CN112710474A - Diesel engine state evaluation method based on real-time vibration data - Google Patents
Diesel engine state evaluation method based on real-time vibration data Download PDFInfo
- Publication number
- CN112710474A CN112710474A CN202011637632.0A CN202011637632A CN112710474A CN 112710474 A CN112710474 A CN 112710474A CN 202011637632 A CN202011637632 A CN 202011637632A CN 112710474 A CN112710474 A CN 112710474A
- Authority
- CN
- China
- Prior art keywords
- diesel engine
- real
- index
- characteristic
- state evaluation
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 52
- 238000010206 sensitivity analysis Methods 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 40
- 230000008859 change Effects 0.000 claims description 25
- 230000008569 process Effects 0.000 claims description 21
- 238000012360 testing method Methods 0.000 claims description 20
- 230000003595 spectral effect Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 125000004122 cyclic group Chemical group 0.000 claims description 8
- 230000035945 sensitivity Effects 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 5
- 230000036541 health Effects 0.000 claims description 4
- 238000001228 spectrum Methods 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 230000003211 malignant effect Effects 0.000 abstract description 2
- 208000024891 symptom Diseases 0.000 abstract description 2
- 238000003745 diagnosis Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 238000012935 Averaging Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000001845 vibrational spectrum Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M15/00—Testing of engines
- G01M15/04—Testing internal-combustion engines
- G01M15/12—Testing internal-combustion engines by monitoring vibrations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Combustion & Propulsion (AREA)
- Combined Controls Of Internal Combustion Engines (AREA)
- Testing Of Engines (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a diesel engine state evaluation method based on real-time vibration data, and belongs to the technical field of diesel engine running state monitoring. Firstly, preliminarily determining a sensor arrangement scheme, secondly, determining a characteristic channel through sensitivity analysis, then selecting a characteristic parameter based on the characteristic channel, then establishing a state evaluation key index according to the characteristic channel and the characteristic parameter, and establishing an index reference of dynamic self-adaptive iterative update; and finally, evaluating the state of the diesel engine based on the established state evaluation index and index standard. The invention can quickly evaluate the instantaneous running state of the diesel engine only by real-time vibration data, finds the fault symptoms of the diesel engine in advance and effectively avoids malignant faults and casualties.
Description
Technical Field
The invention belongs to the technical field of monitoring of running states of diesel engines, and particularly relates to a diesel engine state evaluation method based on real-time vibration data.
Background
The rapid development of global economy accelerates the development of marine industry, so that the marine transportation capacity is greatly increased, and the marine diesel engine serving as a main power device of a ship has an inseparable relationship with marine transportation. With the continuous introduction of technologies such as computer, data communication, automatic control and the like in the world, the diesel engine system is developing towards intellectualization and energy conservation, the automation level of the system is greatly improved, the personnel dependence is greatly reduced, and therefore the failure probability is greatly increased. Once the diesel engine breaks down, the safety of the ship sailing on the sea is directly influenced, catastrophic personal injuries and disastrous equipment damages can be seriously caused, and immeasurable losses are caused. According to statistics, the diesel engine fault accounts for 45% of the mechanical faults and 22% of the whole ship fault.
At present, a diesel engine state evaluation method based on vibration data is mainly vibration spectrum analysis based on fourier transform, and researchers analyze different vibration test information to obtain a fault diagnosis result of a diesel engine. For example, the present inventors propose to integrate the wear state and vibration information of the diesel engine to realize the comprehensive diagnosis and reasoning of two kinds of information on the fault of the diesel engine. The xi' an traffic university Thailand and the like provide a novel fault diagnosis method based on characteristic evaluation and a neural network aiming at the characteristic that the sensitivity of various diagnosis characteristics is different, and the novel fault diagnosis method is applied to the diagnosis of the friction fault of the smoke turbine, so that the effectiveness and the robustness of the provided method are verified. However, most of the research methods are used for fault diagnosis, real-time state evaluation is not considered, and the method belongs to post analysis. The diagnosis model provided by the Zhang Yingtang only utilizes certain specific characteristic parameters as the basis for diagnosing and analyzing the running state, has great limitation, needs similar faults as comparison, and is difficult to have a complete fault model in practical engineering application; the fault diagnosis method based on the neural network proposed by the reyas usually has higher requirements on training samples, and is not easy to change after the training is completed. However, the diesel engine belongs to a typical fault mode which mainly adopts performance degradation, the use environment and the operation working condition are severe and changeable, and the fault diagnosis method has low adaptability.
