Systems and methods for automatically monitoring lubricants of industrial assets

Abstract

A method for monitoring a lubricant of an industrial asset includes receiving by a lubricant monitoring engine sensor data captured by a sensor of the industrial asset, receiving by the lubricant monitoring engine enrichment data characterizing a relationship between historical sensor data and one or more lubricant parameters of one or more historical lubricants, integrating by the lubricant monitoring engine the sensor data with the enrichment data to provide enriched data estimating one or more of the lubricant parameters of the lubricant, and providing by the lubricant monitoring engine a lubricant alert to a user that is based on the one or more estimated lubricant parameters.

Description

SYSTEMS AND METHODS FOR AUTOMATICALLY MONITORING LUBRICANTS OF INDUSTRIAL ASSETSCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims benefit of U.S. provisional patent application No. 63 / 737,828 filed December 23, 2024, and entitled “Systems and Methods for Automatically Monitoring Lubricants of Industrial Assets”, which is hereby incorporated herein in its entirety for all purposes.STATEMENT REGARDING FEDERALLY SPONSORED RESEARCH OR DEVELOPMENT

[0002] Not applicable.BACKGROUND

[0003] Lubricants play a critical role in the maintenance, reliability, and operational efficiency of various kinds of industrial assets in numerous different industries. Particularly, lubricants are typically used to reduce friction between moving parts, dissipate heat, prevent wear, and protect against corrosion. In this manner, lubricants are essential for the smooth functioning of machinery, engines, and other mechanical components of industrial assets.BRIEF SUMMARY OF THE DISCLOSURE

[0004] An embodiment of a computer-implemented method for monitoring a lubricant of an industrial asset comprises (a) receiving by a lubricant monitoring engine sensor data captured by a sensor of the industrial asset, (b) receiving by the lubricant monitoring engine enrichment data characterizing a relationship between historical sensor data and one or more lubricant parameters of one or more historical lubricants, (c) integrating by the lubricant monitoring engine the sensor data with the enrichment data to provide enriched data estimating one or more of the lubricant parameters of the lubricant, and (d) providing by the lubricant monitoring engine a lubricant alert to a user that is based on the one or more estimated lubricant parameters. In some embodiments, the sensor data comprises lubricant data captured by a lubricant sensor in fluid communication with the lubricant. In some embodiments, the lubricant data comprises one or more of an electrical conductivity, a relative permittivity, and a quantity of foreign particles of the lubricant. In certain embodiments, the sensor data comprises at least one of a vibration sensor, an acousticsensor, an acoustic sensor, a pressure sensor of lubricated equipment of the industrial asset that comprises the lubricant. In certain embodiments, the sensor data comprises an environmental sensor configured to monitor one or more ambient conditions of the industrial asset. In some embodiments, the one or more ambient conditions comprises an ambient relative humidity (RH) of the industrial asset. In some embodiments, the lubricant alert is provided to the user in at least one of real-time and near real-time following (a). In certain embodiments, (d) comprises providing by a trained predictive lubricant model of the lubricant monitoring engine the lubricant alert. In certain embodiments, the trained predictive lubricant model is trained at least partially using the enrichment data.

[0005] An embodiment of a computer-implemented method for monitoring a lubricant of an industrial asset comprises (a) receiving by a lubricant monitoring engine lubricant data captured by a lubricant sensor in fluid communication with the lubricant, (b) receiving by the lubricant monitoring engine enrichment data characterizing a relationship between historical lubricant data and one or more lubricant parameters of one or more historical lubricants, (c) integrating by the lubricant monitoring engine the lubricant data with the enrichment data to provide enriched data estimating the one or more lubricant parameters of the lubricant, and (d) providing by the lubricant monitoring engine information to a user that is based on or contains the enriched data. In some embodiments, the lubricant data comprises one or more of an electrical conductivity, a relative permittivity, and a quantity of foreign particles of the lubricant. In some embodiments, the enrichment data comprises at least one of laboratory data containing historical lubricant data and asset data containing historical equipment data besides lubricant data. In certain embodiments, the enrichment data comprises asset data containing historical environmental data associated with the industrial asset. In certain embodiments, the information is provided to the user in at least one of real-time and near real-time following (a). In some embodiments, (d) comprises providing by a trained predictive lubricant model of the lubricant monitoring engine the information that is based on or contains the enriched data.

[0006] An embodiment of a computer-readable medium storing executable code which, when executed by a processor, causes the processor to receive by a lubricant monitoring engine sensor data captured by a sensor of an industrial asset containing a lubricant, receive by the lubricant monitoring engine enrichment data characterizing a relationship between historical sensor data and one or more lubricant parameters of one or morehistorical lubricants, integrate by the lubricant monitoring engine the sensor data with the enrichment data to provide enriched data estimating one or more of the lubricant parameters of the lubricant, and provide by the lubricant monitoring engine a lubricant alert to a user that is based on the one or more estimated lubricant parameters. In some embodiments, the sensor data comprises lubricant data captured by a lubricant sensor in fluid communication with the lubricant. In certain embodiments, the lubricant data comprises one or more of an electrical conductivity, a relative permittivity, and a quantity of foreign particles of the lubricant. In certain embodiments, the executable code, when executed by a processor, causes the processor to provide the lubricant alert to the user in at least one of real-time and near real-time once the lubricant monitoring engine has received the sensor data captured by the sensor of the industrial asset. In some embodiments, the executable code, when executed by a processor, causes the processor to provide by a trained predictive lubricant model of the lubricant monitoring engine the lubricant alert.

[0007] Embodiments described herein comprise a combination of features and characteristics intended to address various shortcomings associated with certain prior devices, systems, and methods. The foregoing has outlined rather broadly the features and technical characteristics of the disclosed embodiments in order that the detailed description that follows may be better understood. The various characteristics and features described above, as well as others, will be readily apparent to those skilled in the art upon reading the following detailed description, and by referring to the accompanying drawings. It should be appreciated that the conception and the specific embodiments disclosed may be readily utilized as a basis for modifying or designing other structures for carrying out the same purposes as the disclosed embodiments. It should also be realized that such equivalent constructions do not depart from the spirit and scope of the principles disclosed herein.BRIEF DESCRIPTION OF THE DRAWINGS

[0008] For a detailed description of exemplary embodiments of the disclosure, reference will now be made to the accompanying drawings in which:

[0009] FIG. 1 depicts a block diagram of a computer-implemented lubricant monitoring system according to some embodiments;

[0010] FIG. 2 depicts a block diagram of another a computer-implemented lubricant monitoring system according to some embodiments;

[0011] FIG. 3 depicts a block diagram of a computer system according to some embodiments; and

[0012] FIG. 4 depicts a flowchart of a computer-implemented method for monitoring a lubricant of an industrial asset according to some embodiments; and

[0013] FIG. 5 depicts a flowchart of another computer-implemented method for monitoring a lubricant of an industrial asset according to some embodiments.DETAILED DESCRIPTION OF THE DISCLOSED EMBODIMENTS

[0014] The following discussion is directed to various exemplary embodiments. However, one skilled in the art will understand that the examples disclosed herein have broad application, and that the discussion of any embodiment is meant only to be exemplary of that embodiment, and not intended to suggest that the scope of the disclosure, including the claims, is limited to that embodiment.

