Method for generating estimation model for oil characteristics, method for diagnosing oil characteristics, and system for diagnosing oil characteristics

Abstract

The purpose of the present invention is to provide a technique for optically quantifying a compound of which a color does not change due to oxidative degradation.　Another aspect of the present invention provides a method for diagnosing oil characteristics, the method being characterized by: using an optical sensor having a light source and a detector that detects light emitted from the light source to acquire an absorption spectrum in a wavelength range of 800 nm to 3000 nm of an oil containing an additive having a maximum molar absorption coefficient value of 50 or less in the ultraviolet visible wavelength range of 250 nm to 800 nm; and inputting data based on the absorption spectrum into an estimation model implemented in an information processing device to predict the concentration of the additive.

Description

Method for generating an estimation model of oil characteristics, method for diagnosing oil characteristics, and system for diagnosing oil characteristics

[0001] The present invention relates to an oil diagnostic technology, particularly to the maintenance of large machinery that uses industrial oils such as lubricating oil, insulating oil, and processing oil, and relates to a technology suitable for monitoring machinery by measuring changes in the composition of lubricating oil or other oils that occur with use, and by assessing the remaining life of the oil and predicting the condition of the machinery.

[0002] Diagnosis of the properties of lubricating oils used in rotating parts such as bearings and gears is an important technology for the maintenance and repair of large rotating machinery, such as wind power generator gearboxes, air compressors, ships, power generation turbines, construction machinery, agricultural machinery, cutting machines, pumps, and reduction gears for railway vehicles.

[0003] In addition to lubricating oils, insulating oils are used in transformers and other devices for electrical insulation, and diagnosing the properties of insulating oils is also important. Processing oils are also used in machining. There are various types of processing oils for various purposes, such as cutting oil, press oil, heat treatment oil, rust prevention oil, and cleaning oil. In this specification, industrial oils such as lubricating oil, insulating oil, and processing oil are sometimes collectively referred to as oil.

[0004] Lubricating oils are classified into various types depending on their intended use, such as engine oil, turbine oil, hydraulic oil, bearing oil, sliding surface oil, gear oil, compressor oil, and cutting oil. Various additives are blended into the base oil (oil used as the base material) to ensure that each type of lubricating oil meets the required performance. Additives are also blended into other oils to achieve the properties required for each type.

[0005] In recent years, machine condition monitoring has often adopted a strategy to minimize the lifecycle cost of the machine. Large machines such as power generation turbines use large amounts of lubricating oil, and changing the lubricating oil requires stopping the machine, which can result in power generation losses and production stoppages. In addition, costs for purchasing and shipping new oil, oil change work, and waste oil disposal are also required, so it is desirable to use the lubricating oil for as long as possible. Refrigerant fluids in electric vehicles and data centers also undergo oil diagnosis, and replacement or hardware repairs are carried out. Similarly, the color and other characteristics of insulating oil in transformers are monitored.

[0006] Recently, from the perspective of carbon neutrality, automobiles and other vehicles that use large amounts of petroleum-based fuels are being electrified, and fuel demand will decrease in the future. However, there are often no alternatives for industrial oil, so there is a need to minimize its use by extending the oil change interval, etc. This is because reducing oil consumption reduces carbon dioxide emissions. However, overlooking oil deterioration and contamination can lead to machine breakdowns.

[0007] Regarding the diagnosis of lubricating oil properties, it is necessary to define and distinguish between "deterioration" and "contamination." Broadly speaking, it is necessary to diagnose two types of deterioration: (1) oxidative deterioration of lubricating oil over time, and (2) contamination by external contaminants such as water, dust, and wear particles.

[0008] (1) Oxidative degradation of lubricating oils includes degradation due to oxidation of the base oil and degradation due to the consumption of additives. Oxidative degradation of lubricating oils leads to a decrease in wear resistance, changes in viscosity and viscosity index, a decrease in rust prevention, and a decrease in corrosion prevention. As a result, it can accelerate wear and material fatigue in gearboxes. While it is desirable to use oil for as long as possible, any abnormal deterioration or contamination requires a prompt oil change and equipment inspection.

[0009] As a conventional diagnostic technology for lubricating oil, Patent Document 1 discloses a system including a sensor that measures the optical properties of a lubricating oil containing an additive having a diphenylamine skeleton, a storage device that stores correlation data, and a processing device that determines the remaining amount of the additive having a diphenylamine skeleton in the lubricating oil based on the data obtained by the sensor and the correlation data.

[0010] Japanese Patent Application Publication No. 2022-118670

[0011] In Patent Document 1, a transmission-type optical sensor equipped with a visible light source and a light-receiving element is used to measure the chromaticity of the lubricating oil, and the remaining amount of an additive having a diphenylamine skeleton in the lubricating oil is quantified from the chromaticity of the lubricating oil obtained by the optical sensor. This method is excellent as a method for measuring the properties of oils such as lubricating oils remotely without contact.

[0012] However, measuring the properties of lubricating oil by color is difficult to quantify because additives do not change color due to oxidation and deterioration.

[0013] Therefore, an object of the present invention is to provide a technique for optically quantifying compounds that do not change color due to oxidative degradation.

[0014] One aspect of the present invention is a method for generating an estimation model of oil characteristics, using an information processing system including an input device, an output device, a processing device, and a storage device, the information processing system including an estimation model generation unit that generates an estimation model capable of machine learning, and inputting an absorption spectrum obtained by transmitting light with at least a portion of wavelengths between 800 nm and 3000 nm through an oil containing an additive, and a value reflecting the characteristics of the oil, into the estimation model generation unit, and generating an estimation model using a value based on the absorption spectrum as an explanatory variable and a value reflecting the characteristics of the oil as a target variable.

[0015] Another aspect of the present invention is a method for diagnosing oil characteristics using a diagnostic system consisting of an information processing device that implements the above-mentioned estimation model, in which an absorption spectrum obtained by transmitting light with at least a portion of wavelengths between 800 nm and 3000 nm through an oil to be diagnosed of the same type as the oil containing the additive is input to the diagnostic system, a value based on the absorption spectrum is input to the estimation model, and a value reflecting the characteristics of the oil to be diagnosed is obtained from the estimation model.

[0016] Another aspect of the present invention is an oil characteristic diagnosis system including an information processing device that implements the above estimation model.

[0017] Another aspect of the present invention is a method for diagnosing oil characteristics, which comprises using an optical sensor having a light source and a detector that detects light emitted from the light source to obtain an absorption spectrum in the wavelength range of 800 nm to 3000 nm of oil containing an additive whose maximum molar absorption coefficient is 50 or less in the ultraviolet-visible wavelength range of 250 nm to 800 nm, and inputting data based on the absorption spectrum into an estimation model implemented in an information processing device to predict the concentration of the additive.

[0018] According to the present invention, it is possible to optically quantify compounds that do not change color due to oxidative degradation. Other problems, configurations, effects, etc. will become clear from the following description of the embodiments.

