CN113516273A - Fault prediction method for diesel engine supercharger for power generation - Google Patents
Fault prediction method for diesel engine supercharger for power generation Download PDFInfo
- Publication number
- CN113516273A CN113516273A CN202110369737.0A CN202110369737A CN113516273A CN 113516273 A CN113516273 A CN 113516273A CN 202110369737 A CN202110369737 A CN 202110369737A CN 113516273 A CN113516273 A CN 113516273A
- Authority
- CN
- China
- Prior art keywords
- supercharger
- lubricating oil
- pressure
- oil inlet
- inlet pressure
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 116
- 238000010248 power generation Methods 0.000 title claims abstract description 20
- 230000014509 gene expression Effects 0.000 claims abstract description 68
- 238000004458 analytical method Methods 0.000 claims abstract description 31
- 230000009467 reduction Effects 0.000 claims abstract description 27
- 230000002159 abnormal effect Effects 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 18
- 239000010687 lubricating oil Substances 0.000 claims description 359
- 239000003921 oil Substances 0.000 claims description 208
- 238000012360 testing method Methods 0.000 claims description 84
- 230000008569 process Effects 0.000 claims description 53
- 230000000875 corresponding effect Effects 0.000 claims description 37
- 238000010586 diagram Methods 0.000 claims description 30
- 230000008859 change Effects 0.000 claims description 14
- 230000002596 correlated effect Effects 0.000 claims description 13
- 238000012216 screening Methods 0.000 claims description 12
- 238000012935 Averaging Methods 0.000 claims description 10
- 238000005461 lubrication Methods 0.000 claims description 9
- 230000001174 ascending effect Effects 0.000 claims description 6
- 239000010710 diesel engine oil Substances 0.000 claims description 5
- 238000009795 derivation Methods 0.000 claims description 4
- 239000012535 impurity Substances 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 229910000831 Steel Inorganic materials 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000001050 lubricating effect Effects 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02B—INTERNAL-COMBUSTION PISTON ENGINES; COMBUSTION ENGINES IN GENERAL
- F02B39/00—Component parts, details, or accessories relating to, driven charging or scavenging pumps, not provided for in groups F02B33/00 - F02B37/00
- F02B39/14—Lubrication of pumps; Safety measures therefor
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04D—NON-POSITIVE-DISPLACEMENT PUMPS
- F04D27/00—Control, e.g. regulation, of pumps, pumping installations or pumping systems specially adapted for elastic fluids
- F04D27/001—Testing thereof; Determination or simulation of flow characteristics; Stall or surge detection, e.g. condition monitoring
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04D—NON-POSITIVE-DISPLACEMENT PUMPS
- F04D27/00—Control, e.g. regulation, of pumps, pumping installations or pumping systems specially adapted for elastic fluids
- F04D27/008—Stop safety or alarm devices, e.g. stop-and-go control; Disposition of check-valves
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- General Physics & Mathematics (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Supercharger (AREA)
Abstract
The invention discloses a method for predicting faults of a supercharger of a diesel engine for power generation, which comprises the following steps of 1: acquiring unit information to form a data set: step 2: processing data, and preliminarily judging fault data characteristics: and step 3: according to the working characteristics of the parallel operation of the diesel generating sets, the noise reduction method is improved, and fault characteristic analysis and threshold determination are respectively carried out according to the load working conditions of 20%, 50%, 75%, 90%, 75%, 50% and 20% under the power factors of 0.6, 0.8 and 0.9: and 4, step 4: summarizing and analyzing, improving a threshold value determining method, and obtaining threshold values under different working conditions: and 5: forming a multi-threshold expression, specifying a result of judging the abnormal condition through the multi-threshold expression, and finishing off-line processing: step 6: and (4) realizing prediction on line. According to the method for predicting the faults of the diesel engine supercharger for power generation, the relations between the oil inlet pressure of the supercharger and active power, the oil inlet temperature of the supercharger and the oil pressure of the diesel engine are read, and the prediction precision is improved by setting a plurality of thresholds at the same level.
Description
Technical Field
The invention relates to the technical field of diesel engine fault prediction, in particular to a fault prediction method for a supercharger of a diesel engine for power generation.
Background
In the onshore joint debugging test of a large ship power system, a plurality of diesel generator sets are connected in parallel for a long time, the stability of the parallel operation is checked, and the main operation working conditions are as follows according to relevant standards: parallel running tests of loading and unloading were performed at power factors of 0.6, 0.8 and 0.9 at load conditions of 20%, 50%, 75%, 90%, 75%, 50%, 20%.
The supercharger of the diesel engine for power generation works by using the exhaust gas of the diesel engine and the residual energy after exhaust through the turbine, so that the compressor can provide more compressed air for the diesel engine to achieve the best running performance. Because the air entering the cylinder is increased, the fuel can be fully combusted, so that the diesel engine can generate larger power, the emission is reduced, and the pollution is reduced. The main types of supercharger faults include assembly quality problems of a supercharger body, unqualified part manufacturing, overlarge rotor unbalance amount, bearing design and processing problems, overspeed operation of a unit, external foreign matters entering the supercharger, oil circuit blockage of a lubricating system, insufficient oil supply of the lubricating system and the like, wherein the bearing failure caused by lubrication is a common fault with high probability.
Disclosure of Invention
The invention provides a method for predicting faults of a supercharger of a diesel engine for power generation, which aims to solve the problem that in the prior art, a detection method for abnormal lubrication of the supercharger sets a fixed threshold value aiming at the too low lubricating oil inlet pressure of the supercharger and sends out an alarm signal when the actual pressure value is lower than the threshold value. However, in the actual process, when the alarm signal is received, the supercharger has a fault, and the prediction and prevention of the fault cannot be realized. And in the actual work process, the booster lubricating oil inlet pressure numerical value is different under the different operating mode circumstances, and the problem that real-time fault identification and trend judgment can not be carried out to the too low lubricating oil inlet pressure to single threshold value.
In order to solve the technical problems, the invention adopts the following technical scheme:
a failure prediction method for a supercharger of a diesel engine for power generation comprises the following steps:
step 1, collecting unit information to form a data set;
collecting all relevant operation data of a fault diesel generator set and a normal diesel generator set from the beginning of a test to the moment of fault occurrence, and collecting operation data after the fault diesel generator set is repaired;
step 2, processing data, preliminarily judging fault data characteristics, judging useful information and parameter correlation so as to determine input and output of multi-threshold expression judgment;
step 3, improving a noise reduction method according to the working characteristics of the land joint debugging test diesel generator set in parallel operation of the large-scale ship electric power system, and respectively performing fault characteristic analysis and threshold determination according to the load working conditions of 20%, 50%, 75%, 90%, 75%, 50% and 20% under the power factors of 0.6, 0.8 and 0.9;
step 4, summarizing and analyzing, and improving a threshold value determining method to obtain threshold values under different working conditions;
step 5, forming a multi-threshold expression, specifying a result of judging the abnormal condition through the multi-threshold expression, and finishing off-line processing;
and 6, realizing prediction on line.
Further, in step 2, the method further comprises the following steps:
step 2.1, denoising the collected unit information: firstly, screening and removing noises collected by a sensor at the moment of non-startup, then carrying out noise reduction treatment by using a moving average filter, preliminarily judging numerical values and variation trends of the oil inlet pressure of the supercharger under the same working condition and different working conditions of a fault diesel engine unit and other units, preliminarily judging fault data characteristics, and preliminarily judging parameters influencing the oil inlet pressure variation of the supercharger;
step 2.2, the input and the output of the judgment of the correlation judgment determination threshold value are as follows: determining active power, supercharger lubricating oil inlet temperature and diesel engine lubricating oil pressure to be related to changes of the supercharger lubricating oil inlet pressure, wherein the changes are useful information, carrying out correlation judgment on the parameters, namely calculating a Pearson correlation coefficient and a Spanish correlation coefficient respectively, finding that the ratios of the supercharger lubricating oil inlet pressure, the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure are highly negatively correlated with the active power and the supercharger lubricating oil inlet temperature respectively, the active power and the supercharger lubricating oil inlet temperature are highly positively correlated, determining that threshold input is the permutation combination of the active power and the supercharger lubricating oil inlet temperature, and outputting the threshold respectively to be the ratios of the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure.