In addition, the existing diesel engine state evaluation method depends on human experience to a certain extent, and the false alarm rate is high. For various types of diesel engines with different types and structures, the selection of the optimal vibration measuring point theoretically needs complicated transmission path analysis deduction, the practicability is not strong, and the method often depends on artificial experience; the existing vibration analysis indexes are numerous, the enumeration method is time-consuming and labor-consuming, and the selection is often carried out by depending on human experience. In addition, the benchmark of state evaluation needs to be dynamically adjusted according to the running-in performance and the actual operation condition of the diesel engine, while the existing scheme is often set according to experience or initial conditions, and once the setting is not allowed to be modified in real time, the self-adaptive updating capability is lacked. Therefore, although the state evaluation of the diesel engine is applied in many occasions, the existing vibration acquisition scheme and state analysis method have certain blindness, and informatization and intelligent improvement based on the principles of mechanical dynamics, statistics and informatics methods is urgently needed.
Disclosure of Invention
In view of the above, the invention provides a method for evaluating the state of a diesel engine based on real-time vibration data, which makes full use of the current large-capacity data storage, large data mining, high-speed operation technology and high-speed low-delay communication technology to realize that the instantaneous operating state of the diesel engine can be quickly evaluated only through the real-time vibration data, so that the fault symptom of the diesel engine can be found in advance, and the occurrence of malignant faults and casualties can be effectively avoided.
A diesel engine state evaluation method based on real-time vibration data comprises the following implementation steps:
the method comprises the following steps: preliminarily determining a sensor arrangement scheme;
step two: determining a characteristic channel through sensitivity analysis;
step three: selecting characteristic parameters based on the characteristic channels;
step four: establishing a state evaluation key index according to the characteristic channel and the characteristic parameter;
step five: constructing an index reference of dynamic self-adaptive iterative updating;
step six: and performing diesel engine state evaluation based on the established state evaluation indexes and index benchmarks.
Further, the process of determining the sensor arrangement scheme in the first step includes: according to the structural characteristics of a target diesel engine, three-direction vibration measuring points capable of directly reflecting dynamic response characteristics of moving parts of the diesel engine are selected, an acceleration sensor with the measuring range being 3-5 times larger than the maximum vibration level of the target measuring points is selected according to the vibration magnitude of the actual measuring points, and multi-channel vibration data acquisition of the diesel engine in a real-time running state is carried out on the basis of the configuration.
Further, the characteristic channel determination process of the second step includes: taking 20% of rated power of the diesel engine as an initial value, taking 1% of the rated power as incremental change, and gradually increasing the load level until the rated power is cut off; each load condition is kept running for 10 seconds, and the time domain peak value of the vibration signal is calculated; calculating the average value of the absolute value of the peak-to-peak value change under the condition of gradually increasing load, defining the average value as the peak-to-peak value load change rate, and using the peak-to-peak value load change rate as an index for evaluating the channel vibration signal sensitivity; and taking 5 signal channels with the maximum peak load change rate as feature sensitive test channels.
Further, the initial power, the power increment, the cut-off power, the time length for maintaining the operation of the characteristic load condition and the number of finally selected signal channels in the second step are all adjusted according to actual requirements.
Further, the process of selecting the characteristic parameters in the third step includes: designing a cyclic operation map containing 5 typical operation states according to the actual operation condition of the diesel engine, performing two cyclic operation tests, and synchronously acquiring vibration signals of the 5 characteristic sensitive test channels determined in the second step; respectively calculating effective value, variance, peak-to-peak value, skewness and kurtosis of each channel original vibration signal, mean value, average frequency, spectral variance, spectral peak value and spectral kurtosis of an amplitude spectrum after Fourier transform of the original signal, effective value, variance, peak-to-peak value, skewness and kurtosis of an amplitude envelope signal of the original signal, mean value, average frequency, spectral variance, spectral peak value and spectral kurtosis of the amplitude spectrum after Fourier transform of the amplitude envelope signal, and totaling 20 characteristic parameter indexes; according to the principle of minimum characteristic difference under the same working condition and maximum characteristic difference under different working conditions, the basis for evaluating the characteristic parameter indexes is designed, and 5 optimal vibration characteristic parameters capable of effectively reflecting the running state of the diesel engine are preferably selected for each channel.
