Method, system and equipment for predicting residual life of lubricating oil of drilling machine equipment and storage medium

Abstract

The invention discloses a drilling machine equipment lubricating oil remaining life prediction method, system and equipment and a storage medium, and relates to the technical field of oil drilling equipment lubricating oil informatization management. The detection data of the target lubricating oil are synthesized into the one-dimensional comprehensive health index, whether the comprehensive health index of the target lubricating oil is in the failure interval or not is judged, if yes, it is judged that the target lubricating oil cannot be continuously used, and otherwise, it is judged that the target lubricating oil cannot be continuously used. If yes, comparing with an existing degradation track library according to the service time and the comprehensive health index of the target lubricating oil, and searching an approximate degradation track as a reference sample; and determining the reference weight of the degradation track by combining the results of four similarity measurements of the time coincidence degree, the comprehensive health index coincidence degree, the equipment service life coincidence degree and the equipment working condition coincidence degree, and comprehensively calculating the residual life of the oil product. The sampling frequency of the lubricating oil of the equipment can be reduced in later maintenance, the labor input is reduced, and the oil change work on a drilling site according to quality is guided.

Description

Technical Field

[0001] The present invention relates to the technical field of information management of lubricating oil for oil drilling equipment, and more specifically to a method, system, equipment and storage medium for predicting the remaining life of lubricating oil for drilling equipment. Background Art

[0002] There are a large number of drilling equipment in the field drilling base, such as generators, engines, mud pumps, gearboxes, winches, hydraulic stations and torque converters. The replacement of lubricating oil of the above-mentioned drilling equipment is one of the important contents of daily maintenance of drilling equipment. For a long time, the replacement cycle of lubricating oil of drilling equipment has been implemented according to the set usage time given by the lubricating oil manufacturer. However, after a period of monitoring of lubricating oil of in-service drilling equipment, it was found that many major performance indicators of lubricating oils that have reached the replacement cycle are still good, which is far from the oil change reference value given by relevant standards. So is the set usage time given by the lubricating oil manufacturer reasonable? If it is not replaced according to the set usage time given by the lubricating oil manufacturer, how many hours should be adjusted to replace it? This has become a real problem facing the management of drilling equipment.

[0003] Published in October 2022 in Lubricating Oil, Vol. 37, No. 5, article number: 1002-3119(2022)05-0028-06, titled "Research on Reasonable Oil Change Cycle of Diesel Engine Oil in Drilling Service Based on Oil Monitoring", the authors are Cai Qingyou, Zeng Wenqiang, Peng Yuanchun, He Jia, Yu Hongjie, Ma Shengping and Yang Lin. Aiming at the problem of short oil change cycle given by the current drilling base power generation diesel engine equipment manufacturers, this paper selected three representative power generation oil production machines to conduct a reasonable oil change cycle test. Through the monitoring and analysis of the key performance indicators of the diesel engine oil in service, combined with the oil change reference values ​​given by the relevant standards, the reasonable oil change cycle of the diesel engine oil in service is found. The test results show that within the 1000h test period, none of the indicators of the service oil of the three test diesel engines exceeded the reference value for oil change, and most of the indicators still had relevant technical margins until the end of the test, indicating that it is basically feasible to increase the oil change cycle of drilling power generation and oil production machines from the original 500h to 1000h.

[0004] The above-mentioned prior art only studies the oil service cycle of the generator diesel engine, and increases the oil replacement cycle of the generator diesel engine from the original 500h to 1000h. The operating conditions of other drilling rig equipment are different from those of the generator diesel engine, and cannot be implemented in accordance with the mechanism replacement cycle of the generator diesel engine. If the mechanism replacement cycle of other drilling rig equipment is studied in accordance with the above-mentioned existing research method, it will take a lot of research time. The operating conditions of the drilling rig equipment are changeable. Even if the replacement cycle of its lubricating oil can be extended, the instability of the equipment operation will be greatly increased during the extended period of time. Therefore, it is necessary to conduct actual analysis in combination with the actual operation of the on-site equipment. Therefore, the above-mentioned prior art can only provide a feasibility study on extending the lubricating oil replacement cycle of the drilling rig equipment. According to the different operating conditions of different drilling rig equipment, the specific extension time of the lubricating oil replacement cycle also varies according to the actual operating conditions. This is also the current problem of monitoring the lubricating oil of the drilling rig equipment. Summary of the invention

[0005] In order to overcome the defects and deficiencies in the above-mentioned prior art, the present invention provides a method, system, device and storage medium for predicting the remaining life of lubricating oil for drilling equipment. The purpose of the present invention is to combine the existing data and the detection data of the lubricating oil to estimate the remaining life of the lubricating oil, so as to reduce the sampling frequency of the lubricating oil, reduce the manual input, and guide the oil replacement work according to the quality at the drilling site. The present invention synthesizes the detection data of the target lubricating oil into a one-dimensional comprehensive health index, judges whether the comprehensive health index of the target lubricating oil is in the failure interval, and if it is in the failure interval, it is determined that the target lubricating oil cannot be used any more. Otherwise, the service time and comprehensive health index of the target lubricating oil are compared with the existing degradation trajectory library, and a close degradation trajectory is found as a reference sample. The reference weight of the degradation trajectory is determined by combining the results of the four similarity measurements of time overlap, comprehensive health index overlap, equipment service years overlap and equipment working condition overlap, and the remaining life of the oil is comprehensively calculated. The present invention can reduce the sampling frequency of the lubricating oil of the equipment in subsequent maintenance, reduce labor input, and guide the oil replacement work according to quality at the drilling site.

[0006] In order to solve the above problems existing in the prior art, the present invention is implemented through the following technical solutions.

[0007] A first aspect of the present invention provides a method for predicting the remaining life of lubricating oil of drilling equipment, the method comprising the following steps:

[0008] S1. Acquire the test data of the target lubricant oil, and synthesize the test data of the target lubricant oil into a one-dimensional comprehensive health index;

[0009] S2, judging whether the comprehensive health index of the target lubricant is in the failure range, if it is in the failure range, judging that the target lubricant cannot be used any more, otherwise, proceeding to step S3;

[0010] S3. Compare the service time and comprehensive health index of the target lubricant with the existing degradation trajectory library, and use the degradation trajectory curve close to the service time and comprehensive health index of the target lubricant as a reference sample;

[0011] S4. Determine the reference weight of the reference sample by combining the results of four similarity measurements: the overlap of service time between the reference sample and the target lubricant, the overlap of comprehensive health index, the overlap of equipment service years, and the overlap of equipment operating conditions;

[0012] S5. Comprehensively calculate the remaining life of the target lubricant based on the remaining life of the reference sample and its reference weight.

[0013] Further preferably, the calculated remaining life, comprehensive health index and service time of the target lubricant are recorded in a degradation trajectory library.

[0014] Further preferably, the degradation trajectory library records the degradation trajectory of the degraded lubricant and its remaining life after each sampling point, and the ordinate of the degradation trajectory curve is the comprehensive health index, and the abscissa is the service time of the lubricant.

[0015] Further preferably, in step S3, a similarity time range is set according to the service time of the target lubricant sample, and degradation trajectory curves whose service time falls within the similarity time range are searched in the degradation trajectory library according to the similarity time range, and then several groups of similar degradation trajectory curves are screened out as reference samples through comparison of the comprehensive health index.

[0016] More preferably, the set similarity time range is 100 hours before and after the service time of the target lubricant.