Further, in step 3, the method further comprises the following steps:
step 3.1, determining a subsequent analysis mode according to the working characteristics of the large ship electric power system on-land joint debugging test diesel generator set in parallel operation:
in the process of parallel operation of diesel generator sets in a land joint debugging test of a large ship electric power system, parallel operation tests of loading and unloading are respectively carried out under the power factors of 0.6, 0.8 and 0.9 according to the load working conditions of 20%, 50%, 75%, 90%, 75%, 50% and 20%, the active power is different under the same load working condition with different power factors, and the corresponding ratios of the oil inlet pressure of the lubricating oil of the supercharger, the oil inlet pressure of the lubricating oil of the supercharger and the oil inlet pressure of the lubricating oil of the diesel engine are different, so that specific analysis is carried out according to different power factors;
step 3.2, improving the noise reduction method, and respectively carrying out fault characteristic analysis according to 20%, 50%, 75% and 90% load working conditions under power factors of 0.6, 0.8 and 0.9:
step 3.2.1, improving a noise reduction method, and carrying out noise reduction classification on data according to power factors of 0.6, 0.8 and 0.9 and load working conditions of 20%, 50%, 75%, 90%, 75%, 50% and 20%: extracting data in each test process from collected data set through a programming language, classifying according to power factor operation working conditions of 0.6, 0.8 and 0.9, extracting the oil inlet pressure of the supercharger lubricating oil and other related information under the conditions of 20%, 50%, 75% and 90% of load in each type of data respectively, and averaging the oil inlet pressure of the supercharger lubricating oil, the ratio of the oil inlet pressure of the supercharger lubricating oil to the oil inlet pressure of the diesel engine and active power in batches respectively;
step 3.2.2, determining a fault characteristic analysis method:
when fault characteristic judgment is carried out, data values corresponding to the same name in the fault data set and the normal data set are respectively compared and judged as follows:
a. the height under the same working condition;
b. the variation trend of multiple tests under the same working condition;
c. different working condition change conditions are tested at the same time;
d. c the variation trend in the process of multiple tests;
wherein a and b can be directly judged by improving the data set after noise reduction processing, and d can be directly judged by c obtained by multiple tests after c is obtained; step 2.2, determining that the ratio of the oil inlet pressure of the lubricating oil of the supercharger, the ratio of the oil inlet pressure of the lubricating oil of the supercharger to the oil pressure of the lubricating oil of the diesel engine are respectively highly negatively correlated with the active power, and performing linear fitting on the extracted ratio of the oil inlet pressure of the lubricating oil of the supercharger, the ratio of the oil inlet pressure of the lubricating oil of the supercharger to the oil pressure of the lubricating oil of the diesel engine in each experimental process under the condition of different power factors and the average value of the active power respectively to judge c, wherein the expression of a fitting curve is as follows:
y＝ax+b (1)
wherein a is a slope, and represents the change trend of the oil inlet pressure and the ratio of the lubricating oil of the supercharger in the test process; b is an intercept representing the integral size of the oil inlet pressure and the ratio of the lubricating oil of the supercharger; x is active power; y is the oil inlet pressure of the lubricating oil of the supercharger;
step 3.2.3, carrying out fault characteristic analysis:
firstly, judging the height of data values corresponding to the same name in fault and normal data sets under the same working condition, and fitting the ratio of the oil inlet pressure of the lubricating oil of the supercharger, the oil inlet pressure of the lubricating oil of the supercharger and the oil inlet pressure of the lubricating oil of the diesel engine under the conditions of power factors of 0.6, 0.8 and 0.9 and loads of 20%, 50%, 75% and 90% and a and b obtained by a fitting curve according to a time sequence to obtain a fitting scatter diagram and a fitting line graph for trend analysis;
in the analysis process, firstly, solving the variance of the data under different power factors, and judging the convergence of the data; and then performing quadratic polynomial fitting on the obtained fitting scatter diagram and the fitting line diagram, wherein the expression of the fitting curve is as follows:
y＝a0t2+b0t+c0 (2)
in the formula: y isThe oil inlet pressure of the lubricating oil of the supercharger; t is the number of tests; the expression is subjected to derivation to obtain the pole position t of the fitting curve0，t0In order to obtain the maximum value in the test of the second time, the descending trend is judged by matching with the coefficient of the quadratic term, and the times of the test under different conditions are collectively called n; the specific judgment criteria are as follows:
if a0＞0，t0If the pressure is less than or equal to 0, b obtained by the ratio of the supercharger lubricating oil inlet pressure/the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure/a fitting curve is in an ascending trend in the process of multiple tests;
if a0＞0，0＜t0If the pressure is less than or equal to n, b obtained by the ratio of the supercharger lubricating oil inlet pressure/the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure/a fitting curve is reduced firstly and then increased in the process of multiple tests;
if a0＞0，t0If n is greater than n, b obtained by the ratio of the supercharger lubricating oil inlet pressure/the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure/a fitting curve is in a descending trend in the process of multiple tests;
if a0＜0，t0If the pressure is less than or equal to 0, b obtained by the ratio of the supercharger lubricating oil inlet pressure/the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure/a fitting curve is in a descending trend in the process of multiple tests;
if a0＜0，0＜t0If the pressure is less than or equal to n, b obtained by the ratio of the supercharger lubricating oil inlet pressure/the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure/a fitting curve rises first and then falls in the process of multiple tests;
if a0＜0，t0If n is greater than n, b obtained by the ratio of the oil inlet pressure of the supercharger/the oil inlet pressure of the supercharger to the oil pressure of the diesel engine/a fitting curve is in an ascending trend in the process of multiple tests;
according to judgment, compared with a normal unit, the ratio variance of the supercharger lubricating oil inlet pressure and the supercharger lubricating oil inlet pressure of the fault unit to the diesel engine lubricating oil pressure is large and is in a descending trend, the integral numerical value is small, and the ratio change trend of the supercharger lubricating oil inlet pressure and the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure under different working conditions in the experimental process of each time is unchanged, namely a is unchanged; finally, determining that the fault characteristics are that the numerical values of the supercharger lubricating oil inlet pressure, the ratio of the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure are small, and the integral descending trend is presented;
step 3.3, determining a threshold value by using a box type graph:
and 3.3.1, because the fault characteristic is that the numerical values of the supercharger lubricating oil inlet pressure, the ratio of the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure are small and continuously reduced, setting low thresholds of the supercharger lubricating oil inlet pressure, the ratio of the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure and the diesel engine lubricating oil pressure are respectively calculated by using a box diagram, wherein the two thresholds are respectively set under the conditions of 0.6 power factor, 0.8 power factor, 0.9 power factor, 20% load, 50% load, 75% load and 90% load, the threshold with the larger numerical value is defined as a pre-alarm value, and the threshold with the lower numerical value is defined as an alarm value.
Further, in step 4, the method further comprises the following steps:
step 4.1, summarizing the threshold values of 0.6, 0.8 and 0.9 under different load conditions to form a threshold value table, and specifically judging abnormal conditions of 0.6, 0.8 and 0.9 under different load conditions by comparing the relation between the actual value and the numerical value in the threshold value table at the later stage;
and 4.2, improving a threshold value determining method, screening fault unit data according to different active powers by using a programming language, screening a part of data with more operation times, averaging the ratios of the supercharger lubricating oil inlet pressure, the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure under the same active power and different tests respectively, and calculating two threshold values of the ratios of the supercharger lubricating oil inlet pressure, the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure respectively by using a box diagram, wherein the threshold value with a larger numerical value is defined as a pre-alarm value, and the threshold value with a smaller numerical value is defined as an alarm value.
Further, in step 5, the method further comprises the following steps:
step 5.1, forming a multi-threshold expression: it is known from step 2.2 that the ratios of the supercharger lubricating oil inlet pressure, the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure are respectively highly negatively correlated with the active power, so that the thresholds under different active powers are gathered together and fitted into a corresponding curve, and the polynomial maximum times of the curve are determined by comparing the residual errors, generally 2 times, that is, two threshold expressions of the ratios of the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure are respectively obtained;
step 5.2, it is known from step 2.2 that the ratios of the pressure of the inlet of the lubricating oil of the supercharger, the pressure of the inlet of the lubricating oil of the supercharger and the pressure of the lubricating oil of the diesel engine are respectively in high negative correlation with the active power and the temperature of the inlet of the lubricating oil of the supercharger, and the active power and the temperature of the inlet of the lubricating oil of the supercharger are in positive correlation, so that the pressure of the inlet of the lubricating oil of the supercharger can be jointly represented by the active power and the temperature of the inlet of the lubricating oil of the supercharger in the actual process, the method is more rigorous than the method in which the judgment is carried out only by the threshold expression of the pressure of the inlet of the lubricating oil of the supercharger and the active power, and the specific method is as follows;
step 5.2.1, when a large number of samples are available, classifying the data screened in the step 4.2 again according to the oil inlet temperature of the lubricating oil of the supercharger, averaging the same active power, the same oil inlet temperature of the supercharger, the oil inlet pressure of the lubricating oil of the supercharger under different tests and the ratio of the oil inlet pressure of the lubricating oil of the supercharger to the oil pressure of the diesel engine respectively, calculating two thresholds respectively by using a box diagram, summarizing the thresholds under different active powers and different oil inlet temperatures of the supercharger together, and fitting the thresholds into corresponding curves, so that two oil inlet pressure threshold expressions of the lubricating oil of the supercharger, the oil inlet pressure of which is determined by the active power and the oil inlet temperature of the supercharger under the condition of sufficient samples can be obtained;
and 5.2.2, when the number of samples is not enough to support the processing of the step 5.2.3, performing multivariate fitting on the obtained data in each test process, wherein the fitted curve expression is as follows:
P＝a2T+b2Pw+c2 (3)
wherein P is the oil inlet pressure of the lubricating oil of the supercharger; pwActive power; t is the oil inlet temperature of the lubricating oil of the supercharger;
setting the same and proper supercharger lubricating oil inlet temperature and active power for each test, and performing threshold selection on the calculated supercharger lubricating oil inlet pressure by using a box diagram, wherein corresponding expressions are two threshold expressions;
finally, a total of 6 threshold expressions are determined, which are of the form:
y1＝a1xn+b1xnww+… (4)
y2＝a1xn+b1xn-1+… (5)
y3＝a2xn+b2xn-1+… (6)
y4＝a2xn+b2xn-1+… (7)
y5＝a1T+b1PW+c1 (8)
y6＝a2T+b2PW+c2 (9)
wherein x is unit active power, namely the ratio of the active power to rated power; pwActive power; t is the oil inlet temperature of the lubricating oil of the supercharger; y is1Representing the pressure of the inlet oil of the supercharger, y2Representing the ratio of the inlet pressure of the oil in the supercharger to the pressure of the oil in the diesel engine, y3Representing the pressure of the inlet oil of the supercharger, y4Representing the ratio of the inlet pressure of the oil in the supercharger to the pressure of the oil in the diesel engine, y5、y6All represent the oil inlet pressure of the lubricating oil of the supercharger;
finally, uniformly using y1、y2、y5To represent three pre-alarm expressions, y3、y4、y6To represent three alarm expressions;
and 5.3, determining the abnormal degree:
let W be the current supercharger oil inlet pressure orRatio of supercharger oil inlet pressure to diesel engine oil pressure, W1And W2The pre-alarm value and the alarm value under the current working condition are as follows:
when W is1When the pressure is less than W, the lubrication of the supercharger is normal;
when W is2＜W≤W1When the pressure is higher than the set pressure, the pressure booster oil pre-alarms;
when W is less than or equal to W2And when the oil is in use, the oil lubrication of the supercharger alarms.