[0019] 1. Structural formula showing the molecular structure of benzene. 2. Structural formula showing the molecular structure of naphthalene. 3. Structural formula showing the molecular structure of phenol. 4. Structural formula showing the molecular structure of aniline. 5. Structural formula showing the oxidation reaction mechanism of BHT. 6. Structural formula showing the molecular structure of a phosphorus-based additive. 7. Schematic diagram of an optical sensor that measures near-infrared absorption spectra. 8. Schematic diagram of another optical sensor that measures near-infrared absorption spectra. 9. Structural formula showing the structure of a sulfur-containing additive. 10. Structural formula showing the molecular structure of a phosphoric acid alkyl ester-based additive. 11. Structural formula showing the molecular structure of a polyacrylate-type dispersion viscosity modifier. 12. Block diagram of an oil diagnostic system according to an embodiment. 13. Flowchart of an oil diagnostic method according to an embodiment. 14. Flowchart of the measured data collection process according to an embodiment. 15. Graph showing the relationship between usage time and oil viscosity, total acid number, and antioxidant concentration. 16. Graph of an example of a near-infrared spectrum. 17. Flowchart of a property estimation model generation process according to an embodiment. 18. Graph of an example of a near-infrared spectrum obtained by second-order differentiation. 19. Flowchart of the oil property estimation process according to an embodiment. Graph showing the consistency between predicted values ​​and actual measured values ​​using the estimation model of the embodiment. Schematic diagram of a lubricant monitoring system for a wind turbine generator of the embodiment. Conceptual diagram of a rotating part equipped with a lubricant sensor. Flow diagram showing a lubricant diagnostic process according to the embodiment. Graph showing the concept of antioxidant concentration in lubricant stored over time. Graph showing an example of displaying results. Structural formula (1) of an organic compound that can be quantified using near-infrared absorption spectrum. Structural formula (2) of an organic compound that can be quantified using near-infrared absorption spectrum. Structural formula (3) of an organic compound that can be quantified using near-infrared absorption spectrum. Structural formula (4) of an organic compound that can be quantified using near-infrared absorption spectrum.

[0020] The embodiments will be described in detail with reference to the drawings. However, the present invention should not be interpreted as being limited to the description of the embodiments shown below. Those skilled in the art will easily understand that the specific configuration can be changed without departing from the concept or purpose of the present invention.

[0021] In the configurations of the embodiments described below, the same parts or parts having similar functions are denoted by the same reference numerals in different drawings, and redundant explanations may be omitted.

[0022] When there are multiple elements with the same or similar functions, they may be described using the same reference numeral with different subscripts. However, when there is no need to distinguish between multiple elements, the subscripts may be omitted.

[0023] The terms "first," "second," "third," etc. used in this specification are used to identify components and do not necessarily limit the number, order, or content of the components. Furthermore, numbers used to identify components are used in different contexts, and numbers used in one context do not necessarily indicate the same configuration in another context. Furthermore, this does not prevent a component identified by a certain number from also serving the function of a component identified by another number.

[0024] In order to facilitate understanding of the invention, the position, size, shape, range, etc. of each component shown in the drawings, etc. may not represent the actual position, size, shape, range, etc. Therefore, the present invention is not necessarily limited to the position, size, shape, range, etc. disclosed in the drawings, etc.

[0025] All publications, patents, and patent applications cited herein are hereby incorporated by reference in their entirety.

[0026] Elements referred to in the singular herein include the plural unless the context clearly indicates otherwise.

[0027] In this specification, the wavelength range of 250 nm to 800 nm is referred to as the ultraviolet-visible range, and the wavelength range of 800 nm to 2500 nm is referred to as the near-infrared range.

[0028] In this specification, a large molar absorption coefficient at a certain wavelength indicates that the light absorption intensity at that wavelength is large, and a small molar absorption coefficient at a certain wavelength indicates that the light absorption intensity at that wavelength is small.

[0029] In accordance with the embodiment, a machine monitoring method using changes in optical absorption intensity in the near-infrared region of additive-containing oils such as lubricating oils achieves accurate quantification of the concentration of additives whose maximum molar absorption coefficient in the ultraviolet-visible region is 50 or less, or even 20 or less, when diagnosing oil deterioration and contamination using a near-infrared optical sensor. In principle, if transmittance = 1 - absorptance, then in the embodiment, transmittance and absorptance have the same meaning. Furthermore, transmittance and absorptance can also be expressed as percentages.

[0030] Lubricating oils include engine oil, turbine oil, hydraulic oil, bearing oil, slideway oil, gear oil, compressor oil, and cutting oil. Lubricating oils are composed of base oil and additives. Additives include antioxidants, rust inhibitors, antifoaming agents, viscosity index improvers, oiliness improvers, extreme pressure additives, detergents and dispersants, pour point depressants, and emulsifiers. Oils used for purposes other than lubrication include transformer oil, cleaning oil, and cutting oil. For many oils, the degree of additive consumption due to use can be used to determine when to change the oil or to indicate any abnormalities in the machine. The concentration of additives can be quantified by measuring changes in absorbance in the near-infrared region.

[0031] One example described in the working examples is a diagnostic method for oil containing an additive whose molar absorption coefficient in the wavelength range of 250 nm to 800 nm, i.e., in the ultraviolet-visible region, is 50 or less, and the concentration of the additive is quantified to determine the state of the oil by measuring the intensity of light transmitted through the oil with an optical sensor having a detector sensitive in the wavelength range of 800 nm to 2500 nm, i.e., in the near-infrared region.

[0032] With this configuration, when detecting changes in the properties of the oil (object of measurement) by measuring changes in the light absorption intensity in the wavelength range of 250 nm to 800 nm using an optical sensor, the condition of the oil can be accurately determined by accurately quantifying the concentration of an additive that does not change color even when oxidized.

[0033] <Function of additives> Lubricating oils are composed of base oils and additives. Base oils include mineral oils made from petroleum, high-performance synthetic oils, bio-oils made from plants, and biodegradable oils. Lubricating oil deterioration is an oxidation reaction involving oxygen. Antioxidants, a typical additive, are added to prevent base oil oxidation, and base oil oxidation usually begins when the antioxidants are depleted to a certain extent. When base oil oxidation begins, changes in viscosity occur, causing changes in the thickness of the lubricating film and other deterioration in lubrication properties, so an oil change is generally recommended. Therefore, by monitoring the level of antioxidant consumption, it is possible to estimate the remaining life of the lubricating oil.

[0034] Among additives, extreme-pressure additives and anti-friction agents function to prevent wear on the sliding surfaces of parts. Consumption of these additives accelerates part wear, so the remaining life of a lubricant is sometimes determined in terms of the concentration of the additives. Therefore, by monitoring the consumption of the additives, it is possible to estimate the remaining life of a lubricant. The lubricant's life is determined when either the amount or concentration of the antioxidant, the additive, or the anti-friction agent reaches a threshold value. At this point, an oil change is generally recommended.

[0035] Other additives such as rust inhibitors, antifoaming agents, viscosity index improvers, oiliness improvers, detergent dispersants, pour point depressants, and emulsifiers are also known to be consumed as the lubricant is used, and thresholds are sometimes set based on the functionality of the lubricant and used as indicators for determining whether to change the oil.

