Oil liquid remote monitoring system and monitoring method thereof

Abstract

The invention relates to the technical field of oil liquid detection, in particular to an oil liquid remote monitoring system and a monitoring method thereof, and the system comprises an oil liquid component monitoring module, a spectral feature analysis module, a component cross interference compensation module, an abnormal component screening module and an intelligent early warning module. According to the invention, continuous tracking of trace elements and chemical substances in the oil liquid is realized through real-time remote monitoring and data analysis of the spectrometer, monitoring of metal elements and oxides is more accurate by using a data processing technology, tiny changes of components can be captured in real time, and through detailed analysis of the spectral absorptivity, the detection accuracy of the oil liquid is improved. The system can identify potential anomalies and allow timely intervention at the initial stage of change, so that equipment failure or performance reduction is avoided, coupling weight and deviation value analysis are comprehensively utilized, understanding of complex interaction is greatly enhanced, and a comprehensive decision support basis is provided for risk management and early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of oil fluid detection, and particularly to an oil fluid remote monitoring system and a monitoring method thereof. Background Art

[0002] The technical field of oil fluid detection includes quality monitoring and analysis methods for industrial and automotive oil fluids such as lubricating oil and hydraulic oil. The core content of this technical field is to evaluate the performance status and service life by monitoring the chemical and physical properties of the oil fluid. From a systematic introduction, the technical field of oil fluid detection involves from simple physical property measurements such as temperature and viscosity to complex chemical composition analyses such as the detection of metal wear particles and additive concentrations. This technology can help prevent mechanical failures and maintain system efficiency, and is commonly applied to the maintenance management of mechanical equipment.

[0003] Among them, an oil fluid remote monitoring system refers to a system that remotely monitors and analyzes the state of the oil fluid through remote technology. The technical matters addressed cover remote data collection, transmission, and analysis and processing of the oil fluid. Specifically, it is solved by the method of collecting oil fluid data with sensors installed on the equipment and sending it to a remote server for processing through a wireless network. The means used include but are not limited to online sensors, remote communication interfaces, and data analysis software, which work together to achieve real-time state monitoring of the oil fluid.

[0004] The prior art relies on periodic sample analysis, unable to achieve continuous monitoring, resulting in data delay, making it impossible to intervene in a timely manner when initial changes occur in the quality of the oil fluid. In addition, the prior art ignores the complex interactions between metal wear particles and additives, limiting the ability to comprehensively evaluate the performance of the oil fluid. Due to the lack of real-time component interaction analysis and trend tracking, it is difficult to accurately predict the rate of oil fluid quality decline and the key influencing factors, increasing the difficulty of identifying abnormal changes in the oil fluid, and at the same time leading to unreasonable setting of the oil fluid replacement cycle, increasing oil fluid consumption and maintenance costs. Summary of the Invention

[0005] In order to solve the technical problems existing in the prior art, such as relying on periodic sample analysis, being unable to achieve continuous monitoring, resulting in data delay, making it impossible to intervene in a timely manner when initial changes occur in the quality of the oil fluid. In addition, the prior art ignores the complex interactions between metal wear particles and additives, limiting the ability to comprehensively evaluate the performance of the oil fluid. Due to the lack of real-time component interaction analysis and trend tracking, it is difficult to accurately predict the rate of oil fluid quality decline and the key influencing factors, increasing the difficulty of identifying abnormal changes in the oil fluid, and at the same time leading to unreasonable setting of the oil fluid replacement cycle, increasing oil fluid consumption and maintenance costs, the embodiments of the present invention provide an oil fluid remote monitoring system and a monitoring method thereof. The technical solutions are as follows:

[0006] On the one hand, an oil fluid remote monitoring system is provided. The system includes:

[0007] The oil fluid composition monitoring module remotely collects spectral data through a spectrometer, analyzes the metal element and oxide concentrations, viscosity parameters, and moisture content in the oil fluid, calculates the change rate of each component concentration, and generates composition dynamic monitoring data.

[0008] Based on the composition dynamic monitoring data, the spectral feature analysis module analyzes the spectral absorption rate of the oil fluid, calculates the change rate of the absorption rate gradient, screens out the spectral points with a change rate exceeding the standard, and generates a spectral difference identifier.

[0009] Based on the spectral difference identifier, the composition cross-interference compensation module extracts the spectral absorption rate change characteristics of each component, calculates the change coupling weight, identifies the abnormal components affecting the interaction of parameters, determines the deviation value of the cross-influence, and generates a coupling influence adjustment result.

[0010] Based on the coupling influence adjustment result, the abnormal component screening module calculates the duration and change rate of the abnormal components, compares the change pattern of the original component data, determines the deviation amplitude of the abnormal components, and analyzes the fluctuation law to form an abnormal fluctuation evaluation index.

[0011] Based on the abnormal fluctuation evaluation index, the intelligent warning module analyzes the change trend of the abnormal component concentration in the oil fluid, calculates the risk level of the abnormal components, and extracts the oil fluid risk monitoring signal.

[0012] On the other hand, the composition dynamic monitoring data includes the metal element concentration change rate, oxide concentration change rate, viscosity value, and moisture content. The spectral difference identifier includes key wavelength points, absorption rate gradient change values, and out-of-standard spectral points. The coupling influence adjustment result includes metal element coupling weight, oxide coupling weight, and parameter cross-influence result. The abnormal fluctuation evaluation index includes abnormal duration, abnormal change rate, and deviation analysis result of baseline data. The oil fluid risk monitoring signal includes risk level classification, risk component identification result, and remote alarm transmission data.

[0013] On the other hand, the oil fluid composition monitoring module includes:

[0014] The element separation module remotely collects spectral data through a spectrometer, separates and extracts metal elements and oxides, measures the absorption peak intensity of the elements, eliminates background interference signals, matches the characteristic wavelengths of the elements, and generates target element concentration data.