Further, in step 6, the method further comprises the following steps:
step 6.1, inputting the oil inlet temperature P of the lubricating oil of the supercharger, the oil inlet temperature T of the lubricating oil of the supercharger and the active power P in real time through a data buswPreprocessing the lubricating oil pressure PD of the diesel engine by using a multi-threshold expression, and outputting W, W under the current working condition1And W2Entering a model for judging abnormal conditions;
and 6.2, outputting a prediction result:
when the pre-alarm is continuously generated, the situation that the oil inlet pressure of the lubricating oil of the supercharger is low and is in a descending trend is shown, impurities begin to exist in the lubricating oil, and corresponding measures are suggested to be taken to increase the pressure and corresponding inspection is carried out;
when an alarm occurs, the two threshold values have an interval range, which shows that the pressure of the lubricating oil in the supercharger is seriously low, the pressure is rapidly and obviously reduced, the supercharger is probably failed, the supercharger should be stopped immediately for checking, and corresponding measures are taken to increase the pressure.
Compared with the prior art, the method for predicting the faults of the supercharger of the diesel engine for power generation has the following remarkable advantages:
the invention provides a method for predicting faults of a diesel supercharger for power generation, wherein after a multi-threshold expression is determined, real-time abnormal information identification and fault prediction can be carried out under different working conditions, and meanwhile, the degree of abnormal conditions can be judged.
The invention provides a method for predicting faults of a supercharger of a diesel engine for power generation, which is characterized in that the relation between the oil inlet pressure of lubricating oil of the supercharger and active power, the oil inlet temperature of the lubricating oil of the supercharger and the oil pressure of the lubricating oil of the diesel engine is read, and the prediction precision is improved by setting a plurality of thresholds at the same level.
Drawings
Fig. 1 is a schematic flow chart of a method for predicting a failure of a supercharger of a diesel engine for power generation according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without any inventive step, are within the scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a method for predicting a failure of a supercharger of a diesel engine for power generation, including the following steps:
step 1, collecting unit information to form a data set;
collecting all relevant operation data of a fault diesel generator set and a normal diesel generator set from the beginning of a test to the moment of fault occurrence, and collecting operation data after the fault diesel generator set is repaired;
step 2, processing data, preliminarily judging fault data characteristics, judging useful information and parameter correlation so as to determine input and output of multi-threshold expression judgment;
step 3, improving a noise reduction method according to the working characteristics of the land joint debugging test diesel generator set in parallel operation of the large-scale ship electric power system, and respectively performing fault characteristic analysis and threshold determination according to the load working conditions of 20%, 50%, 75%, 90%, 75%, 50% and 20% under the power factors of 0.6, 0.8 and 0.9;
step 4, summarizing and analyzing, and improving a threshold value determining method to obtain threshold values under different working conditions;
step 5, forming a multi-threshold expression, specifying a result of judging the abnormal condition through the multi-threshold expression, and finishing off-line processing;
and 6, realizing prediction on line.
Further, in step 2, the method further comprises the following steps:
step 2.1, denoising the collected unit information: firstly, screening and removing noises collected by a sensor at the moment of non-startup, then carrying out noise reduction treatment by using a moving average filter, preliminarily judging numerical values and variation trends of the oil inlet pressure of the supercharger under the same working condition and different working conditions of a fault diesel engine unit and other units, preliminarily judging fault data characteristics, and preliminarily judging parameters influencing the oil inlet pressure variation of the supercharger;
step 2.2, the input and the output of the judgment of the correlation judgment determination threshold value are as follows: determining active power, supercharger lubricating oil inlet temperature and diesel engine lubricating oil pressure to be related to changes of the supercharger lubricating oil inlet pressure, wherein the changes are useful information, carrying out correlation judgment on the parameters, namely calculating a Pearson correlation coefficient and a Spanish correlation coefficient respectively, finding that the ratios of the supercharger lubricating oil inlet pressure, the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure are highly negatively correlated with the active power and the supercharger lubricating oil inlet temperature respectively, the active power and the supercharger lubricating oil inlet temperature are highly positively correlated, determining that threshold input is the permutation combination of the active power and the supercharger lubricating oil inlet temperature, and outputting the threshold respectively to be the ratios of the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure.
Further, in step 3, the method further comprises the following steps:
step 3.1, determining a subsequent analysis mode according to the working characteristics of the large ship electric power system on-land joint debugging test diesel generator set in parallel operation:
in the process of parallel operation of diesel generator sets in a land joint debugging test of a large ship electric power system, parallel operation tests of loading and unloading are respectively carried out under the power factors of 0.6, 0.8 and 0.9 according to the load working conditions of 20%, 50%, 75%, 90%, 75%, 50% and 20%, the active power is different under the same load working condition with different power factors, and the corresponding ratios of the oil inlet pressure of the lubricating oil of the supercharger, the oil inlet pressure of the lubricating oil of the supercharger and the oil inlet pressure of the lubricating oil of the diesel engine are different, so that specific analysis is carried out according to different power factors;
step 3.2, improving the noise reduction method, and respectively carrying out fault characteristic analysis according to 20%, 50%, 75% and 90% load working conditions under power factors of 0.6, 0.8 and 0.9:
step 3.2.1, improving a noise reduction method, and carrying out noise reduction classification on data according to power factors of 0.6, 0.8 and 0.9 and load working conditions of 20%, 50%, 75%, 90%, 75%, 50% and 20%: extracting data in each test process from collected data set through a programming language, classifying according to power factor operation working conditions of 0.6, 0.8 and 0.9, extracting the oil inlet pressure of the supercharger lubricating oil and other related information under the conditions of 20%, 50%, 75% and 90% of load in each type of data respectively, and averaging the oil inlet pressure of the supercharger lubricating oil, the ratio of the oil inlet pressure of the supercharger lubricating oil to the oil inlet pressure of the diesel engine and active power in batches respectively;
step 3.2.2, determining a fault characteristic analysis method:
when fault characteristic judgment is carried out, data values corresponding to the same name in the fault data set and the normal data set are respectively compared and judged as follows:
a. the height under the same working condition;
b. the variation trend of multiple tests under the same working condition;
c. different working condition change conditions are tested at the same time;
d. c the variation trend in the process of multiple tests;
wherein a and b can be directly judged by improving the data set after noise reduction processing, and d can be directly judged by c obtained by multiple tests after c is obtained; step 2.2, determining that the ratio of the oil inlet pressure of the lubricating oil of the supercharger, the ratio of the oil inlet pressure of the lubricating oil of the supercharger to the oil pressure of the lubricating oil of the diesel engine are respectively highly negatively correlated with the active power, and performing linear fitting on the extracted ratio of the oil inlet pressure of the lubricating oil of the supercharger, the ratio of the oil inlet pressure of the lubricating oil of the supercharger to the oil pressure of the lubricating oil of the diesel engine in each experimental process under the condition of different power factors and the average value of the active power respectively to judge c, wherein the expression of a fitting curve is as follows:
y＝ax+b (1)
wherein a is a slope, and represents the change trend of the oil inlet pressure and the ratio of the lubricating oil of the supercharger in the test process; b is an intercept representing the integral size of the oil inlet pressure and the ratio of the lubricating oil of the supercharger; x is active power; y is the oil inlet pressure of the lubricating oil of the supercharger;
step 3.2.3, carrying out fault characteristic analysis:
firstly, judging the height of data values corresponding to the same name in fault and normal data sets under the same working condition, and fitting the ratio of the oil inlet pressure of the lubricating oil of the supercharger, the oil inlet pressure of the lubricating oil of the supercharger and the oil inlet pressure of the lubricating oil of the diesel engine under the conditions of power factors of 0.6, 0.8 and 0.9 and loads of 20%, 50%, 75% and 90% and a and b obtained by a fitting curve according to a time sequence to obtain a fitting scatter diagram and a fitting line graph for trend analysis;
