Systems, methods, and computer-program products for fluid analysis and monitoring are disclosed. Embodiments include a removable and replaceable sampling system and an analytical system connected to the sampling system. A fluid may be routed through the sampling system and data may be collected from the fluid via the sampling system. The sampling system may process and transmit the data to the analytical system. The analytical system may include a command and control system to receive and store the data in a database and compare the data to existing data for the fluid in the database to identify conditions in the fluid. Fluid conditions may be determined using machine learning models that are generated from well-characterized known training data. Predicted fluid conditions may then be used to automatically implement control processes for an operating machine containing the fluid.

Embodiments of the present disclosure provide for systems, apparatuses, and methods for real-time fluid analysis. Embodiments include a removable and replaceable sampling system and an analytical system connected to the sampling system. A fluid may be routed through the sampling system and real-time data may be collected from the fluid via the sampling system. The sampling system may process and transmit the real-time data to the analytical system. The analytical system may include a command and control system that may receive and store the real-time data in a database and compare the real-time data to existing data for the fluid in the database to identify conditions in the fluid.

Systems, methods, and computer-program products for fluid analysis and monitoring are disclosed. Embodiments include a removable and replaceable sampling system and an analytical system connected to the sampling system. A fluid may be routed through the sampling system and data may be collected from the fluid via the sampling system. The sampling system may process and transmit the data to the analytical system. The analytical system may include a command and control system to receive and store the data in a database and compare the data to existing data for the fluid in the database to identify conditions in the fluid. Fluid conditions may be determined using machine learning models that are generated from well-characterized known training data. Predicted fluid conditions may then be used to automatically implement control processes for an operating machine containing the fluid.

Methods for determining nitrogen and/or sulfur containing surfactant residual concentrations in oil and/or water phases of an oil and water system, particularly produced oil and water from an oil or gas well, are provided. The methods utilize pyro-chemiluminescence/pyro-fluorescence techniques which quantify the total residual surfactants in both oil and water phases. The methods may be applied broadly in areas where quantifying or monitoring surfactant concentrations in solution is required.

Described herein are systems and methods for evaluating and mitigating the wax risks of a given hydrocarbon composition such as crude oil. The disclosed systems and methods enable rapid and ready prediction of wax risks using algorithms based on a small sample of the hydrocarbon composition. The wax risks are predicted using predictive models developed from machine learning. The disclosed systems and methods include mitigation strategies for wax risks that can include chemical additives, operation changes, and/or hydrocarbon blend.

The invention relates to a method and an analysis system, wherein the method comprises the following steps: determining an electrical resistivity (R.sub.p) of the hydrocarbon fluid (30) by means of a sensor device, repeating the determining step for the electrical resistivity (R.sub.P) over time (t), monitoring the resistivity (R.sub.P(t)) of the hydrocarbon fluid over time, determining a use of the hydrocarbon fluid under predetermined conditions, determining a change of resistivity (dR.sub.p/dt, dRp/dO) over time (t), monitoring the change of resistivity (dR.sub.p/dt, dRp/dO) of the hydrocarbon fluid (30) over time (t), providing a quality information about an absolute value of a difference of a total base number (TBN) and a total acid number (TAN) on the basis of the monitored change of resistivity (R.sub.P).

A sample testing apparatus is disclosed for use in optical transmission analysis of fluid samples such as oils or engine oils. The apparatus comprises a transmission cell comprising first and second fixed walls (1,2) and a movable window (3) that is moved with respect to the first and second walls in and out of a test region (6). When the movable window (3) is moved into the test region (6) an optical path through a fluid sample in the cell is defined, the optical path through the sample comprising a portion extending through the or each gap (L.sub.1,L.sub.2) between a one of the first and second fixed walls (1,2) and the at least a portion of the first movable window (3). Also disclosed are methods of using the sample testing apparatus and methods of performing a measurement for use in optical transmission analysis of a fluid sample.

A sensing system for detecting degradation of a machine fluid is disclosed. The sensing system may comprise a tag having electrical contacts. The tag may be configured to transmit a wireless signal when the electrical contacts are in electrical communication. The sensing system may further comprise a dissolvable element separating the electrical contacts and obstructing electrical communication between the electrical contacts. The dissolvable element may be configured to dissolve and allow electrical communication between the electrical contacts when an acid content of the machine fluid reaches a level indicative of the degradation of the machine fluid.

The present disclosure refers to the use of very high resolution mass spectrometry analysis methodology in combination with the use of multivariate calibration models to predict Total Acidity Number (TAN). The models are built from data of total abundance value with the application of machine learning methods for regression.

The present invention pertains to a method of determining a lubrication oil condition of a stationary gas engine comprising the steps of retrieving a lubrication oil temperature information and retrieving a lubrication oil level information from a lubrication oil level sensor, wherein the lubrication oil level sensor is a capacitance sensor, and a step of normalizing a lubrication oil level information over the lubrication oil temperature information.