[0036] <Deterioration and Coloration of Additives> Deterioration of organic compounds is generally caused by oxidation due to reaction with oxygen and active radicals generated from oxygen.

[0037] Compounds with aromatic rings tend to produce colored compounds when oxidized. Compounds without aromatic rings, such as aliphatic hydrocarbons and polyalkylene oxides (PAOs) used as base oils, and additives such as carbamates, esters of alkyl alcohols and phosphoric acid, surfactants, dispersants, and antifoaming agents, tend not to produce colored compounds when oxidized. This is because non-aromatic compounds have no electronic conjugation systems or only small conjugation systems.

[0038] <Colors of Organic Compounds> Explain the relationship between the structure and color of organic compounds. There are two ways in which colors appear: the color of emitted light and the color that appears due to light absorption. The color of organic compounds appears when they absorb light of specific wavelengths in the visible light range between 400 nm and 800 nm. Specifically, for example, on the color wheel, red and green, yellow and blue, etc., are located opposite each other, and these are called complementary colors; absorbing blue light with a short wavelength will make the color appear yellow, and absorbing red light with a long wavelength will make the color appear green.

[0039] Light absorption means that a molecule can absorb the energy of that light. There are multiple modes of light absorption by molecules depending on the wavelength. Light absorption in the visible light range is due to the valence electron excitation of the molecule, which occurs when an electron rises from a relatively low energy orbit to another high energy orbit. At this time, if there is no orbital overlap between the orbital where the electron is initially located and the orbital where the electron is located after excitation, the electron cannot move. Bonds between atoms are formed by the overlap of electron orbitals.

[0040] Here we will explain σ bonds and π bonds in organic compounds. For example, a carbon atom can use four hands to bond with other atoms or molecules. A σ bond is formed when a carbon atom uses one hand to bond with another atom such as hydrogen. σ bonds have very high bond energy and are stable because of their strong bond strength. σ bonds are connected by only one hand, so they can rotate freely.

[0041] On the other hand, pi bonds are formed using two or three hands. These are called double bonds or triple bonds. In a double bond, the atoms extend their hands perpendicular to the bond axis between the atoms, and then the bond is formed with great effort. In a double bond, there is one sigma bond and one pi bond, and the bond is weak. A triple bond is made up of one sigma bond and two pi bonds. Compared to sigma bonds, pi bonds are unstable and highly reactive. However, compounds with aromatic rings such as benzene, substituted benzene, naphthalene, and anthracene have an electronic state called conjugation, and the electrons are spread throughout the aromatic ring, resulting in a very stable structure.

[0042] Next, we will explain the relationship between atomic bonds and color. The energy difference in electron transitions in σ bonds, that is, the energy difference between the bonding orbital and antibonding orbital of a σ bond, is 500 kJ / mol or more, which corresponds to a wavelength of 200 nm or less, so only ultraviolet light, which is not visible as a color, is absorbed. In conjugated π bonds, the spread of electrons has the effect of reducing the transition energy, which increases the wavelength of the absorbed light, and light in the ultraviolet range of 200 nm to 400 nm is absorbed.

[0043] <Oxidation of compounds with aromatic rings> Figure 1 shows the molecular structure of benzene. Figure 2 shows the molecular structure of naphthalene. Figure 3 shows the molecular structure of phenol. Figure 4 shows the molecular structure of aniline.

[0044] Among compounds with aromatic rings, compounds with highly symmetric structures, such as benzene (Figure 1) and naphthalene (Figure 2), have no electron imbalance and are therefore very low in reactivity and chemically stable. In other words, they are not easily oxidized.

[0045] On the other hand, in aromatic compounds with substituents, such as phenol (Figure 3) and aniline (Figure 4), the symmetry of the molecular structure is low and there is a bias in the electrons within the molecule, so chemical reactions are more likely to occur at low-energy bonds, such as the C-O bond in phenol.

[0046] Phenol compounds and phenylamine compounds are typical antioxidants added to most lubricating oils. The antioxidant's function is based on this reactivity. In other words, the antioxidant itself oxidizes, preventing the base oil and other additives from oxidizing and losing their functionality.

[0047] It is known that phenol-based antioxidants and amine-based antioxidants generate quinone-based compounds that strongly absorb visible light when oxidized (see, for example, Patent Document 1).

[0048] Figure 5 shows the reaction in which a typical phenolic antioxidant, BHT, is oxidized to produce a benzoquinone derivative. For example, comparing benzene and p-benzoquinone, benzene has an absorption maximum of 255 nm and is colorless, whereas p-benzoquinone has an absorption maximum of 440 nm and is a bright yellow compound. For example, even when an alkyl group is bonded to the benzene ring, electronic conjugation does not extend to the alkyl group, so there is no significant change in the absorption wavelength even with alkyl-substituted phenols such as BHT.

[0049] Figure 6 shows the structures of the phosphorus-based additives TPP and TPPT. Among the compounds commonly used as phosphorus-based antioxidants and extreme pressure agents are ester compounds of phosphoric acid with phenol and substituted phenol, such as TPP and TPPT. These function as antioxidants. Furthermore, when heated on the sliding surface, they decompose to produce phenol (or substituted phenol), which is then oxidized to produce quinone. Compounds with aromatic rings can also produce compounds other than quinone, but generally, they tend to produce colored compounds.

[0050] <Compounds that do not become colored even when oxidized> Deterioration of organic compounds is generally caused by oxidation due to reaction with oxygen and active radicals generated from oxygen.

[0051] Compounds without aromatic rings, such as aliphatic hydrocarbons and polyalkylene oxides (PAOs) used as base oils, and additives such as carbamates, esters of alkyl alcohols and phosphoric acid, surfactants, dispersants, and antifoaming agents, tend not to produce colored compounds when oxidized. This is because non-aromatic compounds have no electronic conjugation system or only a small conjugation system.

[0052] <Molar absorption coefficient> Aromatic compounds are prone to producing colored compounds when oxidized, but from the perspective of ultraviolet-visible absorption spectra, they tend to have stronger absorption in the ultraviolet range compared to compounds without aromatic rings.

[0053] The molar absorption coefficient ε is defined as the optical density of a 1 molar solution per 1 cm of light path, i.e., the absorbance of a certain substance per 1 cm of 1 molar solution for light of a certain wavelength, and is expressed by equation (1). A = -log T = -log(I / IO) = ε x C x l ... Equation (1) A: absorbance, T: transmittance, I: transmitted light intensity, IO: incident light intensity, C: concentration (mol / L), ε: molar absorption coefficient (L / (mol·cm)), l: light path length (cm). The larger the molar absorption coefficient ε, the stronger and more sensitive the color, and the greater the sensitivity of quantification. Aromatic compounds generally have a molar absorption coefficient ε of 100 or more at their maximum absorption wavelengths in the ultraviolet to visible range, from 250 nm to 800 nm. For example, ε for benzene is 180. Adding a substituent to the benzene ring shifts the absorption peak to longer wavelengths, and ε tends to increase. In other words, aromatic compounds can be measured with good sensitivity in the ultraviolet to visible range.