in the analysis process, firstly, the variance of the data under different power factors is solved, and the convergence of the data is judged: and then performing quadratic polynomial fitting on the obtained fitting scatter diagram and the fitting line diagram, wherein the expression of the fitting curve is as follows:
y＝a0t2+b0t+c0 (2)
in the formula: y is the oil inlet pressure of the lubricating oil of the supercharger; t is the number of tests; the expression is subjected to derivation to obtain the pole position t of the fitting curve0Judging the descending trend by matching with the quadratic term coefficient, wherein the times of tests under different conditions are collectively called n; the specific judgment criteria are as follows:
if a0＞0，t0If the pressure is less than or equal to 0, b obtained by the ratio of the supercharger lubricating oil inlet pressure/the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure/a fitting curve is in an ascending trend in the process of multiple tests;
if a0＞0，0＜t0If the pressure is less than or equal to n, b obtained by the ratio of the supercharger lubricating oil inlet pressure/the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure/a fitting curve is reduced firstly and then increased in the process of multiple tests;
if a0＞0，t0If > n, thenB obtained by the ratio of the oil inlet pressure of the supercharger to the oil pressure of the diesel engine/a fitting curve is in a descending trend in the process of multiple tests;
if a0＜0，t0If the pressure is less than or equal to 0, b obtained by the ratio of the supercharger lubricating oil inlet pressure/the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure/a fitting curve is in a descending trend in the process of multiple tests;
if a0＜0，0＜t0If the pressure is less than or equal to n, b obtained by the ratio of the supercharger lubricating oil inlet pressure/the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure/a fitting curve rises first and then falls in the process of multiple tests;
if a0＜0，t0If n is greater than n, b obtained by the ratio of the oil inlet pressure of the supercharger/the oil inlet pressure of the supercharger to the oil pressure of the diesel engine/a fitting curve is in an ascending trend in the process of multiple tests;
according to judgment, compared with a normal unit, the ratio variance of the supercharger lubricating oil inlet pressure and the supercharger lubricating oil inlet pressure of the fault unit to the diesel engine lubricating oil pressure is large and is in a descending trend, the integral numerical value is small, and the ratio change trend of the supercharger lubricating oil inlet pressure and the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure under different working conditions in the experimental process of each time is unchanged, namely a is unchanged; finally, determining that the fault characteristics are that the numerical values of the supercharger lubricating oil inlet pressure, the ratio of the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure are small, and the integral descending trend is presented;
step 3.3, determining a threshold value by using a box type graph:
and 3.3.1, because the fault characteristic is that the numerical values of the supercharger lubricating oil inlet pressure, the ratio of the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure are small and continuously reduced, setting low thresholds of the supercharger lubricating oil inlet pressure, the ratio of the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure and the diesel engine lubricating oil pressure are respectively calculated by using a box diagram, wherein the two thresholds are respectively set under the conditions of 0.6 power factor, 0.8 power factor, 0.9 power factor, 20% load, 50% load, 75% load and 90% load, the threshold with the larger numerical value is defined as a pre-alarm value, and the threshold with the lower numerical value is defined as an alarm value.
Further, in step 4, the method further comprises the following steps:
step 4.1, summarizing the threshold values of 0.6, 0.8 and 0.9 under different load conditions to form a threshold value table, and specifically judging abnormal conditions of 0.6, 0.8 and 0.9 under different load conditions by comparing the relation between the actual value and the numerical value in the threshold value table at the later stage;
and 4.2, improving a threshold value determining method, screening fault unit data according to different active powers by using a programming language, screening a part of data with more operation times, averaging the ratios of the supercharger lubricating oil inlet pressure, the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure under the same active power and different tests respectively, and calculating two threshold values of the ratios of the supercharger lubricating oil inlet pressure, the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure respectively by using a box diagram, wherein the threshold value with a larger numerical value is defined as a pre-alarm value, and the threshold value with a smaller numerical value is defined as an alarm value.
Further, in step 5, the method further comprises the following steps:
step 5.1, forming a multi-threshold expression: it is known from step 2.2 that the ratios of the supercharger lubricating oil inlet pressure, the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure are respectively highly negatively correlated with the active power, so that the thresholds under different active powers are gathered together and fitted into a corresponding curve, and the polynomial maximum times of the curve are determined by comparing the residual errors, generally 2 times, that is, two threshold expressions of the ratios of the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure are respectively obtained;
step 5.2, it is known from step 2.2 that the ratios of the pressure of the inlet of the lubricating oil of the supercharger, the pressure of the inlet of the lubricating oil of the supercharger and the pressure of the lubricating oil of the diesel engine are respectively in high negative correlation with the active power and the temperature of the inlet of the lubricating oil of the supercharger, and the active power and the temperature of the inlet of the lubricating oil of the supercharger are in positive correlation, so that the pressure of the inlet of the lubricating oil of the supercharger can be jointly represented by the active power and the temperature of the inlet of the lubricating oil of the supercharger in the actual process, the method is more rigorous than the method in which the judgment is carried out only by the threshold expression of the pressure of the inlet of the lubricating oil of the supercharger and the active power, and the specific method is as follows;
step 5.2.1, when a large number of samples are available, classifying the data screened in the step 4.2 again according to the oil inlet temperature of the lubricating oil of the supercharger, averaging the same active power, the same oil inlet temperature of the supercharger, the oil inlet pressure of the lubricating oil of the supercharger under different tests and the ratio of the oil inlet pressure of the lubricating oil of the supercharger to the oil pressure of the diesel engine respectively, calculating two thresholds respectively by using a box diagram, summarizing the thresholds under different active powers and different oil inlet temperatures of the supercharger together, and fitting the thresholds into corresponding curves, so that two oil inlet pressure threshold expressions of the lubricating oil of the supercharger, the oil inlet pressure of which is determined by the active power and the oil inlet temperature of the supercharger under the condition of sufficient samples can be obtained;
and 5.2.2, when the number of samples is not enough to support the processing of the step 5.2.3, performing multivariate fitting on the obtained data in each test process, wherein the fitted curve expression is as follows:
P＝a2T+b2Pw+c2 (3)
wherein P is the oil inlet pressure of the lubricating oil of the supercharger; pwActive power; t is the oil inlet temperature of the lubricating oil of the supercharger;
setting the same and proper supercharger lubricating oil inlet temperature and active power for each test, and performing threshold selection on the calculated supercharger lubricating oil inlet pressure by using a box diagram, wherein corresponding expressions are two threshold expressions;
finally, a total of 6 threshold expressions are determined, which are of the form:
y1＝a1xn+b1xn-1+… (4)
y2＝a1xn+b1xn-1+… (5)
y3＝a2xn+b2xn-1+… (6)
y4＝a2xn+b2xn-1+… (7)
y5＝a1T+b1PW+c1 (8)
y6＝a2T+b2PW+c2 (9)
wherein x is unit active power, namely the ratio of the active power to rated power; pwActive power; t is the oil inlet temperature of the lubricating oil of the supercharger; y is1Representing the pressure of the inlet oil of the supercharger, y2Representing the ratio of the inlet pressure of the oil in the supercharger to the pressure of the oil in the diesel engine, y3Representing the pressure of the inlet oil of the supercharger, y4Representing the ratio of the inlet pressure of the oil in the supercharger to the pressure of the oil in the diesel engine, y5、y6All represent the oil inlet pressure of the lubricating oil of the supercharger;
finally, uniformly using y1、y2、y5To represent three pre-alarm expressions, y3、y4、y6To represent three alarm expressions;
and 5.3, determining the abnormal degree:
let W be the current booster oil inlet pressure or the ratio of the booster oil inlet pressure to the diesel engine oil pressure, W1And W2The pre-alarm value and the alarm value under the current working condition are as follows:
when W is1When the pressure is less than W, the lubrication of the supercharger is normal;
when W is2＜W≤W1When the pressure is higher than the set pressure, the pressure booster oil pre-alarms;
when W is less than or equal to W2And when the oil is in use, the oil lubrication of the supercharger alarms.