[0017] Further preferably, in step S4, based on the similarity measurement function, the service time, comprehensive health index, equipment service life and equipment operating condition of the target lubricant are respectively subjected to similarity measurement calculation with the service time, comprehensive health index, equipment service life and equipment operating condition of the reference sample, and the reference weight of the reference sample is determined based on the calculated overlap of the service time, the overlap of the comprehensive health index, the overlap of the equipment service life and the overlap of the equipment operating condition.

[0018] More preferably, in step S5, the remaining life of the target lubricant is calculated by weighted summing the reference weights of multiple groups of reference samples and their remaining life.

[0019] More preferably, the similarity measurement function is:

[0020] In the formula, represents the degradation index of the mth diesel engine oil in service at the ith monitoring time point; Indicates the degradation index of the nth failed diesel engine oil that changes continuously.

[0021] Further preferred weight w n The calculation of (k) is based on the similarity Based on this, and to predict the remaining life of the diesel engine oil in service, define z n (k) is:

[0022] The weight function formula of the reference sample n at time t is: Where w n (k) represents the reference weight of the k-th sampling.

[0023] More preferably, the calculation formula for the remaining life of the target lubricant sample is:

[0024] In the formula, i represents the number of reference samples, w i (k) represents the reference weight of the reference sample, It represents the remaining life of the reference sample after the kth sampling; RULm(k) represents the remaining life of the tested lubricating oil sample after the kth sampling.

[0025] Further preferably, in step S1, the test data of the target lubricant is synthesized into a one-dimensional comprehensive health index, specifically, relative degradation calculations are performed on each test indicator in the test data of the target lubricant; then, the interval hierarchical analysis method is used to determine the weight value of each test indicator, and the comprehensive health index is calculated based on the weight value and relative degradation value of each test indicator.

[0026] More preferably, the value range of the comprehensive health index is [0,1]. The closer the comprehensive health index is to 0, the better the health status of the tested lubricant sample is. Conversely, the closer the comprehensive health index is to 1, the worse the health status of the tested lubricant sample is.

[0027] More preferably, the failure interval is [0.75, 1].

[0028] More preferably, the relative inferiority calculation is to perform comparative analysis and normalization processing on the detection indicators to eliminate the difference effects caused by different physical meanings and dimensional units;

[0029] Specifically, for the detection index whose value is larger, the better, the relative deterioration calculation formula is:

[0030]

[0031] For the detection index with smaller value, the better value, the relative deterioration calculation formula is:

[0032]

[0033] For the detection index with intermediate value, the relative deterioration calculation formula is:

[0034]

[0035] In the formula, θ represents the relative degradation value of each detection index, θ max Represents the upper limit of the detection index; θ min Represents the lower limit of the detection index; θ x Represents the initial value of the detection indicator.

[0036] More preferably, the interval analytic hierarchy process is used to determine the weight value of each detection index, specifically, an interval judgment matrix is ​​established, and the reciprocity 1-9 scaling rule is used to compare the indicators at the same level in pairs, and an interval number is used. Represents the results of pairwise comparisons, where: and According to the number of intervals, the interval judgment matrix A can be constructed as follows: ij ) m×m ;

[0037] The calculation formula for the weight value of each detection indicator is:

[0038] In the formula, λ- represents A - The maximum eigenvalue and the corresponding normalized eigenvector of A; λ+ represents + The maximum eigenvalue and the corresponding normalized eigenvector of ; w represents the weight value of the detection index, m represents the number of relative degradations, i represents the number of rows of the corresponding matrix, j represents the number of columns of the corresponding matrix, and w - Indicates A - The corresponding weights of each indicator, w + Indicates A + The corresponding weights of each indicator.

[0039] Further preferably, the calculation formula of the comprehensive health index is: Where HI represents the comprehensive health index, n represents the total number of detection index categories, i represents the detection index category, θ i represents the degradation value of the i-th type of detection index, w i Represents the weight value of the i-th category detection indicator.

[0040] Further preferably, the detection data of the target lubricating oil includes but is not limited to any one or more combinations of kinematic viscosity change rate, acid value increase value, base value decrease rate, moisture, closed cup flash point, fuel dilution, oxidation value, nitration value, soot, Fe content, Cu content, Al content and Si content.

[0041] A second aspect of the present invention provides a system for predicting the remaining life of lubricating oil for drilling equipment, the prediction system comprising:

[0042] The first module is used to obtain the detection data of the target lubricating oil;

[0043] The second module is used to synthesize the detection data of the target lubricant into a one-dimensional comprehensive health index;

[0044] The third module is used to determine whether the comprehensive health index of the target lubricant is in the failure range. If it is in the failure range, it is determined that the target lubricant cannot be used any more;

[0045] The fourth module is used to compare the service time and comprehensive health index of the target lubricant with the existing degradation trajectory library, and the degradation trajectory curve close to the service time and comprehensive health index of the target lubricant is used as a reference sample;

[0046] The fifth module is used to determine the reference weight of the reference sample by combining the results of four similarity measurements: the overlap of service time between the reference sample and the target lubricant, the overlap of comprehensive health index, the overlap of equipment service years, and the overlap of equipment operating conditions;

[0047] The sixth module is used to comprehensively calculate the remaining life of the target lubricant based on the remaining life of the reference sample and its reference weight.

[0048] Further preferably, the sixth module records the calculated remaining life, comprehensive health index and service time of the target lubricant into the degradation trajectory library.

[0049] Further preferably, the degradation trajectory library records the degradation trajectory of the degraded lubricant and its remaining life after each sampling point, and the ordinate of the degradation trajectory curve is the comprehensive health index, and the abscissa is the service time of the lubricant.

[0050] Further preferably, in the fourth module, a similarity time range is set according to the service time of the target lubricant sample, and degradation trajectory curves whose service time falls within the similarity time range are searched in the degradation trajectory library according to the similarity time range, and then several groups of similar degradation trajectory curves are screened out as reference samples through comparison of the comprehensive health index.

[0051] More preferably, the set similarity time range is 100 hours before and after the service time of the target lubricant.

[0052] Further preferably, the fifth module performs similarity measurement calculation on the service time, comprehensive health index, equipment service life and equipment operating condition of the target lubricant with the service time, comprehensive health index, equipment service life and equipment operating condition of the reference sample according to the similarity measurement function, and determines the reference weight of the reference sample according to the calculated overlap of service time, overlap of comprehensive health index, overlap of equipment service life and overlap of equipment operating condition.

[0053] More preferably, the sixth module uses the reference weights of multiple groups of reference samples and their remaining life to perform weighted summation calculation to obtain the remaining life of the target lubricant.

[0054] More preferably, the similarity measurement function is:

[0055] In the formula, represents the degradation index of the mth diesel engine oil in service at the ith monitoring time point; Indicates the degradation index of the nth failed diesel engine oil that changes continuously.

[0056] Further preferred weight w n The calculation of (k) is based on the similarity Based on this, and to predict the remaining life of the diesel engine oil in service, define z n (k) is:

[0057] The weight function formula of the reference sample n at time t is: Where w n (k) represents the reference weight of the k-th sampling.

[0058] More preferably, the calculation formula for the remaining life of the target lubricant sample is:

[0059] In the formula, i represents the number of reference samples, w i (k) represents the reference weight of the reference sample, It represents the remaining life of the reference sample after the kth sampling; RULm(k) represents the remaining life of the tested lubricating oil sample after the kth sampling.