[0054] On the other hand, the molar absorption coefficient ε at the maximum absorption wavelength in the ultraviolet to visible region of wavelengths from 250 nm to 800 nm of compounds without aromatic rings is 50 or less. In other words, compounds without aromatic rings have low sensitivity in the ultraviolet to visible region.

[0055] <Additives involved in and not involved in lubricating oil coloration due to oxidation> As mentioned above, additives that are involved in lubricating oil coloration due to oxidation are those with aromatic rings. Additives that are not involved in coloration are compounds that do not have aromatic rings. There is a demand for monitoring the concentrations of additives that are not involved in coloration.

[0056] <Quantification of additives using near-infrared absorption spectroscopy> Through research by the inventors, it was discovered that it is possible to quantify additives in lubricating oils that are resistant to discoloration due to oxidative degradation, i.e., compounds that do not have aromatic rings, which have previously been difficult to quantify, by measuring near-infrared light absorption spectroscopy in the wavelength range of 800 nm to 2500 nm using an optical sensor.

[0057] 7 is a diagram showing one form of optical sensor. The optical sensor 700 incorporates a light source 701 that emits at least a portion of near-infrared light with wavelengths of, for example, 800 nm to 3 μm (3000 nm), and a detector 703 that can detect the light emitted from the light source 701. The light emitted from the light source 701 (indicated by the arrow in the figure) passes through the lubricating oil 702 to be measured, and the transmitted light is measured by the detector 703. It is sufficient for the optical sensor 700 to obtain an absorption spectrum of at least a portion of the wavelengths of near-infrared light with wavelengths of 800 nm to 3 μm (3000 nm).

[0058] Near-infrared spectroscopy measures the vibrational energy of atomic bonds in organic compounds. The near-infrared wavelength range only corresponds to overtones and combination tones of the fundamental tone, and the fundamental tone is not detected, so absorption intensity is low. The reason for the low absorption is that overtones and combination tones are forbidden transitions with a low probability of occurring.

[0059] The advantage of near-infrared spectroscopy, which measures low-probability forbidden transition absorption, is its excellent transparency and is less susceptible to the concentration saturation problem that occurs with ultraviolet-visible spectroscopy and mid-infrared spectroscopy. This means that there is no need to make the optical path length extremely short when measuring liquids such as lubricating oil, and an optical path length of approximately 3 mm to 20 mm can be selected.

[0060] Spectral analysis for quantifying additives in lubricating oil involves spectral preprocessing, as shown in the following representative example. In the first step, smoothing is performed to remove spectral noise. For example, a method is used in which the centered moving average method is applied to a selected interval of approximately 3 to 20 adjacent points. In the second step, a second-order differential filter is applied to the spectrum, which allows wavelengths with large spectral changes to be extracted, making it possible to extract peaks from spectra with complex overlaps and unclear peak positions, which is typical of near-infrared absorption spectra. Either of these two steps can be performed first.

[0061] Next, multivariate analysis, a type of machine learning, is performed on the preprocessed spectra. A predictive method, PLS (Partial Least Square) regression analysis, can be used to quantify additive concentrations. A calibration curve is created by creating a dataset with the spectra as explanatory variables and additive concentrations determined by quantitative analysis methods such as HPLC (High Performance Liquid Chromatography) as the target variables, and then performing PLS regression analysis. Cross-validation can be used to validate PLS regression analysis using the dataset. The additive concentration estimation model created is used to estimate additive concentrations in lubricating oils with unknown additive concentrations.

[0062] <Method of measurement by sensor> The near-infrared absorption spectrum measurement of the lubricating oil is performed by an optical sensor 700 having a light source that generates light of a wavelength in the near-infrared region and a detector that detects wavelengths in the near-infrared region. The lubricating oil to be measured is measured by a detector 703, which detects the light intensity of light emitted from a light source 701 after it passes through the lubricating oil 702.

[0063] FIG. 7 shown above is a diagram illustrating one form of sensor, but it is also possible to have the light emitted from the light source 701 pass through the lubricating oil 702 and enter the detector 703 using means such as reflection by a mirror, focusing by a lens, or passing through a prism.

[0064] 8 is a diagram showing another form of sensor. In an optical sensor 700A, a light source 701 and a detector 703 are arranged on the same plane and in contact with lubricating oil 702, with a reflector 704 installed on the opposite side, and light emitted from the light source 701 (indicated by the arrow in the figure) is reflected by the reflector 704 and received by the detector 703. Even in this form, a lens, mirror, or prism may be installed along the optical path.

[0065] <Target Additives> In this example, the properties of additives that do not contain aromatic rings in their molecular structure can be optically measured. Examples of additives made of organic compounds that do not contain aromatic rings are shown below.

[0066] Figure 9 shows the structure of a sulfur-containing additive. Figure 10 shows the molecular structure of a phosphoric acid alkyl ester-based additive, where R is an alkyl group. Figure 11 shows the molecular structure of a polyacrylate-type dispersant viscosity modifier.

[0067] <Scope of application> Types of oils containing additives include engine oil, turbine oil, hydraulic oil, bearing oil, slideway oil, gear oil, compressor oil, cutting oil, insulating oil, cutting processing oil, press processing oil, heat treatment oil, rust preventative oil, cleaning oil, etc. Types of additives include antioxidants, rust inhibitors, antifoaming agents, viscosity index improvers, oiliness improvers, extreme pressure additives, detergent dispersants, pour point depressants, emulsifiers, etc.

[0068] 12 shows an example of a system used for diagnosing engine oil in the embodiment. The diagnostic system 1200 in the embodiment is configured using a normal computer such as a server. The diagnostic system 1200 includes an input device 1210, an output device 1220, and a processing device 1230, and stores programs and data for processing in a storage device 1240. The storage device 1240 may be configured by combining known storage devices such as semiconductor memories and magnetic disk devices.

[0069] The storage device 1240 includes an estimation model generation unit 1250 and an oil property estimation unit 1260. In this embodiment, the estimation model generation unit 1250 and the oil property estimation unit 1260 are included in the same device, but they may also be configured as separate devices.

[0070] The estimation model generation unit 1250 includes a measurement database 1251 , a preprocessing unit 1252A, a learning database 1253 , and a multivariate analysis unit 1254 .

[0071] The oil property estimation unit 1260 includes a preprocessing unit 1252 B, an estimation model 1261 , and a characteristic conversion table 1262 .

[0072] 13 shows an example of engine oil diagnosis using the diagnosis system 1200. First, actual measurement data is acquired from actual engine oil to generate an actual measurement database 1251. This is done by collecting engine oil samples and analyzing the engine oil using known methods (S1310).

[0073] The preprocessing unit 1252A of the estimation model generation unit 1250 prepares explanatory variables and objective variables for model generation from the actual measurement data and stores them in the learning database 1253. The multivariate analysis unit 1254 generates an oil property estimation model 1261 using the explanatory variables and objective variables (S1320).