Further, in step 6, the method further comprises the following steps:
step 6.1, inputting the oil inlet temperature P of the lubricating oil of the supercharger, the oil inlet temperature T of the lubricating oil of the supercharger and the active power P in real time through a data buswPreprocessing the lubricating oil pressure PD of the diesel engine by using a multi-threshold expression, and outputting W, W under the current working condition1And W2Entering a model for judging abnormal conditions;
and 6.2, outputting a prediction result:
when the pre-alarm is continuously generated, the situation that the oil inlet pressure of the lubricating oil of the supercharger is low and is in a descending trend is shown, impurities begin to exist in the lubricating oil, and corresponding measures are suggested to be taken to increase the pressure and corresponding inspection is carried out;
when an alarm occurs, the two threshold values have an interval range, which shows that the pressure of the lubricating oil in the supercharger is seriously low, the pressure is rapidly and obviously reduced, the supercharger is probably failed, the supercharger should be stopped immediately for checking, and corresponding measures are taken to increase the pressure.
The invention relates to a failure prediction method for a supercharger of a diesel engine for power generation, which comprises the following steps of:
step 1: acquiring unit information to form a data set: collecting all relevant operation data of a fault diesel generator set and a normal diesel generator set from the beginning of a test to the moment of fault occurrence, and collecting operation data after the fault diesel generator set is repaired;
step 2: processing data, preliminarily judging fault data characteristics, judging useful information and parameter correlation so as to determine input and output of multi-threshold expression judgment:
and step 3: according to the working characteristics of the land joint debugging test diesel generator set parallel operation of the large ship electric power system, the noise reduction method is improved, and fault characteristic analysis and threshold determination are respectively carried out according to the load working conditions of 20%, 50%, 75%, 90%, 75%, 50% and 20% under the power factors of 0.6, 0.8 and 0.9:
and 4, step 4: summarizing and analyzing, improving a threshold value determining method, and obtaining threshold values under different working conditions:
and 5: forming a multi-threshold expression, specifying a result of judging the abnormal condition through the multi-threshold expression, and finishing off-line processing:
step 6: and (3) realizing prediction on line:
the step 2 specifically comprises the following steps:
step 2.1: carrying out noise reduction treatment on the collected unit information: firstly, screening and removing noises collected by a sensor at the moment of non-startup, then carrying out noise reduction treatment by using a moving average filter, preliminarily judging numerical values and variation trends of the oil inlet pressure of the supercharger under the same working condition and different working conditions of a fault unit and other units, preliminarily judging fault data characteristics, and preliminarily judging parameters influencing the oil inlet pressure variation of the supercharger;
step 2.2: input/output of correlation determination threshold determination: determining that the active power, the oil inlet temperature of the supercharger and the oil pressure of the diesel engine are related to the change of the oil inlet pressure of the supercharger, and performing correlation judgment on the parameters to obtain useful information, namely calculating a Pearson correlation coefficient and a Sperman correlation coefficient respectively
TABLE 1 parameter-dependent coefficient table
When the absolute value of each parameter is more than or equal to 0.7, the absolute value and the absolute value are in high (linear) correlation, and then the table can find that the ratio of the oil inlet pressure of the lubricating oil of the supercharger, the oil inlet pressure of the lubricating oil of the supercharger and the oil inlet pressure of the lubricating oil of the diesel engine is respectively in high negative correlation with the active power and the oil inlet temperature of the lubricating oil of the supercharger, and the active power is in high positive correlation with the oil inlet temperature of the lubricating oil of the supercharger; therefore, the threshold input is determined to be the permutation and combination of active power and the oil inlet temperature of the supercharger, and the threshold output is the oil inlet pressure of the supercharger and the ratio of the oil inlet pressure of the supercharger to the oil pressure of the diesel engine respectively.
The step 3 specifically comprises the following steps:
step 3.1: determining a subsequent analysis mode according to the working characteristics of the large ship electric power system on-land joint debugging test diesel generator set in parallel operation: in the process of parallel operation of diesel generator sets in a land joint debugging test of a large ship electric power system, parallel operation tests of loading and unloading are respectively carried out under the power factors of 0.6, 0.8 and 0.9 according to the load working conditions of 20%, 50%, 75%, 90%, 75%, 50% and 20%, the active power is different under the same load working conditions with different power factors, and the corresponding ratios of the oil inlet pressure of the lubricating oil of the supercharger, the oil inlet pressure of the lubricating oil of the supercharger and the oil inlet pressure of the lubricating oil of the diesel engine are different, so that the method is specifically analyzed according to different power factors.
Step 3.2: the noise reduction method is improved, and fault characteristic analysis is respectively carried out according to 20%, 50%, 75% and 90% load working conditions under power factors of 0.6, 0.8 and 0.9:
step 3.2.1: and (3) improving a noise reduction method, and carrying out noise reduction classification on the data according to power factors of 0.6, 0.8 and 0.9 and load working conditions of 20%, 50%, 75%, 90%, 75%, 50% and 20%: the noise-reduced result in the step 2.1 contains the pressure values of the lubricating oil inlet of the supercharger under various working conditions, accurate judgment cannot be carried out, and multiple tests, different power factors and pressure values under different load conditions can be fused together by adopting a windowing noise reduction method, so that the method needs to be improved as follows. Data in each test process are extracted from collected data set through a programming language, the data are classified according to power factor operation conditions of 0.6, 0.8 and 0.9, supercharger lubricating oil inlet pressure and other related information under the conditions of 20%, 50%, 75% and 90% of loads are respectively extracted from each type of data, and the supercharger lubricating oil inlet pressure, the ratio of the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure and active power are respectively averaged in batches.
Step 3.2.2: determining a fault characteristic analysis method:
when fault characteristic judgment is carried out, data values corresponding to the same name in the fault data set and the normal data set are respectively compared and judged as follows:
a. the height of the steel wire is equal to the height of the steel wire under the same working condition,
b. the change trend of multiple tests under the same working condition,
c. the same test is carried out on different working condition change conditions,
d. c the trend of change over the course of several trials,
wherein a and b can be directly judged by improving the data set after the noise reduction processing, and d can be directly judged by c obtained by a plurality of times of experiments after c is obtained. Step 2.2, determining that the ratio of the oil inlet pressure of the lubricating oil of the supercharger, the ratio of the oil inlet pressure of the lubricating oil of the supercharger to the oil pressure of the lubricating oil of the diesel engine are respectively highly negatively correlated with the active power, and performing linear fitting on the extracted ratio of the oil inlet pressure of the lubricating oil of the supercharger, the ratio of the oil inlet pressure of the lubricating oil of the supercharger to the oil pressure of the lubricating oil of the diesel engine in each experimental process under the condition of different power factors and the average value of the active power respectively to judge c, wherein the expression of a fitting curve is as follows:
y＝ax+b (1)
wherein a is a slope, and represents the change trend of the oil inlet pressure and the ratio of the lubricating oil of the supercharger in the test process;
b is an intercept representing the integral size of the oil inlet pressure and the ratio of the lubricating oil of the supercharger;
x is active power;
and y is the oil inlet pressure of the lubricating oil of the supercharger.
Step 3.2.3: and (3) carrying out fault characteristic analysis:
firstly, judging the height of data values corresponding to the same name in fault and normal data sets under the same working condition, then respectively fitting the supercharger lubricating oil inlet pressure, the ratio of the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure and a and b obtained by fitting curves under the conditions of power factors of 0.6, 0.8 and 0.9 and loads of 20%, 50%, 75% and 90% of the multiple units processed in the step 4 according to the time sequence (test times), obtaining a fitting scatter diagram and a fitting broken line diagram, and analyzing the trend.
In the analysis process, firstly, solving the variance of the data under different power factors, and judging the convergence of the data; performing quadratic polynomial fitting on the obtained fitting scatter diagram and fitting line diagram, and obtaining derivation of the obtained current expression to obtain the pole position t of the fitting curve0Judging the descending trend by matching with the quadratic term coefficient, wherein 1 and 2 are descending, and 0 is other;
TABLE 2 multiple test trends for supercharger oil admission pressure
Through judgment, compared with a normal unit, the ratio variance of the supercharger lubricating oil inlet pressure of the fault unit, the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure is large (divergent) and is in a descending trend, and the whole numerical value is smaller. Finally, the fault characteristic is determined to be that the numerical value of the ratio of the oil inlet pressure of the supercharger lubricating oil to the oil pressure of the diesel engine is small, and the integral fault characteristic shows a descending trend.
Step 3.3: determining the threshold value by using a boxed graph:
step 3.3.1: the fault is characterized in that the numerical value of the ratio of the oil inlet pressure of the supercharger to the oil pressure of the diesel engine is small and continuously reduced, so that the two are respectively set to be low in threshold value;
the box chart is a statistical chart for displaying a group of data dispersion situation data; the box type graph has the greatest advantage that the discrete distribution situation of the data can be accurately and stably depicted without being influenced by abnormal values; it can show the upper edge value, the lower edge value, the median, the upper quartile (Q3), the lower quartile (Q1), and the outlier of a set of data. The quartile is that all numerical values are arranged from small to large and divided into quarters, the numerical values at the three dividing point positions are the quartile, the quartering distance IQR is Q3-Q1, the numerical values at Q3+1.5IQR and Q1-1.5IQR are positioned at abnormal value cut-off points and are called inner limits (upper and lower edge values), the numerical values at Q3+3IQR and Q1-3IQR are called outer limits, the numerical values outside the inner limits are abnormal values, the numerical values between the inner and outer limits are mild abnormal values, and the numerical values outside the outer limits are extreme abnormal values. Because the box-type diagram has the function of eliminating abnormal values, the ratios of the whole supercharger lubricating oil inlet pressure of the fault unit, the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure are far smaller than those of other normal units, and the box-type diagram has a descending trend, and in order to keep a certain allowance, the upper quartile and the lower quartile of the box-type diagram are two thresholds under each condition;
and respectively calculating two thresholds of the ratio of the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure under the power factors of 0.6, 0.8 and 0.9, and the power factors of 20%, 50%, 75% and 90% of load conditions by using a box type graph, wherein the threshold with a larger numerical value is defined as a pre-alarm value, and the threshold with a lower numerical value is defined as an alarm value.