[0060] Further preferably, the second module performs relative degradation calculations on each detection index in the detection data of the target lubricant oil; then uses the interval hierarchical analysis method to determine the weight value of each detection index, and calculates the comprehensive health index based on the weight value and relative degradation value of each detection index.

[0061] More preferably, the value range of the comprehensive health index is [0,1]. The closer the comprehensive health index is to 0, the better the health status of the tested lubricant sample is. Conversely, the closer the comprehensive health index is to 1, the worse the health status of the tested lubricant sample is.

[0062] More preferably, the failure interval is [0.75, 1].

[0063] More preferably, the relative inferiority calculation is to perform comparative analysis and normalization processing on the detection indicators to eliminate the difference effects caused by different physical meanings and dimensional units;

[0064] Specifically, for the detection index whose value is larger, the better, the relative deterioration calculation formula is:

[0065]

[0066] For the detection index with smaller value, the better value, the relative deterioration calculation formula is:

[0067]

[0068] For the detection index with intermediate value, the relative deterioration calculation formula is:

[0069]

[0070] In the formula, θ represents the relative degradation value of each detection index, θ max Represents the upper limit of the detection index; θ min Represents the lower limit of the detection index; θ x Represents the initial value of the detection indicator.

[0071] More preferably, the interval analytic hierarchy process is used to determine the weight value of each detection index, specifically, an interval judgment matrix is ​​established, and the reciprocity 1-9 scaling rule is used to compare the indicators at the same level in pairs, and an interval number is used. Represents the results of pairwise comparisons, where: and According to the number of intervals, the interval judgment matrix A can be constructed as follows: ij ) m×m ;

[0072] The calculation formula for the weight value of each detection indicator is:

[0073] In the formula, λ- represents the maximum eigenvalue of A- and the corresponding normalized eigenvector; λ+ represents A +The maximum eigenvalue and the corresponding normalized eigenvector of ; w represents the weight value of the detection index, m represents the number of relative degradations, i represents the number of rows of the corresponding matrix, j represents the number of columns of the corresponding matrix, and w - Indicates A - The corresponding weights of each indicator, w + Indicates A + The corresponding weights of each indicator.

[0074] Further preferably, the calculation formula of the comprehensive health index is: Where HI represents the comprehensive health index, n represents the total number of detection index categories, i represents the detection index category, θ i represents the degradation value of the i-th type of detection index, w i Represents the weight value of the i-th category detection indicator.

[0075] Further preferably, the detection data of the target lubricating oil acquired by the first module includes but is not limited to any one or more combinations of kinematic viscosity change rate, acid value increase value, base value decrease rate, moisture, closed cup flash point, fuel dilution, oxidation value, nitration value, soot, Fe content, Cu content, Al content and Si content.

[0076] The third aspect of the present invention provides a computer device, comprising a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute some or all of the steps described in the first aspect of the present invention.

[0077] The fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute some or all of the steps described in the first aspect of the present invention.

[0078] Compared with the prior art, the beneficial technical effects brought by the present invention are as follows:

[0079] 1. The present invention utilizes the detection data of the target lubricant and synthesizes it into a one-dimensional comprehensive health index. The comprehensive health index is used to determine whether the target lubricant has failed. If it has not failed, its remaining life is calculated. The predicted remaining life can provide a data reference for management personnel, so as to better manage the lubricant information used on drilling equipment in a unified manner. It is also beneficial to plan the maintenance frequency and sampling frequency of the target lubricant, further reduce the sampling monitoring frequency, reduce manual input, and predict the next monitoring time through the current monitoring data analysis, which not only meets the monitoring needs of oil change according to quality, but also further promotes the work of improving quality and efficiency, and can further improve the efficiency of oil change according to quality.

[0080] 2. When predicting the remaining life of a lubricant, the present invention compares the degradation trajectory of the lubricant with the existing degradation trajectory library to find a degradation trajectory curve that is similar to the service time and comprehensive health index of the target lubricant, and uses the existing data to predict the remaining life of the target lubricant, providing data support and basis for the prediction of the remaining life of the target lubricant, so that the prediction result is closer to the actual situation, the prediction result is more accurate, and has reference value.

[0081] 3. When predicting the remaining life of lubricating oil, the present invention also combines the results of four similarity measurements, namely, the overlap of time, the overlap of comprehensive health index, the overlap of equipment service life and the overlap of equipment working condition, to determine the reference weight of the degradation trajectory, so as to ensure the accuracy of the prediction results. Among them, the service time, comprehensive health index, equipment service life, equipment working condition, etc. are all the main reference standards affecting the service life of lubricating oil. Through the similarity measurement results of these four items, the degradation trajectory curve closest to the actual working condition of the target lubricating oil can be used to enhance its reference weight and improve its reference ratio, so that the predicted remaining life is more accurate. The service life of diesel engine oil in service can be calculated by taking the weighted average of the remaining life of similar diesel engine oil that has failed at a certain moment, and the similarity can be further determined by similarity matching of the degradation trend or status monitoring data between the service diesel engine oil and the failed diesel engine oil. Its prediction results are more referenceable and more accurate.

[0082] 4. In the present invention, the remaining life, comprehensive health index and service time of the target lubricant are recorded in the degradation trajectory library, which further enriches the data of the degradation trajectory library. As the amount of monitoring data increases, the data in the degradation trajectory library will become more and more optimized and richer, and the matching degree of the degradation trajectory of the lubricant sample detection data will become higher and higher, the accuracy of judging the state of the lubricant will be higher, and the calculated value of the remaining life of the lubricant will also be more accurate.

[0083] 5. The present invention introduces "relative degradation value" and "comprehensive health index" to evaluate and calculate the status of the lubricating oil in use, and conducts a comprehensive evaluation of the lubricating oil in use based on the test results of multiple indicators, rather than judging the performance of the lubricating oil in use based on a certain indicator. The evaluation system is more scientific and the evaluation results are more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] Figure 1 This is a flow chart of the method for predicting the remaining life of lubricating oil for drilling rig equipment of the present invention;

[0085] Figure 2 This is a framework diagram of the drilling rig assembly lubricant remaining life prediction system of the present invention;

[0086] Figure 3 It is the CI-class diesel engine lubricant oil degradation trajectory library;

[0087] Figure 4 It is the degradation trajectory library of CF-class diesel engine lubricating oil;

[0088] Figure 5 It is a Carter-specific diesel engine lubricant degradation trajectory library;

[0089] Figure 6 It is a Volvo diesel engine lubricant degradation trajectory library. DETAILED DESCRIPTION

[0090] The following will be combined with the drawings of the present invention specification 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0091] Example 1

[0092] As a preferred embodiment of the present invention, refer to the attached Figure 1 As shown, this embodiment provides a method for predicting the remaining life of lubricating oil of drilling equipment, and the prediction method includes the following steps:

[0093] S1. Acquire the test data of the target lubricant oil, and synthesize the test data of the target lubricant oil into a one-dimensional comprehensive health index;

[0094] S2, judging whether the comprehensive health index of the target lubricant is in the failure range, if it is in the failure range, judging that the target lubricant cannot be used any more, otherwise, proceeding to step S3;

[0095] S3. Compare the service time and comprehensive health index of the target lubricant with the existing degradation trajectory library, and use the degradation trajectory curve close to the service time and comprehensive health index of the target lubricant as a reference sample;

[0096] S4. Determine the reference weight of the reference sample by combining the results of four similarity measurements: the overlap of service time between the reference sample and the target lubricant, the overlap of comprehensive health index, the overlap of equipment service years, and the overlap of equipment operating conditions;

[0097] S5. Comprehensively calculate the remaining life of the target lubricant based on the remaining life of the reference sample and its reference weight.