Furthermore, the number of the running states, the number of the cycle tests, the number and the types of the characteristic parameter indexes and the number of the optimal vibration characteristic parameters in the third step can be properly adjusted according to actual requirements.
Further, the process of establishing the state evaluation key index in the fourth step includes: and removing channels and parameters with the same type and similar effects based on the selected diesel engine characteristic sensitivity test channel in the step two and the optimized vibration characteristic parameter of each channel in the step three, normalizing and multiplying the characteristic parameters of the rest channels, and fusing the characteristic parameters into a key evaluation index.
Further, the construction process of the index reference in the fifth step includes: and taking the health state of the diesel engine as an initial state, taking 20 percent of rated power of the diesel engine as an initial value, taking 1 percent of the rated power as an incremental change, and gradually increasing the load level until the rated power is cut off. And (4) keeping running for 5 minutes under each load condition, and calculating a corresponding state evaluation index as an initial index standard. In the actual running process of the diesel engine, the state evaluation index calculation is carried out on the vibration data collected in real time, and the latest index reference is calculated again every 10 minutes based on the running state data of the latest 10 minutes, so that the index reference of dynamic self-adaptive iterative updating is formed.
Further, the initial power, the power increment, the cut-off power, the specific load maintaining operation time and the index reference updating time in the fifth step are all properly adjusted according to actual requirements.
Further, the state evaluation process of the sixth step includes: based on the established state evaluation index and the dynamically self-adaptive iterative updated index standard, carrying out real-time vibration data acquisition and rapid index calculation on the diesel engine, and comparing the real-time vibration data acquisition and rapid index calculation with the real-time index standard; when the real-time state evaluation index value exceeds 10% of the current standard, judging that the diesel engine is abnormal, and performing state early warning; and analyzing the original vibration data corresponding to the abnormal moment by using a time-frequency analysis technology, and diagnosing the abnormal reason so as to guide the real-time state evaluation of the diesel engine.
Has the advantages that:
1. compared with the prior art, the diesel engine state evaluation method based on real-time vibration data provided by the invention obviously reduces the deviation caused by human intervention. The method does not depend on manual experience to select the measuring points and the characteristic indexes of the diesel engine, but automatically selects the measuring points and the evaluation indexes which are most sensitive to state change based on the self vibration characteristics of the diesel engine to be measured, thereby improving the accuracy of state evaluation.
2. Compared with the prior art, the diesel engine state evaluation method based on real-time vibration data can effectively reduce the false alarm rate. In the actual operation process of the diesel engine, the vibration characteristic changes along with the assembly condition of parts and the running-in of contact parts, and even under the condition that no fault occurs, the overall vibration characteristic also has the characteristic of nonlinear change. On the premise of fixing the index reference, false alarm is easy to occur. The method provided by the invention updates the index reference at regular time without human intervention, and can integrate the performance change information of the diesel engine into the state evaluation flow, thereby reducing the false alarm rate.
Drawings
FIG. 1 is a flow chart illustrating the steps of a method for estimating the state of a diesel engine based on real-time vibration data according to the present invention;
FIG. 2 is a schematic diagram of a preferred process for a sensing channel;
FIG. 3 is a schematic diagram of a characteristic indicator optimization process;
FIG. 4 is a diagram illustrating reference setup and update.
Detailed Description
The invention is described in detail below by way of example with reference to the accompanying drawings.
As shown in fig. 1, the invention provides a method for evaluating the state of a diesel engine based on real-time vibration data, which comprises the following implementation steps:
step 1: preliminarily determining a sensor arrangement scheme; according to the structural characteristics of a target diesel engine, three-direction vibration measuring points such as a cylinder cover, a bearing seat and a machine foot which can directly reflect the dynamic response characteristics of moving parts of the diesel engine are selected, an acceleration sensor with the measuring range being 3-5 times larger than the maximum vibration level of the target measuring point is selected according to the vibration magnitude of the actual measuring point, and a sensor bolt connection installation mode is selected for ensuring the testing quality and safety. Based on the configuration, multichannel vibration data acquisition of the diesel engine in a real-time running state is carried out.
Preferably, in step 1, other common vibration measuring points can be selected, and the measuring range and the installation mode of the sensor can be set according to actual requirements.