The step 4 specifically comprises the following steps:
step 4.1: threshold values of 0.6, 0.8 and 0.9 power factors under different load conditions are gathered together to form a threshold value table, and abnormal conditions of 0.6, 0.8 and 0.9 power factors under different load conditions can be specifically judged by comparing the relation between the actual value and the numerical value in the threshold value table at the later stage;
step 4.2: the method for determining the improved threshold value comprises the steps of screening fault unit data according to different active powers by using a programming language, screening a part of data with more operation times, averaging the oil inlet pressure of the supercharger lubricating oil and the ratio of the oil inlet pressure of the supercharger lubricating oil to the lubricating oil pressure of the diesel engine under the same active power and different tests respectively, and calculating two threshold values of the ratio of the oil inlet pressure of the supercharger lubricating oil to the lubricating oil pressure of the diesel engine by using a box diagram respectively, wherein the threshold value with the larger numerical value is defined as a pre-alarm value, and the threshold value with the lower numerical value is defined as an alarm value;
the step 5 specifically comprises the following steps:
step 5.1: forming a multi-threshold expression: step 2.2 shows that the ratios of the supercharger lubricating oil inlet pressure, the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure are respectively in high negative correlation with the active power, so that the thresholds under different active powers can be summarized together and fitted into a corresponding curve, the highest times of a polynomial of the curve are determined by comparing residual errors, and two threshold expressions of the ratios of the supercharger lubricating oil inlet pressure, the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure can be respectively obtained.
Step 5.2: performing multivariate fitting on the obtained data in each test process, wherein the fitted curve expression is as follows:
P＝a2T+b2Pw+c2 (3)
wherein: p is the oil inlet pressure of the lubricating oil of the supercharger;
Pwactive power;
t is the oil inlet temperature of the lubricating oil of the supercharger;
setting the same and proper supercharger lubricating oil inlet temperature and active power for each test, and performing threshold selection on the calculated supercharger lubricating oil inlet pressure by using a box diagram, wherein corresponding expressions are two threshold expressions;
finally, a total of 6 threshold expressions are determined, which are of the form:
y1＝a1x2+b1x+c1 (4)
y2＝a1x2+b1x+c1 (5)
y3＝a2x2+b2x+c2 (6)
y4＝a2x2+b2x+c2 (7)
y5＝a1T+b1PW+c1 (8)
y6＝a2T+b2PW+c2 (9)
wherein: x is unit active power, namely the ratio of the active power to rated power;
Pwactive power;
t is the oil inlet temperature of the lubricating oil of the supercharger;
y1、y3representing the oil inlet pressure of the supercharger lubricating oil, y2、y4Ratio of supercharger oil inlet pressure to diesel engine oil pressure, y5、y6Representing the supercharger oil inlet pressure.
Finally, uniformly using y1、y2、y5To represent three pre-alarm expressions, y3、y4、y6To represent three alarm expressions;
after comparing and analyzing the threshold curve with other unit parameters, the ratio of the normal unit and the repaired unit supercharger lubricating oil inlet pressure/supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure is generally larger than a corresponding first threshold, only one unit is slightly smaller than a pre-alarm value under the extremely individual condition, the unit supercharger lubricating oil inlet pressure is generally smaller than that of other normal units, and the diameter of an oil inlet hole plate is enlarged due to the fact that the supercharger lubricating oil pressure is lower in the later period; the ratio of the lubricating oil inlet pressure of the supercharger/the lubricating oil inlet pressure of the supercharger to the lubricating oil pressure of the diesel engine is larger than a corresponding second threshold, and the threshold is reasonable;
step 5.3: determining the degree of abnormality:
let W be the current booster oil inlet pressure or the ratio of the booster oil inlet pressure to the diesel engine oil pressure, W1And W2The pre-alarm value and the alarm value under the current working condition,
when W is1When the pressure is less than W, the lubrication of the supercharger is normal;
when W is2＜W≤W1When the pressure is higher than the set pressure, the pressure booster oil pre-alarms;
when W is less than or equal to W2When the pressure is higher than the set pressure, the oil leakage of the pressure booster is alarmed;
the step 6 specifically comprises the following steps:
step 6.1: inputting P (supercharger lubricating oil inlet temperature), T (supercharger lubricating oil inlet temperature) and P in real time through a data busw(active power) and PD (diesel engine lubricating oil pressure), preprocessing by using a multi-threshold expression, and outputting W, W under the current working condition1And W2Entering a model for judging abnormal conditions;
step 6.2: and outputting a prediction result:
when the pre-alarm is continuously generated, the situation that the oil inlet pressure of the lubricating oil of the supercharger is low and is in a descending trend and impurities possibly begin to exist in the lubricating oil is shown, and corresponding measures are suggested to increase the pressure and corresponding inspection is carried out;
when an alarm occurs, the values of the two thresholds have a certain interval range, which shows that the pressure of the lubricating oil inlet of the supercharger is seriously low, the pressure is rapidly and obviously reduced, the supercharger is probably failed, the supercharger should be stopped immediately for checking, and corresponding measures are taken to increase the pressure.
In the description herein, particular features, structures, materials, or characteristics may be combined in any suitable manner in any one or more embodiments or examples.
The present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof, and it is therefore intended that all such changes and modifications as fall within the true spirit and scope of the invention be considered as within the following claims.
Claims (6)
1. A failure prediction method for a supercharger of a diesel engine for power generation is characterized by comprising the following steps:
step 1, collecting unit information to form a data set;
collecting all relevant operation data of a fault diesel generator set and a normal diesel generator set from the beginning of a test to the moment of fault occurrence, and collecting operation data after the fault diesel generator set is repaired;
step 2, processing data, preliminarily judging fault data characteristics, judging useful information and parameter correlation so as to determine input and output of multi-threshold expression judgment;
step 3, improving a noise reduction method according to the working characteristics of the land joint debugging test diesel generator set in parallel operation of the large-scale ship electric power system, and respectively performing fault characteristic analysis and threshold determination according to the load working conditions of 20%, 50%, 75%, 90%, 75%, 50% and 20% under the power factors of 0.6, 0.8 and 0.9;
step 4, summarizing and analyzing, and improving a threshold value determining method to obtain threshold values under different working conditions;
step 5, forming a multi-threshold expression, specifying a result of judging the abnormal condition through the multi-threshold expression, and finishing off-line processing;
and 6, realizing prediction on line.
2. The method of predicting a failure of a diesel supercharger for electric power generation according to claim 1, further comprising, in step 2, the steps of:
step 2.1, denoising the collected unit information: firstly, screening and removing noises collected by a sensor at the moment of non-startup, then carrying out noise reduction treatment by using a moving average filter, preliminarily judging numerical values and variation trends of the oil inlet pressure of the supercharger under the same working condition and different working conditions of a fault diesel engine unit and other units, preliminarily judging fault data characteristics, and preliminarily judging parameters influencing the oil inlet pressure variation of the supercharger;
step 2.2, the input and the output of the judgment of the correlation judgment determination threshold value are as follows: determining active power, supercharger lubricating oil inlet temperature and diesel engine lubricating oil pressure to be related to changes of the supercharger lubricating oil inlet pressure, wherein the changes are useful information, carrying out correlation judgment on the parameters, namely calculating a Pearson correlation coefficient and a Spanish correlation coefficient respectively, finding that the ratios of the supercharger lubricating oil inlet pressure, the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure are highly negatively correlated with the active power and the supercharger lubricating oil inlet temperature respectively, the active power and the supercharger lubricating oil inlet temperature are highly positively correlated, determining that threshold input is the permutation combination of the active power and the supercharger lubricating oil inlet temperature, and outputting the threshold respectively to be the ratios of the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure.