[0098] In this embodiment, the prediction of the remaining life of the in-use lubricating oil based on the similarity of degradation trajectories is proposed. Considering the influence of relevant influencing factors on the prediction, the degradation trajectories can be considered similar in theory. Therefore, it is believed that the life of the diesel engine oil in service can be calculated by the weighted average of the remaining life of the similar diesel engine oil that has failed at a certain moment, and the similarity can be further determined by similarity matching of the degradation trend or state monitoring data between the in-service diesel engine oil and the failed diesel engine oil. Its prediction results are more referenceable and more accurate.

[0099] Example 2

[0100] As another preferred embodiment of the present invention, this embodiment further elaborates and supplements the technical solution of the present invention on the basis of the above-mentioned embodiment 1.

[0101] In this embodiment, the calculated remaining life, comprehensive health index and service time of the target lubricant are recorded in the degradation trajectory library. The data of the degradation trajectory library is further enriched. As the amount of monitoring data increases, the data in the degradation trajectory library will be more optimized and more abundant, and the matching degree of the degradation trajectory of the lubricant sample detection data will be higher and higher, the accuracy of judging the state of the lubricant will be higher, and the calculated value of the remaining life of the lubricant will be more accurate.

[0102] Further preferably, the degradation trajectory library records the degradation trajectory of the degraded lubricant and its remaining life after each sampling point, and the ordinate of the degradation trajectory curve is the comprehensive health index, and the abscissa is the service time of the lubricant.

[0103] In this embodiment, the applicant analyzes the monitoring data of 384 types of diesel engine lubricants, combines the existing monitoring data to predict the future data change trend, and performs trend analysis based on the ARMA time series prediction model. This method is a common time series prediction analysis model and a typical method for studying stationary random processes. The applicant uses monitoring data and operating time to establish a degradation trajectory library for 4 types of oil products and 79 degradation trajectory models within the complete life cycle, as shown in the attached manual. Figure 3 , Attachment Figure 4 , Attachment Figure 5 and attached Figure 6 As shown, Figure 3 It is a CI-class diesel engine lubricant degradation trajectory library. Figure 4 It is the degradation trajectory library of CF-class diesel engine lubricating oil. Figure 5 It is a Carter-specific diesel engine lubricant degradation trajectory library. Figure 6 It is a Volvo diesel engine lubricant degradation trajectory library.

[0104] In this embodiment, a corresponding degradation trajectory library is selected according to the equipment model of the lubricating oil sample, and then a degradation trajectory in the corresponding degradation trajectory library is selected according to the equipment usage condition of the lubricating oil sample. Then, when the lubricating oil sample is sampled, the service time and the comprehensive health index of the lubricating oil are compared with the degradation trajectory. Specifically, the degradation trajectory of the degraded lubricating oil in the degradation collection library is compared with the service time and the comprehensive health index of the detected lubricating oil sample to find the closest degradation trajectory of the degraded lubricating oil.

[0105] The specific comparison process is as follows: set a similarity time range according to the service life of the target lubricant sample, search for degradation trajectory curves whose service life falls within the similarity time range in the degradation trajectory library, and then select several groups of similar degradation trajectory curves as reference samples through comparison of the comprehensive health index.

[0106] As an example, the similarity time range is set to 100 hours before and after the service time of the lubricant.

[0107] In step S4, based on the similarity measurement function, the service time, comprehensive health index, equipment service life and equipment operating condition of the target lubricant are respectively measured and calculated for similarity with the service time, comprehensive health index, equipment service life and equipment operating condition of the reference sample, and the reference weight of the reference sample is determined based on the calculated overlap of the service time, the overlap of the comprehensive health index, the overlap of the equipment service life and the overlap of the equipment operating condition. In step S5, the remaining life of the target lubricant is calculated by weighted summing the reference weights of multiple groups of reference samples and their remaining life.

[0108] Example 3

[0109] As another preferred embodiment of the present invention, this embodiment is an actual prediction case proposed on the basis of the above-mentioned embodiment 1 or embodiment 2. This case is a case of predicting the remaining life of a CI-grade diesel engine lubricant. There is a set of relevant detection indicators and service time information of the service diesel engine lubricant as shown in Table 1. Through the method described in the above embodiment 2, the detection data is synthesized into a one-dimensional comprehensive health index, and then the service time and the obtained one-dimensional comprehensive health index are brought into the following table: Figure 3 The CI-level diesel engine lubricating oil degradation trajectory library shown in the figure is used to find similar degradation trajectory curves and then calculate their remaining life values.

[0110] Table 1 shows the test data of CI grade diesel engine lubricating oil in the case

[0111]

[0112] The similarity time range is set to 100 hours before and after, that is, the test data in the time range of [197h, 397h] are used as the comparison range. In the existing CI-level diesel engine lubricant degradation trajectory library, there are 3 test data in this time range, namely 278h, 327h and 373h.

[0113] The similarity measurement with existing samples is carried out from four aspects: the first is the overlap of time, the second is the overlap of test data, the third is the overlap of equipment service life, and the fourth is the similarity of equipment working conditions (blocks). The reference weight of each sample is determined based on the results of the similarity measurement. The relevant calculations are shown in Table 2 below.

[0114] Table 2 is the similarity and weight calculation table

[0115]

[0116]

[0117] The matching degree of the test data in Table 2 above is determined by the comprehensive health index HI value of each reference sample and lubricant sample; the matching degree of service life is accurate to the year, and the matching degree differs by 1% for a difference of 1 year; the matching degree of operating conditions mainly considers the block where the diesel engine is located, the matching degree of the same drilling team is 100%, the matching degree of different drilling teams in the same area is 95%, and the matching degree of different areas is 90%.

[0118] Remaining life calculation: The remaining life calculation formula of the target lubricant sample is RUL = S1*W1+S2*W2+S3*W3, where S1, S2, and S3 represent the remaining life of the reference sample at their respective time points, and W1, W2, and W3 represent the weights of each sample. Figure 5 As shown in the existing CI-grade diesel engine lubricant degradation trajectory library, the S1, S2, and S3 values ​​are respectively substituted into the calculation to obtain: RUL=1090*0.33+1124*0.34+1270*0.33=1161h.

[0119] Example 4

[0120] As another preferred embodiment of the present invention, this embodiment is a further detailed supplement and elaboration of the technical solution of the present invention on the basis of the above-mentioned embodiment 1, embodiment 2 or embodiment 3.

[0121] In this embodiment, the similarity measurement function is:

[0122] In the formula, represents the degradation index of the mth diesel engine oil in service at the ith monitoring time point; Indicates the degradation index of the nth failed diesel engine oil that changes continuously.

[0123] Further preferred weight w n The calculation of (k) is based on the similarity Based on this, and to predict the remaining life of the diesel engine oil in service, define z n (k) is:

[0124] The weight function formula of the reference sample n at time t is: Where w n (k) represents the reference weight of the k-th sampling.

[0125] The remaining life of the target lubricant sample is calculated as follows:

[0126] In the formula, i represents the number of reference samples, w i (k) represents the reference weight of the reference sample, Represents the remaining life of the reference sample after the kth sampling; RUL m (k) represents the remaining life of the lubricating oil sample after the kth sampling.