[0015] Based on the target element concentration data, the physical parameter extraction sub-module detects viscosity parameters and moisture content, calculates the variation trend of viscosity with temperature, determines the influence of moisture content on spectral characteristics, corrects the spectral shift caused by environmental factors, and obtains the characteristic values of oil physical parameters;

[0016] The dynamic change calculation sub-module calls the characteristic values of the oil physical parameters, calculates the change rate of each component concentration, determines the increasing and decreasing trend of the concentration over time, judges whether the change rate exceeds the standard range, calculates the increment and ratio of each parameter, and generates component dynamic monitoring data.

[0017] On the other hand, the spectral characteristic analysis module includes;

[0018] The spectral data analysis sub-module, based on the component dynamic monitoring data, extracts the spectral absorption rates of the oil in different wavelength intervals, identifies the positions of the absorption peaks in the wavelength intervals, corrects the influence of background noise on the absorption rate, determines the stability of the spectral signal, and obtains the spectral absorption rate distribution data;

[0019] The absorption rate gradient calculation sub-module calls the spectral absorption rate distribution data, calculates the change gradient of the absorption rate in adjacent wavelength intervals, determines the positive and negative trends of the change gradient, screens the wavelength intervals with abnormal absorption rate changes, and obtains the spectral gradient change value;

[0020] The spectral anomaly screening sub-module calls the spectral gradient change value, screens the spectral points with a change rate exceeding the standard, eliminates the abnormal absorption rates caused by short-term fluctuations, analyzes the absorption characteristics of the wavelength intervals, determines the corresponding relationship between the wavelength intervals and the component concentration changes, and generates spectral difference identifiers.

[0021] On the other hand, the formula used to calculate the change gradient of the absorption rate in adjacent wavelength intervals is:

[0022]

[0023] Determine the positive and negative trends of the change gradient, screen the wavelength intervals with abnormal absorption rate changes, and obtain the spectral gradient change value;

[0024] Where G λ represents the absorption rate gradient of the wavelength interval, represents the spectral absorption rate at wavelength λ2, represents the spectral absorption rate at wavelength λ1, represents the spectral absorption rate at the i-th wavelength point, represents the average value of the spectral absorption rates of all wavelength points, and n represents the total number of wavelength data points.

[0025] On the other hand, the component cross-interference compensation module includes;

[0026] Based on the spectral difference identification, the component coupling weight calculation sub-module extracts the change trends of metal elements, oxides, viscosity, and moisture content at different wavelengths, determines the synchronous change rate between components, calculates the component coupling correlation degree, and adjusts the abnormal deviation in the coupling relationship to obtain the component coupling weight value;

[0027] The cross-influence deviation determination sub-module calls the component coupling weight value, determines the influence of the change in metal element concentration on the oxide generation rate, analyzes the influence intensity of the change in viscosity on the fluctuation of moisture content, determines the interference degree of components on adjacent parameters, and calculates the interference offset value to obtain the cross-influence deviation value;

[0028] The abnormal interference adjustment sub-module calls the cross-influence deviation value, identifies the abnormal components affecting the interaction of parameters, eliminates the error data caused by the abnormal components, adjusts the proportion distribution of the abnormal parameters, and generates the coupling influence adjustment result.

[0029] On the other hand, the calculation of the component coupling correlation degree adopts the formula:

[0030]

[0031] And adjust the abnormal deviation in the coupling relationship to obtain the component coupling weight value;

[0032] Among them, C ij represents the coupling correlation degree between component i and component j, X it represents the concentration value of component i at time t, X jt represents the concentration value of component j at time t, represents the average concentration of component i at all time points, represents the average concentration of component j at all time points, and n represents the total number of observed time points.

[0033] On the other hand, the abnormal component screening module includes;

[0034] The abnormal persistence analysis sub-module extracts the time series data of abnormal components based on the coupling influence adjustment result, determines the change trend of abnormal components at different time points, calculates the duration interval of the abnormal state, and obtains the abnormal persistence parameter;

[0035] The change rate determination sub-module calls the abnormal persistence parameter, calculates the concentration change rate of abnormal components at key time nodes, analyzes the increasing and decreasing trend of the rate, determines the stability of the change amplitude, screens abnormal components whose rate fluctuation exceeds the standard, and obtains the abnormal change rate value;

[0036] The short-term fluctuation elimination sub-module calls the abnormal change rate value, compares the change pattern of the abnormal component with the fluctuation trend of the original component data, identifies the short-term abnormal fluctuation data, eliminates the error data caused by random fluctuations, and forms an abnormal fluctuation evaluation index.

[0037] On the other hand, the intelligent early warning module includes;

[0038] The trend recognition sub-module, based on the abnormal fluctuation evaluation index, measures the difference in component concentration at the differential time point, analyzes the increasing and decreasing trend of the concentration over time, identifies the direction of trend change, calculates the fluctuation amplitude, and obtains the abnormal trend characteristic value;

[0039] The risk assessment sub-module calls the abnormal trend characteristic value, calculates the risk change level of the abnormal component, measures the fluctuation range of the change level, analyzes the risk evolution process of the abnormal component, divides the risk level standard, and classifies the abnormal component to obtain the risk level classification result;

[0040] The alarm trigger sub-module calls the risk level classification result, screens the abnormal components whose risk levels reach the warning standard, marks the risk signal, sets up the remote alarm trigger condition, and obtains the oil fluid risk monitoring signal.