[0015] Certain terms are used throughout the following description and claims to refer to particular features or components. As one skilled in the art will appreciate, different persons may refer to the same feature or component by different names. This document does not intend to distinguish between components or features that differ in name but not function. The drawing figures are not necessarily to scale. Certain features and components herein may be shown exaggerated in scale or in somewhat schematic form and some details of conventional elements may not be shown in interest of clarity and conciseness.

[0016] In the following discussion and in the claims, the terms "including" and "comprising" are used in an open-ended fashion, and thus should be interpreted to mean "including, but not limited to...” Also, the term "couple" or "couples" is intended to mean either an indirect or direct connection. Thus, if a first device couples to a second device, that connection may be through a direct connection, or through an indirect connection via other devices, components, and connections. In addition, as used herein, the terms "axial" and "axially" generally mean along or parallel to a central axis (e.g., central axis of a body or a port), while the terms "radial" and "radially" generally mean perpendicular to the central axis. For instance, an axial distance refers to a distance measured along or parallel to the central axis, and a radial distance means a distance measured perpendicular to the central axis.

[0017] As described above, lubricants serve multiple functions in industrial assets and associated equipment. As used herein, the term “industrial asset” is interpreted broadly as covering various types of systems including lubricated equipment such as fixed plants or facilities as well as moveable systems such as vehicles, ships, aircraft and the like. Generally, lubricants may form a protective film between lubricated contacting surfaces of lubricated equipment of an industrial asset to reduce friction and wear therebetween so as to minimize energy losses and prevent damaging of the lubricated equipment. In internal combustion engines (ICEs), for instance, lubricants may form a thin barrier between moving parts of the ICE, such as pistons and cylinders, to prevent metal-to-metal contact therebetween. Additionally, lubricants aid in minimizing and dissipating heat generated during operation (e.g., due to frictional contact) of an industrial asset. Particularly, mechanical components of industrial assets often operates under relatively high temperatures such that excessive heat may lead to thermal degradation of the mechanical components. To combat these issues, lubricants facilitate the transference of heat away from said mechanical components, thereby reducing the risk of overheating said mechanical components and ensuring the industrial asset operates within its designed temperature range. Additionally, lubricants serve as a medium to trap and suspend contaminants within industrial assets, such as wear particles, dust, and / or other debris. By trapping said debris therein, lubricants prevent the debris them from settling on or damaging lubricated surfaces of equipment of the industrial asset. Further, lubricants also protect against corrosion in industrial assets by forming a corrosion barrier along selected surfaces of equipment of the industrial asset, the corrosion barrier preventing moisture and / or other corrosive substances from contacting the lubricated surfaces. For instance, in marine applications, lubricants prevent the ingress of seawater, which can be highly corrosive to metal surfaces.

[0018] Despite their essential roles, the various functionalities of lubricants outlined above generally degrade over time due to various factors related to changes that occur in and to the lubricant over time. As a first example, at least some lubricants are susceptible to oxidative degradation when exposed to high temperature, oxygenated environments over extended periods of time. For instance, oxidation may result in the formation of acidic byproducts and sludge, which can undesirably increase the viscosity of the lubricant and lead to the formation of deposits on lubricated surfaces of the equipment of an industrial assetthat may impair lubrication efficiency and accelerate wear and tear of the lubricated equipment. As another example, at least some lubricants may be susceptible to thermal degradation when exposed to temperatures beyond their designed operating range. Particularly, excessive heat applied to the lubricant can cause the breakdown of the lubricant's molecular structure, leading to the loss of essential properties such as viscosity, lubricity, and load-carrying capacity of the lubricant that can, in turn, result in inadequate lubrication and increased wear of the mechanical components.

[0019] As a further example, contamination is another common cause of lubricant quality degradation. For instance, industrial lubricants can become contaminated with water, dust, dirt, and / or other foreign particles during operation. Water ingress is particularly problematic as it can lead to emulsification, corrosion, and / or a significant reduction in the lubricant's load-carrying ability. Additionally, debris accumulation in lubricants, such as metal particles generated through wear and tear of lubricated surfaces of the equipment of an industrial asset, can increase the abrasive nature of the lubricant and cause further damage to the lubricated surfaces. In addition, chemical contaminants, such as fuel or coolant leaks and the like, can alter the chemical composition of the lubricant, rendering it ineffective for its intended purpose.

[0020] Lubricant degradation over time, in accordance with the examples provided herein, typically necessitates regular or periodic monitoring of the lubricant to ensure that it remains within acceptable limits and continues to provide effective protection and performance. Typically, lubricants used in industrial assets are conventionally monitored through offsite laboratory testing and analysis. Particularly, samples of a selected lubricant of the industrial asset may be collected at regular intervals and subsequently provided to an offsite laboratory for analysis, with the laboratory including equipment needed fortesting and analyzing the sampled lubricant. Various parameters of the lubricant may be tested at the offsite laboratory including, for example, viscosity, total acid number (TAN), total base number (TBN), water content, particle count, and / or the presence of wear metals in the lubricant.

[0021] Viscosity is a particularly important lubricant parameter that indicates the lubricant's ability to form a protective film between moving parts. For instance, changes in viscosity detected at the offsite laboratory can signal thermal degradation or contamination of the lubricant. Additionally, the TAN and TBN measurements performed at the offsitelaboratory may provide insights into the acidity or alkalinity of the lubricant, which can indicate oxidation or depletion of additives in the lubricant, respectively. Further, the presence of water and particulate matter in the lubricant (e.g., detected at the offsite laboratory) can significantly impair the performance of the lubricant.

[0022] While conventional lubricant monitoring techniques relying on testing of sampled lubricant at offsite laboratories may provide accurate and detailed information regarding various salient parameters of the lubricant, such conventional monitoring techniques are generally incapable of providing real-time or near real-time lubricant analysis and, instead, typically take several weeks or longer between collecting samples of the lubricant to be tested, transporting the collected samples to the offsite laboratory, testing the collected lubricant samples at the offsite laboratory, analyzing the results of such testing, and communicating the test results to the operator of the industrial asset from which the lubricant was collected. This relatively significant delay in obtaining the test results from the offsite laboratory can, in some instances, lead to prolonged exposure of equipment lubricated by the tested lubricant to suboptimal lubrication conditions, increasing the risk of damage and unplanned downtime of the industrial asset.

[0023] Additionally, the intermittent nature of lubricant sample collection means that shortterm, unexpected changes in one or more parameters of the lubricant (e.g., thermal degradation, water ingress, and the like) may go undetected, as they such issues may occur between sampling intervals. These recurring gaps in lubricant monitoring may be particularly problematic in high-stress environments where lubricated equipment of the industrial asset is subject to rapid and significant changes in operating conditions. Further, the requirement of physically collecting lubricant samples from the lubricated equipment may introduce an additional avenue for human error and contamination, which can affect the accuracy and reliability of the test results obtained from the offsite laboratory. Thus, while offsite laboratory testing provides a comprehensive analysis of a sampled lubricant, such offsite testing is reactive rather than proactive, often identifying issues only after they have begun to affect the lubricated equipment.