[0127] Example 5

[0128] As another preferred embodiment of the present invention, this embodiment further elaborates and supplements the technical solution of the present invention on the basis of the above-mentioned embodiment 1, embodiment 2, embodiment 3 or embodiment 4.

[0129] This embodiment specifically discloses: in step S1, the detection data of the target lubricant is synthesized into a one-dimensional comprehensive health index, specifically, the relative degradation value of each detection index in the detection data of the target lubricant is calculated respectively; then the interval hierarchy analysis method is used to determine the weight value of each detection index, and the comprehensive health index is calculated according to the weight value and relative degradation value of each detection index.

[0130] As an example, the value range of the comprehensive health index is [0,1]. The closer the comprehensive health index is to 0, the better the health status of the lubricant sample is. On the contrary, the closer the comprehensive health index is to 1, the worse the health status of the lubricant sample is. For specific evaluation registration, see Table 3.

[0131] Table 3 is the comprehensive health index evaluation level table

[0132]

[0133] It can be seen from Table 3 above that the failure interval is [0.75, 1].

[0134] The relative inferiority calculation is to compare and analyze the test indicators and normalize them to eliminate the difference caused by different physical meanings and dimensional units;

[0135] Specifically, for the detection index whose value is larger, the better, the relative deterioration calculation formula is:

[0136]

[0137] For the detection index with smaller value, the better value, the relative deterioration calculation formula is:

[0138]

[0139] For the detection index with intermediate value, the relative deterioration calculation formula is:

[0140]

[0141] In the formula, θ represents the relative degradation value of each detection index, θ max Represents the upper limit of the detection index; θ min Represents the lower limit of the detection index; θ x Represents the initial value of the detection indicator.

[0142] The interval analytic hierarchy process is used to determine the weight value of each detection index. Specifically, an interval judgment matrix is ​​established, as shown in Table 4 below, and the reciprocity 1-9 scaling rule is used to compare the indicators at the same level pairwise.

[0143] Table 4 shows the reciprocity 1-9 scaling rules

[0144]

[0145] Use an interval number Represents the results of pairwise comparisons, where: and According to the number of intervals, the interval judgment matrix A can be constructed as follows: ij ) m×m ;

[0146] The calculation formula for the weight value of each detection indicator is:

[0147] In the formula, λ- represents the maximum eigenvalue of A- and the corresponding normalized eigenvector; λ+ represents A + The maximum eigenvalue and the corresponding normalized eigenvector of ; w represents the weight value of the detection index, m represents the number of relative degradations, i represents the number of rows of the corresponding matrix, j represents the number of columns of the corresponding matrix, and w - Indicates A - The corresponding weights of each indicator, w + Indicates A+ The corresponding weights of each indicator.

[0148] The calculation formula of comprehensive health index is: Where HI represents the comprehensive health index, n represents the total number of detection index categories, i represents the detection index category, θ i represents the degradation value of the i-th type of detection index, w i Represents the weight value of the i-th category detection indicator.

[0149] As an implementation mode of this embodiment, the detection data of the target lubricating oil includes but is not limited to any one or more combinations of kinematic viscosity change rate, acid value increase value, base value decrease rate, moisture, closed cup flash point, fuel dilution, oxidation value, nitration value, soot, Fe content, Cu content, Al content and Si content.

[0150] Specifically, the normal distribution method is used to analyze the limit values ​​of each test index in the lubricating oil test data, and the degree of change of each test index with the service time of the oil product is used as the standard for whether to include it in the multi-index judgment system. The more obvious the change of the index with the service time of the oil product is, the more it needs to be included in the multi-index judgment system; otherwise, it will not be included in the multi-index system.

[0151] Example 6

[0152] As another preferred embodiment of the present invention, refer to the attached specification Figure 2 As shown, this embodiment discloses a system for predicting the remaining life of lubricating oil for drilling equipment, the prediction system comprising:

[0153] The first module is used to obtain the detection data of the target lubricating oil;

[0154] The second module is used to synthesize the detection data of the target lubricant into a one-dimensional comprehensive health index;

[0155] The third module is used to determine whether the comprehensive health index of the target lubricant is in the failure range. If it is in the failure range, it is determined that the target lubricant cannot be used any more;

[0156] The fourth module is used to compare the service time and comprehensive health index of the target lubricant with the existing degradation trajectory library, and the degradation trajectory curve close to the service time and comprehensive health index of the target lubricant is used as a reference sample;

[0157] The fifth module is used to determine the reference weight of the reference sample by combining the results of four similarity measurements: the overlap of service time between the reference sample and the target lubricant, the overlap of comprehensive health index, the overlap of equipment service years, and the overlap of equipment operating conditions;

[0158] The sixth module is used to comprehensively calculate the remaining life of the target lubricant based on the remaining life of the reference sample and its reference weight.

[0159] In this embodiment, the fourth module and the fifth module are predictions of the remaining life of the in-use lubricating oil based on the similarity of degradation trajectories. Considering the influence of relevant influencing factors on the prediction, the degradation trajectories can be considered similar in theory. Therefore, it is believed that the life of the diesel engine oil in service can be calculated by the weighted average of the remaining life of the similar diesel engine oil that has failed at a certain moment, and the similarity can be further determined by similarity matching of the degradation trend or state monitoring data between the in-service diesel engine oil and the failed diesel engine oil. Its prediction results are more referenceable and more accurate.

[0160] Example 7

[0161] As another preferred embodiment of the present invention, this embodiment is a further detailed supplement and elaboration of the technical solution of the present invention on the basis of the above-mentioned embodiment 6. In this embodiment, the sixth module records the calculated remaining life, comprehensive health index and service time of the target lubricant into the degradation trajectory library. The degradation trajectory library records the degradation trajectory of the degraded lubricant and its remaining life after each sampling point. The ordinate of the degradation trajectory curve is the comprehensive health index, and the abscissa is the service time of the lubricant. The data in the degradation trajectory library is further enriched. With the increase in the amount of monitoring data, the data in the degradation trajectory library will be more and more optimized and richer. The matching degree of the degradation trajectory of the lubricant sample detection data will be higher and higher, the accuracy of judging the state of the lubricant will be higher, and the calculated value of the remaining life of the lubricant will be more accurate.

[0162] In this embodiment, the applicant analyzes the monitoring data of 384 types of diesel engine lubricants, combines the existing monitoring data to predict the future data change trend, and performs trend analysis based on the ARMA time series prediction model. This method is a common time series prediction analysis model and a typical method for studying stationary random processes. The applicant uses monitoring data and operating time to establish a degradation trajectory library for 4 types of oil products and 79 degradation trajectory models within the complete life cycle, as shown in the attached manual. Figure 3 , Attachment Figure 4 , Attachment Figure 5 and attached Figure 6 As shown, Figure 3 It is a CI-class diesel engine lubricant degradation trajectory library. Figure 4 It is the degradation trajectory library of CF-class diesel engine lubricating oil. Figure 5 It is a Carter-specific diesel engine lubricant degradation trajectory library. Figure 6 It is a Volvo diesel engine lubricant degradation trajectory library.

[0163] In this embodiment, a corresponding degradation trajectory library is selected according to the equipment model of the lubricating oil sample, and then a degradation trajectory in the corresponding degradation trajectory library is selected according to the equipment usage condition of the lubricating oil sample. Then, when the lubricating oil sample is sampled, the service time and the comprehensive health index of the lubricating oil are compared with the degradation trajectory. Specifically, the degradation trajectory of the degraded lubricating oil in the degradation collection library is compared with the service time and the comprehensive health index of the detected lubricating oil sample to find the closest degradation trajectory of the degraded lubricating oil.