[0041] On the other hand, an oil fluid remote monitoring method is provided. This method is applied to an oil fluid remote monitoring system and includes the following steps:

[0042] S1: Analyze the metal, oxide, viscosity, and moisture content according to the spectral data remotely collected by the spectrometer, calculate the concentration change rate, and use time series comparison to obtain the component dynamic monitoring data;

[0043] S2: Based on the component dynamic monitoring data, calculate the gradient change rate of the spectral absorption rate, screen the key spectral points, and obtain the spectral difference identifier;

[0044] S3: Based on the spectral difference identifier, calculate the change coupling weight of each component, measure the interaction effects of metal, oxide, viscosity, and moisture, screen the components with abnormal interactions, calculate the cross-interference deviation, and eliminate the interference error to obtain the coupling effect adjustment result;

[0045] S4: Based on the coupling effect adjustment result, calculate the duration and change rate of the abnormal component, compare the change pattern of the original component, and screen the fluctuation area of the component deviation to obtain the abnormal fluctuation evaluation index;

[0046] S5: Based on the abnormal fluctuation evaluation index, analyze the change trend of the abnormal component, calculate the risk level of the abnormal component, and screen the high-risk signals to obtain the oil fluid risk monitoring signal.

[0047] The beneficial effects brought by the technical solutions provided in the embodiments of the present invention at least include:

[0048] Through real-time remote monitoring of spectrometers and data analysis, continuous tracking of trace elements and chemical substances in oil is achieved. Using data processing technology, the monitoring of metal elements and oxides is made more accurate, and minute changes in composition can be captured in real time. Through detailed analysis of spectral absorption rates, the system can identify potential anomalies at the initial stage of changes, allowing for timely intervention to avoid equipment failures or performance degradation. In addition, by comprehensively using coupling weight and deviation value analysis, the understanding of complex interactions is greatly enhanced, providing a comprehensive decision-making support basis for risk management and early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0050] Figure 1 It is a schematic diagram of the system of the present invention;

[0051] Figure 2 It is a schematic diagram of the system framework of the present invention;

[0052] Figure 3 It is a flowchart of the oil component monitoring module of the present invention;

[0053] Figure 4 It is a flowchart of the spectral feature analysis module of the present invention;

[0054] Figure 5 It is a flowchart of the component cross-interference compensation module of the present invention;

[0055] Figure 6 It is a flowchart of the abnormal component screening module of the present invention;

[0056] Figure 7 It is a flowchart of the intelligent early warning module of the present invention;

[0057] Figure 8 It is a flowchart of the method steps of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0058] The following describes the technical solutions in the present invention in conjunction with the drawings.

[0059] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to give examples, illustrations or explanations. Any embodiment or design solution described as an "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of the word "example" is intended to present concepts in a specific manner. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0060] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when their differences are not emphasized, their intended meanings are the same. "(of)", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when their differences are not emphasized, their intended meanings are the same.

[0061] In the embodiments of the present invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When their differences are not emphasized, their intended meanings are the same.

[0062] To make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0063] The embodiments of the present invention provide an oil fluid remote monitoring system, as Figure 1 shown, the system includes:

[0064] The oil fluid component monitoring module remotely collects spectral data through a spectrometer, separates and extracts metal elements and oxides in the oil fluid sample, identifies the viscosity parameters and moisture content in the sample, performs time series analysis on each parameter, calculates the change rate of the component concentration, and generates component dynamic monitoring data;

[0065] The spectral feature analysis module analyzes the spectral absorption rate of the oil fluid in different wavelength intervals based on the component dynamic monitoring data, calculates the change rate of the absorption rate gradient in adjacent wavelength intervals, screens the spectral points whose change rate exceeds the standard, and generates a spectral difference identifier;

[0066] The component cross-interference compensation module extracts the absorption rate change characteristics of each component at different wavelengths based on the spectral difference identifier, calculates the change coupling weights of metal elements, oxides, viscosity and moisture, identifies the abnormal components that affect the interaction between metal elements and oxides, determines the deviation value of the cross-influence, and generates a coupling influence adjustment result;

[0067] Based on the coupled influence adjustment results, the abnormal component screening module calculates the duration and change rate of abnormal components, compares the change patterns of the original component data, analyzes the fluctuation rules of abnormal components, eliminates the abnormal components caused by short-term fluctuations, and forms an abnormal fluctuation evaluation index;

[0068] Based on the abnormal fluctuation evaluation index, the intelligent early warning module analyzes the change trend of the abnormal components in the oil fluid, calculates the risk level of the abnormal components, classifies them, extracts the risk signals whose abnormal levels reach the early warning standard, remotely sends alarm information, and obtains the oil fluid risk monitoring signal.

[0069] The component dynamic monitoring data includes the change rate of metal element concentration, the change rate of oxide concentration, viscosity value and moisture content. The spectral difference identification includes key wavelength points, absorption rate gradient change values and exceeded spectral points. The coupled influence adjustment results include metal element coupling weights, oxide coupling weights and parameter cross-influence results. The abnormal fluctuation evaluation index includes abnormal duration, abnormal change rate and deviation analysis results of baseline data. The oil fluid risk monitoring signal includes risk level classification, risk component identification results and remote alarm transmission data.

[0070] As Figure 2 and Figure 3 shown, the oil fluid component monitoring module includes;

[0071] The element separation module remotely collects spectral data through a spectrometer, separates and extracts metal elements and oxides, measures the absorption peak intensity of the elements, eliminates background interference signals, matches the characteristic wavelengths of the elements, and generates target element concentration data;

[0072] The trace element component data contains the spectral responses of the concentrations of various metal elements and oxides. The obtained spectral data needs to be preprocessed to eliminate irrelevant background noise. Call the absorption peak screening rule to extract the spectral intensity values within the characteristic wavelength range. For different metal elements, analyze the positions and spectral intensities of their characteristic absorption peaks, calculate the change of absorption rate in different wavelength intervals using spectral integration, screen the absorption peaks of the main elements, and use the formula: Calculate the absorption rate of different elements in the spectral data, where A λ represents the absorption rate at wavelength λ, I0 represents the incident light intensity without a sample, I represents the light intensity after sample absorption. For the main components such as metal elements Fe, Cu, Al, Si, etc., calculate their absorption rates at multiple characteristic wavelengths, establish the absorption peak data set corresponding to the elements, use the intensity ratio method to calculate the spectral response ratio of different elements at the corresponding wavelengths, eliminate the noise interference components, match the known spectral characteristics in the database, conduct element identification and concentration calculation, and calculate the element concentration according to Beer's law: Where C is the element concentration, ε is the extinction coefficient, and b is the optical path length. The optical path b is corrected according to the experimental data and the standard extinction coefficient is matched to determine the change range of the concentration of each element, obtain the concentration distribution of different elements, and finally form the target element concentration data.