Step 2: determining a characteristic channel through sensitivity analysis; and taking 20 percent of rated power of the diesel engine as an initial value and 1 percent of rated power as incremental change, and gradually increasing the load level until the rated power is cut off. Each load condition was maintained for 10 seconds and the time domain peak to peak value of the vibration signal segment was calculated. And averaging the absolute value of the peak-to-peak value change under the condition of gradually increasing load, defining the average value as the peak-to-peak value load change rate, and using the average value as an index for evaluating the channel vibration signal sensitivity. And taking 5 signal channels with the maximum peak load change rate as feature sensitive test channels.
Preferably, the initial power, the power increment, the cut-off power, the time length for maintaining the operation of the characteristic load condition and the number of the finally selected signal channels in the step 2 can be properly adjusted according to actual requirements.
And step 3: selecting characteristic parameters based on the characteristic channels; and (3) designing a cyclic operation map containing 5 typical operation states according to the actual operation condition of the diesel engine, performing two cyclic operation tests, and synchronously acquiring the vibration signals of the 5 characteristic sensitive test channels determined in the step two. The 20 characteristic parameter indexes of each channel are respectively calculated. According to the principle of minimum characteristic difference under the same working condition and maximum characteristic difference under different working conditions, the basis for evaluating the characteristic parameter indexes is designed, and 5 optimal vibration characteristic parameters capable of effectively reflecting the running state of the diesel engine are preferably selected for each channel.
Preferably, the number of the running states, the number of the cycle tests, the number and the types of the characteristic parameter indexes, and the number of the optimal vibration characteristic parameters in the step 3 can be properly adjusted according to actual requirements.
And 4, step 4: establishing a state evaluation key index according to the characteristic channel and the characteristic parameter; and removing channels and parameters with the same type and similar effects based on the selected diesel engine characteristic sensitivity test channel in the step two and the optimized vibration characteristic parameter of each channel in the step three, normalizing and multiplying the characteristic parameters of the rest channels, and fusing the characteristic parameters into 1 key evaluation index.
And 5: and constructing an index reference of dynamic self-adaptive iterative updating. And taking the health state of the diesel engine as an initial state, taking 20 percent of rated power of the diesel engine as an initial value, taking 1 percent of the rated power as an incremental change, and gradually increasing the load level until the rated power is cut off. And (4) keeping running for 5 minutes under each load condition, and calculating a corresponding state evaluation index as an initial index standard. In the actual running process of the diesel engine, the state evaluation index calculation is carried out on the vibration data collected in real time, and the latest index reference is calculated again every 10 minutes based on the running state data of the latest 10 minutes, so that the index reference of dynamic self-adaptive iterative updating is formed.
Preferably, the starting power, the power increment, the cut-off power, the specific load maintaining operation time and the index reference updating time in the step 5 can be properly adjusted according to actual requirements.
Step 6: and index monitoring and state early warning are carried out. And based on the established state evaluation index and the dynamically self-adaptive iterative updated index reference, carrying out real-time vibration data acquisition and rapid index calculation on the diesel engine, and comparing the real-time vibration data acquisition and rapid index calculation with the real-time index reference. And when the real-time state evaluation index value exceeds 10% of the current standard, judging that the diesel engine is abnormal, and performing state early warning.
Preferably, the index threshold range can be properly adjusted according to actual requirements.
FIG. 2 is a schematic diagram of a preferred process for determining a signature channel by sensitivity analysis. First, a set of basic experiments was performed, with 20% of the rated power of the diesel engine as the starting value and 1% of the rated power as incremental changes, to gradually increase the load level until the rated power cut-off was reached. Each load condition was maintained for 10 seconds and the time domain peak to peak value of the vibration signal segment was calculated. And averaging the absolute value of the peak-to-peak value change under the condition of gradually increasing load, defining the average value as the peak-to-peak value load change rate, and using the average value as an index for evaluating the channel vibration signal sensitivity. And taking 5 signal channels with the maximum peak load change rate as feature sensitive test channels. Preferably, the initial power, the power increment, the cut-off power, the time length for maintaining the operation of the characteristic load condition and the number of finally selected signal channels can be properly adjusted according to the actual requirement.