[0024] Accordingly, embodiments of computer-implemented automated lubricant monitoring systems and methods are disclosed herein intended to decrease the amount of time required for analyzing the state or quality of a selected lubricant of an industrial asset such that changes in one or more parameters of the lubricant may be more swiftly,conveniently, and accurately detected as compared to conventional techniques reliant on offsite laboratory testing. In this manner, the time between initiating the lubricant monitoring system and receiving a test result may be minimized. Indeed, in some embodiments, lubricant monitoring systems disclosed herein provide for real-time or near real-time monitoring of one or more parameters of interest of a selected lubricant of an industrial asset, whether that industrial asset comprises a fixed plant or other facility or a moveable / transportable system such as a vehicle, ship, and / or aircraft.

[0025] Embodiments of lubricant monitoring systems may provide real-time or near realtime analysis (e.g., lubricant scores, lubricant alerts) of one or more parameters of selected lubricants of an industrial asset. In some embodiments, the lubricant monitoring system includes a lubricant monitoring engine that integrates sensor data captured from the industrial asset with enrichment data containing historical data associated with the lubricant and / or the industrial asset. The enrichment data may be applied or integrated with the sensor data to determine one or more current lubricant parameters of the selected lubricant from which additional information such as lubricant scores, lubricant alerts, and the like may be produced to provide a monitoring solution having a substantially reduced “control loop” or delay between the original capturing of the sensor data and the reporting to a user of lubricant parameters and / or additional information such as lubricant alerts.

[0026] Referring initially to FIG. 1, an embodiment of a computer-implemented lubricant monitoring system 10 is shown. Lubricant monitoring system 10 generally includes a plurality of sensors 12, 14, and 16 installed at an industrial asset 1 that includes a lubricant (indicated by arrow 3 in FIG. 1), and a computer-implemented lubricant monitoring engine 50 in signal communication with the plurality of sensors 12, 14, and 16. In this configuration, lubricant monitoring engine 50 receives sensor data from the sensors 12, 14, and 16 of the industrial asset 1 from which the lubricant monitoring engine 50 determines one or more lubricant parameters 52 of the lubricant 3 using enrichment data 40 (e.g., stored in a datastore or other structure of, or in signal communication with, lubricant monitoring engine 50). The lubricant parameters 52 may be provided to a user 2 (e.g., an operator or other personnel associated with the industrial asset 1) of lubricant monitoring system 10 who may be located at the industrial asset 1 or remote from the industrial asset 1.

[0027] Industrial asset 1 comprises lubricated equipment 5 defining a pair of corresponding equipment surfaces 7 and 9 respectively that are each lubricated by the lubricant 3 positioned therebetween whereby friction, heat, and / or wear of equipment surfaces 7 and 9 may be minimized or at least managed by the lubricant 3. In this exemplary embodiment, sensor 12 comprises a primary or lubricant sensor 12, sensor 14 comprises a secondary or vibration sensor 14, and sensor 16 comprises a tertiary or environmental sensor 16. Lubricant sensor 12 and vibration sensor 14 are each coupled to the lubricated equipment 5 with lubricant sensor 12 in contact with lubricant 3 for taking direct measurements therefrom. In this manner, lubricant sensor 12 may capture primary sensor or lubricant data 13 of the lubricants such as, for example, relative permittivity (the dielectric constant) of the lubricant 3, the electrical conductivity of the lubricant 3, the presence or quantity of foreign particles (e.g., water, wear particles, contaminants, and the like) in the lubricant 3, and / or other parameters of the lubricant 3 that may be determined in real-time or near realtime (e.g., every second, every minute, every hour, and the like).

[0028] As an example, lubricant sensor 12 may include a dielectric sensor for measuring relative permittivity of the lubricant 3 may comprise a pair of electrically conductive plates in fluid communication with lubricant 3 whereby the lubricant 3 may act as a dielectric material as it passes between the pair of conductive plates such that the capacitance of the dielectric sensor changes over time in response to changes in lubricant 3. To provide another example, the lubricant sensor 12 may include a magnetic inductive or ferrofluid sensor configured to detect and quantify the presence of ferromagnetic particles (e.g., contaminants, wear debris, and / or other particulate matter suspended in lubricant 3) in the lubricant 3. The ferromagnetic sensor may generate a magnetic field in the lubricant 3 via one or more permanent or electromagnets whereby the interaction between the magnetic field and any ferromagnetic particles suspended in the lubricant 3 may be monitored.

[0029] Vibration sensor 14 is in contact with the lubricated equipment 5 but not necessarily the lubricant 3 itself. In this configuration, vibration sensor 14 is configured to measure or capture secondary sensor or vibration data 15 from the lubricated equipment that may be used by the lubricant monitoring engine 50 to inform or contextualize the lubricant data 13 obtained from lubricant sensor 12. For instance, in this exemplary embodiment, vibration sensor 14 may monitor vibration in lubricated equipments, including vibration of surfaces 7 and 9 which may be dependent on the state or performance of lubricant 3. In otherembodiments, the secondary sensor 14 may comprise other types of sensors such as, for example, acoustic sensors for capturing acoustic data of the lubricated equipment 5, temperature sensors for capturing temperature data of the lubricated equipment 5, and / or other types of secondary sensors 14 associated with the particular lubricated equipment 5.

[0030] In this exemplary embodiment, environmental sensor 16 is not directly coupled to the lubricated equipment 5 and may not be particularly or uniquely associated with the lubricated equipment 5 as with sensors 12 and 14. Instead, in some embodiments, environmental sensor 16 is only specific to the industrial asset 1 itself and is configured to capture tertiary sensor or environmental data 17 associated with the industrial asset 1. Particularly, in this exemplary embodiment, environmental sensor 16 comprises a relative humidity (RH) sensor 16 configured to monitor the ambient relative humidity to which the industrial asset 1 (including lubricated equipment 5) is exposed. In other embodiments, environmental sensor 16 may comprise an ambient temperature sensor, an ambient pressure sensor, and / or a precipitation sensor for monitoring additional environmental parameters of the industrial asset 1. In other embodiments, lubricant monitoring system 10 may include only lubricant sensor 12 but not vibration sensor 14 and / or environmental sensor 16 or any other secondary and / or tertiary sensors. In still other embodiments, lubricant monitoring system 10 may include sensors in addition to the sensors 12, 14, and 16 shown in FIG. 1.

[0031] In this exemplary embodiment, each of sensors 12, 14, and 16 is in signal communication with a sensor data transmitter 18 of the lubricant monitoring system 10 whereby the lubricant data 13, vibration data 15, and environmental data 17 may be provided or communicated to the lubricant monitoring engine 50 (e.g., wirelessly) across a network 30 such as, for example, the Internet. In this manner, sensor data transmitter 18 provides a local data transmitter through which each of the lubricant data 13, vibration data 15, environmental data 17, and / or other sensor data of lubricant monitoring system 10 may be provided (e.g., in real-time or near real-time) to lubricant monitoring engine 50 generally irrespective of the physical locations of industrial asset 1 and lubricant monitoring engine 50.

