Diesel engine oil monitoring and fault diagnosis device

Abstract

The present invention discloses a diesel engine lubricating oil monitoring and fault diagnosis device, including an intelligent sensor component, a data acquisition and storage unit, an intelligent edge terminal and a display unit; it can cope with the complex and diverse faults of diesel engines, the high difficulty of daily maintenance and fault repair, the low early warning rate and other problems, and utilizes the intelligent sensor component to realize the prediction of lubricating oil service life and fault diagnosis functions through data acquisition, feature extraction, real-time data recording and status monitoring. The diesel engine lubricating oil monitoring and fault diagnosis device can operate online for a long time, and realize the early detection and warning of oil pollution, deterioration and mechanical wear.

Description

Technical Field

[0001] The invention relates to the technical field of diesel engine safety prediction, and in particular to a diesel engine lubricating oil monitoring and fault diagnosis device. Background Art

[0002] The condition monitoring and maintenance of ship equipment is the main means to ensure the normal operation of equipment, improve equipment efficiency and extend equipment service life. Ship equipment is complex and diverse, and the degree of automation is getting higher and higher. The daily maintenance and troubleshooting of equipment are becoming more and more difficult, and the cost of equipment maintenance is getting higher and higher. In the context of the big data era, ship intelligence has become an inevitable trend in the development of shipbuilding and shipping. Oil monitoring technology is a technology that obtains lubrication and wear status information of equipment by analyzing the performance changes of the lubricating oil in use of mechanical equipment and the wear particles carried, and then diagnoses potential faults and predicts the development trend of faults.

[0003] At present, the monitoring method for lubricating oil of most equipment is regular sampling and inspection. Generally, for medium and high-speed diesel engines, the sampling period is 300-500 hours or 60 days, and for low-speed diesel engines, the sampling period is 1000 hours or 90 days. The advantage of offline inspection is that offline lubricating oil testing can carry out detailed physical, chemical and composition testing and analysis with high accuracy. However, offline testing is limited by the timeliness of testing and the randomness of samples sent for inspection, and it is impossible to monitor the real-time lubrication status and mutation of the equipment. At present, there are a small number of online lubricating oil monitoring devices that monitor the viscosity, density and particle concentration of lubricating oil online. However, most lubricating oil monitoring devices have not carried out in-depth research and feature extraction on their monitoring parameters, and then carried out fault diagnosis and provided oil change cycles.

[0004] Therefore, the prior art has defects and is in urgent need of improvement. Summary of the invention

[0005] The purpose of the present invention is to provide a diesel engine lubricating oil monitoring and fault diagnosis device to solve the problem that the current lubricating oil monitoring device has not carried out in-depth research and feature extraction on its monitoring parameters.

[0006] An embodiment of the present invention provides a diesel engine lubricating oil monitoring and fault diagnosis device, comprising: an intelligent sensor component, used to collect parameter information of the lubricating oil; a data acquisition and storage unit, used to collect, parse and store data of the sensor component; an intelligent edge terminal, based on the data of the data acquisition and storage unit, statistics and corrects the lubricating oil running time, carries out dynamic threshold modeling of various parameters of the lubricating oil, monitors the lubricating oil status, predicts the service life of the lubricating oil and diagnoses the faults of the diesel engine; and a display unit, used to display the real-time status of the lubricating oil and the fault diagnosis results of the diesel engine.

[0007] Optionally, in some embodiments of the present invention, the intelligent sensor assembly includes: a lubricating oil viscosity sensor for collecting the viscosity and temperature of the lubricating oil; a lubricating oil moisture sensor for collecting the water activity and water content in the lubricating oil; a lubricating oil dielectric constant sensor for collecting the dielectric constant of the lubricating oil; and a lubricating oil particle sensor for collecting the number of ferromagnetic particles and the number of non-ferromagnetic particles in each gear of the lubricating oil.