Fig. 3 is a schematic diagram of a preferred process of feature index, which illustrates a detailed process of selecting feature parameters based on feature channels. Firstly, according to the actual operation condition of the diesel engine, a cyclic operation map containing 5 typical operation states is designed, two cyclic operation tests are carried out, and the vibration signals of the 5 characteristic sensitive test channels determined in the second step are synchronously acquired. The 20 characteristic parameter indexes of each channel are respectively calculated. According to the principle that the distance in the same working condition characteristic group is minimum and the distance of different working condition characteristic assemblies is maximum, the basis for evaluating the characteristic parameter indexes is designed, and 5 optimal vibration characteristic parameters capable of effectively reflecting the running state of the diesel engine are preferably selected for each channel. Preferably, the number of the running states, the number of the cycle tests, the number and the types of the characteristic parameter indexes and the number of the optimal vibration characteristic parameters can be properly adjusted according to actual requirements.
Fig. 4 is a schematic diagram of reference setting and updating, which illustrates a specific process of constructing a dynamically adaptive iteratively updated index reference. And taking the health state of the diesel engine as an initial state, taking 20 percent of rated power of the diesel engine as an initial value, taking 1 percent of the rated power as an incremental change, and gradually increasing the load level until the rated power is cut off. And (3) keeping running for 10 minutes under each load condition, taking every 10 seconds as a section, and calculating a corresponding state evaluation index mean value as an initial index standard. In the actual running process of the diesel engine, the state evaluation index calculation is carried out on the vibration data collected in real time, and the latest index reference is calculated again every 10 minutes based on the running state data of the latest 10 minutes, so that the index reference of dynamic self-adaptive iterative updating is formed. Preferably, the starting power, the power increment, the cut-off power, the specific load maintaining operation time and the index reference updating time can be properly adjusted according to actual requirements.
In summary, the above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A diesel engine state evaluation method based on real-time vibration data is characterized by comprising the following implementation steps:
the method comprises the following steps: preliminarily determining a sensor arrangement scheme;
step two: determining a characteristic channel through sensitivity analysis;
step three: selecting characteristic parameters based on the characteristic channels;
step four: establishing a state evaluation key index according to the characteristic channel and the characteristic parameter;
step five: constructing an index reference of dynamic self-adaptive iterative updating;
step six: and performing diesel engine state evaluation based on the established state evaluation indexes and index benchmarks.
2. The method for evaluating the condition of a diesel engine based on real-time vibration data according to claim 1, wherein the step one of determining the sensor arrangement scheme comprises: according to the structural characteristics of a target diesel engine, three-direction vibration measuring points capable of directly reflecting dynamic response characteristics of moving parts of the diesel engine are selected, an acceleration sensor with the measuring range being 3-5 times larger than the maximum vibration level of the target measuring points is selected according to the vibration magnitude of the actual measuring points, and multi-channel vibration data acquisition of the diesel engine in a real-time running state is carried out on the basis of the configuration.
3. The diesel engine state evaluation method based on real-time vibration data according to claim 2, wherein the characteristic channel determination process of the second step comprises: taking 20% of rated power of the diesel engine as an initial value, taking 1% of the rated power as incremental change, and gradually increasing the load level until the rated power is cut off; each load condition is kept running for 10 seconds, and the time domain peak value of the vibration signal is calculated; calculating the average value of the absolute value of the peak-to-peak value change under the condition of gradually increasing load, defining the average value as the peak-to-peak value load change rate, and using the peak-to-peak value load change rate as an index for evaluating the channel vibration signal sensitivity; and taking 5 signal channels with the maximum peak load change rate as feature sensitive test channels.
4. The diesel engine state evaluation method based on real-time vibration data as set forth in claim 3, wherein the initial power, the power increment, the cut-off power, the duration of maintaining the operation of the characteristic load condition, and the number of the finally selected signal channels in the second step are adjusted according to actual requirements.