[0073] Based on the target element concentration data, the physical parameter extraction sub-module detects the viscosity parameter and moisture content, calculates the change trend of viscosity with temperature, determines the influence of moisture content on spectral characteristics, corrects the spectral shift caused by environmental factors, and obtains the characteristic values of the physical parameters of the oil.

[0074] The target element concentration data is used to analyze the physical properties of the oil, extract the viscosity parameter and moisture content. The trend of the oil viscosity changing with temperature needs to be corrected based on the original data. The viscosity-temperature relationship curve is called to establish the viscosity change equation, and the experimental fitting method is used to analyze the viscosity values at different temperatures and determine the temperature influence factor. The relationship between viscosity and temperature can be expressed as: Where η represents the oil viscosity at the current temperature T, η0 represents the viscosity at the reference temperature T0, B is the temperature influence factor, and the value of B is obtained by fitting the experimental data. Determine the influence of moisture content on spectral characteristics, analyze the moisture characteristic absorption band in the infrared spectral data, calculate the spectral absorption ratio of the moisture content, and calculate the moisture content using the Beer-Lambert law: Where W is the moisture content, A represents the spectral absorption rate at a specific wavelength, ε is the extinction coefficient of moisture, and b is the optical path length. The moisture content is measured through multiple experiments, combined with the physical property data of the oil, and the influence of environmental temperature and humidity on the measurement results is corrected to obtain the characteristic values of the physical parameters of the oil.

[0075] The dynamic change calculation sub-module calls the characteristic values of the physical parameters of the oil, calculates the change rate of the concentration of each component, determines the increasing and decreasing trend of the concentration with time, judges whether the change rate exceeds the standard range, calculates the increment and ratio of each parameter, and generates the component dynamic monitoring data.

[0076] Call the characteristic values of the physical parameters of the oil, calculate the change rate of the component concentration with time, obtain the time series data, determine the increasing and decreasing trend of the concentration of each component, calculate the change rate of the time series data, use the moving average method to smooth the time series data, calculate the concentration increment at adjacent time points, and calculate the concentration change rate: Where R represents the concentration change rate, C t+1 and C t represent the concentration values at adjacent time points, Δt represents the time interval, analyze the time series data, judge whether the change rate exceeds the standard range, set the concentration change rate threshold, determine the abnormal change rate threshold according to the original data, calculate the increment and ratio of each parameter, screen the abnormal concentration change points, and generate the component dynamic monitoring data.

[0077] As Figure 2 and Figure 4 shown, the spectral feature analysis module includes;

[0078] Based on the component dynamic monitoring data, the spectral data analysis sub-module extracts the spectral absorption rates of the oil fluid in different wavelength intervals, identifies the positions of the absorption peaks in the wavelength intervals, corrects the influence of background noise on the absorption rates, determines the stability of the spectral signals, and obtains the spectral absorption rate distribution data;

[0079] Based on the component dynamic monitoring data, extract the spectral absorption rates of the oil fluid in different wavelength intervals, call the spectral database, identify the positions of the absorption peaks in each wavelength interval, use the baseline correction method to remove the background noise, calculate the change amplitude of the absorption rates at different wavelengths, establish the spectral intensity calibration curve, analyze the stability of the signals at different wavelengths, calculate the fluctuation of the spectral signals using the standard deviation, and use the formula: where σ θ represents the standard deviation of the spectral signal, represents the spectral absorption rate at wavelength θ j at, is the average value of the spectral absorption rates of all wavelengths, p is the number of observed wavelength points, calculate the spectral stability of each wavelength point, screen the spectral points whose standard deviation exceeds the set threshold, filter the signals, eliminate the interference of background noise, and obtain the spectral absorption rate distribution data.

[0080] The absorption rate gradient calculation sub-module calls the spectral absorption rate distribution data, calculates the change gradient of the absorption rates in adjacent wavelength intervals, determines the positive and negative trends of the change gradient, screens the wavelength intervals with abnormal absorption rate changes, and obtains the spectral gradient change value;

[0081] Calculate the change gradient of the absorption rates in adjacent wavelength intervals, using the formula:

[0082]

[0083] Determine the positive and negative trends of the change gradient, screen the wavelength intervals with abnormal absorption rate changes, and obtain the spectral gradient change value;

[0084] where, G λ represents the absorption rate gradient of the wavelength interval, represents the spectral absorption rate at wavelength λ2, represents the spectral absorption rate at wavelength λ1, represents the spectral absorption rate at the i-th wavelength point, represents the average value of the spectral absorption rates of all wavelength points, and n represents the total number of wavelength data points;

[0085] Assume This value is monitored by the spectrometer at a wavelength of λ2 = 550 nm;

[0086] Assume This value is monitored by the spectrometer at a wavelength of λ1 = 540 nm;

[0087] Assume that there are 5 observation points in the wavelength dataset, and their absorption rates are in sequence

[0088] is the mean spectral absorption rate of all wavelength points, and the calculation method is as follows:

[0089]

[0090] Substitute the data:

[0091]

[0092] n is the total number of wavelength data points, and its value is 5;