[0032] In this exemplary embodiment, lubricant monitoring engine 50 receives via the network 30 the lubricant data 13, vibration data 15, and environmental data 17 captured by sensors 12, 14, and 16, respectively, of industrial asset 1. Although only a single industrialasset 1 is shown in FIG. 1 , lubricant monitoring engine 50 may be similarly connected via network 30 with a plurality (e.g., tens, hundreds, or thousands) of different industrial assets 1 which may vary in configuration (e.g., with respect to lubricated equipment 5 of the industrial asset 1 and / or the sensors associated with the industrial asset 1) from the industrial asset 1 shown in FIG. 1. In this arrangement, lubricant monitoring engine 50 may receive in parallel and in real-time or near real-time a plurality of separate sensor datastreams associated with different industrial assets including the industrial asset 1 shown in FIG. 1.

[0033] Generally, lubricant monitoring engine 50 generates or determines the lubricant parameters 52 of the lubricant 3 (and / or other lubricants of industrial asset 1 and / or other industrial assets besides industrial asset 1) based on both the collection of sensor data obtained from the industrial asset 1, and enrichment data 40 that may be obtained separately from the particular industrial asset 1. In other words, lubricant monitoring engine 50 may determine the lubricant parameters 52 of lubricant 3 by integrating the sensor data (e.g., lubricant data 13, vibration data 15, and / or environmental data 17) with the enrichment data 40 to thereby enrich the sensor data to permit the determination of lubricant parameters 52. For example, in some embodiments, lubricant monitoring engine 50 comprises a predictive model for determining the lubricant parameters 52 based on lubricant data 13, vibration data 15, and / or environmental data 17 where the predictive model may be trained using the enrichment data 40 or otherwise configured to integrate the enrichment data 40 with the lubricant data 13, vibration data 15, and / or environmental data 17. Thus, in some embodiments, at least some of the enrichment data 40 may configure a predictive model (e.g., define weights of the predictive model) of the lubricant monitoring engine 50 for determining lubricant parameters 52 in real-time (e.g., in intervals less than 15 minutes in duration) or near real-time (e.g., in intervals approximately between 15 minutes and one hour in duration) based on the lubricant data 13, vibration data 15 (and / or other secondary sensor data), and environmental data 17 (and / or other tertiary sensor data).

[0034] The lubricant parameters 52 may include a variety of parameters of the lubricant 3 indicative of the state, quality, and / or current performance of the lubricant 3. For example, lubricant parameters 52 may quantify the presence of water, debris, and / or other contaminants in the lubricant 3. In some embodiments, lubricant parameters 52 mayinclude such parameters as the viscosity, TAN, TBN, and / or other parameters of the lubricant 3 which may be determined by the lubricant monitoring engine 50 in real-time or near real-time.

[0035] In some embodiments, the different lubricant parameters 52 may be presented or indicated (e.g., via a computer-implemented user interface) as a nondimensional lubricant score 54 (e.g., a water content score, a debris score, a viscosity score, and the like) to the user 2 rather than as a dimensional unit to make the lubricant scores 54 more readily intelligible to the user 2. For instance, the lubricant parameters 52 may each be scaled using a baseline parameter. The baseline parameter may be indicative of issue free performance of the lubricant 3 prior to any degradation to the lubricant 3 whereby the baseline parameter may be used as a benchmark with the lubricant scores 54 reflecting a degree of divergence from the benchmark established by the baseline parameter. However, the configuration of the baseline parameter may vary in other embodiments. Additionally, the lubricant scores 54 may be updated automatically in real-time or near realtime as sensor data (e.g., lubricant data 13, vibration data 15, and environmental data 17) is received by the lubricant monitoring engine 50 from the industrial asset 1. In some embodiments, the lubricant scores 54 (or the lubricant parameters 52 themselves) may comprise rolling averages having a temporal window size defined by the provider of lubricant monitoring engine 50 and / or by the user 2.

[0036] In some embodiments, lubricant monitoring engine 50 may additionally be configured to provide the user 2 with a lubricant alert 56 in response to one of the lubricant scores 54 equaling or exceeding a predefined threshold. For instance, a water ingress alert may be provided automatically (e.g., in real-time or near real-time) in response to a water ingress score equally or exceeding a predefined threshold to thereby alert the user 2 of a potential leak or other issue in the lubricated equipment 5 that is currently resulting in water ingress into the lubricant 3.

[0037] As described above, lubricant monitoring engine 50 leverages enrichment data 40 in order to determine the lubricant parameters 52 from the industrial asset 1 supplied sensor data (e.g., lubricant data 13, vibration data 15, and environmental data 17). Particularly, the enrichment data 40 may include data characterizing (e.g., correlating) the relationships between the sensor data obtained from industrial asset 1 with the lubricant parameters 52. For example, enrichment data 40 may model, based on historical data obtained throughprevious offsite laboratory testing, the relationship between relative permittivity of the lubricant 3 and the water content of the lubricant 3. In another example, the enrichment data 40 may model the relationship between RH as captured in the environmental data 17 and relative permittivity of the lubricant 3 captured in the lubricant data 13 to adjust or calibrate or a water content score (in view of the RH data) of the lubricant 3. Thus, in some embodiments, at least some of the enrichment data 40 provided to lubricant monitoring engine 50 comprises lubricant enrichment data that models or otherwise characterizes the lubricant 3 itself and may be obtained via historical data collected through past testing (e.g., performed using an offsite laboratory) of lubricant 3 or other lubricants having at least some features in common with lubricant 3.

[0038] In some embodiments, enrichment data 40 includes equipment enrichment data associated with the lubrication equipment 5 and / or industrial asset 1 rather than the lubricant 3 itself. As an example, equipment enrichment data may model or otherwise characterize the relationship between vibration data 15, lubricant data 13, environmental data 17, and / or one or more of the lubricant parameters 52 to maximize the accuracy of the lubricant parameters 52. For instance, excess vibration in lubricated equipment 5 may be indicative of water ingress or other issues with respect to lubricant 3 that may be leveraged to improve the accuracy of lubricant monitoring engine 50 in determining lubricant parameters 52. In certain embodiments, the equipment enrichment data comprises historical data of the lubricated equipment 5 (or other equipment of industrial asset 1) collected during past operation of the lubricated equipment 5. In some embodiments, enrichment data 40 builds correlations between different data sources (e.g., lubricant data 13, vibration data 15, environmental data 17) to generate enrichment data that are not directly captured by any given sensor and thus does not comprise sensor data.

[0039] Referring to FIG. 2, another embodiment of a computer-implemented lubricant monitoring system 100 is shown. Lubricant monitoring system 100 may include features in common with the lubricant monitoring system 10 shown in FIG. 1, and shared features are labeled similarly. In this exemplary embodiment, lubricant monitoring system 100 generally includes one or more equipment sensors 104 each associated with lubricated equipment 106 of an industrial asset 102, one or more asset sensors 108 also associated with the industrial asset 102, and a lubricant monitoring engine 150 in signal communication with the equipment sensors 104 and the asset sensors 108 via, for example, the network 30.Equipment sensors 104 and asset sensors 108 may each be located at (e.g., co-located with) the industrial asset 102 such as being located at a physical facility defining the industrial asset 102. Conversely, in this exemplary embodiment, lubricant monitoring engine 150 may be at least partially located at one or more sites other than the site of the industrial asset 102. In other embodiments, lubricant monitoring engine 150 may instead be entirely located at the site (e.g., the physical facility) of industrial asset 102.