[0164] Specifically, in the fourth module, a similarity time range is set according to the service life of the target lubricant sample, and degradation trajectory curves whose service life falls within the similarity time range are searched in the degradation trajectory library according to the similarity time range. Then, by comparing the comprehensive health index, several groups of similar degradation trajectory curves are selected as reference samples.

[0165] As an example, the similarity time range is set to 100 hours before and after the service time of the target lubricant.

[0166] Furthermore, the fifth module performs similarity measurement calculations on the service time, comprehensive health index, equipment service life and equipment operating condition of the target lubricant and the service time, comprehensive health index, equipment service life and equipment operating condition of the reference sample respectively according to the similarity measurement function, and determines the reference weight of the reference sample according to the calculated overlap of the service time, the overlap of the comprehensive health index, the overlap of the equipment service life and the overlap of the equipment operating condition.

[0167] The sixth module uses the reference weights of multiple groups of reference samples and their remaining life to perform weighted summation calculation to obtain the remaining life of the target lubricant.

[0168] Example 8

[0169] As another preferred embodiment of the present invention, this embodiment is based on the above-mentioned embodiment 6 or embodiment 7, and proposes an actual prediction case for the technical solution of the present invention. This case is a case of predicting the remaining life of CI-grade diesel engine lubricating oil. There is a set of service diesel engine lubricating oil related detection indicators and service time information as shown in Table 5. Through the system content described in the above embodiment 6 or embodiment 7, the detection data is synthesized into a one-dimensional comprehensive health index, and then the service time and the obtained one-dimensional comprehensive health index are brought into the following example. Figure 3 The CI-level diesel engine lubricating oil degradation trajectory library shown in the figure is used to find similar degradation trajectory curves and then calculate their remaining life values.

[0170] Table 5 shows the test data of CI-grade diesel engine lubricating oil in the case

[0171]

[0172] The similarity time range is set to 100 hours before and after, that is, the test data in the time range of [197h, 397h] are used as the comparison range. In the existing CI-level diesel engine lubricant degradation trajectory library, there are 3 test data in this time range, namely 278h, 327h and 373h.

[0173] The similarity measurement with existing samples is carried out from four aspects: the first is the overlap of time, the second is the overlap of test data, the third is the overlap of equipment service life, and the fourth is the similarity of equipment working conditions (blocks). The reference weight of each sample is determined based on the results of the similarity measurement. The relevant calculations are shown in Table 6 below.

[0174] Table 6 is the similarity and weight calculation table

[0175]

[0176] The matching degree of the test data in the above Table 6 is determined by the comprehensive health index HI value of each reference sample and lubricant sample; the matching degree of service life is accurate to the year, and the matching degree differs by 1% for a difference of 1 year; the matching degree of operating conditions mainly considers the block where the diesel engine is located, the matching degree of the same drilling team is 100%, the matching degree of different drilling teams in the same area is 95%, and the matching degree of different areas is 90%.

[0177] Remaining life calculation: The remaining life calculation formula of the target lubricant sample is RUL = S1*W1+S2*W2+S3*W3, where S1, S2, and S3 represent the remaining life of the reference sample at their respective time points, and W1, W2, and W3 represent the weights of each sample. Figure 5 As shown in the existing CI-grade diesel engine lubricant degradation trajectory library, the S1, S2, and S3 values ​​are respectively substituted into the calculation to obtain: RUL=1090*0.33+1124*0.34+1270*0.33=1161h.

[0178] Example 9

[0179] As another preferred embodiment of the present invention, this embodiment is a further detailed supplement and elaboration of the technical solution of the present invention on the basis of the above-mentioned embodiment 6, embodiment 7 or embodiment 8.

[0180] The similarity measurement function is In the formula, represents the degradation index of the mth diesel engine oil in service at the ith monitoring time point; Indicates the degradation index of the nth failed diesel engine oil that changes continuously.

[0181] Further preferred weight w nThe calculation of (k) is based on the similarity Based on this, and to predict the remaining life of the diesel engine oil in service, define z n (k) is:

[0182] The weight function formula of the reference sample n at time t is: Where w n (k) represents the reference weight of the k-th sampling.

[0183] More preferably, the calculation formula for the remaining life of the target lubricant sample is:

[0184] In the formula, i represents the number of reference samples, w i (k) represents the reference weight of the reference sample, It represents the remaining life of the reference sample after the kth sampling; RULm(k) represents the remaining life of the tested lubricating oil sample after the kth sampling.

[0185] Example 10

[0186] As another preferred embodiment of the present invention, this embodiment is a further detailed supplement and elaboration of the technical solution of the present invention on the basis of the above-mentioned embodiment 6, embodiment 7, embodiment 8 or embodiment 9.

[0187] The second module calculates the relative deterioration of each test indicator in the test data of the target lubricant; then uses the interval hierarchical analysis method to determine the weight value of each test indicator, and calculates the comprehensive health index based on the weight value and relative deterioration value of each test indicator.

[0188] As an example, the value range of the comprehensive health index is [0,1]. The closer the comprehensive health index is to 0, the better the health status of the lubricant sample is. On the contrary, the closer the comprehensive health index is to 1, the worse the health status of the lubricant sample is. For specific evaluation registration, see Table 6.

[0189] Table 6 is the comprehensive health index evaluation level table

[0190]

[0191] It can be seen from Table 3 above that the failure interval is [0.75, 1].

[0192] In the second module, the relative inferiority calculation is to compare and analyze the detection indicators and normalize them to eliminate the difference caused by different physical meanings and dimensional units;

[0193] Specifically, for the detection index whose value is larger, the better, the relative deterioration calculation formula is:

[0194]

[0195] For the detection index with smaller value, the better value, the relative deterioration calculation formula is:

[0196]

[0197] For the detection index with intermediate value, the relative deterioration calculation formula is:

[0198]

[0199] In the formula, θ represents the relative degradation value of each detection index, θ max Represents the upper limit of the detection index; θ min Represents the lower limit of the detection index; θ x Represents the initial value of the detection indicator.

[0200] The interval analytic hierarchy process is used to determine the weight value of each detection index. Specifically, an interval judgment matrix is ​​established, as shown in Table 8 below, and the reciprocity 1-9 scaling rule is used to compare the indicators at the same level pairwise.

[0201] Table 8 shows the reciprocity 1-9 scaling rules

[0202]

[0203] Use an interval number Represents the results of pairwise comparisons, where: and According to the number of intervals, the interval judgment matrix A can be constructed as follows: ij ) m×m ;

[0204] The calculation formula for the weight value of each detection indicator is:

[0205] In the formula, λ- represents A - The maximum eigenvalue and the corresponding normalized eigenvector of A; λ+ represents + The maximum eigenvalue and the corresponding normalized eigenvector of ; w represents the weight value of the detection index, m represents the number of relative degradations, i represents the number of rows of the corresponding matrix, j represents the number of columns of the corresponding matrix, and w - Indicates A - The corresponding weights of each indicator, w + Indicates A + The corresponding weights of each indicator.

[0206] The calculation formula of comprehensive health index is: Where HI represents the comprehensive health index, n represents the total number of detection index categories, i represents the detection index category, θ i represents the degradation value of the i-th type of detection index, w i Represents the weight value of the i-th category detection indicator.