[0093] Substitute the parameters into the formula for calculation

[0094] Calculate the numerator part:

[0095]

[0096] Calculate the denominator part (normalization factor):

[0097]

[0098] Calculate each term:

[0099] (-0.112) 2 = 0.012544;

[0100] (0.048) 2 = 0.002304;

[0101] (0.118) 2 = 0.013924;

[0102] (-0.062) 2 = 0.003844;

[0103] (0.008) 2 = 0.000064;

[0104] Sum:

[0105] 0.012544 + 0.002304 + 0.013924 + 0.003844 + 0.000064 = 0.03268;

[0106] Calculate the root mean square value:

[0107]

[0108] Calculate the final absorption rate gradient G λ :

[0109]

[0110] The result shows that the absorption rate change gradient between the wavelength ranges of 540 nm and 550 nm is 1.978. This gradient value will be used to screen for spectral points with abnormal change rates. If this value exceeds the set threshold (e.g., 2.5), then this wavelength point is an abnormal wavelength point, and it is necessary to further analyze the concentration change of its corresponding component.

[0111] The spectral anomaly screening sub-module calls the spectral gradient change value, screens for spectral points with change rates exceeding the standard, eliminates the abnormal absorption rates caused by short-term fluctuations, analyzes the absorption characteristics of the wavelength range, determines the corresponding relationship between the wavelength range and the component concentration change, and generates a spectral difference identifier.

[0112] Call the spectral gradient change value, screen for spectral points with spectral change rates exceeding the standard, calculate the spectral gradient change of adjacent wavelength ranges, use the normalization method to balance the spectral intensity, calculate the change rate of the short-term fluctuation signal, using the formula: where G φ represents the spectral gradient change of the wavelength range, and represent the spectral absorption rates of adjacent wavelength points, is the average value of the spectral absorption rate, q is the total number of wavelength data points, screen for data points with spectral point change rates exceeding the standard threshold, analyze the absorption characteristics of different wavelength ranges, determine the corresponding relationship between the wavelength range and the component concentration change, and generate a spectral difference identifier.

[0113] Such as Figure 2 and Figure 5 shown, the component cross-interference compensation module includes;

[0114] The component coupling weight calculation sub-module, based on the spectral difference identifier, extracts the change trends of metal elements, oxides, viscosity, and moisture content at the differential wavelengths, determines the synchronous change rate between components, calculates the coupling correlation, adjusts the abnormal deviation in the coupling relationship, and obtains the component coupling weight value;;

[0115] Calculate the component coupling correlation degree, using the formula:

[0116]

[0117] And adjust the abnormal deviation in the coupling relationship to obtain the component coupling weight value;

[0118] Among them, C ij represents the coupling correlation degree between component i and component j, X it represents the concentration value of component i at time t, X jt represents the concentration value of component j at time t, represents the average concentration of component i at all time points, represents the average concentration of component j at all time points, and n represents the total number of observed time points;

[0119] Assume that the measured values of the metal element concentration at 5 time points are X i1 = 32.5, X i2 = 35.1, X i3 = 33.7, X i4 = 36.0, X i5 = 34.2 ppm;

[0120] X jt is the concentration value of component j at time t, obtained from the viscosity measurement value at the same time point. The viscosity numerical unit is cSt, and the corresponding time point data recorded by the monitoring system is X j1 = 46.8, X j2 = 48.2, X j3 = 47.1, X j4 = 49.0, X j5 = 47.5;

[0121] is the average concentration of component i at all time points, and the calculation method is as follows:

[0122]

[0123] Substitute the data:

[0124]

[0125] is the average concentration of component j at all time points, and the calculation method is as follows:

[0126]

[0127] Substitute the data:

[0128]

[0129] n is the total number of time points, and the value is 5;

[0130] Substitute the parameters into the formula for calculation;

[0131] Calculate the numerator part (covariance term):

[0132]

[0133] Calculate the deviation at each time point:

[0134]

[0135] Calculate the deviation of component j:

[0136]

[0137] Calculate the deviation product: (-1.8 × -0.92) + (0.8 × 0.48)· + (-0.6 × -0.62) + (1.7 × 1.28) + (-0.1 × -0.22);

[0138] = 1.656 + 0.384 + 0.372 + 2.176 + 0.022;

[0139] = 4.610;

[0140] Calculate the denominator part (normalization factor):

[0141]

[0142] Calculate the sum of squares:

[0143] (-1.8) 2 + (0.8) 2 + (-0.6) 2 + (1.7) 2 + (-0.1) 2 ;

[0144] = 3.24 + 0.64 + 0.36 + 2.89 + 0.01 = 7.14;

[0145] (-0.92) 2 + (0.48) 2 + (-0.62) 2 + (1.28) 2 + (-0.22) 2 ;

[0146] = 0.8464 + 0.2304 + 0.3844 + 1.6384 + 0.0484 = 3.148;

[0147] Calculate the normalization factor:

[0148]

[0149] Calculate the final coupling correlation degree:

[0150]

[0151] Result analysis

[0152] The result shows that the coupling correlation degree between the metal element concentration and the viscosity is 0.9711. This value is close to 1, indicating that the change trends of the two are highly consistent and there is a significant mutual influence. This coupling correlation degree will be used to adjust the calculation weights between components to reduce the interference of abnormal deviations on the evaluation of component concentrations and obtain more accurate component coupling weight values.