[0074] The oil property estimation unit 1260 estimates the oil property using the obtained estimation model 1261 (S1330).

[0075] In this example, the viscosity of new engine oil is 20 cP, and it is recommended to change the oil when the viscosity reaches 25 cP with use. This engine oil does not contain an antioxidant with an aromatic ring, although viscosity increases due to consumption of the antioxidant.

[0076] The antioxidant, consisting of the sulfur-containing additive shown in Figure 9, was used in the engine oil, and its concentration in the new oil was 3 wt%. The molar absorption coefficient of this antioxidant at the maximum absorption wavelength between 250 nm and 400 nm was 42.

[0077] FIG. 14 is a flow diagram of the measurement data collection process S1310. The above engine oil was applied to an automobile engine and continuously operated. Every 10 hours (S1311), 10 ml of engine oil was sampled (S1312), and the near-infrared absorption spectrum was measured using the optical sensor shown in FIG. 7 or 8 (S1313). The wavelength resolution of the near-infrared absorption spectrum was 1 nm. The antioxidant concentration of the sampled engine oil was quantified using LC / MS, a type of high-performance liquid chromatography (HPLC). The viscosity and total acid number of the engine oil were measured using any known method (S1314). The RGB color coordinates were measured using the method described in Patent Document 1 (S1315). The measured near-infrared absorption spectrum, antioxidant concentration, viscosity, total acid number, and RGB color coordinates were linked to time information and recorded in the measurement database 1251 (S1316). The sample acquisition amount and acquisition time interval are merely examples, and the oil characteristic analysis method may be arbitrarily selected from known methods.

[0078] 15 shows a graph of the relationship between usage time and oil viscosity, total acid number, and antioxidant concentration as an example of data representation in the actual measurement database 1251. By preparing such relationships as reference data, it is possible to obtain the total acid number from the antioxidant concentration, and the viscosity from the antioxidant concentration.

[0079] 7 or 8, the near-infrared absorption spectrum of the sampled engine oil was measured (S1313), and the RGB color coordinates were measured in the visible light range using the method described in Patent Document 1 (S1315). These data were also linked to time and stored in the actual measurement database 1251. Note that the RGB color coordinate measurement is performed to confirm whether measurement using visible light is possible, and may be omitted in actual operation.

[0080] Figure 16 shows an example of the near-infrared absorption spectrum of engine oil. In this example, the absorbance is shown for wavelengths from 1550 nm to 1950 nm. The curves show the spectra after different periods of use.

[0081] Next, explanatory variables are generated using the measured near-infrared absorption spectrum, and an oil property estimation model is generated using the antioxidant concentration measured using LC / MS as the response variable (S1320).

[0082] In generating the model, it is possible to use a known machine learning method in which explanatory variables are input and a target variable is output. In this example, a PLS regression analysis was performed.

[0083] 17 is a flow diagram of the oil property estimation model generation process S1320. This process is performed by the estimation model generation unit 1250, which is a general computer, and the processing unit 1230 executes software.

[0084] First, the preprocessing unit 1252A reads out data of the near-infrared absorption spectrum at a certain time point (S1321) from the actual measurement database 1251. The preprocessing of the near-infrared absorption spectrum in the preprocessing unit 1252A includes smoothing by the Savitzky-Golay (SG) method using data from nine adjacent points (S1322) and second-order differentiation of the spectrum (S1323).

[0085] Figure 18 shows a graph of the results of differentiating the spectrum twice. The curves represent the derivatives of the spectrum at different times after use. Differentiation can emphasize the difference in the near-infrared absorption spectrum over time. Differentiation may not be necessary in some cases. Differentiation may also be performed only once. Alternatively, differentiation may be performed three or more times.

[0086] The twice-differentiated near-infrared absorption spectrum is stored in the learning database 1253 as an explanatory variable x, and the antioxidant concentration at the same time as the objective variable y.

[0087] The multivariate analysis unit 1254 performed PLS regression analysis using the explanatory variable x and the objective variable y (S1324) to generate an oil property estimation model 1261. After the PLS regression analysis, cross-validation was performed (S1325). The generated estimation model 1261 was implemented in the oil property estimation unit 1260.

[0088] 19 is a flow diagram of the oil property estimation process S1330 using the generated estimation model 1261. This process is performed by the oil property estimation unit 1260, which is a general computer, through software processing.

[0089] First, the near-infrared absorption spectrum of the engine oil whose properties are to be determined is acquired and input from the input device 1210 of the diagnostic system 1200 (S1331). The near-infrared absorption spectrum is acquired by the optical sensor shown in Fig. 7 or 8. One of the features of the embodiment is that the near-infrared absorption spectrum can be collected contactlessly and remotely.

[0090] The near-infrared absorption spectrum is subjected to preprocessing such as smoothing and second differentiation by the preprocessing unit 1252B in the same manner as when the estimation model was generated in Fig. 17 (S1332). The preprocessed near-infrared absorption spectrum is input to the oil property estimation model, and the antioxidant concentration is estimated (S1333).

[0091] The oil property estimation unit 1260 can have a characteristic conversion table 1262 (which does not necessarily have to be in table form, and may be data showing the relationship between antioxidant concentration and viscosity as shown in FIG. 15 ) that uses all or part of the actual measurement database 1251 to mutually convert antioxidant concentration, viscosity, and total acid value.

[0092] The viscosity of the engine oil is estimated (S1334) based on the estimated antioxidant concentration and the characteristic conversion table 1262. Using the results of this analysis, it was found that the viscosity of the engine oil reaches 25 cP when the antioxidant concentration is reduced to 40% of the initial concentration.

[0093] Figure 20 is a graph showing the consistency between predicted and measured values ​​of antioxidant concentration using estimation model 1261. The reference value is the actual measured value of the sample, and the PLS regression equation is obtained as a result of analysis using the PLS model. The predicted value is the result predicted from the actual measured value using this regression equation (estimation model), and if the reference value and the predicted value match well, a good PLS model has been constructed. Using Figure 20 as a calibration curve, the concentration of a sample with an unknown additive concentration can be quantified.

[0094] On the other hand, the correlation coefficient between the RGB color coordinates of the collected oil and the antioxidant concentration was only 0.5, and it was found that it is difficult to predict the viscosity using color coordinates for organic compounds that do not have a benzene ring.

[0095] In the above example, the viscosity of the engine oil is finally determined and output from the output device 1220, but as will be described later, the total acid number, concentration, or usage time may also be output. Furthermore, the estimation model was generated using multivariate analysis using software capable of executing PLS without using special hardware, but other well-known machine learning methods using a GPU (Graphic Processor Unit) or the like may also be adopted.

[0096] In the above example, the near-infrared absorption spectrum was used as the explanatory variable x, and the antioxidant concentration was used as the response variable y. However, values ​​reflecting other oil characteristics (such as other additive concentrations, viscosity, total acid number, and usage time) can also be used as the response variable.