[0207] As an implementation mode of this embodiment, the detection data of the target lubricating oil includes but is not limited to any one or more combinations of kinematic viscosity change rate, acid value increase value, base value decrease rate, moisture, closed cup flash point, fuel dilution, oxidation value, nitration value, soot, Fe content, Cu content, Al content and Si content;

[0208] Specifically, the normal distribution method is used to analyze the limit values ​​of each test index in the lubricating oil test data, and the degree of change of each test index with the service time of the oil product is used as the standard for whether to include it in the multi-index judgment system. The more obvious the change of the index with the service time of the oil product is, the more it needs to be included in the multi-index judgment system; otherwise, it will not be included in the multi-index system.

[0209] Embodiment 11

[0210] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps of the above-mentioned hospital logistics equipment economic analysis method based on historical data are implemented.

[0211] In this embodiment, the processor may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0212] The memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer executable programs and units, such as the corresponding program units in the above method embodiments of the present invention. The processor executes various functional applications of the processor and works data processing by running the non-transitory software programs, instructions and modules stored in the memory, that is, implementing the method in the above method embodiments.

[0213] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0214] The one or more units are stored in the memory, and when executed by the processor, perform the steps in the above-mentioned embodiment 1, embodiment 2, embodiment 3, embodiment 4 or embodiment 5.

[0215] Example 12

[0216] As another preferred embodiment of the present invention, this embodiment discloses a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps in the above-mentioned embodiment 1, embodiment 2, embodiment 3, embodiment 4 or embodiment 5 are implemented.

Claims

1. A method for predicting the remaining life of lubricating oil for drilling equipment, characterized by: The prediction method includes the following steps: S1. Acquire the test data of the target lubricant oil, and synthesize the test data of the target lubricant oil into a one-dimensional comprehensive health index; S2, judging whether the comprehensive health index of the target lubricant is in the failure range, if it is in the failure range, judging that the target lubricant cannot be used any more, otherwise, proceeding to step S3; S3. Compare the service time and comprehensive health index of the target lubricant with the existing degradation trajectory library, and use the degradation trajectory curve close to the service time and comprehensive health index of the target lubricant as a reference sample; S4. Determine the reference weight of the reference sample by combining the results of four similarity measurements: the overlap of service time between the reference sample and the target lubricant, the overlap of comprehensive health index, the overlap of equipment service years, and the overlap of equipment operating conditions; S5. Comprehensively calculate the remaining life of the target lubricant based on the remaining life of the reference sample and its reference weight.

2. The method for predicting the remaining life of lubricating oil for drilling equipment according to claim 1, characterized in that: The calculated remaining life, comprehensive health index and service time of the target lubricant are recorded in the degradation trajectory library.

3. The method for predicting the remaining life of lubricating oil for drilling equipment according to claim 1 or 2, characterized in that: The degradation trajectory library records the degradation trajectory of the degraded lubricant and its remaining life after each sampling point. The ordinate of the degradation trajectory curve is the comprehensive health index, and the abscissa is the service time of the lubricant.

4. The method for predicting the remaining life of lubricating oil for drilling equipment according to claim 1 or 2, characterized in that: In step S3, a similarity time range is set according to the service life of the target lubricant sample, and degradation trajectory curves whose service life falls within the similarity time range are searched in the degradation trajectory library according to the similarity time range. Then, by comparing the comprehensive health index, several groups of similar degradation trajectory curves are selected as reference samples.

5. The method for predicting the remaining life of lubricating oil for drilling equipment according to claim 4, characterized in that: The similarity time range is set to 100 hours before and after the service time of the target lubricant.

6. The method for predicting the remaining life of lubricating oil for drilling equipment according to claim 1, characterized in that: In step S4, based on the similarity measurement function, the service time, comprehensive health index, equipment service life and equipment operating condition of the target lubricant are respectively measured and calculated for similarity with the service time, comprehensive health index, equipment service life and equipment operating condition of the reference sample, and the reference weight of the reference sample is determined based on the calculated overlap of the service time, the overlap of the comprehensive health index, the overlap of the equipment service life and the overlap of the equipment operating condition.

7. The method for predicting the remaining life of lubricating oil for drilling equipment according to claim 1, 2 or 6, characterized in that: In step S5, the reference weights of multiple groups of reference samples and their remaining lives are used to perform weighted summation calculation to obtain the remaining life of the target lubricant.

8. The method for predicting the remaining life of lubricating oil for drilling equipment according to claim 6, characterized in that: The similarity measure function is In the formula, represents the degradation index of the mth diesel engine oil in service at the ith monitoring time point; Indicates the degradation index of the nth failed diesel engine oil that changes continuously.

9. The method for predicting the remaining life of lubricating oil for drilling equipment according to claim 1 or 6, characterized in that: The calculation formula of the reference weight is: Where w n (k) represents the reference weight of the kth sampling, Indicates similarity.

10. The method for predicting the remaining life of lubricating oil of drilling equipment according to claim 7, characterized in that: The remaining life of the target lubricant sample is calculated by: In the formula, i represents the number of reference samples, w i (k) represents the reference weight of the reference sample, Represents the remaining life of the reference sample after the kth sampling; RUL m (k) represents the remaining life of the lubricating oil sample after the kth sampling.

11. The method for predicting the remaining life of lubricating oil for drilling equipment according to claim 1, characterized in that: In step S1, the test data of the target lubricant are synthesized into a one-dimensional comprehensive health index. Specifically, the relative degradation of each test indicator in the test data of the target lubricant is calculated respectively; then the interval hierarchical analysis method is used to determine the weight value of each test indicator, and the comprehensive health index is calculated based on the weight value and relative degradation value of each test indicator.

12. The method for predicting the remaining life of lubricating oil for drilling equipment according to claim 1, 2, 6 or 11, characterized in that: The value range of the comprehensive health index is [0,1]. The closer the comprehensive health index is to 0, the better the health status of the tested lubricant sample is. Conversely, the closer the comprehensive health index is to 1, the worse the health status of the tested lubricant sample is.

13. The method for predicting the remaining life of lubricating oil for drilling equipment according to claim 12, characterized in that: The failure interval is [0.75, 1].

14. The method for predicting the remaining life of lubricating oil of drilling equipment according to claim 11, characterized in that: The relative inferiority calculation is to compare and analyze the test indicators and normalize them to eliminate the difference caused by different physical meanings and dimensional units; Specifically, for the detection index whose value is larger, the better, the relative deterioration calculation formula is: For the detection index with smaller value, the better value, the relative deterioration calculation formula is: For the detection index with intermediate value, the relative deterioration calculation formula is: In the formula, θ represents the relative degradation value of each detection index, θ max Represents the upper limit of the detection index; θ min Represents the lower limit of the detection index; θ x Represents the initial value of the detection indicator.

15. The method for predicting the remaining life of lubricating oil of drilling equipment according to claim 11, characterized in that: The interval analytic hierarchy process is used to determine the weight value of each detection index. Specifically, an interval judgment matrix is ​​established, and the reciprocity 1-9 scaling rule is used to compare the indicators at the same level. Represents the results of pairwise comparisons, where: and According to the number of intervals, the interval judgment matrix A can be constructed as follows: ij ) m×m ; The calculation formula for the weight value of each detection indicator is: In the formula, λ- represents A - The maximum eigenvalue and the corresponding normalized eigenvector of A; λ+ represents + The maximum eigenvalue and the corresponding normalized eigenvector of ; w represents the weight value of the detection index, m represents the number of relative degradations, i represents the number of rows of the corresponding matrix, j represents the number of columns of the corresponding matrix, and w - Indicates A - The corresponding weights of each indicator, w + Indicates A + The corresponding weights of each indicator.