[0153] The cross - influence deviation determination sub - module calls the component coupling weight value, determines the influence of the change in metal element concentration on the oxide generation rate, analyzes the influence intensity of the change in viscosity on the moisture content fluctuation, determines the interference degree of components on adjacent parameters, and calculates the interference offset value to obtain the cross - influence deviation value;

[0154] Call the component coupling weight value, determine the influence of the change in metal element concentration on the oxide generation rate, obtain time - series data, analyze the change rate of metal element concentration at adjacent time points, calculate the correlation between the increment of metal element concentration and the oxide generation rate, using the formula: where, R αβ represents the influence intensity of the metal element concentration on the oxide generation rate, X α,k is the metal element concentration at time k, Y β,k is the oxide generation rate at time k, and are the mean values of the metal element concentration and the oxide generation rate respectively. Calculate the influence value of the metal element concentration on the oxide change, analyze the influence intensity of the change in viscosity on the moisture content fluctuation, obtain the change rates of viscosity and moisture content at adjacent time points, calculate the ratio of the viscosity increment to the change in moisture content, using the formula: where, I γδ represents the influence intensity of the change in viscosity on the moisture content fluctuation, ΔQ γ is the change amount of viscosity, ΔQ δ is the change amount of moisture content. Determine the interference degree of components on adjacent parameters, calculate the interference offset value, and obtain the cross - influence deviation value.

[0155] The abnormal interference adjustment sub - module calls the cross - influence deviation value, identifies the abnormal components that affect the interaction of parameters, eliminates the error data caused by the abnormal components, adjusts the proportion distribution of the abnormal parameters, and generates the coupling influence adjustment result.

[0156] Call the cross - influence deviation value, identify the abnormal components that affect the interaction of parameters, calculate the deviation range of the abnormal components, extract the concentration data of the abnormal components, calculate the offset ratio between the abnormal components and other components, using the formula: Among them, P μν represents the offset ratio between component μ and component ν, Z μ and Z ν are the concentration values of the abnormal component and the adjacent component respectively, and are the means of the corresponding components. Calculate the interference ratio of the abnormal component to the adjacent component, screen the abnormal data points whose offset ratio exceeds the set threshold, eliminate the error data caused by the abnormal component, adjust the proportion distribution of the abnormal parameters, and generate the adjusted result of the coupling effect.

[0157] For example Figure 2 and Figure 6 as shown, the abnormal component screening module includes;

[0158] The abnormal persistence analysis sub-module extracts the time series data of the abnormal component based on the adjusted result of the coupling effect, determines the change trend of the abnormal component at different time points, calculates the duration interval of the abnormal state, and obtains the abnormal persistence parameter;

[0159] Based on the adjusted result of the coupling effect, extract the time series data of the abnormal component, calculate the concentration change at each time point, determine the change trend of the abnormal component at different time points, calculate the duration interval of the abnormal state, and use the time span calculation formula: D χ = t χf - t χi , where D χ represents the duration of the abnormal state, t χf represents the end time of the abnormal state, t χi represents the start time of the abnormal state, calculate the time span of the abnormal state, judge whether the abnormal state is continuous, screen the time period of short-term abnormality, and obtain the abnormal persistence parameter.

[0160] The change rate determination sub-module calls the abnormal persistence parameter, calculates the concentration change rate of the abnormal component at the key time nodes, analyzes the increasing and decreasing trend of the rate, determines the stability of the change amplitude, screens the abnormal components whose rate fluctuations exceed the standard, and obtains the abnormal change rate value;

[0161] Call the abnormal persistence parameter, calculate the concentration change rate of the abnormal component at the key time nodes, determine the concentration change of the abnormal state at multiple time points, calculate the increasing and decreasing trend of the rate, and use the change rate calculation formula: where V ζ represents the concentration change rate of the abnormal component at time point k, and are the component concentration values at times k and k-1 respectively, analyze the increasing and decreasing trend of the rate, determine the stability of the change amplitude, screen the abnormal components whose rate fluctuations exceed the standard, and obtain the abnormal change rate value.

[0162] The short-term fluctuation elimination sub-module calls the abnormal change rate value, compares the change pattern of the abnormal component with the fluctuation trend of the original component data, identifies the short-term abnormal fluctuation data, eliminates the error data caused by random fluctuations, and forms an abnormal fluctuation evaluation index.

[0163] Call the abnormal change rate value, compare the change pattern of the abnormal component with the fluctuation trend of the original component data, calculate the deviation value between the abnormal fluctuation and the normal fluctuation, and use the deviation calculation formula: Among them, E τ represents the fluctuation deviation of the abnormal component, B τ represents the fluctuation amplitude of the abnormal component, A τ represents the fluctuation amplitude of the original component data, identifies the short-term abnormal fluctuation data, eliminates the error data caused by random fluctuations, and forms an abnormal fluctuation evaluation index.

[0164] As Figure 2 and Figure 7 shown, the intelligent early warning module includes;

[0165] Based on the abnormal fluctuation evaluation index, the trend recognition sub-module measures the difference in component concentration at different time points, analyzes the increasing and decreasing trend of the concentration over time, identifies the direction of trend change, calculates the fluctuation amplitude, and obtains the abnormal trend characteristic value;

[0166] Based on the abnormal fluctuation evaluation index, measure the difference in component concentration at different time points, extract the time series data, calculate the change in concentration between adjacent time points, analyze the increasing and decreasing trend of the concentration over time, use a linear change model to calculate the trend change rate, determine the direction of trend change, and use the formula: Among them, T κ represents the concentration change rate of component κ between time t a and t b , and are the component concentration values at time t b and t a respectively, calculate the fluctuation amplitude, determine the trend fluctuation range, screen the abnormal trend fluctuation interval, and obtain the abnormal trend characteristic value.

[0167] The risk assessment sub-module calls the abnormal trend characteristic value, calculates the risk change level of the abnormal component, determines the fluctuation range of the change level, analyzes the risk evolution process of the abnormal component, divides the risk level standard, and classifies the abnormal component to obtain the risk level classification result;

[0168] Call the abnormal trend eigenvalue, calculate the risk change level of the abnormal component, analyze the risk change trend, determine the fluctuation range of the change level, calculate the risk fluctuation coefficient, and calculate the risk fluctuation level using the standard deviation method. The formula is: where W λ represents the risk fluctuation level of the abnormal component, represents the risk change value at time point n, is the average value of the risk changes at all time points, m is the total number of time data points. Analyze the risk evolution process of the abnormal component, divide the risk level standard, classify the abnormal component, and obtain the risk level classification result.