[0040] Equipment sensors 104 may be associated with their corresponding lubricated equipment 106 by monitoring one or more parameters (e.g., temperature, pressure, velocity, vibration, acoustics, conductivity, relative permittivity, and the like) of the lubricated equipment 106. Similarly, the asset sensors 108 may be associated with its corresponding industrial asset 102 by monitoring one or more parameters of the industrial asset 102 including contextual information not captured directly from equipment thereof such as local environmental conditions (e.g., temperature, barometric pressure, precipitation, RH, and the like). Further, while only a single industrial asset 102 is shown in FIG. 2, lubricant monitoring system 100 may include multiple sets of equipment sensors 104 and / or asset sensors 108 associated with a plurality of separate industrial assets 102.

[0041] In some embodiments, equipment sensors 104 may include sensor 12 and 14 shown in FIG. 1 while asset sensors 108 may include environmental sensor 16 shown in FIG. 1; however, in other embodiments, the configuration of equipment sensors 104 and / or asset sensors 108 may vary. For example, in some embodiments, equipment sensors 104 may not include each of sensors 12 and vibration sensor 14 shown in FIG. 1 and / or may include equipment sensors 104 in addition to sensors 12 and / or 14. Similarly, in certain embodiments, asset sensors 108 may not include environmental sensor 16 and / or may include asset sensors 108 in addition to environmental sensor 16.

[0042] In this exemplary embodiment, lubricant monitoring system 100 additionally includes a sensor data transmitter 120 connected or otherwise in signal communication with each of the equipment sensors 104 and asset sensors 108 associated with the industrial asset 102. Sensor data transmitter 120 may facilitate the transmission of data captured by equipment sensors 104 and asset sensors 108 across the network 30 to the lubricant monitoring engine 150. For example, the sensor data transmitter 120 may selectably adjust a sampling rate (e.g., reduce the sampling rate to limit computational demands on the ingestion engine 152 or network bandwidth limitations across network 30), atransmission or network protocol, or other parameters of the data captured by equipment sensors 104 and asset sensors 108 as part of facilitating the external transmission and / or eventual storage of the captured sensor data. In some embodiments, the sensor data transmitter 120 comprises an edge computing gateway that provides the sensor data captured by equipment sensors 104 and asset sensors 108 to the network 30 using a selected network protocol such as MQTT and the like. In addition, sensor data transmitter 120 may aggregate the various datastreams or sets captured by the equipment sensors 104 and asset sensors 108 when facilitating the transmission of said captured sensor data to the lubricant monitoring engine 150.

[0043] In this exemplary embodiment, the lubricant monitoring engine 150 of lubricant monitoring system 100 generally includes a sensor data ingestion engine 152, a sensor data enrichment engine 170, a predictive lubricant model 185, and a user interface 190 that provides a gateway for users 2 of lubricant monitoring system 100 to access the lubricant monitoring engine 150. For instance, the user interface 190 may comprise one or more input / output devices using which the user 2 may access information from the lubricant monitoring engine 150 and / or provide information (e.g., one or more selected user inputs) to the lubricant monitoring engine 150.

[0044] The sensor data ingestion engine 152 (or simply “ingestion engine 152”) of lubricant monitoring engine 150 receives information provided by the sensor data transmitter 120 (e.g., via network 30) as an aggregated datastream (indicated by arrow 122 in FIG. 2) that captures and aggregates the sensor data captured by equipment sensors 104 and the asset sensors 108. Although only a single aggregated sensor datastream 122 is shown in FIG. 2, in some embodiments, ingestion engine 152 may receive a plurality of separate aggregated sensor datastreams 122 each associated with, for example, a unique industrial asset 102. Aggregated sensor datastream 122 may aggregate various kinds of different sensor data including both equipment data captured by equipment sensors 104 and / or asset data captured by asset sensors 108.

[0045] In this exemplary embodiment, ingestion engine 152 generally includes a raw data ingestion engine or ingester 154, a data enriching engine or enricher 158, and an enriched data ingestion engine or ingester 160. Raw data ingester 154 receives aggregated sensor datastreams 122 from the sensor data transmitters 120 of one or more different industrial assets 102. Raw data ingester 154 may initially process the received aggregated sensordatastreams 122 whereby said aggregated sensor datastreams 122 may be transformed and / or filtered to provide a raw or ingested sensor datastream (indicated by arrows 155 in FIG. 2) for further processing and / or storage. In this exemplary embodiment, raw data ingester 153 stores the ingested datastream 155 in a raw data store 156 of the ingestion engine 152. In some embodiments, aggregated sensor datastream 122 may be provided to the raw data ingester 154 continuously or in batches of a predefined (e.g., user-selected) temporal size or duration (e.g., an hourly batch, a daily batch, and the like).

[0046] Raw data ingester 154 provides the ingested datastream 155 to the data enricher 158 which produces an enriched datastream or simply “enriched data” (indicated by arrow 159 in FIG. 2) from the ingested datastream 155. As used herein, the terms “enriched data” and “enriched datastream” is defined herein as data or datastreams that have been filtered to eliminate or at least mitigate spurious or erroneous data. For instance, enriched data may be generated from raw data by averaging a predefined number of datapoints of the raw data to produce a plurality of condensed datapoints of the enriched data. As another example, predefined data limits may be utilized to filter datapoints of the raw data that fall outside of said data limits which indicate that the filtered raw data is likely spurious. As a further example, rate-of-change analysis may be applied to the datapoints of the raw data to identify datapoints that exceed a predefined rate-of-change threshold. Such identified datapoints may generate an alert or may be filtered from the enriched data.

[0047] In some embodiments, the enriched datastream 159 includes estimates of one or more lubricant parameters of one or more lubricants of one or more corresponding industrial assets 102 and which are indicative of the state, quality, and / or current performance of the lubricant. For instance, the estimated lubricant parameters captured in the enriched datastream 159 may include, amount other parameters, water, debris, or other contaminant content, viscosity, TAN, and / or TBN.

[0048] As will be discussed further herein, the data enricher 158 additionally receives an enrichment datastream 180 from the enrichment engine 170 sensor data enrichment engine 170 (or simply “enrichment engine 170”) of lubricant monitoring engine 150. Particularly, data enricher 158 integrates the ingested datastream 155 received from raw data ingester 154 with the enrichment datastream 180 provided by enrichment engine 170 to produce the enriched datastream 159 containing the estimated lubricant parameters. For example, the data enricher 158 may apply the enrichment datastream 180 to theingested datastream 155 and / or vice-a-versa to produce the enriched datastream 159. In some embodiments, the enriched datastream 159 is provided in real-time or near real-time following the original collection of the sensor data by the equipment sensors 104 and / or asset sensors 108 of the given industrial asset 102.