5. The diesel engine state evaluation method based on real-time vibration data as set forth in claim 4, wherein the process of selecting the characteristic parameters in the third step comprises: designing a cyclic operation map containing 5 typical operation states according to the actual operation condition of the diesel engine, performing two cyclic operation tests, and synchronously acquiring vibration signals of the 5 characteristic sensitive test channels determined in the second step; respectively calculating effective value, variance, peak-to-peak value, skewness and kurtosis of each channel original vibration signal, mean value, average frequency, spectral variance, spectral peak value and spectral kurtosis of an amplitude spectrum after Fourier transform of the original signal, effective value, variance, peak-to-peak value, skewness and kurtosis of an amplitude envelope signal of the original signal, mean value, average frequency, spectral variance, spectral peak value and spectral kurtosis of the amplitude spectrum after Fourier transform of the amplitude envelope signal, and totaling 20 characteristic parameter indexes; according to the principle of minimum characteristic difference under the same working condition and maximum characteristic difference under different working conditions, the basis for evaluating the characteristic parameter indexes is designed, and 5 optimal vibration characteristic parameters capable of effectively reflecting the running state of the diesel engine are preferably selected for each channel.
6. The diesel engine state evaluation method based on real-time vibration data as set forth in claim 5, wherein the process of establishing the state evaluation key index in the fourth step comprises: and removing channels and parameters with the same type and similar effects based on the selected diesel engine characteristic sensitivity test channel in the step two and the optimized vibration characteristic parameter of each channel in the step three, normalizing and multiplying the characteristic parameters of the rest channels, and fusing the characteristic parameters into a key evaluation index.
7. The diesel engine state evaluation method based on real-time vibration data as set forth in claim 6, wherein the construction process of the index reference in the step five comprises: and taking the health state of the diesel engine as an initial state, taking 20 percent of rated power of the diesel engine as an initial value, taking 1 percent of the rated power as an incremental change, and gradually increasing the load level until the rated power is cut off. And (4) keeping running for 5 minutes under each load condition, and calculating a corresponding state evaluation index as an initial index standard. In the actual running process of the diesel engine, the state evaluation index calculation is carried out on the vibration data collected in real time, and the latest index reference is calculated again every 10 minutes based on the running state data of the latest 10 minutes, so that the index reference of dynamic self-adaptive iterative updating is formed.
8. The diesel engine state estimation method based on real-time vibration data according to claim 7, wherein the state estimation process of the sixth step includes: based on the established state evaluation index and the dynamically self-adaptive iterative updated index standard, carrying out real-time vibration data acquisition and rapid index calculation on the diesel engine, and comparing the real-time vibration data acquisition and rapid index calculation with the real-time index standard; when the real-time state evaluation index value exceeds 10% of the current standard, judging that the diesel engine is abnormal, and performing state early warning; and analyzing the original vibration data corresponding to the abnormal moment by using a time-frequency analysis technology, and diagnosing the abnormal reason so as to guide the real-time state evaluation of the diesel engine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011637632.0A CN112710474B (en) | 2020-12-31 | 2020-12-31 | Diesel engine state evaluation method based on real-time vibration data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011637632.0A CN112710474B (en) | 2020-12-31 | 2020-12-31 | Diesel engine state evaluation method based on real-time vibration data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112710474A true CN112710474A (en) | 2021-04-27 |
| CN112710474B CN112710474B (en) | 2022-11-04 |
Family
ID=75547919
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011637632.0A Active CN112710474B (en) | 2020-12-31 | 2020-12-31 | Diesel engine state evaluation method based on real-time vibration data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112710474B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113358359A (en) * | 2021-05-25 | 2021-09-07 | 中国人民解放军92493部队计量测试研究所 | Method for detecting working performance state of diesel engine |
| CN114577480A (en) * | 2022-03-02 | 2022-06-03 | 中国船舶重工集团柴油机有限公司 | Diesel engine state monitoring method and system based on sequence transformation |