[0169] The alarm trigger sub-module calls the risk level classification result, screens out the abnormal components whose risk levels reach the warning standard, marks the risk signal, sets up the remote alarm trigger condition, and obtains the oil risk monitoring signal.

[0170] Call the risk level classification result, screen out the abnormal components whose risk levels reach the warning standard, set the warning threshold, calculate the proportion of component risk exceeding the limit, and use the warning proportion calculation formula: where S ω represents the proportion of component ω's risk exceeding the limit, Z ω represents the risk value of the current component, Z crit is the set warning threshold. Screen out the abnormal components whose risks exceed the warning value, mark the risk signal, set up the remote alarm trigger condition, and obtain the oil risk monitoring signal.

[0171] As Figure 8 shown, an oil remote monitoring method includes the following steps:

[0172] S1: Analyze the metal, oxide, viscosity, and moisture content according to the spectral data remotely collected by the spectrometer, calculate the concentration change rate, and use time series comparison to obtain the component dynamic monitoring data;

[0173] S2: Based on the component dynamic monitoring data, calculate the gradient change rate of the spectral absorption rate, screen the key spectral points, and obtain the spectral difference identifier;

[0174] S3: Based on the spectral difference identifier, calculate the change coupling weight of each component, determine the interaction effects of metal, oxide, viscosity, and moisture, screen out the components with abnormal interactions, calculate the cross-interference deviation, and eliminate the interference error to obtain the coupling effect adjustment result;

[0175] S4: Based on the coupling effect adjustment result, calculate the duration and change rate of the abnormal component, compare with the change pattern of the original component, screen the fluctuation area of the component deviation, and obtain the abnormal fluctuation evaluation index;

[0176] S5: Based on the abnormal fluctuation evaluation index, analyze the change trend of the abnormal components, calculate the risk level of the abnormal components, and screen high-risk signals to obtain the oil risk monitoring signal.

[0177] It should be understood that the term "and / or" in this article is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. Additionally, the character " / " in this article generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0178] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single item (s) or plural item (s). For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, c can be single or multiple.

[0179] It should be understood that in various embodiments of the present invention, the magnitude of the sequence numbers of the above processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0180] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different systems for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0181] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described devices, apparatuses, and units can refer to the corresponding processes in the foregoing system embodiments, and will not be elaborated herein.

[0182] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and systems can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections between each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0183] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0184] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0185] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the systems described in each embodiment of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0186] As described above, this is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. An oil fluid remote monitoring system, characterized in that, The system includes: The oil fluid component monitoring module remotely collects spectral data through a spectrometer, analyzes the concentrations of metal elements and oxides, viscosity parameters, and moisture content in the oil fluid, calculates the change rate of each component concentration, and generates component dynamic monitoring data; The spectral feature analysis module analyzes the spectral absorption rate of the oil fluid based on the component dynamic monitoring data, calculates the change rate of the absorption rate gradient, screens the spectral points with a change rate exceeding the standard, and generates a spectral difference identifier; The component cross-interference compensation module extracts the spectral absorption rate change characteristics of each component based on the spectral difference identifier, calculates the change coupling weight, identifies the abnormal components affecting the interaction of parameters, determines the deviation value of the cross-influence, and generates a coupling influence adjustment result; The abnormal component screening module calculates the duration and change rate of the abnormal components based on the coupling influence adjustment result, compares the change mode of the original component data, determines the deviation amplitude of the abnormal components, and analyzes the fluctuation law to form an abnormal fluctuation evaluation index; The intelligent warning module calculates the risk level of the abnormal components based on the abnormal fluctuation evaluation index, analyzes the change trend of the concentration of the abnormal components in the oil fluid, and extracts the oil fluid risk monitoring signal.

2. The oil hydraulic remote monitoring system according to claim 1, characterized in that The component dynamic monitoring data includes the change rate of metal element concentration, the change rate of oxide concentration, viscosity value, and moisture content. The spectral difference identifier includes key wavelength points, absorption rate gradient change values, and out-of-standard spectral points. The coupling influence adjustment result includes metal element coupling weight, oxide coupling weight, and parameter cross-influence result. The abnormal fluctuation evaluation index includes abnormal duration, abnormal change rate, and deviation analysis result of baseline data. The oil fluid risk monitoring signal includes risk level classification, risk component identification result, and remote alarm transmission data.

3. The oil fluid remote monitoring system according to claim 1, characterized in that, The oil fluid component monitoring module includes; The element separation sub-module remotely collects spectral data through a spectrometer, separates and extracts metal elements and oxides, measures the absorption peak intensity of the elements, eliminates background interference signals, matches the characteristic wavelengths of the elements, and generates target element concentration data; The physical parameter extraction sub-module detects viscosity parameters and moisture content based on the target element concentration data, calculates the change trend of viscosity with temperature, measures the influence of moisture content on spectral characteristics, corrects the spectral shift caused by environmental factors, and obtains the physical parameter characteristic values of the oil fluid; The dynamic change calculation sub-module calls the physical parameter characteristic values of the oil fluid, calculates the change rate of each component concentration, measures the increasing and decreasing trend of the concentration with time, determines whether the change rate exceeds the standard range, calculates the increment and ratio of each parameter, and generates component dynamic monitoring data.