[0049] In this exemplary embodiment, the enriched data ingester 160 of ingestion engine 152 receives the enriched datastream 159 produced by data enricher 158 and subjects the enriched datastream 159 to additional processing whereby said enriched datastream 159 may be analyzed, transformed, and / or filtered to provide an output datastream (indicated by arrows 161 in FIG. 2) that forms an output of the ingestion engine 152. In this exemplary embodiment, enriched data ingester 160 stores the output datastream 161 in an output data store 162 of the ingestion engine 152 that may, in certain embodiments, be externally accessible such as via network 30. In some embodiments, enriched datastream 159 may be provided to the enriched data ingester 160 continuously or in batches of a predefined (e.g., user-selected) temporal size or duration (e.g., an hourly batch, a daily batch, and the like).

[0050] The output datastream 161 is based on the enriched datastream 159 and may include the estimated lubricant parameters captured in the enriched datastream 159. Additionally, in some embodiments, output datastream 161 may include information beyond that contained in the enriched datastream 159 including, for example, one or more lubricant scores associated with the given lubricant of the industrial asset 102 and / or one or more lubricant alerts also associated with the given lubricant. For example, the output datastream 161 may include lubricant scores similar to the lubricant scores 54 shown in FIG. 1. Similarly, in certain embodiments, the output datastream 161 may include lubricant alerts similar to the lubricant alerts 56 shown in FIG. 1.

[0051] In this exemplary embodiment, the output datastream 161 produced by enriched data ingester 160 is provided to the user interface 190 whereby it may be accessed by the user 2. For example, the user 2 may utilize the user interface 190 to receive one or more lubricant alarms, and / or to review one or more lubricant scores or lubricant parameters captured in the output datastream 161. Additionally, in some embodiments, the user 2 may input via the user interface 190 information to the lubricant monitoring engine 150 including the ingestion engine 152. For instance, the user 2 may provide one or more user-selected thresholds used as triggers for the one or more lubricant alerts contained inthe output datastream 161. In another example, the user 2, via the user interface 190, may define a batch size of the enriched datastream 159 and / or other operational parameters of the ingestion engine 152 including providing user-selected parameters used to determine lubricant scores contained in the output datastream 161. In a further example, the user 2, via the user interface 190, may define a window size (e.g., a temporal window size having a defined, user-selected duration) for determining the one or more lubricant scores from the enriched datastream 159.

[0052] In this exemplary embodiment, the enrichment engine 170 of lubricant monitoring engine 150 generally includes one or more enrichment function 178 that provide, as an output of the enrichment engine 170, the enrichment datastream 180 to the data enricher 158 of ingestion engine 152. Additionally, although predictive lubricant model 185 is shown as separate from enrichment engine 170 in FIG. 2, in other embodiments, predictive lubricant model 185 may comprise a component or feature of the enrichment engine 170. For example, the enrichment function 178 and predictive lubricant model 185 may work together or jointly to produce the enrichment datastream 180 provided to ingestion engine 152.

[0053] Enrichment function 178 receives secondary, tertiary, and / or other contextual information from which enrichment datastream 180 is based or determined. For instance, in this exemplary embodiment, enrichment function 178 receives (or is permitted to access) a laboratory dataset 172, an asset dataset 174, and an enrichment ruleset 176. In other embodiments, the sources of contextual information from which enrichment function 178 draws may vary from that shown in FIG. 2. For example, in other embodiments, enrichment function 178 may not receive laboratory dataset 172 and / or asset dataset 174, and / or may receive additional datasets not shown in FIG. 2. In some embodiments, the laboratory dataset 172 includes historical data obtained, for example, through previous or historical offsite laboratory testing that models or otherwise relates sensor data such as previously captured historical sensor data (e.g., historical lubricant data associated with one or more historical lubricants) similar in nature (e.g., including lubricant data, vibration data, and the like) to the sensor data captured in the aggregated sensor datastream 122 and ingested datastream 155. In other words, the laboratory dataset 172 may at least partially explain or characterize the relationship between equipment sensor data (e.g.,sensor data captured by sensors like equipment sensors 104) and lubricant parameters of a selected lubricant of the industrial asset 102.

[0054] The asset dataset 174 also includes historical data but unlike the laboratory dataset 172 which is directly relates to the selected lubricant (or historical data associated with similar lubricants), asset dataset 174 pertains instead generally to the industrial asset 102 (including selected lubricated equipment 106 thereof) rather than specifically to lubricant the contained in the industrial asset 102. In other words, the historical data specific to the selected industrial asset 102 contained in asset dataset 174 may contextualize the relationships (e.g., between lubricant data and lubricant parameters) characterized by laboratory dataset 172.

[0055] For instance, the operating conditions of industrial asset 102 generally as well as the operating conditions of selected pieces of lubricated equipment 106 may, in addition to the lubricant data, affect the lubricant parameters of a given lubricant of the industrial asset 102. As an example, the (historically and / or currently) operating temperature, pressure, vibration, and the like lubricated equipment 106 may impact the lubricant parameters of lubricant of the lubricated equipment in ways not fully captured or explained by lubricant data collected from the given lubricant. As an additional example, the (historically and / or current) RH, temperature, precipitation, and the like of the ambient environment of industrial asset 102 may also impact the lubricant parameters of lubricant of the lubricated equipment in ways not fully captured or explained by lubricant data collected from the given lubricant. The relationships between such secondary, tertiary, and / or other contextual data (e.g., operating parameters beyond lubricant data of lubricated equipment 106, generalized or ambient conditions of industrial asset 102) and the current lubricant parameters of a selected lubricant of the industrial asset 102 may be at least partially explained or characterized by asset dataset 174 to assist in calibrating estimates of the current lubricant parameters of a selected lubricant that are obtained using the laboratory dataset 172.

[0056] The enrichment ruleset 176 may contain predefined (e.g., at least partially user-selected) instructions for the enrichment function 178 of enrichment engine 170 for integrating the information contained in the laboratory dataset 172 and asset dataset 174 in producing enrichment datastream 180. For example, enrichment ruleset 176 may define the influence to be accorded to the different datasets 172 and 174 in producing enrichment datastream 180, and determine when particular relationships or models between variables(e.g., relationships between selected primary, secondary, and / or tertiary data and one or more lubricant parameters) should be leveraged in producing enrichment datastream 180. As an example, enrichment datastream 180 could take the form of a predicted TBN of a selected lubricant that is based on data (e.g., obtained by equipment sensors 104) in the form of bulk resistance data.

[0057] Although enrichment ruleset 176 is shown in FIG. 2 as separate from enrichment function 178, in other embodiments, enrichment ruleset 176 may comprise a feature or component of enrichment function 178. Additionally, in other embodiments, enrichment engine 170 may not include both laboratory dataset 172 and asset dataset 174, and instead, enrichment datastream 180 may be based only on the laboratory dataset 172 or the asset dataset 174. In still other embodiments, additional datasets other than datasets 172 and 174 may be leveraged by enrichment function 178 in producing enrichment data 180.