16. The method for predicting the remaining life of lubricating oil of drilling equipment according to claim 11, characterized in that: The calculation formula of comprehensive health index is: Where HI represents the comprehensive health index, n represents the total number of detection index categories, i represents the detection index category, θ i represents the degradation value of the i-th detection index, and wi represents the weight value of the i-th detection index.

17. The method for predicting the remaining life of lubricating oil for drilling equipment according to claim 1, 2, 6 or 11, characterized in that: The detection data of the target lubricating oil include but are not limited to any one or more combinations of kinematic viscosity change rate, acid value increase value, base value decrease rate, moisture, closed cup flash point, fuel dilution, oxidation value, nitration value, soot, Fe content, Cu content, Al content and Si content.

18. The remaining life prediction system of lubricating oil for drilling rig equipment is characterized by: The forecasting system includes The first module is used to obtain the detection data of the target lubricating oil; The second module is used to synthesize the detection data of the target lubricant into a one-dimensional comprehensive health index; The third module is used to determine whether the comprehensive health index of the target lubricant is in the failure range. If it is in the failure range, it is determined that the target lubricant cannot be used any more; The fourth module is used to compare the service time and comprehensive health index of the target lubricant with the existing degradation trajectory library, and the degradation trajectory curve close to the service time and comprehensive health index of the target lubricant is used as a reference sample; The fifth module is used to determine the reference weight of the reference sample by combining the results of four similarity measurements: the overlap of service time between the reference sample and the target lubricant, the overlap of comprehensive health index, the overlap of equipment service years, and the overlap of equipment operating conditions; The sixth module is used to comprehensively calculate the remaining life of the target lubricant based on the remaining life of the reference sample and its reference weight.

19. The drilling equipment lubricant remaining life prediction system according to claim 18, characterized in that: The sixth module records the calculated remaining life, comprehensive health index and service time of the target lubricant into the degradation trajectory library.

20. The drilling equipment lubricant remaining life prediction system according to claim 18 or 19, characterized in that: The degradation trajectory library records the degradation trajectory of the degraded lubricant and its remaining life after each sampling point. The ordinate of the degradation trajectory curve is the comprehensive health index, and the abscissa is the service time of the lubricant.

21. The drilling equipment lubricant remaining life prediction system according to claim 18 or 19, characterized in that: In the fourth module, a similarity time range is set according to the service life of the target lubricant sample, and degradation trajectory curves whose service life falls within the similarity time range are searched in the degradation trajectory library according to the similarity time range. Then, by comparing the comprehensive health index, several groups of similar degradation trajectory curves are selected as reference samples.

22. The drilling equipment lubricant remaining life prediction system according to claim 21, characterized in that: The similarity time range is set to 100 hours before and after the service time of the target lubricant.

23. The drilling equipment lubricant remaining life prediction system according to claim 18, characterized in that: The fifth module performs similarity measurement calculations on the service time, comprehensive health index, equipment service life and equipment operating condition of the target lubricant and the service time, comprehensive health index, equipment service life and equipment operating condition of the reference sample respectively based on the similarity measurement function, and determines the reference weight of the reference sample based on the calculated overlap of the service time, the overlap of the comprehensive health index, the overlap of the equipment service life and the overlap of the equipment operating condition.

24. The system for predicting the remaining life of lubricating oil for drilling equipment according to claim 18, characterized in that: The sixth module uses the reference weights of multiple groups of reference samples and their remaining life to perform weighted summation calculation to obtain the remaining life of the target lubricant.

25. The drilling equipment lubricant remaining life prediction system according to claim 23, characterized in that: The similarity measure function is In the formula, represents the degradation index of the mth diesel engine oil in service at the ith monitoring time point; Indicates the degradation index of the nth failed diesel engine oil that changes continuously.

26. The drilling equipment lubricant remaining life prediction system according to claim 23, characterized in that: The calculation formula of the reference weight is: Where w n (k) represents the reference weight of the kth sampling, Indicates similarity.

27. The drilling equipment lubricant remaining life prediction system according to claim 24, characterized in that: The remaining life of the target lubricant sample is calculated by: In the formula, i represents the number of reference samples, w i (k) represents the reference weight of the reference sample, It represents the remaining life of the reference sample after the kth sampling; RULm(k) represents the remaining life of the tested lubricating oil sample after the kth sampling.

28. The drilling equipment lubricant remaining life prediction system according to claim 18, characterized in that: The second module calculates the relative deterioration of each test indicator in the test data of the target lubricant; then uses the interval hierarchical analysis method to determine the weight value of each test indicator, and calculates the comprehensive health index based on the weight value and relative deterioration value of each test indicator.

29. The drilling equipment lubricant remaining life prediction system according to claim 18 or 28, characterized in that: The value range of the comprehensive health index is [0,1]. The closer the comprehensive health index is to 0, the better the health status of the tested lubricant sample is. Conversely, the closer the comprehensive health index is to 1, the worse the health status of the tested lubricant sample is.

30. The drilling equipment lubricant remaining life prediction system according to claim 29, characterized in that: The failure interval is [0.75, 1].

31. The drilling equipment lubricant remaining life prediction system according to claim 28, characterized in that: The relative inferiority calculation is to compare and analyze the test indicators and normalize them to eliminate the difference caused by different physical meanings and dimensional units; Specifically, for the detection index whose value is larger, the better, the relative deterioration calculation formula is: For the detection index with smaller value, the better value, the relative deterioration calculation formula is: For the detection index with intermediate value, the relative deterioration calculation formula is: In the formula, θ represents the relative degradation value of each detection index, θ max Represents the upper limit of the detection index; θ min Represents the lower limit of the detection index; θ x Represents the initial value of the detection indicator.

32. The drilling equipment lubricant remaining life prediction system according to claim 28, characterized in that: The interval analytic hierarchy process is used to determine the weight value of each detection index. Specifically, an interval judgment matrix is ​​established, and the reciprocity 1-9 scaling rule is used to compare the indicators at the same level. Represents the results of pairwise comparisons, where: and According to the number of intervals, the interval judgment matrix can be constructed The calculation formula for the weight value of each detection indicator is: In the formula, λ- represents A - The maximum eigenvalue and the corresponding normalized eigenvector of A; λ+ represents + The maximum eigenvalue and the corresponding normalized eigenvector of ; w represents the weight value of the detection index, m represents the number of relative degradations, i represents the number of rows of the corresponding matrix, j represents the number of columns of the corresponding matrix, and w - Indicates A - The corresponding weights of each indicator, w + Indicates A + The corresponding weights of each indicator.

33. The drilling equipment lubricant remaining life prediction system according to claim 28, characterized in that: The calculation formula of comprehensive health index is: Where HI represents the comprehensive health index, n represents the total number of detection index categories, i represents the detection index category, θ i represents the degradation value of the i-th type of detection index, w i Represents the weight value of the i-th category detection indicator.

34. The system for predicting the remaining life of lubricating oil for drilling equipment according to any one of claims 18, 19 or 23-28, characterized in that: The detection data of the target lubricating oil obtained by the first module includes but is not limited to any one or more combinations of kinematic viscosity change rate, acid value increase value, base value decrease rate, moisture, closed cup flash point, fuel dilution, oxidation value, nitration value, soot, Fe content, Cu content, Al content and Si content.

35. A computer device, characterized in that: The method comprises a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 17.

36. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the method according to any one of claims 1 to 17.

Images