4. The oil hydraulic remote monitoring system according to claim 1, characterized in that The spectral feature analysis module includes; The spectral data analysis sub-module extracts the spectral absorption rate of the oil fluid in the differential wavelength range based on the component dynamic monitoring data, identifies the absorption peak positions in the wavelength range, corrects the influence of background noise on the absorption rate, measures the stability of the spectral signal, and obtains the spectral absorption rate distribution data; The absorption rate gradient calculation sub-module calls the spectral absorption rate distribution data, calculates the absorption rate change gradient of adjacent wavelength intervals, determines the positive and negative trends of the change gradient, screens the wavelength intervals with abnormal absorption rate changes, and obtains the spectral gradient change value; The spectral anomaly screening sub-module calls the spectral gradient change value, screens the spectral points with a change rate exceeding the standard, eliminates the abnormal absorption rate caused by short-term fluctuations, analyzes the absorption characteristics of the wavelength interval, determines the corresponding relationship between the wavelength interval and the component concentration change, and generates a spectral difference identifier.

5. The oil fluid remote monitoring system according to claim 4, characterized in that, The calculation of the absorption rate change gradient of adjacent wavelength intervals uses the formula: Determine the positive and negative trends of the change gradient, screen the wavelength intervals with abnormal absorption rate changes, and obtain the spectral gradient change value; Among them, G λ represents the absorption rate gradient of the wavelength range, represents the spectral absorption rate at wavelength λ2, represents the spectral absorption rate at wavelength λ1, represents the spectral absorption rate at the i-th wavelength point, represents the average value of the spectral absorption rates of all wavelength points, and n represents the total number of wavelength data points.

6. The oil hydraulic remote monitoring system according to claim 1, wherein The component cross-interference compensation module includes; The component coupling weight calculation sub-module extracts the change trends of metal elements, oxides, viscosity, and moisture content at different wavelengths based on the spectral difference identifier, determines the synchronous change rate between components, calculates the component coupling correlation degree, and adjusts the abnormal deviation in the coupling relationship to obtain the component coupling weight value; The cross-influence deviation determination sub-module calls the component coupling weight value, determines the influence of the change in metal element concentration on the oxide generation rate, analyzes the influence intensity of the change in viscosity on the moisture content fluctuation, determines the interference degree of the component on adjacent parameters, and calculates the interference offset value to obtain the cross-influence deviation value; The abnormal interference adjustment sub-module calls the cross-influence deviation value, identifies the abnormal components affecting the interaction of parameters, eliminates the error data caused by the abnormal components, adjusts the proportion distribution of the abnormal parameters, and generates a coupling influence adjustment result.

7. The oil fluid remote monitoring system according to claim 6, wherein The calculation of the component coupling correlation degree uses the formula: And adjust the abnormal deviation in the coupling relationship to obtain the component coupling weight value; Among them, C ij represents the coupling correlation degree between component i and component j, X it represents the concentration value of component i at time t, X jt represents the concentration value of component j at time t, represents the average concentration of component i at all time points, represents the average concentration of component j at all time points, and n represents the total number of observed time points.

8. The oil - liquid remote monitoring system according to claim 1, characterized in that, The abnormal component screening module includes; The abnormal persistence analysis sub-module extracts the time series data of the abnormal components based on the coupling influence adjustment result, determines the change trend of the abnormal components at different time points, calculates the duration interval of the abnormal state, and obtains the abnormal persistence parameter; The change rate determination sub-module calls the abnormal persistence parameter, calculates the concentration change rate of the abnormal components at key time nodes, analyzes the increase and decrease trend of the rate, determines the stability of the change amplitude, screens the abnormal components with a rate fluctuation exceeding the standard, and obtains the abnormal change rate value; The short-term fluctuation elimination sub-module calls the abnormal change rate value, compares the change pattern of the abnormal components with the fluctuation trend of the original component data, identifies the short-term abnormal fluctuation data, and eliminates the error data caused by random fluctuations to form an abnormal fluctuation evaluation index.

9. The oil hydraulic remote monitoring system according to claim 1, characterized in that The intelligent early warning module includes; The trend recognition sub-module determines the component concentration difference at different time points based on the abnormal fluctuation evaluation index, analyzes the increase and decrease trend of the concentration over time, identifies the trend change direction, calculates the fluctuation amplitude, and obtains the abnormal trend characteristic value; The risk assessment sub-module calls the abnormal trend characteristic value, calculates the risk change level of the abnormal components, determines the fluctuation range of the change level, analyzes the risk evolution process of the abnormal components, divides the risk level standard, and classifies the abnormal components to obtain the risk level classification result; The alarm trigger sub-module calls the risk level classification result, filters out abnormal components whose risk levels reach the warning standard, marks risk signals, sets up remote alarm trigger conditions, and obtains the oil fluid risk monitoring signal.

10. A method for remote monitoring of oil fluid, which is used to implement the oil fluid remote monitoring system according to any one of claims 1-9, characterized in that, It includes the following steps: S1: Analyze the metal, oxide, viscosity, and moisture content based on the spectral data remotely collected by the spectrometer, calculate the concentration change rate, and use time series comparison to obtain the component dynamic monitoring data. S2: Based on the component dynamic monitoring data, calculate the gradient change rate of the spectral absorption rate, filter out key spectral points, and obtain the spectral difference identifier. S3: Based on the spectral difference identifier, calculate the change coupling weight of each component, measure the interactive effects of metal, oxide, viscosity, and moisture, filter out components with abnormal interactions, calculate the cross-interference deviation, and eliminate interference errors to obtain the coupling effect adjustment result. S4: Based on the coupling effect adjustment result, calculate the duration and change rate of abnormal components, compare the change patterns of the original components, and filter out the fluctuation regions of component deviation to obtain the abnormal fluctuation evaluation index. S5: Based on the abnormal fluctuation evaluation index, analyze the change trend of abnormal components, calculate the risk levels of abnormal components, and filter out high-risk signals to obtain the oil fluid risk monitoring signal.

Images