenges. Some challenges originate from measurement operations in continuous and uncontrolled environments, whilst some are unique to different sensors. Challenges faced in data-driven modelling of flow measurement systems include:
Data quality - poor quality data displayed in the shape of missing values, highly correlated time series with redundant information, duplicate data, numerous non-informative parameters, and outliers can cause significant challenges in the deployment of machine learning models in big data applications. Statistical methods including imputation of missing values, outlier detection, dimensionality reduction, signal processing and data transformations enhance data quality.
Lack of standardised benchmarks for model evaluation - this is crucial when building a foundation for unsupervised/supervised data- driven diagnostics.
Optimising machine learning techniques in the oil and gas industry
Feature extraction - multi-sensor systems regularly generate a large amount of heterogeneous data in structured or unstructured formats. These data can contain complex inter-sensor relationships, time-dependent patterns and/or spatial correlations. Given the complexities in such multivariate data structures, it is hard to distinguish deviations from these relationships. Different conditions may have similar characteristics, making it challenging to build unique connections between features and conditions.
46 October 2022 Instrumentation Monthly
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86