[0008] Optionally, in some embodiments of the present invention, the dynamic viscosity range of the lubricating oil collected by the lubricating oil viscosity sensor is between 0 and 400 cst, and the temperature range is between 0 and 150°C; the water activity range of the lubricating oil collected by the lubricating oil moisture sensor is between 0 and 100 aw, and the water content range is between 0 and 3000 ppm; the dielectric constant range of the lubricating oil collected by the lubricating oil dielectric constant sensor is between 0 and 10; the minimum diameter of the ferromagnetic particles in the lubricating oil collected by the lubricating oil particle sensor is 40um, and the minimum diameter of the non-ferromagnetic particles is 135um.

[0009] Optionally, in some embodiments of the present invention, the data of the sensor component analyzed by the data acquisition and storage unit includes: the rate of change of lubricating oil kinematic viscosity, the oil degradation rate of lubricating oil and the first-order difference of various data; the data acquisition and storage unit also includes: a real-time database storage module, which performs partitioned and compressed storage on the real-time parameters of the diesel engine.

[0010] Optionally, in some embodiments of the present invention, the kinematic viscosity change rate formula is as follows:

[0011]

[0012] Where η is the kinematic viscosity change rate; v1 is the measured value of the kinematic viscosity of the new lubricating oil, in mm 2 / s; v2 is the measured value of the kinematic viscosity of the lubricating oil in use, in mm 2 / s.

[0013] Optionally, in some embodiments of the present invention, the oil degradation rate formula of the lubricating oil is as follows:

[0014]

[0015] Among them, k is the oil deterioration rate; ε1 is the measured value of the dielectric constant of new oil; ε2 is the measured value of the dielectric constant of the used oil.

[0016] Optionally, in some embodiments of the present invention, the first-order differences of various types of data include: water activity in lubricating oil, water content in lubricating oil, number of ferromagnetic particles and / or number of non-ferromagnetic particles in lubricating oil per minute, number of ferromagnetic particles and / or mass of non-ferromagnetic particles in lubricating oil per hour; the first-order differences of their time series are extracted as eigenvalues, and the formula is as follows:

[0017] D y1 =y t+1 -y t

[0018] Among them, D y1 is the first-order difference of the parameter; y t+1 is the real-time value at time t+1; y t is the real-time value at time t.

[0019] Optionally, in some embodiments of the present invention, the intelligent edge terminal has a built-in self-learning module; the self-learning module can establish a viscosity-temperature curve and adjust the viscosity-temperature curve in real time according to sample parameters; and the self-learning module can set an alarm threshold and adjust the alarm threshold in real time according to the cumulative distribution function.

[0020] Optionally, in some embodiments of the present invention, the steps of establishing the viscosity-temperature curve are as follows:

[0021] Extracting the viscosity history data of the diesel engine at various temperatures within a specified time after adding new lubricating oil from the data acquisition and storage unit;

[0022] The viscosity history data are arranged in ascending order according to temperature, and after integrating the arranged viscosity history data, the oil coefficients A and B are calculated according to the following formula;

[0023] log(log(v+0.7))=AB log T

[0024] Where: v is the kinematic viscosity of the lubricating oil, in centistokes;

[0025] T is the temperature of the lubricating oil in Kelvin;

[0026] A and B are the oil quality coefficients of the lubricating oil;

[0027] According to the above results, taking the minimum error as the objective function, the optimization mathematical model of coefficients A and B is established to obtain the optimal A and B coefficients when the error is minimum;

[0028] Substituting the optimal coefficients A and B into the following formula, the viscosity-temperature curve of the lubricating oil is obtained:

[0029]

[0030] Where: v t is the viscosity-temperature curve function of the lubricating oil.

[0031] Optionally, in some embodiments of the present invention, data on the number and mass of ferromagnetic particles in the lubricating oil within a specified time after the diesel engine running-in are extracted from the data acquisition and storage unit, and a continuous probability distribution analysis is performed, and a probability greater than 99.8% is used as an initial alarm threshold for the number and mass of ferromagnetic particles in the lubricating oil; data on the number and mass of ferromagnetic particles in the lubricating oil within at least 10 times the specified time after the diesel engine running-in are extracted from the data acquisition and storage unit, and a continuous probability distribution analysis is performed, and a probability greater than 99.8% is used as a final alarm threshold for the number and mass of ferromagnetic particles in the lubricating oil.