[0058] In this exemplary embodiment, predictive lubricant model 185 is additionally leveraged by enrichment engine 170 in producing enrichment datastream 180. In some embodiments, predictive lubricant model 185 comprises a machine learning (ML) or artificial intelligence (Al) model such as a classification model and the like that is trained on data provided by enrichment engine 170. For example, predictive lubricant model 185 may be trained using the historical data contained in the laboratory dataset 172, asset dataset 174, and / or additional datasets provided by enrichment engine 170. In some embodiments, predictive lubricant model 185 may be trained or tuned using additional sources of data including, for example, ingested datastream 155, enriched datastream 159, and / or output datastream 161. In this exemplary embodiment, predictive lubricant model 185 may provide its own lubricant alerts (indicated by arrow 186 in FIG. 2) to the user interface 190 to warn the user 2 of significant or material changes to one or more lubricant parameters of a lubricant of industrial asset 102. Additionally, in some embodiments, the user 2 may interact or adjust parameters (e.g., hyperparameters) of the predictive lubricant model 185 via the user interface 190.

[0059] As described above, the user 2 may receive lubricant alerts from the ingestion engine 152 and / or predictive lubricant model 185 in this exemplary embodiment whereby the end-user may swiftly act to address the issues raised in the lubricant alerts. For example, the user 2 may adjust the operation of the industrial asset 102 such as by, forinstance, adjusting one or more operational parameters of lubricated equipment 106 of industrial asset 102. In another example, the user 2 may replace or redress the lubricant of industrial asset 102 to which the lubricant alert pertains in response to receiving such via user interface 190. In this manner, the user may act substantially more quickly (e.g., in real-time or near real-time) to limit or prevent undesirable issues associated with the lubricant alerts provided thereto compared to conventional laboratory analysis of the selected lubricants.

[0060] Referring now to FIG. 3, an embodiment of a computer system 300 is shown suitable for implementing one or more components disclosed herein. As an example, computer system 300 may be used to execute various embodiments of lubricant monitoring systems (e.g., lubricant monitoring systems 10 and 100 shown in FIGS. 1 and 2, respectively) disclosed herein.

[0061] The computer system 300 of FIG. 9 generally includes a processor 302 (which may be referred to as a central processor unit or CPU) that is in communication with memory devices including secondary storage 304, read only memory (ROM) 306, random access memory (RAM) 308, input / output (I / O) devices 310, and network connectivity devices 312. The processor 302 may be implemented as one or more CPU chips. It is understood that by programming and / or loading executable instructions onto the computer system 300, at least one of the CPU 302, the RAM 308, and the ROM 306 are changed, transforming the computer system 300 in part into a particular machine or apparatus having the novel functionality taught by the present disclosure.

[0062] Additionally, after the system 300 is turned on or booted, the CPU 302 may execute a computer program or application. For example, the CPU 302 may execute software or firmware stored in the ROM 306 or stored in the RAM 308. In some cases, on boot and / or when the application is initiated, the CPU 302 may copy the application or portions of the application from the secondary storage 304 to the RAM 308 or to memory space within the CPU 302 itself, and the CPU 302 may then execute instructions that the application is comprised of. In some cases, the CPU 302 may copy the application or portions of the application from memory accessed via the network connectivity devices 312 or via the I / O devices 310 to the RAM 308 or to memory space within the CPU 302, and the CPU 302 may then execute instructions that the application is comprised of. During execution, an application may load instructions into the CPU 302, for example load some of theinstructions of the application into a cache of the CPU 302. In some contexts, an application that is executed may be said to configure the CPU 302 to do something, e.g., to configure the CPU 302 to perform the function or functions promoted by the subject application. When the CPU 302 is configured in this way by the application, the CPU 302 becomes a specific purpose computer or a specific purpose machine.

[0063] Secondary storage 304 may be used to store programs which are loaded into RAM 308 when such programs are selected for execution. The ROM 306 is used to store instructions and perhaps data which are read during program execution. ROM 306 is a non-volatile memory device which typically has a small memory capacity relative to the larger memory capacity of secondary storage 304. The secondary storage 304, the RAM 308, and / or the ROM 306 may be referred to in some contexts as computer readable storage media and / or non-transitory computer readable media. I / O devices 310 may include printers, video monitors, liquid crystal displays (LCDs), touch screen displays, keyboards, keypads, switches, dials, mice, track balls, voice recognizers, card readers, paper tape readers, or other well-known input devices.

[0064] The network connectivity devices 312 may take the form of modems, modem banks, Ethernet cards, universal serial bus (USB) interface cards, wireless local area network (WLAN) cards, radio transceiver cards, and / or other well-known network devices. The network connectivity devices 312 may provide wired communication links and / or wireless communication links. These network connectivity devices 312 may enable the processor 302 to communicate with the Internet or one or more intranets. With such a network connection, it is contemplated that the processor 302 might receive information from the network, or might output information to the network. Such information, which may include data or instructions to be executed using processor 302 for example, may be received from and outputted to the network, for example, in the form of a computer data baseband signal or signal embodied in a carrier wave.

[0065] The processor 302 executes instructions, codes, computer programs, scripts which it accesses from hard disk, floppy disk, optical disk, flash drive, ROM 306, RAM 308, or the network connectivity devices 312. While only one processor 302 is shown, multiple processors may be present. Thus, while instructions may be discussed as executed by a processor, the instructions may be executed simultaneously, serially, or otherwise executed by one or multiple processors. Instructions, codes, computer programs, scripts,and / or data that may be accessed from the secondary storage 304, for example, hard drives, floppy disks, optical disks, and / or other device, the ROM 306, and / or the RAM 308 may be referred to in some contexts as non-transitory instructions and / or non-transitory information.

[0066] In an embodiment, the computer system 300 may comprise two or more computers in communication with each other that collaborate to perform a task. For example, but not by way of limitation, an application may be partitioned in such a way as to permit concurrent and / or parallel processing of the instructions of the application. Alternatively, the data processed by the application may be partitioned in such a way as to permit concurrent and / or parallel processing of different portions of a dataset by the two or more computers. In an embodiment, the functionality disclosed above may be provided by executing the application and / or applications in a cloud computing environment. Cloud computing may comprise providing computing services via a network connection using dynamically scalable computing resources.

[0067] Referring now to FIG. 4, an embodiment of a method 350 for monitoring a lubricant (e.g., lubricant 3 shown in FIG. 1) of an industrial asset (e.g., industrial assets 1 and 102 shown in FIGS. 1 and 2, respectively) is shown. Initially, at block 352, method 350 includes receiving by a lubricant monitoring engine (e.g., lubricant monitoring engines 50 and 150 shown in FIGS. 1 and 2, respectively) sensor data (e.g., lubricant data 13, vibration data 15, environmental data 17 shown in FIG. 1, aggregated sensor datastream 122 shown in FIG. 2) captured by a sensor (e.g., sensors 12, 14, and 16 shown in FIG. 1, sensors 104 and 108 shown in FIG. 2) of the industrial asset.