3. The method of predicting a failure of a diesel supercharger for electric power generation according to claim 1, further comprising, in step 3, the steps of:
step 3.1, determining a subsequent analysis mode according to the working characteristics of the large ship electric power system on-land joint debugging test diesel generator set in parallel operation:
in the process of parallel operation of diesel generator sets in a land joint debugging test of a large ship electric power system, parallel operation tests of loading and unloading are respectively carried out under the power factors of 0.6, 0.8 and 0.9 according to the load working conditions of 20%, 50%, 75%, 90%, 75%, 50% and 20%, the active power is different under the same load working condition with different power factors, and the corresponding ratios of the oil inlet pressure of the lubricating oil of the supercharger, the oil inlet pressure of the lubricating oil of the supercharger and the oil inlet pressure of the lubricating oil of the diesel engine are different, so that specific analysis is carried out according to different power factors;
step 3.2, improving the noise reduction method, and respectively carrying out fault characteristic analysis according to 20%, 50%, 75% and 90% load working conditions under power factors of 0.6, 0.8 and 0.9:
step 3.2.1, improving a noise reduction method, and carrying out noise reduction classification on data according to power factors of 0.6, 0.8 and 0.9 and load working conditions of 20%, 50%, 75%, 90%, 75%, 50% and 20%: extracting data in each test process from collected data set through a programming language, classifying according to power factor operation working conditions of 0.6, 0.8 and 0.9, extracting the oil inlet pressure of the supercharger lubricating oil and other related information under the conditions of 20%, 50%, 75% and 90% of load in each type of data respectively, and averaging the oil inlet pressure of the supercharger lubricating oil, the ratio of the oil inlet pressure of the supercharger lubricating oil to the oil inlet pressure of the diesel engine and active power in batches respectively;
step 3.2.2, determining a fault characteristic analysis method:
when fault characteristic judgment is carried out, data values corresponding to the same name in the fault data set and the normal data set are respectively compared and judged as follows:
a. the height under the same working condition;
b. the variation trend of multiple tests under the same working condition;
c. different working condition change conditions are tested at the same time;
d. c the variation trend in the process of multiple tests;
wherein a and b can be directly judged by improving the data set after noise reduction processing, and d can be directly judged by c obtained by multiple tests after c is obtained; step 2.2, determining that the ratio of the oil inlet pressure of the lubricating oil of the supercharger, the ratio of the oil inlet pressure of the lubricating oil of the supercharger to the oil pressure of the lubricating oil of the diesel engine are respectively highly negatively correlated with the active power, and performing linear fitting on the extracted ratio of the oil inlet pressure of the lubricating oil of the supercharger, the ratio of the oil inlet pressure of the lubricating oil of the supercharger to the oil pressure of the lubricating oil of the diesel engine in each experimental process under the condition of different power factors and the average value of the active power respectively to judge c, wherein the expression of a fitting curve is as follows:
y＝ax+b (1)
wherein a is a slope, and represents the change trend of the oil inlet pressure and the ratio of the lubricating oil of the supercharger in the test process; b is an intercept representing the integral size of the oil inlet pressure and the ratio of the lubricating oil of the supercharger; x is active power; y is the oil inlet pressure of the lubricating oil of the supercharger;
step 3.2.3, carrying out fault characteristic analysis:
firstly, judging the height of data values corresponding to the same name in fault and normal data sets under the same working condition, and fitting the ratio of the oil inlet pressure of the lubricating oil of the supercharger, the oil inlet pressure of the lubricating oil of the supercharger and the oil inlet pressure of the lubricating oil of the diesel engine under the conditions of power factors of 0.6, 0.8 and 0.9 and loads of 20%, 50%, 75% and 90% and a and b obtained by a fitting curve according to a time sequence to obtain a fitting scatter diagram and a fitting line graph for trend analysis;
in the analysis process, firstly, solving the variance of the data under different power factors, and judging the convergence of the data; and then performing quadratic polynomial fitting on the obtained fitting scatter diagram and the fitting line diagram, wherein the expression of the fitting curve is as follows:
y＝a0t2+b0t+c0 (2)
in the formula: y is the oil inlet pressure of the lubricating oil of the supercharger; t is the number of tests; the expression is subjected to derivation to obtain the pole position t of the fitting curve0Judging the descending trend by matching with the quadratic term coefficient, wherein the times of tests under different conditions are collectively called n; the specific judgment criteria are as follows:
if a0＞0，t0If the pressure is less than or equal to 0, b obtained by the ratio of the supercharger lubricating oil inlet pressure/the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure/a fitting curve is in an ascending trend in the process of multiple tests;
if a0＞0，0＜t0N is less than or equal to n, the oil inlet pressure of the lubricating oil of the superchargerB obtained by the ratio of the oil inlet pressure of the lubricating oil of the supercharger to the lubricating oil pressure of the diesel engine/a fitting curve firstly falls and then rises in the process of multiple tests;
if a0＞0，t0If n is greater than n, b obtained by the ratio of the supercharger lubricating oil inlet pressure/the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure/a fitting curve is in a descending trend in the process of multiple tests;
if a0＜0，t0If the pressure is less than or equal to 0, b obtained by the ratio of the supercharger lubricating oil inlet pressure/the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure/a fitting curve is in a descending trend in the process of multiple tests;
if a0＜0，0＜t0If the pressure is less than or equal to n, b obtained by the ratio of the supercharger lubricating oil inlet pressure/the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure/a fitting curve rises first and then falls in the process of multiple tests;
if a0＜0，t0If n is greater than n, the ratio of the supercharger lubricating oil inlet pressure/the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure/b obtained by fitting a curve is in an ascending trend in the process of multiple tests:
according to judgment, compared with a normal unit, the ratio variance of the supercharger lubricating oil inlet pressure and the supercharger lubricating oil inlet pressure of the fault unit to the diesel engine lubricating oil pressure is large and is in a descending trend, the integral numerical value is small, and the ratio change trend of the supercharger lubricating oil inlet pressure and the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure under different working conditions in the experimental process of each time is unchanged, namely a is unchanged; finally, determining that the fault characteristics are that the numerical values of the supercharger lubricating oil inlet pressure, the ratio of the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure are small, and the integral descending trend is presented;
step 3.3, determining a threshold value by using a box type graph:
and 3.3.1, because the fault characteristic is that the numerical values of the supercharger lubricating oil inlet pressure, the ratio of the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure are small and continuously reduced, setting low thresholds of the supercharger lubricating oil inlet pressure, the ratio of the supercharger lubricating oil inlet pressure to the diesel engine lubricating oil pressure and the diesel engine lubricating oil pressure are respectively calculated by using a box diagram, wherein the two thresholds are respectively set under the conditions of 0.6 power factor, 0.8 power factor, 0.9 power factor, 20% load, 50% load, 75% load and 90% load, the threshold with the larger numerical value is defined as a pre-alarm value, and the threshold with the lower numerical value is defined as an alarm value.
4. The method of predicting a failure of a diesel supercharger for electric power generation according to claim 1, further comprising, in step 4, the steps of:
step 4.1, summarizing the threshold values of 0.6, 0.8 and 0.9 under different load conditions to form a threshold value table, and specifically judging abnormal conditions of 0.6, 0.8 and 0.9 under different load conditions by comparing the relation between the actual value and the numerical value in the threshold value table at the later stage;
and 4.2, improving a threshold value determining method, screening fault unit data according to different active powers by using a programming language, screening a part of data with more operation times, averaging the ratios of the supercharger lubricating oil inlet pressure, the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure under the same active power and different tests respectively, and calculating two threshold values of the ratios of the supercharger lubricating oil inlet pressure, the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure respectively by using a box diagram, wherein the threshold value with a larger numerical value is defined as a pre-alarm value, and the threshold value with a smaller numerical value is defined as an alarm value.