[0032] Optionally, in some embodiments of the present invention, the intelligent edge terminal monitors the lubricating oil status including: monitoring a fixed threshold, monitoring a trend, and monitoring an abnormal point.

[0033] In summary, the present invention provides a diesel engine lubricating oil monitoring and fault diagnosis device, including an intelligent sensor component, a data acquisition and storage unit, an intelligent edge terminal and a display unit; it can solve the problems of the complexity and diversity of diesel engines, the high difficulty of daily maintenance and fault repair, and the low early warning rate, and realize the prediction of lubricating oil service life and fault diagnosis functions through data acquisition, feature extraction, real-time data recording, and status monitoring by using the intelligent sensor component. The diesel engine lubricating oil monitoring and fault diagnosis device can operate online for a long time to realize the early detection and warning of oil pollution, deterioration, and mechanical wear.

[0034] The intelligent edge terminal can count and correct the running time of lubricating oil, carry out dynamic threshold modeling of various parameters of lubricating oil, monitor the state of lubricating oil, predict the service life of lubricating oil and diagnose the fault of diesel engine based on the data of the data acquisition and storage unit. It has a built-in self-learning module, which can establish a viscosity-temperature curve and adjust the viscosity-temperature curve in real time according to the sample parameters, as well as set the alarm threshold and adjust the alarm threshold in real time according to the cumulative distribution function. It can timely discover and warn the deterioration and contamination of lubricating oil products, cut off the risk of abnormal wear of equipment from the root, arrange maintenance before the diesel engine lubricating oil system suffers from serious wear and failure, and reduce equipment damage; reasonably arrange maintenance time according to the equipment status, reduce the impact of fault downtime and regular maintenance on production, improve the average failure interval time of equipment, and improve productivity; improve the versatility of the diesel engine lubricating oil monitoring and fault diagnosis device, reduce the degree of manual intervention, and can be used for different types of lubricating oil systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0036] Figure 1 It is a schematic diagram of the structural distribution of a diesel engine lubricating oil monitoring and fault diagnosis device in an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0038] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0039] An embodiment of the present invention provides a diesel engine lubricating oil monitoring and fault diagnosis device, comprising an intelligent sensor component, a data acquisition and storage unit, an intelligent edge terminal and a display unit; the intelligent sensor component is used to collect parameter information of the lubricating oil; the data acquisition and storage unit is used to collect, parse and store data of the sensor component; the intelligent edge terminal, based on the data of the data acquisition and storage unit, counts and corrects the lubricating oil running time, carries out dynamic threshold modeling of various parameters of the lubricating oil, monitors the lubricating oil status, predicts the service life of the lubricating oil and diagnoses the faults of the diesel engine; and the display unit is used to display the real-time status of the lubricating oil and the fault diagnosis results of the diesel engine.

[0040] In the condition monitoring project of mechanical equipment such as diesel engines, the lubricating viscosity, water ingress, aging and deterioration of diesel engine oil and mechanical wear are the most important dimensions related to the health and life of diesel engines. The intelligent sensor assembly of the present invention includes: lubricating oil viscosity sensor, lubricating oil moisture sensor, lubricating oil dielectric constant sensor and lubricating oil particle sensor.

[0041] The lubricating oil viscosity sensor is used to collect the viscosity and temperature of the lubricating oil. Appropriate diesel engine oil viscosity is the basic guarantee for the normal lubrication of the diesel engine. The kinematic viscosity change rate characterizes the decay of the oil quality. Oil oxidation, sludge generation and the increase of insolubles will increase the viscosity of the oil. The degradation of additives in the oil, fuel leakage and dilution will reduce the viscosity. The rapid increase of kinematic viscosity indicates that oxidation is intensified, sludge is increased, fluidity is poor, and lubricity is low. The decrease of kinematic viscosity will cause the diesel engine oil film to become thinner and the lubrication performance to decrease. In severe cases, it will cause diesel engine failures such as cylinder scuffing and tile burning. The lubricating oil moisture sensor is used to collect the water activity and water content in the lubricating oil. The aging and leakage of diesel engine cylinder liners, the water generator in the combustion chamber, and the water inflow of the lubricating oil system (leakage of water-cooled lubricating oil cooler) will cause water in the lubricating oil. The presence of water in the oil will destroy the strength of the oil film and cause the hydrolysis of additives. With the increase of water in the oil, the emulsification of the oil will intensify, causing the corrosion of metal parts. The lubricating oil dielectric constant sensor is used to collect the dielectric constant of lubricating oil, and characterizes the change of oil quality by monitoring the change of dielectric constant caused by the change of the content of substances such as water, acid, alkali and sludge. The lubricating oil particle sensor is used to collect the number of ferromagnetic particles and the number of non-ferromagnetic particles in each gear of lubricating oil. The metal particle sensor in lubricating oil mainly characterizes the degree of wear of the moving parts of the diesel engine, mainly for the wear of the three main friction pairs of the diesel engine crankshaft-bearing, camshaft-bearing, and cylinder liner-piston. The number and quality of ferromagnetic particles can monitor the wear of ferromagnetic particles such as iron and nickel in the friction pair of the diesel engine. The number of non-ferromagnetic particles can monitor the chromium, lead, copper, aluminum, zinc, titanium, manganese, tin, silver, vanadium, molybdenum, tungsten, antimony, etc. in the friction pair of the diesel engine. The present invention realizes data collection through the intelligent sensor component, which can realize early detection and early warning of oil pollution, deterioration, and mechanical wear.

[0042] In some embodiments of the present invention, the dynamic viscosity of the lubricating oil collected by the lubricating oil viscosity sensor is in the range of 0 to 400 cst, and the temperature range is between 0 and 150 ° C; the water activity of the lubricating oil collected by the lubricating oil moisture sensor is in the range of 0 to 100 aw, and the water content range is between 0 and 3000 ppm; the dielectric constant of the lubricating oil collected by the lubricating oil dielectric constant sensor is in the range of 0 to 10; the minimum diameter of the ferromagnetic particles in the lubricating oil collected by the lubricating oil particle sensor is 40 um, and the minimum diameter of the non-ferromagnetic particles is 135 um. The ferromagnetic particles and non-ferromagnetic particles in the lubricating oil collected by the lubricating oil particle sensor are shown in the following table:

[0043]

[0044] The following table shows the original data of the measuring points collected through the field bus in one embodiment. The measuring points of the main monitoring parameters of the lubricating oil are detailed as follows:

[0045]

[0046]

[0047]

[0048] In some embodiments of the present invention, based on the above original parameters of the lubricating oil, the fault characteristic parameters are analyzed and extracted by the data acquisition and storage unit, including: the change rate of the kinematic viscosity of the lubricating oil, the oil degradation rate of the lubricating oil and the first-order difference of various data.

[0049] The kinematic viscosity change rate formula is as follows:

[0050]

[0051] Where η is the kinematic viscosity change rate; v1 is the measured value of the kinematic viscosity of the new lubricating oil, in mm 2 / s; v2 is the measured value of the kinematic viscosity of the lubricating oil in use, in mm 2 / s.

[0052] The oil degradation rate formula of the lubricating oil is as follows:

[0053]

[0054] Among them, k is the oil deterioration rate; ε1 is the measured value of the dielectric constant of new oil; ε2 is the measured value of the dielectric constant of the used oil.

[0055] The first-order differences of various data include: water activity in lubricating oil, water content in lubricating oil, number of ferromagnetic particles and / or number of non-ferromagnetic particles in lubricating oil per minute, number of ferromagnetic particles and / or mass of non-ferromagnetic particles in lubricating oil per hour; the first-order difference of its time series is extracted as the eigenvalue, and the formula is as follows:

[0056] D y1 =y t+1 -y t

[0057] Among them, D y1 is the first-order difference of the parameter; y t+1 is the real-time value at time t+1; y t is the real-time value at time t.

[0058] The data acquisition and storage unit also includes: a real-time database storage module, which compresses and stores the real-time parameters of the diesel engine in partitions, provides a lossless compression storage algorithm and an efficient data retrieval interface, and realizes the data block retrieval function. The running time of the equipment is counted according to the "diesel engine running" signal. Since there is a certain error in the software statistics, when the error increases to a certain extent, the user can correct the running time in the software interface of the display unit. For devices that can provide the monitoring parameter of running time, the running time of the device itself can be used directly.

[0059] In some embodiments of the present invention, the intelligent edge terminal has a built-in self-learning module; the self-learning module can establish a viscosity-temperature curve and adjust the viscosity-temperature curve in real time according to sample parameters. And the self-learning module can set an alarm threshold and adjust the alarm threshold in real time according to a cumulative distribution function.

[0060] The "GB / T 7607-2010 Diesel Engine Oil Change Index" stipulates that when the change rate of kinematic viscosity at 100°C is greater than 25%, the oil needs to be changed, but the normal working temperature of the diesel engine is 55-85°C. Since the oil viscosity itself changes with the oil temperature, it is necessary to find a more ideal formula to convert the viscosity within the working range of the diesel engine in real time, so as to calculate the theoretical viscosity of new oil at any temperature in the working range in real time, and characterize the degree of deterioration of the lubricating oil by the viscosity change rate at different temperatures, so as to realize the viscosity state monitoring of diesel engine lubricating oil and the formulation of predictive plans.

[0061] The steps for establishing the viscosity-temperature curve of the present invention are as follows:

[0062] The viscosity history data of the diesel engine at various temperatures within a specified time after the new lubricant is added is extracted from the data acquisition and storage unit; preferably, the viscosity history data of the diesel engine at various temperatures within 100 hours after the new lubricant is added is extracted from the data acquisition and storage unit, outliers are removed, and samples within the [10-90] percentile are taken as learning samples.

[0063] The above data are divided into two groups: high temperature data DataH [temperature, viscosity] and low temperature data DataL [temperature, viscosity]. The two groups of data are arranged in ascending order according to temperature. The two groups of data are sorted and integrated into a group of Data [DataH [i], DataL [i]] (i = 0, l). The calculation formula in ASTM D341-17 Standard Practice for Viscosity-Temperature Diagrams of Liquid Petroleum Products is used to calculate the l group of coefficients A and B. The formula is as follows:

[0064] log(log(v+0.7))=AB log T

[0065] Where: v is the kinematic viscosity of the lubricating oil, in centistokes;

[0066] T is the temperature of the lubricating oil in Kelvin;

[0067] A and B are the oil quality coefficients of the lubricating oil;

[0068] According to the above results, taking the minimum error as the objective function, the optimization mathematical model of coefficients A and B is established to obtain the optimal A and B coefficients when the error is minimum;

[0069] Substituting the optimal coefficients A and B into the following formula, the viscosity-temperature curve of the lubricating oil is obtained:

[0070]

[0071] Where: v t is the viscosity-temperature curve function of the lubricating oil.

[0072] Reasonable setting of the thresholds of each parameter is a key link in carrying out condition monitoring. The present invention adopts different strategies for setting the thresholds according to the different characteristics of the parameters. The main ideas are as follows: fixed thresholds can be set according to industry standards and expert experience. For measurement points that have no industry standards and expert experience and have not yet reached a consensus, dynamic threshold modeling can be carried out based on historical data statistics and modeling of typical working conditions. For the thresholds of parameters such as water content and viscosity change rate in lubricating oil, if the lubricating oil manufacturer has recommended standards, the thresholds are set according to the manufacturer's recommended standards. Otherwise, the thresholds are set according to the provisions of "GB / T7607-2010 Diesel Engine Oil Change Index".

[0073] For different types of diesel engines, the quantity and quality of metal particles carried in their lubricating oil are difficult to set a unified alarm threshold due to their different designs, manufacturing processes, sampling errors and operating conditions. Diesel engines need to be run-in before they are officially put into use, which is essentially a process of transitioning the friction surface from the initial state to the use state. The running-in process of a diesel engine generally does not exceed 200 hours. After the diesel engine running-in is completed and the mechanical equipment is put into operation at the beginning, the equipment is in good health. The present invention extracts the data of the quantity and quality of ferromagnetic particles in the lubricating oil within a specified time after the diesel engine running-in from the data acquisition and storage unit, and performs a continuous probability distribution analysis, and uses its probability greater than 99.8% as the initial alarm threshold of the quantity and quality of ferromagnetic particles in the lubricating oil; extracts the data of the quantity and quality of ferromagnetic particles in the lubricating oil within at least 10 times the specified time after the diesel engine running-in from the data acquisition and storage unit, and performs a continuous probability distribution analysis, and uses its probability greater than 99.8% as the final alarm threshold of the quantity and quality of ferromagnetic particles in the lubricating oil. Preferably, the specified time is 200 hours. That is to say, the data on the number and mass of ferromagnetic particles in the lubricating oil within 200 hours after the diesel engine running-in are extracted from the data acquisition and storage unit, and a continuous probability distribution analysis is performed, and a probability greater than 99.8% is used as the initial alarm threshold of the number and mass of ferromagnetic particles in the lubricating oil; the data on the number and mass of ferromagnetic particles in the lubricating oil within the specified time of 2000 hours after the diesel engine running-in are extracted from the data acquisition and storage unit, and a continuous probability distribution analysis is performed, and a probability greater than 99.8% is used as the final alarm threshold of the number and mass of ferromagnetic particles in the lubricating oil.

[0074] In some embodiments of the present invention, the intelligent edge terminal monitors the lubricating oil state including: monitoring fixed thresholds, monitoring trends, and monitoring abnormal points. In actual use, the three state monitoring methods can be used simultaneously, or one or two of them can be selected. Under normal conditions, the parameters of diesel engine lubricating oil should be within the normal range, such as the water content and viscosity change rate in the lubricating oil, and the fixed threshold monitoring method is adopted. Monitoring the change trend of oil parameters is also very important. The abnormal change trend of parameters often corresponds to sudden failures. The abnormal change trend of water content indicates that the diesel engine lubricating oil system is flooded. The abnormal change trend of metal particles indicates abnormal wear of the diesel engine. The abnormal downward trend of viscosity indicates that fuel is mixed in the lubricating oil. The abnormal upward trend of viscosity indicates that the friction of the lubricating oil is aggravated or the oil flow is not smooth, the oil is overheated, and the oxidation and deterioration of the lubricating oil are accelerated, shortening the service life of the oil. The trend monitoring algorithm adopted by the present invention is the first-order difference summation method and the CUSUM control chart method. After the diesel engine running-in is completed and the mechanical equipment is put into operation at the beginning, the equipment is in good health. Therefore, the running time data of the diesel engine after 200 hours of running-in is used as the learning sample (or the self-learning time period of the modeling sample is manually set), where the data at time T is used as the training set, and the data at time T+1 is used as the test set. The built-in self-learning algorithm module is used to establish the random isolation forest and one-class SVM abnormal monitoring models. The model self-evaluation adopts two strategies. Self-evaluation strategy 1 is to automatically carry out the model accuracy test based on the test set, and self-evaluation strategy 2 is to generate abnormal data based on the distribution and statistical characteristics of the original data, and perform model self-evaluation. After the self-evaluation accuracy reaches the set accuracy, the model operation result feedback is given manually, and finally gradually learns, completes the self-learning of the model, and realizes the abnormal monitoring of lubricating oil.

[0075] The intelligent edge terminal of the present invention, based on the data of the data acquisition and storage unit, on the one hand, predicts the viscosity change rate at each typical temperature in the future through the ARMA prediction model based on time series, thereby realizing the state monitoring of diesel engine lubricating oil viscosity and the formulation of predictive maintenance plan. On the other hand, the prediction of lubricating oil life based on dielectric constant is carried out, and the characteristic study of dielectric constant changing with the pH value, water content, iron abrasive concentration, number and distribution of metal particles in lubricating oil is carried out. The significant advantage of dielectric constant is that it can monitor the comprehensive performance of oil and characterize the aging and contamination of lubricating oil as a whole. Based on the comprehensive life prediction of lubricating oil based on dielectric constant, according to the established time interval, the window data of the recent period is extracted, and the LSTM (Long Short-Term Memory) algorithm is used to predict the dielectric constant of lubricating oil, thereby realizing the state monitoring of diesel engine comprehensive performance and the formulation of predictive maintenance plan. Based on the state monitoring results of each parameter, a fault inference machine is established in combination with the fault mechanism and expert knowledge base to realize fault inference and diagnosis.

[0076] The display unit of the present invention can display the real-time status of lubricating oil and the results of diesel engine fault diagnosis, but is not limited thereto. Preferably, the display unit can also include function settings, data display, decision support, and the functions of normal intelligent display devices, which will not be described in detail in this application.

[0077] In summary, the present invention provides a diesel engine lubricating oil monitoring and fault diagnosis device, including an intelligent sensor component, a data acquisition and storage unit, an intelligent edge terminal and a display unit; it can solve the problems of the complexity and diversity of diesel engines, the high difficulty of daily maintenance and fault repair, and the low early warning rate, and realize the prediction of lubricating oil service life and fault diagnosis functions through data acquisition, feature extraction, real-time data recording, and status monitoring by using the intelligent sensor component. The diesel engine lubricating oil monitoring and fault diagnosis device can operate online for a long time to realize the early detection and warning of oil pollution, deterioration, and mechanical wear.

[0078] The intelligent edge terminal can count and correct the running time of lubricating oil, carry out dynamic threshold modeling of various parameters of lubricating oil, monitor the state of lubricating oil, predict the service life of lubricating oil and diagnose the fault of diesel engine based on the data of the data acquisition and storage unit. It has a built-in self-learning module, which can establish a viscosity-temperature curve and adjust the viscosity-temperature curve in real time according to the sample parameters, as well as set the alarm threshold and adjust the alarm threshold in real time according to the cumulative distribution function. It can timely discover and warn the deterioration and contamination of lubricating oil products, cut off the risk of abnormal wear of equipment from the root, arrange maintenance before the diesel engine lubricating oil system suffers from serious wear and failure, and reduce equipment damage; reasonably arrange maintenance time according to the equipment status, reduce the impact of fault downtime and regular maintenance on production, improve the average failure interval time of equipment, and improve productivity; improve the versatility of the diesel engine lubricating oil monitoring and fault diagnosis device, reduce the degree of manual intervention, and can be used for different types of lubricating oil systems.

[0079] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0080] The technical solutions provided by the embodiments of the present invention are introduced in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the methods and core ideas of the present invention. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A diesel engine lubricating oil monitoring and fault diagnosis device, characterized in that: include: Intelligent sensor components, used to collect parameter information of lubricating oil; A data acquisition and storage unit, used for acquiring, analyzing and storing data of the sensor assembly; An intelligent edge terminal, based on the data of the data acquisition and storage unit, counts and corrects the running time of the lubricating oil, carries out dynamic threshold modeling of various parameters of the lubricating oil, monitors the state of the lubricating oil, predicts the service life of the lubricating oil, and diagnoses the fault of the diesel engine; as well as Display unit, used to display the real-time status of lubricating oil and the results of diesel engine fault diagnosis; Wherein, the intelligent edge terminal has a built-in self-learning module; The self-learning module is capable of establishing a viscosity-temperature curve and adjusting the viscosity-temperature curve of different oil products in real time according to sample parameters; and The self-learning module is capable of setting an alarm threshold and adjusting the alarm threshold in real time according to a cumulative distribution function; The steps for establishing the viscosity-temperature curve are as follows: Extracting the viscosity history data of the diesel engine at various temperatures within a specified time after adding new lubricating oil from the data acquisition and storage unit; The viscosity history data are arranged in ascending order according to temperature, and after integrating the arranged viscosity history data, the oil coefficients A and B are calculated according to the following formula; log(log(v+0.7))=AB log T Where: v is the kinematic viscosity of the lubricating oil, in centistokes; T is the temperature of the lubricating oil in Kelvin; A and B are the oil quality coefficients of the lubricating oil; According to the above results, taking the minimum error as the objective function, the optimization mathematical model of coefficients A and B is established to obtain the optimal A and B coefficients when the error is minimum; The optimal coefficients A and B are substituted into the following formula to obtain the viscosity-temperature curve of the lubricating oil: Where: v t is the viscosity-temperature curve function of the lubricating oil.