| CN114894460A (en) * | 2022-05-10 | 2022-08-12 | 同济大学 | IMU-based method for monitoring and evaluating damage state of anti-seismic support and hanger |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014126459A (en) * | 2012-12-26 | 2014-07-07 | National Fisheries Univ | State monitoring system of reciprocating mechanical device, and method and program thereof |
| CN104807640A (en) * | 2015-05-08 | 2015-07-29 | 重庆交通大学 | Method of detecting life state of spatial rolling bearing based on vibration-sensitive time-frequency characteristics |
| CN110044631A (en) * | 2019-03-13 | 2019-07-23 | 中交广州航道局有限公司 | Trend prediction method, device and the computer equipment of ship machine diesel engine |
| CN110455546A (en) * | 2019-07-19 | 2019-11-15 | 广西大学 | Engine Condition Monitoring and Fault Diagnosis Method Based on Vibration and Oil Information |
| CN111779573A (en) * | 2020-06-28 | 2020-10-16 | 河南柴油机重工有限责任公司 | Method and device for online fault detection of diesel engine |
-
2020
- 2020-12-31 CN CN202011637632.0A patent/CN112710474B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014126459A (en) * | 2012-12-26 | 2014-07-07 | National Fisheries Univ | State monitoring system of reciprocating mechanical device, and method and program thereof |
| CN104807640A (en) * | 2015-05-08 | 2015-07-29 | 重庆交通大学 | Method of detecting life state of spatial rolling bearing based on vibration-sensitive time-frequency characteristics |
| CN110044631A (en) * | 2019-03-13 | 2019-07-23 | 中交广州航道局有限公司 | Trend prediction method, device and the computer equipment of ship machine diesel engine |
| CN110455546A (en) * | 2019-07-19 | 2019-11-15 | 广西大学 | Engine Condition Monitoring and Fault Diagnosis Method Based on Vibration and Oil Information |
| CN111779573A (en) * | 2020-06-28 | 2020-10-16 | 河南柴油机重工有限责任公司 | Method and device for online fault detection of diesel engine |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113358359A (en) * | 2021-05-25 | 2021-09-07 | 中国人民解放军92493部队计量测试研究所 | Method for detecting working performance state of diesel engine |
| CN114577480A (en) * | 2022-03-02 | 2022-06-03 | 中国船舶重工集团柴油机有限公司 | Diesel engine state monitoring method and system based on sequence transformation |
| CN114577480B (en) * | 2022-03-02 | 2023-11-10 | 中船发动机有限公司 | Diesel engine state monitoring method and system based on sequence transformation |
| CN114894460A (en) * | 2022-05-10 | 2022-08-12 | 同济大学 | IMU-based method for monitoring and evaluating damage state of anti-seismic support and hanger |
| CN114894460B (en) * | 2022-05-10 | 2023-03-28 | 同济大学 | IMU-based method for monitoring and evaluating damage state of anti-seismic support and hanger |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112710474B (en) | 2022-11-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112710474B (en) | Diesel engine state evaluation method based on real-time vibration data | |
| US10496466B2 (en) | Preprocessor of abnormality sign diagnosing device and processing method of the same | |
| CN109559025A (en) | A kind of bridge detecting/monitoring integrated health condition evaluation system and its application method | |
| CN110378034B (en) | Locomotive engine fault diagnosis method, system and implementation device | |
| CN116881673B (en) | Shield tunneling machine operation and maintenance method based on big data analysis | |
| CN111776006B (en) | Pre-alarming method and device for train axle temperature | |
| CN105487530A (en) | Diesel low-exhaust-temperature fault prediction system and method | |
| CN118245808B (en) | Machine learning-based speed reducer fault diagnosis method and system | |
| CN117554752A (en) | Power cable fault on-line detection system and method | |
| CN118332467B (en) | Rotational speed sensor operation fault diagnosis management system based on data analysis | |
| CN116878728A (en) | Pressure sensor fault detection analysis processing system | |
| CN118066934A (en) | Intelligent fault positioning system for weapon equipment | |
| CN118965241B (en) | Fault monitoring and early warning method and system for fuel regulator | |
| CN116049958A (en) | Historical building structure monitoring data anomaly diagnosis and repair system | |
| CN118094278B (en) | Data quality inspection method, device and medium based on power application scene difference | |
| CN119420050A (en) | A power grid abnormal state monitoring and early warning system | |
| CN112326255B (en) | A kind of engine remote health monitoring system and monitoring method | |
| CN112766772B (en) | Method and device for monitoring oil-gas-water well in real time, computer equipment and storage medium | |
| CN112948925B (en) | Bridge health state evaluation method, system and storage medium | |
| CN117662491A (en) | Main pump fault diagnosis method and system based on principal component and deep learning algorithm | |
| CN117819387A (en) | An early warning method for upper and lower bound estimation intervals based on quay crane health monitoring data | |
| CN115600402A (en) | Construction method and system of fracturing equipment service life and construction process parameter relation model | |
| CN114237128A (en) | Hydropower station equipment real-time monitoring data monitoring system and monitoring method based on trend alarm | |
| CN113358359B (en) | Method for detecting working performance state of diesel engine | |
| CN119780388A (en) | A real-time monitoring method and device for light gas |
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 |