[0097] This is an example of a diagnosis of hydraulic oil (hereafter referred to as hydraulic oil) for a large ship. This hydraulic oil contained 2% of a phosphoric acid alkyl ester extreme pressure agent, as shown in Figure 10, in new oil. The acid value of this hydraulic oil was 1.6 when new, and it was supposed to be changed when the acid value reached 2. From past experience, it was known that the oil would need to be changed after an average of 3,000 hours of use.

[0098] Hydraulic oil was continuously used under the same conditions as those used on large ships, with 15 ml sampled every 10 hours. The near-infrared absorption spectrum of the sampled oil was obtained using the optical sensor shown in Figure 7. The acid value, viscosity, and contamination level (mass method) were also determined using the sampled oil. The correlation coefficients between the total acid value, viscosity, and contamination level obtained in the sampled oil and the antioxidant concentration were calculated, and the correlation coefficient between the acid value and antioxidant concentration was found to be the highest at 0.98. This demonstrates that the acid value can be determined by quantifying the antioxidant concentration.

[0099] The near-infrared absorption spectrum was used as the explanatory variable in PLS regression analysis, and the antioxidant concentration was used as the target variable. After 11-point smoothing and double differentiation of the near-infrared absorption spectrum, PLS regression analysis was performed. Cross-validation was then performed on the results.

[0100] The analysis results showed that it is possible to predict the antioxidant concentration from the near-infrared absorption spectrum, and that it is also possible to predict the acid value from the antioxidant concentration.

[0101] An example of gas engine oil diagnosis is shown below. New gas engine oil contains 1% of a polyacrylate dispersant viscosity modifier with the structure shown in Figure 11. The viscosity of the new oil is 10 cP, and it is recommended to change the oil when the viscosity drops to 13 cP.

[0102] This gas engine was operated continuously, and an optical sensor capable of measuring near-infrared absorption spectra was installed in a sight glass (a part made of a transparent material that is installed so that the color of the oil can be seen) installed in the engine oil piping.

[0103] The near-infrared absorption spectrum was measured every hour while the engine was running, continuing for 1,000 hours. A small amount of engine oil was also sampled every 20 hours to measure the viscosity and viscosity modifier concentration. The results of the viscosity and viscosity modifier concentration measurements can be shown in a graph like that shown in Figure 15, similar to Example 2.

[0104] A PLS regression analysis was performed using the acquired near-infrared absorption spectrum, separately measured viscosity data, and viscosity modifier concentration data to generate an estimation model for viscosity modifier concentration. Using this estimation model, it was confirmed that the viscosity and viscosity modifier concentration can be predicted from the near-infrared absorption spectrum of engine oil.

[0105] In this embodiment, the configurations of the first to third embodiments are applied to a system and method for monitoring lubricating oil in a wind power generator. This embodiment is a system for monitoring lubricating oil supplied to a mechanical drive unit of a wind power generator. This system includes a diagnostic system 1200 shown in FIG. 12.

[0106] A storage device in the monitoring system stores additive concentration data that chronologically stores the concentration of additives in the lubricating oil as a reference, and the diagnostic system 1200 estimates the time when the additive concentration in the lubricating oil, obtained from the near-infrared absorption spectrum of the lubricating oil, will reach a predetermined threshold value.

[0107] (1. Overall System Configuration) Figure 21 shows a schematic diagram of a lubricant monitoring system for a wind power generator having a lubricant supply system. Inside the nacelle 3 of the wind power generator 1, there are a main shaft 31, a gearbox 33, a generator 34, and bearings such as yaw and pitch bearings (not shown), all of which are supplied with lubricant from an oil tank 37. The system also has the general components of a wind power generator, such as a hub 4, a nacelle bulkhead 30, a shrink disk 32, a main frame 35, a radiator 36, and a coupling 38.

[0108] 21 , multiple wind turbines 1 are usually installed on the same site, and these are collectively referred to as a farm 200a, etc. Each wind turbine 1 is equipped with various sensors (not shown) in its lubricating oil supply system, and sensor signals reflecting the state of the lubricating oil are collected in a server 210 in the nacelle 3.

[0109] Furthermore, sensor signals obtained from the server 210 of each wind power generator 1 are sent to an aggregation server 220 arranged for each farm. Data from the aggregation server 220 is sent to a central server 240 via a network 230. Data from other farms 200b and 200c is also sent to the central server 240. The central server 240 can also send instructions to each wind power generator 1 via the aggregation server 220 and server 210. The central server 240 basically has the functions of the diagnostic system 1200 shown in FIG. 12, and the system of this embodiment is capable of remote monitoring of oil that does not have a benzene ring.

[0110] (2. Sensor Arrangement) Fig. 22 is a conceptual diagram of a rotating part equipped with a lubricant sensor. Lubricant is supplied to a rotating part 302 from a lubricant supply device 301 such as a pump. The lubricant supply device 301 is connected to an oil tank 37 and receives the supply of lubricant. The rotating part 302 is, for example, a gearbox 33 or any other general part where mechanical contact occurs, and is not particularly limited.

[0111] The optical sensor 304 is disposed in the lubricating oil flow path etc. in order to detect the state of the lubricating oil. Specific examples of the optical sensor 304 are shown in FIG.

[0112] In this embodiment, a transparent measurement unit 303 is provided in a flow path (near the end of the lubricant path) branching off from the lubricant flow path connected to the lubricant drain port of the rotating part 302, and a portion of the lubricant is introduced into this measurement unit 303. An optical sensor 304 is then installed in the measurement unit 303. The measurement unit 303 is not provided in the main lubricant flow path in order to adjust the flow rate of the lubricant in the measurement unit 303 to a flow rate suitable for detecting the state of the lubricant. The lubricant discharged from the rotating part 302 returns to the oil tank 37 via a filter 305. Note that the filter 305 is not essential. The optical sensor 304 measures the near-infrared absorption spectrum of the oil. The state of the lubricant can be evaluated based on the temporal change in the near-infrared absorption spectrum of the lubricant.

[0113] In this embodiment, the optical sensor 304 includes an optical sensor equipped with a near-infrared light source and a light-receiving element. The optical sensor acquires the near-infrared absorption spectrum of the lubricating oil. The optical sensor 304 acquires the near-infrared absorption spectrum by transmitting near-infrared light from the near-infrared light source through the oil and detecting the near-infrared light that has transmitted through the oil with a light-receiving element that has sensitivity according to the wavelength. The acquired near-infrared absorption spectrum reflects the oil's absorptivity or transmittance for light of each wavelength. The acquired near-infrared absorption spectrum and the estimation model are used to determine the amount of remaining additives in the lubricating oil, and to perform deterioration diagnosis and remaining life diagnosis.

[0114] The quality of lubricating oil deteriorates with use and it no longer performs its original function. For this reason, maintenance such as replacement is required depending on the degree of quality deterioration. In order to know the timing of such maintenance, it is useful for the efficiency of maintenance management to be able to remotely monitor data that can be collected by optical sensors 304 installed on-site. The data collected by the optical sensors 304 is collected, for example, in a server 210 in the nacelle 3, and then sent via an aggregation server 220 that aggregates data within the farm 200 to a central server 240 that aggregates data from multiple farms.

[0115] However, for analyses that require equipment for measurement, such as LC (liquid chromatography), FT-IR (Fourier transform infrared spectroscopy), and NMR (nuclear magnetic resonance), it is necessary to collect lubricant samples as appropriate and analyze them using separately provided equipment. The results of these LC, FT-IR, and NMR measurements are also stored as data in the central server 240, and it is desirable to aggregate the data and take this data into consideration when understanding the properties of the lubricant.

[0116] The aggregated data may include not only data related to lubricants but also data indicating the operating status of the wind turbine. For example, the wind turbine output value (the higher the value, the faster the lubricant deteriorates), the actual operating time (the longer the value, the faster the lubricant deteriorates), the machine temperature (the higher the value, the faster the lubricant deteriorates), the shaft rotation speed (the faster the lubricant deteriorates), etc. These data can be collected from sensors with known configurations installed at various locations on the wind turbine or from control signals from the device.

[0117] (3. Lubricant Diagnosis Flow) Figure 23 is a flow diagram showing the lubricant diagnosis process according to this embodiment. The process shown in Figure 23 is performed under the control of any of the server 210, aggregation server 220, or central server 240 in Figure 20. In the following example, it is assumed that the process is performed by the central server 240. Functions such as calculation and control are realized by software stored in the server's storage device being executed by a processor, and the specified processes are realized in cooperation with other hardware. Note that functions equivalent to those configured by software can also be realized by hardware such as an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit).

[0118] When the central server 240 performs control, it has multiple wind power generators 1 under its control, so the following processing is performed for each wind power generator. This processing is basically a repeated process, and the start timing is set by a timer or the like, for example, starting at midnight every day (S601). Alternatively, the central server 240 can perform the processing at any timing in response to an operator's instruction.

[0119] In step S602, the central server 240 checks when the lubricant needs to be replaced. The initial value of the replacement time can be calculated based on the physical properties, for example, by using the Arrhenius reaction rate, assuming that the lubricant is operating at its design temperature, and the remaining life can be set as an initial value. This replacement time can be updated later in step S610 based on actual measurement data.

[0120] If it is time to change the lubricating oil, the lubricating oil is changed in step S603. Since changing the lubricating oil is normally performed by a worker, the central server 240 displays and notifies the worker when and what to change.

[0121] If it is not time to change the lubricant, in process S604, the central server 240 performs a diagnosis using sensor data. As sensor data, in addition to the near-infrared absorption spectrum of the lubricant obtained by an optical sensor, oil temperature, oil pressure, particle concentration in the lubricant, and the like that can be measured using conventional technology can be used. The data collected by the optical sensor 304 is sent to the central server 240, and the central server evaluates the characteristics of the lubricant, for example, by comparing the oil temperature, oil pressure, and particle concentration in the lubricant obtained from the sensor with predetermined thresholds.

[0122] If the diagnosis result in step S605 is abnormal, the lubricating oil is changed in step S603. If no abnormality is found, step S606 is carried out.

[0123] In this embodiment, the near-infrared absorption spectrum of the lubricating oil is used, and the B / R value of the oil, as disclosed in the conventional Patent Document 1, can also be acquired and used. For example, in step S605, if the B / R value, based on the R, G, and B values ​​of an optical sensor, changes from a decrease to an increase, it is determined that there is an abnormal contamination. In this way, step S605 can also be determined using the G / R value, B value, G value, and ΔE value. Patent Document 1 provides detailed information on such evaluation of oil characteristics using color information and a calibration curve.

[0124] In S605, using the correlation between viscosity and the amount of remaining additive, it is determined that there is a viscosity abnormality when the viscosity corresponding to the amount of remaining additive estimated from the near-infrared absorption spectrum measured by the optical sensor exceeds a predetermined threshold. It is also possible to determine that there is an abnormality when the amount of remaining additive becomes smaller than a predetermined threshold without calculating the viscosity. The method of estimating the amount of remaining additive using the near-infrared absorption spectrum is as explained in Examples 1 to 3.

[0125] In step S606, the near-infrared absorption spectrum, chromaticity measurement data, etc. are input to the central server 240, and the data is stored in chronological order.

[0126] From the perspective of preventive and planned maintenance of wind turbines, it is desirable to perform predictive diagnosis of lubricant deterioration based on the transition in the concentration of additives contained in the lubricant before determining that an abnormality exists.

[0127] Figure 24 is a graph showing the concept of antioxidant concentration in lubricating oil stored over time. The horizontal axis represents time (months), and the vertical axis represents antioxidant concentration. For example, the antioxidant concentration is observed at fixed points, and the antioxidant concentration up to 60 months is plotted. A significant relationship is observed between the elapsed time and the antioxidant concentration, and for example, the antioxidant concentration decreases linearly with time.

[0128] In this example, in step S607, the viscosity threshold is set to 200, and the time to replace the additive is estimated when the viscosity estimated from the additive concentration measurement results stored in chronological order reaches 200. Various known methods may be used as the estimation method. If actual measured values ​​are available, a known method of extrapolating data can be used, assuming that the viscosity increases monotonically. Furthermore, if the viscosity changes in a more complex manner, a known method such as function fitting (curve fitting) can be used.

[0129] In this embodiment, the near-infrared absorption spectrum measured by the optical sensor is stored over time, and the deterioration level of the lubricating oil is estimated based on the stored spectrum.

[0130] The replacement timing estimation result obtained in step S607 can be displayed as a lubricant diagnosis result (step S608).

[0131] 25 shows an example of the display of the results of process S610. Since it is predicted that the viscosity will reach 200 in 50 months, the new replacement time can be set to a time before that (for example, half a month before). Process S610 completes one cycle of processing, and in process S602 of the next cycle, judgment processing is performed according to the new replacement time.

[0132] For example, after S608, the near-infrared absorption spectrum and chromaticity data measured by the optical sensor can be displayed on the display screen of the lubricant diagnosis results. By displaying the lubricant deterioration state in color on the display screen in this way, workers can visually recognize the lubricant deterioration state. This helps workers, for example, to roughly grasp the lubricant deterioration state when visually inspecting the lubricant state on-site.

[0133] Figures 26A to 26C show examples of organic compounds that can be quantified using the near-infrared absorption spectra measured with the optical sensor described in Examples 1 to 4. Structural formulas (a) to (w) are all antioxidants. The names of the structural formulas from (g) onwards are as follows: (g) Triphenyl phosphite (h) Tris(2,4-ditert-butylphenyl) phosphite (i) Isodecyl diphenyl phosphite (j) 2,2'-Methylenebis(4,6-di-tert-butylphenyl) 2-ethylhexyl phosphite (k) 3,9-Bis(2,6-di-tert-butyl-4-methylphenoxy)-2,4,8,10-tetraoxa-3,9-diphosphaspiro [5.5] undecane (l) 3,9-Bis(octadecyloxy)-2,4,8,10-tetraoxa-3,9-diphosphaspiro[5.5] undecane (m) Tris(nonylphenyl) phosphite (n) diphenylamine (o) substituted diphenylamine (p) substituted diphenylamine (q) 4,4'-Bis(α,α-dimethylbenzyl)diphenylamine (r) N,N'-Di-sec-butyl-1,4-phenylenediamine (s) N-(1,3-Dimethylbutyl)-N'-phenyl-1,4-phenylenediamine (t) N-Isopropyl-N'-phenyl-1,4-phenylenediamine (u) N,N'-Diphenyl-1,4-phenylenediamine (v) 1-Anilinonaphthalene (w) 6-Ethoxy-2,2,4-trimethyl-1,2-dihydroquinoline Note that R shown in (o) in the figure represents a linear or branched alkyl group having 2 to 20 carbon atoms, or an alkyl-substituted phenyl group.

[0134] Figure 27 shows examples of organic compounds that can be quantified using the near-infrared absorption spectrum measured by the optical sensor described in Examples 1 to 4. The structural formula in Figure 26 is used as a detergent dispersant.

[0135] In principle, near-infrared quantification is possible for organic compounds regardless of whether they contain a benzene ring, and the techniques described in the examples are applicable to organic compounds in general. This is because the wavelengths at which interatomic vibrations such as C-H and O-H occur are determined by the molecular structure. However, compounds containing benzene rings, particularly phenol and phenylamine structures, are prone to coloration due to oxidative degradation, making the RGB color diagnosis described in Patent Document 1 possible. For example, diphenylamine antioxidants, which can be quantified using the ΔE and B values ​​of visible light, can also be quantified using near-infrared absorption spectra.

[0136] However, visible light sensors for RGB color diagnosis are inexpensive, while near-infrared sensors are expensive. By combining the two depending on the application and the target additive, such as prioritizing RGB color diagnosis for organic compounds that have a benzene ring and for which color diagnosis is possible, and using near-infrared absorption spectra for those for which color diagnosis is difficult, cost-effective quantification is possible.

[0137] As described above, this embodiment uses near-infrared absorption spectra from an optical sensor to detect the remaining amounts of many types of oil additives, including antioxidants, rust inhibitors, antifoaming agents, viscosity index improvers, oiliness improvers, extreme-pressure additives, detergents and dispersants, pour point depressants, and emulsifiers. This allows for proper maintenance, such as lubricating oil changes, to prevent wind turbine malfunctions. It also makes it possible to optimize the lubricating oil change cycle. Furthermore, viscosity can be measured easily, and installing an optical sensor inside the nacelle enables online remote monitoring of lubricating oil deterioration.

[0138] In this example, we have described a method and system for monitoring by installing an optical sensor in the lubricating oil of a rotating part. However, it is also possible to sample the lubricating oil inside the rotating part during inspection, measure it with an optical sensor outside the rotating part, and perform a similar diagnosis.

[0139] According to this embodiment, when detecting changes in the oil composition by measuring the change in the absorption spectrum of the oil (object of measurement) in the near-infrared wavelength range using an optical sensor, it is possible to quantify the concentration of additives that do not change color even when oxidized and deteriorated, which has previously been difficult to quantify using color measurements, and to accurately determine the condition of the oil.

[0140] According to the above embodiment, efficient oil maintenance management can be realized, which reduces energy consumption, reduces carbon emissions, prevents global warming, and contributes to the realization of a sustainable society.

[0141] Diagnostic system 1200, estimation model generation unit 1250, oil property estimation unit 1260, actual measurement data collection process S1310, property estimation model generation process S1320, oil property estimation process S1330

Claims

1. A method for generating an estimation model of oil characteristics, using an information processing system having an input device, an output device, a processing device, and a storage device, the information processing system having an estimation model generation unit that generates an estimation model capable of machine learning, inputting an absorption spectrum obtained by transmitting light with at least a portion of wavelengths between 800 nm and 3000 nm through an oil containing an additive, and a value reflecting the characteristics of the oil into the estimation model generation unit, and generating an estimation model using a value based on the absorption spectrum as an explanatory variable and a value reflecting the characteristics of the oil as a target variable.

2. The method for generating an estimation model of oil characteristics according to claim 1, wherein the wavelength of the light is in the range of 800 nm to 2500 nm.

3. A method for generating an estimation model of oil characteristics as described in claim 1, wherein the oil contains an organic compound having no aromatic ring as the additive, and the value reflecting the characteristics of the oil is correlated with the amount of the organic compound.

4. A method for generating an estimation model of oil characteristics as described in claim 1, wherein the oil contains, as the additive, an organic compound having a maximum molar absorption coefficient of 50 or less in the ultraviolet-visible wavelength range of 250 nm to 800 nm, and the value reflecting the characteristics of the oil is correlated with the amount of the organic compound.

5. A method for generating an estimation model of oil characteristics as described in claim 1, wherein the explanatory variables are values ​​obtained by differentiating the absorption spectrum one or more times.

6. A method for generating an estimation model of oil characteristics as described in claim 1, wherein the value reflecting the oil characteristic is the concentration of the additive.

7. The method for generating an estimation model of oil characteristics according to claim 1, wherein the optical path length of light passing through the oil is 1 mm to 20 mm.

8. The method for generating an estimation model of oil characteristics according to claim 1, wherein the estimation model generation unit performs multivariate analysis using PLS regression analysis.

9. A method for diagnosing oil characteristics using a diagnostic system consisting of an information processing device implementing the estimation model described in claim 1, comprising: inputting an absorption spectrum obtained by transmitting light having at least a portion of a wavelength between 800 nm and 3000 nm through an oil to be diagnosed of the same type as the oil containing the additive into the diagnostic system; inputting a value based on the absorption spectrum into the estimation model; and obtaining a value reflecting the characteristics of the oil to be diagnosed from the estimation model.

10. The method for diagnosing oil characteristics according to claim 9, further comprising inputting a value obtained by one or more times differentiating the absorption spectrum into the estimation model.

11. The method for diagnosing an oil characteristic according to claim 9, wherein the value reflecting the oil characteristic is a concentration of the additive.

12. The method for diagnosing oil characteristics as described in claim 9, wherein the diagnostic system is capable of using data to convert a value reflecting the oil characteristics into at least one of the viscosity, total acid number, and usage time of the oil, and outputs at least one of the viscosity, total acid number, and usage time of the oil.

13. A method for diagnosing oil characteristics as described in claim 9, further comprising inputting color information obtained by transmitting light in the ultraviolet-visible range of wavelengths from 250 nm to 800 nm through an oil to be diagnosed that is the same type as the oil containing the additive, into the diagnostic system, and estimating the characteristics of the oil using the color information and a calibration curve.

14. An oil characteristic diagnostic system comprising an information processing device implementing the estimation model according to claim 1.

15. A method for diagnosing oil characteristics, comprising: using an optical sensor having a light source and a detector for detecting light emitted from the light source, acquiring an absorption spectrum in the wavelength range of 800 nm to 3000 nm of an oil containing an additive whose maximum molar absorption coefficient is 50 or less in the ultraviolet-visible wavelength range of 250 nm to 800 nm; and inputting data based on the absorption spectrum into an estimation model implemented in an information processing device to predict the concentration of the additive.

Images