2. The diesel engine lubricating oil monitoring and fault diagnosis device according to claim 1, characterized in that: The smart sensor assembly comprises: Lubricating oil viscosity sensor, used to collect the viscosity and temperature of lubricating oil; Lubricating oil moisture sensor, used to collect water activity and water content in lubricating oil; A lubricating oil dielectric constant sensor, used to collect the dielectric constant of the lubricating oil; and The lubricating oil particle sensor is used to collect the number of ferromagnetic particles and non-ferromagnetic particles in the lubricating oil at each gear.

3. The diesel engine lubricating oil monitoring and fault diagnosis device according to claim 2, characterized in that: The lubricating oil dynamic viscosity collected by the lubricating oil viscosity sensor is in the range of 0 to 400 cst and the temperature range is in the range of 0 to 150°C; The water activity range of the lubricating oil collected by the lubricating oil moisture sensor is between 0 and 100 aw, and the water content range is between 0 and 3000 ppm; The dielectric constant of the lubricating oil collected by the lubricating oil dielectric constant sensor ranges from 0 to 10; The minimum diameter of the ferromagnetic particles in the lubricating oil collected by the lubricating oil particle sensor is 40um, and the minimum diameter of the non-ferromagnetic particles is 135um.

4. The diesel engine lubricating oil monitoring and fault diagnosis device according to claim 1, characterized in that: The data of the sensor assembly analyzed by the data acquisition and storage unit include: the rate of change of the kinematic viscosity of the lubricating oil, the rate of degradation of the lubricating oil, and the first-order difference of various data; The data acquisition and storage unit also includes: The real-time database storage module performs partition compression storage on the real-time parameters of the diesel engine.

5. The diesel engine lubricating oil monitoring and fault diagnosis device according to claim 4, characterized in that: The kinematic viscosity change rate formula is as follows: Wherein, η is the rate of change of kinematic viscosity; v1 is the measured value of the kinematic viscosity of the new lubricating oil, in mm 2 / s; v2 is the measured value of the kinematic viscosity of the lubricating oil in use, in mm 2 / s.

6. The diesel engine lubricating oil monitoring and fault diagnosis device according to claim 4, characterized in that: The oil degradation rate formula of the lubricating oil is as follows: Among them, k is the oil degradation rate; ε1 is the measured value of the medium point constant of new oil; ε2 is the measured value of the dielectric constant of the oil in use.

7. The diesel engine lubricating oil monitoring and fault diagnosis device according to claim 4, characterized in that: The first-order differences of various data include: water activity in lubricating oil, water content in lubricating oil, number of ferromagnetic particles and / or number of non-ferromagnetic particles in lubricating oil per minute, number of ferromagnetic particles and / or mass of non-ferromagnetic particles in lubricating oil per hour; Extract the first-order difference of its time series as the eigenvalue, the formula is as follows: D y1 =y t+1 -y t Among them, D y1 is the first-order difference of the parameter; y t+1 is the real-time value at time t+1; y t is the real-time value at time t.

8. The diesel engine lubricating oil monitoring and fault diagnosis device according to claim 1, characterized in that: Extracting data on the quantity and mass of ferromagnetic particles in the lubricating oil within a specified time after the diesel engine is run-in from the data acquisition and storage unit, and performing continuous probability distribution analysis, using a probability greater than 99.8% as an initial alarm threshold for the quantity and mass of ferromagnetic particles in the lubricating oil; The data of the number and mass of ferromagnetic particles in the lubricating oil within at least 10 times the specified time after the diesel engine running-in is extracted from the data acquisition and storage unit, and a continuous probability distribution analysis is performed, and the final alarm threshold of the number and mass of ferromagnetic particles in the lubricating oil is taken as the probability greater than 99.8%.

9. The diesel engine lubricating oil monitoring and fault diagnosis device according to claim 1, characterized in that: The intelligent edge terminal monitors the lubricating oil status including: monitoring fixed thresholds, monitoring trends, and monitoring abnormal points.

Images