[0068] At block 354, method 350 includes receiving by the lubricant monitoring engine enrichment data (e.g., enrichment data 40 and 180 shown in FIGS. 1 and 2, respectively) characterizing a relationship between historical sensor data and one or more lubricant parameters (e.g., lubricant parameters 52 shown in FIG. 1) of one or more historical lubricants. At block 356, method 350 includes integrating by the lubricant monitoring engine the sensor data with the enrichment data to provide enriched data (e.g., enriched datastream 159 shown in FIG. 2) estimating one or more of the lubricant parameters of the lubricant. At block 358, method 350 includes providing by the lubricant monitoring engine a lubricant alert (e.g., lubricant alerts 56 shown in FIG. 1, lubricant alerts 186 shown in FIG.2) to a user (e.g., user 2 shown in FIGS. 1 and 2) that is based on the one or more estimated lubricant parameters.

[0069] Referring now to FIG. 5, another embodiment of a method 370 for monitoring a lubricant (e.g., lubricant 3 shown in FIG. 1) of an industrial asset (e.g., industrial assets 1 and 102 shown in FIGS. 1 and 2, respectively) is shown. Initially, at block 372, method 370 includes receiving by a lubricant monitoring engine (e.g., lubricant monitoring engines 50 and 150 shown in FIGS. 1 and 2, respectively) lubricant data (e.g., lubricant data 13 shown in FIG. 1) captured by a lubricant sensor (e.g., lubricant sensor 12 shown in FIG. 1) in fluid communication with the lubricant.

[0070] At block 374, method 370 includes receiving by the lubricant monitoring engine enrichment data (e.g., enrichment data 40 and 180 shown in FIGS. 1 and 2, respectively) characterizing a relationship between historical lubricant data and one or more lubricant parameters (e.g., lubricant parameters 52 shown in FIG. 1) of one or more historical lubricants. At block 376, method 370 includes integrating by the lubricant monitoring engine the lubricant data with the enrichment data to provide enriched data (e.g., enriched datastream 159 shown in FIG. 2) estimating the one or more lubricant parameters of the lubricant. At block 378, method 370 includes providing by the lubricant monitoring engine information (e.g., lubricant parameters 52, lubricant scores 54, and lubricant alerts 56 shown in FIG. 1, output datastream 161 and lubricant alerts 186 shown in FIG. 2) to a user (e.g., user 2 shown in FIGS. 1 and 2) that is based on or contains the enriched data.

[0071] While embodiments of the disclosure have been shown and described, modifications thereof can be made by one skilled in the art without departing from the scope or teachings herein. The embodiments described herein are exemplary only and are not limiting. Many variations and modifications of the systems, apparatus, and processes described herein are possible and are within the scope of the disclosure. For example, the relative dimensions of various parts, the materials from which the various parts are made, and other parameters can be varied. Accordingly, the scope of protection is not limited to the embodiments described herein, but is only limited by the claims that follow, the scope of which shall include all equivalents of the subject matter of the claims. Unless expressly stated otherwise, the steps in a method claim may be performed in any order. The recitation of identifiers such as (a), (b), (c) or (1), (2), (3) before steps in amethod claim are not intended to and do not specify a particular order to the steps, but rather are used to simplify subsequent reference to such steps.

Claims

CLAIMSWhat is claimed is:

1. A computer-implemented method for monitoring a lubricant of an industrial asset, the method comprising:(a) receiving, by a lubricant monitoring engine, sensor data captured by a sensor of the industrial asset;(b) receiving, by the lubricant monitoring engine, enrichment data characterizing a relationship between historical sensor data and one or more lubricant parameters of one or more historical lubricants;(c) integrating, by the lubricant monitoring engine, the sensor data with the enrichment data to provide enriched data estimating one or more of the lubricant parameters of the lubricant; and(d) providing, by the lubricant monitoring engine, a lubricant alert to a user that is based on the one or more estimated lubricant parameters.

2. The method of claim 1, wherein the sensor data comprises lubricant data captured by a lubricant sensor in fluid communication with the lubricant.

3. The method of claim 2, wherein the lubricant data comprises one or more of an electrical conductivity, a relative permittivity, and a quantity of foreign particles of the lubricant.

4. The method of claim 1, wherein the sensor data comprises at least one of a vibration sensor, an acoustic sensor, an acoustic sensor, a pressure sensor of lubricated equipment of the industrial asset that comprises the lubricant.

5. The method of claim 1 , wherein the sensor data comprises an environmental sensor configured to monitor one or more ambient conditions of the industrial asset.

6. The method of claim 5, wherein the one or more ambient conditions comprises an ambient relative humidity (RH) of the industrial asset.

7. The method of claim 1 , wherein the lubricant alert is provided to the user in at least one of real-time and near real-time following (a).

8. The method of claim 1, wherein (d) comprises providing by a trained predictive lubricant model of the lubricant monitoring engine the lubricant alert.

9. The method of claim 8, wherein the trained predictive lubricant model is trained at least partially using the enrichment data.

10. A computer-implemented method for monitoring a lubricant of an industrial asset, the method comprising:(a) receiving, by a lubricant monitoring engine, lubricant data captured by a lubricant sensor in fluid communication with the lubricant;(b) receiving, by the lubricant monitoring engine, enrichment data characterizing a relationship between historical lubricant data and one or more lubricant parameters of one or more historical lubricants;(c) integrating, by the lubricant monitoring engine, the lubricant data with the enrichment data to provide enriched data estimating the one or more lubricant parameters of the lubricant; and(d) providing, by the lubricant monitoring engine, information to a user that is based on or contains the enriched data.

11. The method of claim 10, wherein the lubricant data comprises one or more of an electrical conductivity, a relative permittivity, and a quantity of foreign particles of the lubricant.

12. The method of claim 10, wherein the enrichment data comprises at least one of laboratory data containing historical lubricant data and asset data containing historical equipment data other than the lubricant data.

13. The method of claim 10, wherein the enrichment data comprises asset data containing historical environmental data associated with the industrial asset.

14. The method of claim 10, wherein the information is provided to the user in at least one of real-time and near real-time following (a).

15. The method of claim 10, wherein (d) comprises providing by a trained predictive lubricant model of the lubricant monitoring engine the information.

16. A computer-readable medium storing executable code which, when executed by a processor, causes the processor to:receive, by a lubricant monitoring engine, sensor data captured by a sensor of an industrial asset containing a lubricant;receive, by the lubricant monitoring engine, enrichment data characterizing a relationship between historical sensor data and one or more lubricant parameters of one or more historical lubricants;integrate, by the lubricant monitoring engine, the sensor data with the enrichment data to provide enriched data estimating one or more of the lubricant parameters of the lubricant; andprovide, by the lubricant monitoring engine, a lubricant alert to a user that is based on the one or more estimated lubricant parameters.

17. The computer-readable medium of claim 16, wherein the sensor data comprises lubricant data captured by a lubricant sensor in fluid communication with the lubricant.

18. The computer-readable medium of claim 17, wherein the lubricant data comprises one or more of an electrical conductivity, a relative permittivity, and a quantity of foreign particles of the lubricant.

19. The computer-readable medium of claim 16, wherein the executable code, when executed by a processor, causes the processor to:provide the lubricant alert to the user in at least one of real-time and near real-time once the lubricant monitoring engine has received the sensor data captured by the sensor of the industrial asset.

20. The computer-readable medium of claim 16, wherein the executable code, when executed by a processor, causes the processor to:provide by a trained predictive lubricant model of the lubricant monitoring engine the lubricant alert.29

Images