5. The method of predicting a failure of a diesel supercharger for electric power generation according to claim 1, further comprising, in step 5, the steps of:
step 5.1, forming a multi-threshold expression: it is known from step 2.2 that the ratios of the supercharger lubricating oil inlet pressure, the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure are respectively highly negatively correlated with the active power, so that the thresholds under different active powers are gathered together and fitted into a corresponding curve, and the polynomial maximum times of the curve are determined by comparing the residual errors, generally 2 times, that is, two threshold expressions of the ratios of the supercharger lubricating oil inlet pressure and the diesel engine lubricating oil pressure are respectively obtained;
step 5.2, it is known from step 2.2 that the ratios of the pressure of the inlet of the lubricating oil of the supercharger, the pressure of the inlet of the lubricating oil of the supercharger and the pressure of the lubricating oil of the diesel engine are respectively in high negative correlation with the active power and the temperature of the inlet of the lubricating oil of the supercharger, and the active power and the temperature of the inlet of the lubricating oil of the supercharger are in positive correlation, so that the pressure of the inlet of the lubricating oil of the supercharger can be jointly represented by the active power and the temperature of the inlet of the lubricating oil of the supercharger in the actual process, the method is more rigorous than the method in which the judgment is carried out only by the threshold expression of the pressure of the inlet of the lubricating oil of the supercharger and the active power, and the specific method is as follows;
step 5.2.1, when a large number of samples are available, classifying the data screened in the step 4.2 again according to the oil inlet temperature of the lubricating oil of the supercharger, averaging the same active power, the same oil inlet temperature of the supercharger, the oil inlet pressure of the lubricating oil of the supercharger under different tests and the ratio of the oil inlet pressure of the lubricating oil of the supercharger to the oil pressure of the diesel engine respectively, calculating two thresholds respectively by using a box diagram, summarizing the thresholds under different active powers and different oil inlet temperatures of the supercharger together, and fitting the thresholds into corresponding curves, so that two oil inlet pressure threshold expressions of the lubricating oil of the supercharger, the oil inlet pressure of which is determined by the active power and the oil inlet temperature of the supercharger under the condition of sufficient samples can be obtained;
and 5.2.2, when the number of samples is not enough to support the processing of the step 5.2.3, performing multivariate fitting on the obtained data in each test process, wherein the fitted curve expression is as follows:
P＝a2T+b2Pw+c2 (3)
wherein P is the oil inlet pressure of the lubricating oil of the supercharger; pwActive power; t is the oil inlet temperature of the lubricating oil of the supercharger;
setting the same and proper supercharger lubricating oil inlet temperature and active power for each test, and performing threshold selection on the calculated supercharger lubricating oil inlet pressure by using a box diagram, wherein corresponding expressions are two threshold expressions;
finally, a total of 6 threshold expressions are determined, which are of the form:
y1＝a1xn+b1xn-1+… (4)
y2＝a1xn+b1xn-1+… (5)
y3＝a2xn+b2xn-1+… (6)
y4＝a2xn+b2xn-1+… (7)
y5＝a1T+b1PW+c1 (8)
y6＝a2T+b2PW+c2 (9)
wherein x is unit active power, namely the ratio of the active power to rated power; pwActive power; t is the oil inlet temperature of the lubricating oil of the supercharger; y is1Representing the pressure of the inlet oil of the supercharger, y2Representing the ratio of the inlet pressure of the oil in the supercharger to the pressure of the oil in the diesel engine, y3Representing the pressure of the inlet oil of the supercharger, y4Representing the ratio of the inlet pressure of the oil in the supercharger to the pressure of the oil in the diesel engine, y5、y6All represent the oil inlet pressure of the lubricating oil of the supercharger;
finally, uniformly using y1、y2、y5To represent three pre-alarm expressions, y3、y4、y6To represent three alarm expressions;
and 5.3, determining the abnormal degree:
let W be the current booster oil inlet pressure or the ratio of the booster oil inlet pressure to the diesel engine oil pressure, W1And W2The pre-alarm value and the alarm value under the current working condition are as follows:
when W is1When the pressure is less than W, the lubrication of the supercharger is normal;
when W is2＜W≤W1When the pressure is higher than the set pressure, the pressure booster oil pre-alarms;
when W is less than or equal to W2And when the oil is in use, the oil lubrication of the supercharger alarms.
6. The method of predicting a failure of a diesel supercharger for electric power generation according to claim 1, further comprising, in step 6, the steps of:
step 6.1, inputting the oil inlet temperature P of the lubricating oil of the supercharger, the oil inlet temperature T of the lubricating oil of the supercharger and the active power P in real time through a data buswDiesel engine lubricating oil pressure PDPreprocessing by using a multi-threshold expression and outputting W, W under the current working condition1And W2Entering a model for judging abnormal conditions;
and 6.2, outputting a prediction result:
when the pre-alarm is continuously generated, the situation that the oil inlet pressure of the lubricating oil of the supercharger is low and is in a descending trend is shown, impurities begin to exist in the lubricating oil, and corresponding measures are suggested to be taken to increase the pressure and corresponding inspection is carried out;
when an alarm occurs, the two threshold values have an interval range, which shows that the pressure of the lubricating oil in the supercharger is seriously low, the pressure is rapidly and obviously reduced, the supercharger is probably failed, the supercharger should be stopped immediately for checking, and corresponding measures are taken to increase the pressure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110369737.0A CN113516273B (en) | 2021-04-02 | 2021-04-02 | Diesel engine supercharger fault prediction method for power generation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110369737.0A CN113516273B (en) | 2021-04-02 | 2021-04-02 | Diesel engine supercharger fault prediction method for power generation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113516273A true CN113516273A (en) | 2021-10-19 |
| CN113516273B CN113516273B (en) | 2024-06-04 |
Family
ID=78062265
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110369737.0A Active CN113516273B (en) | 2021-04-02 | 2021-04-02 | Diesel engine supercharger fault prediction method for power generation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113516273B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114112447A (en) * | 2021-11-24 | 2022-03-01 | 中车大连机车车辆有限公司 | Method for testing functions of locomotive before departure |
| CN114856820A (en) * | 2022-05-16 | 2022-08-05 | 太仓点石航空动力有限公司 | Fault analysis method, system and equipment based on health management of lubricating oil system |
| CN114944698A (en) * | 2022-04-29 | 2022-08-26 | 南通电博士自动化设备有限公司 | Intelligent control method and system for diesel generator group |
| CN115774847A (en) * | 2022-11-22 | 2023-03-10 | 上海船舶运输科学研究所有限公司 | Diesel engine performance evaluation and prediction method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105487530A (en) * | 2016-02-01 | 2016-04-13 | 中国人民解放军镇江船艇学院 | Diesel low-exhaust-temperature fault prediction system and method |
| CN105928710A (en) * | 2016-04-15 | 2016-09-07 | 中国船舶工业系统工程研究院 | Diesel engine fault monitoring method |
| CN111814849A (en) * | 2020-06-22 | 2020-10-23 | 浙江大学 | DA-RNN-based wind turbine generator key component fault early warning method |
-
2021
- 2021-04-02 CN CN202110369737.0A patent/CN113516273B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105487530A (en) * | 2016-02-01 | 2016-04-13 | 中国人民解放军镇江船艇学院 | Diesel low-exhaust-temperature fault prediction system and method |
| CN105928710A (en) * | 2016-04-15 | 2016-09-07 | 中国船舶工业系统工程研究院 | Diesel engine fault monitoring method |
| CN111814849A (en) * | 2020-06-22 | 2020-10-23 | 浙江大学 | DA-RNN-based wind turbine generator key component fault early warning method |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114112447A (en) * | 2021-11-24 | 2022-03-01 | 中车大连机车车辆有限公司 | Method for testing functions of locomotive before departure |
| CN114112447B (en) * | 2021-11-24 | 2024-05-28 | 中车大连机车车辆有限公司 | Locomotive departure front function test method |
| CN114944698A (en) * | 2022-04-29 | 2022-08-26 | 南通电博士自动化设备有限公司 | Intelligent control method and system for diesel generator group |
| CN114944698B (en) * | 2022-04-29 | 2024-05-03 | 湛江伟力机电设备有限公司 | Intelligent diesel generator group control method and system |
| CN114856820A (en) * | 2022-05-16 | 2022-08-05 | 太仓点石航空动力有限公司 | Fault analysis method, system and equipment based on health management of lubricating oil system |
| CN114856820B (en) * | 2022-05-16 | 2024-04-09 | 太仓点石航空动力有限公司 | Fault analysis method, system and equipment based on lubricating oil system health management |
| CN115774847A (en) * | 2022-11-22 | 2023-03-10 | 上海船舶运输科学研究所有限公司 | Diesel engine performance evaluation and prediction method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113516273B (en) | 2024-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113516273B (en) | Diesel engine supercharger fault prediction method for power generation | |
| EP1982301B1 (en) | Method of condition monitoring | |
| US5951611A (en) | Diagnostic trend analysis | |
| Gebraeel et al. | Residual life predictions in the absence of prior degradation knowledge | |
| CN111159844B (en) | Abnormity detection method for exhaust temperature of gas turbine of power station | |
| CN110208019A (en) | A kind of dynamic equipment condition monitoring dynamic threshold method for early warning | |
| US20100292937A1 (en) | Turbocharger bearing health monitor | |
| CN108801641B (en) | Fault diagnosis and reliability prediction method and system for exhaust gas turbocharger | |
| CN116873156B (en) | Intelligent monitoring method for power abnormality of natural gas ship based on big data | |
| CN112052871B (en) | Rocket engine health diagnosis method and system based on support vector machine | |
| CN111506049B (en) | Multiple fault diagnosis method for aero-engine control system based on AANN network system | |
| CN110704987B (en) | Bearing abnormal state assessment method based on similar working condition of failure data mining | |
| CN112580267A (en) | Aero-engine surge prediction method based on multi-branch feature fusion network | |
| CN111103137A (en) | Wind turbine gearbox fault diagnosis method based on deep neural network | |
| CN116976191A (en) | Method for predicting shafting stability degradation trend of hydroelectric generating set | |
| CN114969645A (en) | Statistical distribution model-based aircraft engine state monitoring and evaluation method | |
| CN117272032B (en) | Air compressor fault diagnosis method and device based on vibration detection | |
| CN110956268A (en) | Compressor fault diagnosis method based on big data | |
| CN114252273A (en) | Online detection method for abnormal exhaust temperature of gas turbine | |
| CN114252270A (en) | Online early warning method for abnormal exhaust temperature of gas turbine | |
| CN109872511B (en) | Self-adaptive two-stage alarm method for monitoring axial displacement sudden change | |
| CN108716463A (en) | A kind of method for diagnosing faults of reciprocating compressor ring air flap | |
| Joshuva et al. | Split-point and attribute-reduced classifier approach for fault diagnosis of wind turbine blade through vibration signals | |
| CN116577104A (en) | Engine fault detection method and equipment | |
| Kenyon et al. | Development of an intelligent system for detection of exhaust gas temperature anomalies in gas turbines |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |