CN115774847B - Diesel engine performance evaluation and prediction method and system - Google Patents
Diesel engine performance evaluation and prediction method and system Download PDFInfo
- Publication number
- CN115774847B CN115774847B CN202211467398.0A CN202211467398A CN115774847B CN 115774847 B CN115774847 B CN 115774847B CN 202211467398 A CN202211467398 A CN 202211467398A CN 115774847 B CN115774847 B CN 115774847B
- Authority
- CN
- China
- Prior art keywords
- diesel engine
- data
- performance parameter
- performance
- diesel
- 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.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012549 training Methods 0.000 claims abstract description 47
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 238000003064 k means clustering Methods 0.000 claims abstract description 12
- 239000000446 fuel Substances 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000006835 compression Effects 0.000 claims description 8
- 238000007906 compression Methods 0.000 claims description 8
- 239000002283 diesel fuel Substances 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 230000002000 scavenging effect Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Combined Controls Of Internal Combustion Engines (AREA)
Abstract
The invention provides a diesel engine performance evaluation and prediction method and system, the method firstly obtains a plurality of diesel engine load percentages and key performance parameter data under the corresponding load percentages, then uses the key performance parameter data as a training set sample, trains by adopting a polynomial fitting method to obtain polynomial models of all diesel engines, inputs actual values corresponding to the diesel engine load percentages and the key performance parameter data as data to be detected into the polynomial models to obtain reference values corresponding to the data to be detected, calculates deviation according to the actual values and the reference values, finally uses the calculated deviation as a data set, clusters by adopting a K-means clustering algorithm to obtain a plurality of clustering centers, then carries out linear fitting to obtain a performance parameter operation deviation trend graph of all diesel engines, evaluates and predicts the performance trend of the diesel engines according to the performance parameter operation deviation trend graph, displays the evaluation and prediction results, and can predict the variation trend of the performance of the diesel engines at future time.
Description
Technical Field
The invention relates to the technical field of diesel engine performance prediction, in particular to a diesel engine performance evaluation and prediction method and system.
Background
With the high-speed development of intelligent ship technology, ship intellectualization becomes a trend, the maintenance and management requirements on the diesel engine are changed from real-time monitoring to prediction of future states, and the performance change trend of the diesel engine is predicted, so that the diesel engine can be prevented from being failed, the downtime is reduced, the shipping cost is saved, and the safe and stable operation of the ship is ensured.
The traditional diesel engine performance prediction method is mainly based on a model, and prediction is performed by establishing a mathematical or physical model. For example: 1) Based on a two-stroke diesel engine simulation model, analyzing the variation of performance parameters such as power, exhaust temperature, highest explosion pressure and the like of the diesel engine under the fault condition; 2) Analyzing the influence of exhaust temperature, scavenging pressure and the like on power and fuel consumption rate degradation by establishing a zero-dimensional double-drive model of the marine diesel engine; 3) And predicting the output power, the burst pressure and the exhaust temperature according to different oil injection rules.
However, the prediction method is complex in modeling and low in prediction precision, and when the parameters to be explored are continuously increased, the workload and the cost are increased, so that the requirements of modern complex equipment cannot be met.
Disclosure of Invention
In order to solve the problems of complex modeling, low prediction precision, large workload and cost and the like in the existing diesel engine performance prediction process, the invention provides a diesel engine performance evaluation and prediction method, which is based on key performance parameter data of a diesel engine, a polynomial model is established by adopting a polynomial fitting method, and a specific calculation method is combined with linear fitting, so that the variation trend of the performance of the diesel engine at the future moment can be predicted, the occurrence of diesel engine faults can be effectively prevented and reduced, and the stable operation of a ship can be ensured. The invention also relates to a diesel engine performance evaluation and prediction system.
The technical scheme of the invention is as follows:
the diesel engine performance evaluation and prediction method is characterized by comprising the following steps:
a data acquisition step: acquiring a plurality of diesel engine load percentages and key performance parameter data under the corresponding load percentages, and preprocessing;
And (3) model establishment: taking the pretreated diesel engine load percentage and key performance parameter data as training set samples, and performing supervised training on the training set samples by adopting a polynomial fitting method to obtain polynomial models of all diesel engines;
And a deviation calculating step: inputting the actual values corresponding to the load percentage of the diesel engine and the key performance parameter data as data to be detected into a polynomial model to obtain a reference value corresponding to the data to be detected, and calculating deviation according to the actual values and the reference value corresponding to the actual values;
Performance evaluation and prediction steps: and performing unsupervised training on the calculated deviation serving as a data set, clustering the data set at intervals by adopting a K-means clustering algorithm to obtain a plurality of clustering centers, performing linear fitting on the clustering centers to obtain a performance parameter operation deviation trend graph of each diesel engine, evaluating and predicting the performance trend of the diesel engine according to the performance parameter operation deviation trend graph, and displaying the evaluation and prediction results.
Preferably, in the model building step, polynomial fitting is further adopted to increase the high power of each key performance parameter data, and nonlinear changes in each data are captured, so that the accuracy of the polynomial model is improved.
Preferably, in the performance evaluation and prediction step, a K-means clustering algorithm is adopted to perform one-time clustering in one hour to obtain a plurality of clustering centers;
And/or after the clustering center is linearly fitted to obtain the performance parameter operation deviation trend graph of each diesel engine, the operation state of each diesel engine in a certain period of time is monitored according to the performance parameter operation deviation trend graph, and the performance trend of each diesel engine is estimated and predicted according to the operation state.
Preferably, the key performance parameter data includes several combinations of diesel cylinder maximum burst pressure, diesel cylinder compression pressure, turbocharger inlet exhaust gas temperature, turbocharger outlet exhaust gas temperature, scavenge air pressure, turbocharger speed, fuel index, main engine speed, and diesel fuel consumption rate.
Preferably, the higher power includes a square term or a cubic term.
A diesel engine performance evaluation and prediction system is characterized by comprising a data acquisition module, a model building module, a deviation calculation module and a performance evaluation and prediction module which are connected in sequence,
The data acquisition module acquires the load percentages of the plurality of diesel engines and key performance parameter data under the corresponding load percentages, and performs pretreatment;
The model building module takes the pretreated diesel engine load percentage and key performance parameter data as a training set sample, and adopts a polynomial fitting method to carry out supervised training on the training set sample to obtain a polynomial model of each diesel engine;
The deviation calculation module is used for inputting actual values corresponding to the load percentage of the diesel engine and the key performance parameter data as data to be detected into the polynomial model, obtaining a reference value corresponding to the data to be detected, and calculating deviation according to the actual values and the reference value corresponding to the actual values;
The performance evaluation and prediction module is used for performing unsupervised training on the calculated deviation serving as a data set, clustering the data set at intervals by adopting a K-means clustering algorithm to obtain a plurality of clustering centers, performing linear fitting on the clustering centers to obtain a performance parameter operation deviation trend graph of each diesel engine, evaluating and predicting the performance trend of the diesel engine according to the performance parameter operation deviation trend graph, and displaying the evaluation and prediction result.
Preferably, in the model building module, polynomial fitting is further adopted to increase the high power of each key performance parameter data, and nonlinear changes in each data are captured, so that the accuracy of the polynomial model is improved.
Preferably, in the performance evaluation and prediction module, after the cluster center is linearly fitted to obtain a performance parameter operation deviation trend graph of each diesel engine, the operation state of each diesel engine in a certain period of time is monitored according to the performance parameter operation deviation trend graph, and the performance trend of each diesel engine is evaluated and predicted according to the operation state.
Preferably, the key performance parameter data includes several combinations of diesel cylinder maximum burst pressure, diesel cylinder compression pressure, turbocharger inlet exhaust gas temperature, turbocharger outlet exhaust gas temperature, scavenge air pressure, turbocharger speed, fuel index, main engine speed, and diesel fuel consumption rate.
Preferably, the higher power includes a square term or a cubic term.
The beneficial effects of the invention are as follows:
According to the diesel engine performance evaluation and prediction method provided by the invention, key performance parameter data under the load percentages and the corresponding load percentages of a plurality of diesel engines are firstly obtained, the load percentages and the key performance parameter data of the diesel engines are taken as training set samples, the training set samples are subjected to supervised training by adopting a polynomial fitting method to obtain polynomial models of all diesel engines, and nonlinear changes in all the data are captured by adopting polynomial fitting to increase the high power of all the key performance parameter data, namely to increase the degree of freedom of the model; inputting the data to be detected into a polynomial model to obtain a reference value corresponding to the data to be detected, and calculating deviation according to the actual value and the reference value corresponding to each key performance parameter, so that the performance of the diesel engine can be effectively measured; then taking the calculated deviation as a data set, performing unsupervised training, clustering the deviation data set at intervals by adopting a K-means clustering algorithm to obtain a plurality of clustering centers, and performing clustering at intervals can effectively reduce the value of an objective function and reduce the complexity of a time space; and finally, performing linear fitting on the clustering center to obtain the performance parameter operation deviation trend of each diesel engine, evaluating and predicting the performance trend of the diesel engine according to the performance parameter operation deviation trend, and displaying the evaluation and prediction result. The invention is based on data driving, selects a proper machine learning algorithm, combines the supervised training by adopting a polynomial fitting method and the unsupervised training by adopting a clustering algorithm, realizes the performance prediction of the diesel engine, has simple algorithm, small calculated amount, high prediction precision and low cost, can predict the variation trend of the performance of the diesel engine at the future moment, prevents and reduces the occurrence of the fault of the diesel engine, and ensures the stable operation of the ship.
The invention also relates to a diesel engine performance evaluation and prediction system, which corresponds to the diesel engine performance evaluation and prediction method, and can be understood as a system for realizing the diesel engine performance evaluation and prediction method.
Drawings
FIG. 1 is a flow chart of a diesel engine performance evaluation and prediction method of the present invention.
FIG. 2 is a preferred flow chart of the diesel engine performance evaluation and prediction method of the present invention.
Detailed Description
The present invention will be described below with reference to the accompanying drawings.
The invention relates to a diesel engine performance evaluation and prediction method, a flow chart of which is shown in figure 1, comprising the following steps in sequence:
s1, a data acquisition step or further called a data acquisition and preprocessing step: acquiring a plurality of diesel engine load percentages and key performance parameter data under the corresponding load percentages, and preprocessing; specifically, as shown in the preferred flowchart of fig. 2, key performance parameter data of a plurality of diesel engine load percentages and corresponding load percentages are obtained from a historical database, and after the data are obtained, preprocessing operation is performed to eliminate null values and unconditional data. Wherein, all data are a number of load percentages Tx and a key performance parameter Ty at the corresponding load percentage Tx; several sets of Tx and Ty in each diesel engine make up a training set Tset, and each set (Tx, ty) makes up one training data T. Preferably, the key performance parameter data includes diesel cylinder maximum burst pressure, diesel cylinder compression pressure, turbocharger inlet exhaust gas temperature, turbocharger outlet exhaust gas temperature, scavenge air pressure, turbocharger speed, fuel index, main engine speed, and fuel consumption rate. That is, the input device (diesel) performance parameter data set includes (diesel load, cylinder maximum burst pressure), (diesel load, cylinder compression pressure), (diesel load, turbocharger inlet exhaust gas temperature), (diesel load, turbocharger outlet exhaust gas temperature), (diesel load, scavenging air pressure), (diesel load, turbocharger rotational speed), (diesel load, fuel index), (diesel load, host rotational speed), (diesel load, diesel fuel consumption rate).
S2, a model building step: taking the pretreated diesel engine load percentage and key performance parameter data as training set samples, and performing supervised training on the training set samples by adopting a polynomial fitting method to obtain polynomial models of all diesel engines; that is, the step is supervised training, and the polynomial fitting method is used for training the data set obtained in the first step, preferably 80% of data are used as training samples, 20% of data are used as test samples, and polynomial fitting parameters are obtained.
Specifically, the pretreated diesel engine load percentage and key performance parameter data are used as training set samples, and a polynomial fitting method is adopted to conduct supervised training on the training set samples to obtain polynomial models corresponding to all diesel engines, wherein the polynomial fitting is adopted to increase the high power of all the key performance parameter data (such as square terms or cubic terms) and the like, which is equivalent to increasing the degree of freedom of the polynomial models, so that nonlinear changes in all the data are captured, and the accuracy of the models is improved. In addition, by comparing the training error with the curve of the nonlinear variation of the data, a suitable polynomial model is selected.
S3, calculating deviation: and inputting the actual values corresponding to the load percentage of the diesel engine and the key performance parameter data as data to be detected into a polynomial model to obtain a reference value corresponding to the data to be detected, and calculating deviation according to the actual values and the reference value corresponding to the actual values.
Specifically, the actual value corresponding to the diesel engine load percentage and each key performance parameter data (i.e. the key performance parameter corresponding to the diesel engine load to be evaluated, for example, the compression pressure corresponding to 20% of the diesel engine load) is used as the data to be detected and is input into a polynomial model, the reference value corresponding to the data to be detected at that moment is obtained, and the actual value corresponding to the actual value is subtracted from the actual value to be evaluated to obtain the deviation, wherein the deviation is the main evaluation index for measuring the performance of the diesel engine.
S4, performance evaluation and prediction steps: and performing unsupervised training on the calculated deviation serving as a data set, clustering the deviation data set at intervals by adopting a K-means clustering algorithm to obtain a plurality of clustering centers, performing linear fitting on the clustering centers to obtain a performance parameter operation deviation trend graph of each diesel engine, evaluating and predicting the performance trend of the diesel engine according to the performance parameter operation deviation trend graph, and displaying the evaluation and prediction results. The clustering is carried out at intervals, so that the value of the objective function can be effectively reduced, and the time-space complexity is reduced.
Specifically, the method comprises the steps of performing unsupervised training, taking calculated deviation as a data set, clustering the deviation data set once every other hour by adopting a K-means clustering algorithm (K is taken as 1), obtaining a plurality of clustering centers, performing linear fitting on the clustering centers to obtain performance parameter operation deviation trend graphs of all diesel engines, observing the operation states of different diesel engines in one day (the time can be adjusted according to the ship shore synchronous frequency), evaluating and predicting the performance trend of the diesel engines according to the performance parameter operation deviation trend graphs, wherein the abrasion and the like of devices and the like of the diesel engines occur with the increase of the operation time of the diesel engines, the increase of the fuel consumption rate, the increase of the fuel index and the like occur, the conditions such as the increase of the fuel consumption rate deviation trend graphs become the rising trend, the increase of the fuel consumption rate and the decrease of the performance of the diesel engines are displayed, and finally, evaluating and predicting results are displayed. That is, the running deviation trend diagrams of the performance parameters of different equipment obtained in the step can intuitively reflect the running state of the diesel engine for a certain period of time, and the performance of the diesel engine can be estimated and predicted by analyzing the trend diagrams of different equipment.
It should be noted that, the clustering of the deviation data sets by adopting the K-means clustering algorithm at intervals may be performed once every hour, or may be performed once every two hours or every other day, and specific time intervals may be reasonably selected according to actual conditions.
The invention also relates to a diesel engine performance evaluation and prediction system, which corresponds to the diesel engine performance evaluation and prediction method, and can be understood as a system for realizing the method, wherein the system comprises a data acquisition module, a model building module, a deviation calculation module and a performance evaluation and prediction module which are connected in sequence, and particularly,
The data acquisition module acquires the load percentages of the plurality of diesel engines and key performance parameter data under the corresponding load percentages, and performs pretreatment;
The model building module takes the pretreated diesel engine load percentage and key performance parameter data as a training set sample, and adopts a polynomial fitting method to carry out supervised training on the training set sample to obtain a polynomial model of each diesel engine;
The deviation calculation module is used for inputting actual values corresponding to the load percentage of the diesel engine and the key performance parameter data as data to be detected into the polynomial model, obtaining a reference value corresponding to the data to be detected, and calculating deviation according to the actual values and the reference value corresponding to the actual values;
The performance evaluation and prediction module is used for performing unsupervised training on the calculated deviation serving as a data set, clustering the data set at intervals by adopting a K-means clustering algorithm to obtain a plurality of clustering centers, performing linear fitting on the clustering centers to obtain a performance parameter operation deviation trend graph of each diesel engine, evaluating and predicting the performance trend of the diesel engine according to the performance parameter operation deviation trend graph, and displaying the evaluation and prediction result.
Preferably, in the model building module, polynomial fitting is further adopted to increase the high power of each key performance parameter data, and nonlinear changes in each data are captured, so that the accuracy of the polynomial model is improved.
Preferably, in the performance evaluation and prediction module, after the cluster center is linearly fitted to obtain a performance parameter operation deviation trend graph of each diesel engine, the operation state of each diesel engine in a certain period of time is monitored according to the performance parameter operation deviation trend graph, and the performance trend of each diesel engine is evaluated and predicted according to the operation state.
Preferably, the key performance parameters include several combinations of diesel cylinder maximum burst pressure, diesel cylinder compression pressure, turbocharger inlet exhaust gas temperature, turbocharger outlet exhaust gas temperature, scavenge air pressure, turbocharger speed, fuel index, main engine speed, and diesel fuel consumption rate.
Preferably, the higher power comprises a square term or a cubic term.
The invention provides an objective and scientific diesel engine performance evaluation and prediction method and system, which are based on key performance parameter data of a diesel engine, a polynomial model is established by adopting a polynomial fitting method, and a specific calculation method is combined with linear fitting, so that the variation trend of the performance of the diesel engine at the future moment can be predicted, the occurrence of diesel engine faults can be effectively prevented and reduced, and the stable operation of a ship can be ensured.
It should be noted that the above-described embodiments will enable those skilled in the art to more fully understand the invention, but do not limit it in any way. Therefore, although the present invention has been described in detail with reference to the drawings and examples, it will be understood by those skilled in the art that the present invention may be modified or equivalent, and in all cases, all technical solutions and modifications which do not depart from the spirit and scope of the present invention are intended to be included in the scope of the present invention.
Claims (8)
1. The diesel engine performance evaluation and prediction method is characterized by comprising the following steps:
a data acquisition step: acquiring a plurality of diesel engine load percentages and key performance parameter data under the corresponding load percentages, and preprocessing;
And (3) model establishment: taking the pretreated diesel engine load percentage and key performance parameter data as training set samples, adopting a polynomial fitting method to increase the higher power of each key performance parameter data, performing supervised training on the training set samples to obtain polynomial models of each diesel engine, increasing the degree of freedom of the polynomial models, and capturing nonlinear changes in each data;
And a deviation calculating step: inputting the actual values corresponding to the load percentage of the diesel engine and the key performance parameter data as data to be detected into a polynomial model to obtain a reference value corresponding to the data to be detected, and calculating deviation according to the actual values and the reference value corresponding to the actual values;
Performance evaluation and prediction steps: and performing unsupervised training on the calculated deviation serving as a data set, performing unsupervised training on the data set by adopting a K-means clustering algorithm at intervals to reduce the value of an objective function and reduce the complexity of a time space, combining the supervised training based on a data-driven polynomial fitting method with the unsupervised training by adopting a clustering algorithm to obtain a plurality of clustering centers, performing linear fitting on the clustering centers to obtain a performance parameter operation deviation trend graph of each diesel engine, evaluating and predicting the performance trend of the diesel engine according to the performance parameter operation deviation trend graph, and displaying the evaluation and prediction results.
2. The method for evaluating and predicting the performance of a diesel engine according to claim 1, wherein in the step of evaluating and predicting the performance, a K-means clustering algorithm is adopted to perform clustering once an hour to obtain a plurality of clustering centers;
And/or after the clustering center is linearly fitted to obtain the performance parameter operation deviation trend graph of each diesel engine, the operation state of each diesel engine in a certain period of time is monitored according to the performance parameter operation deviation trend graph, and the performance trend of each diesel engine is estimated and predicted according to the operation state.
3. The method of claim 1, wherein the key performance parameter data comprises a number of combinations of diesel cylinder maximum burst pressure, diesel cylinder compression pressure, turbocharger inlet exhaust gas temperature, turbocharger outlet exhaust gas temperature, scavenging air pressure, turbocharger speed, fuel index, host speed, and fuel consumption rate.
4. The method of claim 1, wherein the higher power comprises a square term or a cubic term.
5. A diesel engine performance evaluation and prediction system is characterized by comprising a data acquisition module, a model building module, a deviation calculation module and a performance evaluation and prediction module which are connected in sequence,
The data acquisition module acquires the load percentages of the plurality of diesel engines and key performance parameter data under the corresponding load percentages, and performs pretreatment;
The model building module takes the pretreated diesel engine load percentage and key performance parameter data as training set samples, adopts a polynomial fitting method to increase the higher order of each key performance parameter data, and then carries out supervised training on the training set samples to obtain polynomial models of each diesel engine, increases the degree of freedom of the polynomial models and captures nonlinear changes in each data;
The deviation calculation module is used for inputting actual values corresponding to the load percentage of the diesel engine and the key performance parameter data as data to be detected into the polynomial model, obtaining a reference value corresponding to the data to be detected, and calculating deviation according to the actual values and the reference value corresponding to the actual values;
the performance evaluation and prediction module is used for performing unsupervised training on the calculated deviation serving as a data set, performing unsupervised training on the data set by adopting a K-means clustering algorithm at intervals so as to reduce the value of an objective function and reduce the complexity of a time space, combining supervised training based on a data-driven polynomial fitting method with unsupervised training by adopting a clustering algorithm to obtain a plurality of clustering centers, performing linear fitting on the clustering centers to obtain a performance parameter operation deviation trend graph of each diesel engine, evaluating and predicting the performance trend of the diesel engine according to the performance parameter operation deviation trend graph, and displaying the evaluation and prediction result.
6. The system according to claim 5, wherein the performance evaluation and prediction module is configured to monitor an operation state of each diesel engine within a certain period of time according to the performance parameter operation deviation trend graph after performing linear fitting on the clustering center to obtain the performance parameter operation deviation trend graph of each diesel engine, and evaluate and predict performance trends of each diesel engine according to the operation state.
7. The diesel engine performance evaluation and prediction system according to claim 5, wherein the key performance parameter data comprises a number of combinations of diesel cylinder maximum burst pressure, diesel cylinder compression pressure, turbocharger inlet exhaust gas temperature, turbocharger outlet exhaust gas temperature, scavenging air pressure, turbocharger rotational speed, fuel index, host rotational speed, and diesel fuel consumption rate.
8. The diesel engine performance evaluation and prediction system according to claim 5 wherein the higher power comprises a square term or a cubic term.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211467398.0A CN115774847B (en) | 2022-11-22 | 2022-11-22 | Diesel engine performance evaluation and prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211467398.0A CN115774847B (en) | 2022-11-22 | 2022-11-22 | Diesel engine performance evaluation and prediction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115774847A CN115774847A (en) | 2023-03-10 |
| CN115774847B true CN115774847B (en) | 2024-07-12 |
Family
ID=85389768
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211467398.0A Active CN115774847B (en) | 2022-11-22 | 2022-11-22 | Diesel engine performance evaluation and prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115774847B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116429183B (en) * | 2023-04-24 | 2023-09-26 | 广东海洋大学 | Diesel engine performance monitoring method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113077172A (en) * | 2021-04-19 | 2021-07-06 | 瑞湖智科数据(苏州)有限公司 | Equipment state trend analysis and fault diagnosis method |
| CN114662314A (en) * | 2022-03-23 | 2022-06-24 | 安徽大学 | Working condition switching-oriented marine diesel engine thermal parameter estimation method |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11124317B2 (en) * | 2018-01-26 | 2021-09-21 | Dalian University Of Technology | Method for prediction of key performance parameters of aero-engine in transition condition |
| CN109215165B (en) * | 2018-08-08 | 2021-06-22 | 南京航空航天大学 | Performance evaluation and fault early warning method for APU (auxiliary Power Unit) of civil aircraft |
| CN111222702A (en) * | 2020-01-09 | 2020-06-02 | 中国电力科学研究院有限公司 | Method and system for predicting operation change trend of regulation and control system |
| CN113516273B (en) * | 2021-04-02 | 2024-06-04 | 中国船舶重工集团公司军品技术研究中心 | Diesel engine supercharger fault prediction method for power generation |
| CN113033011B (en) * | 2021-04-07 | 2023-06-06 | 大连海事大学 | Ship mechanical health state assessment method and system |
| CN114738132B (en) * | 2022-04-07 | 2023-06-20 | 上海船舶运输科学研究所有限公司 | Supercharger rotation speed sensor fault diagnosis method and system based on real ship data |
-
2022
- 2022-11-22 CN CN202211467398.0A patent/CN115774847B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113077172A (en) * | 2021-04-19 | 2021-07-06 | 瑞湖智科数据(苏州)有限公司 | Equipment state trend analysis and fault diagnosis method |
| CN114662314A (en) * | 2022-03-23 | 2022-06-24 | 安徽大学 | Working condition switching-oriented marine diesel engine thermal parameter estimation method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115774847A (en) | 2023-03-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109522600B (en) | Complex equipment residual service life prediction method based on combined deep neural network | |
| EP2495631B1 (en) | A system for analysis of turbo machinery | |
| CN110530650B (en) | Method for monitoring performance state of heavy-duty gas turbine based on generalized regression neural network and box diagram analysis | |
| CN112197973A (en) | Diesel generating set health diagnosis method | |
| CN115774847B (en) | Diesel engine performance evaluation and prediction method and system | |
| CN114881342A (en) | System and method for predicting residual life of ship power equipment | |
| CN115586009A (en) | Fault diagnosis and health management system and method | |
| CN111483125A (en) | Hydraulic fault early warning system for injection molding machine | |
| CN116596503A (en) | Importance-based intelligent health monitoring system and method for ship equipment | |
| CN114048629A (en) | Ship diesel engine health management and control system and management and control method | |
| KR20210079230A (en) | Method of real time fault detection and diagnosis for onboard engine room and system for forperming the same | |
| Tong et al. | Fault prediction of marine diesel engine based on time series and support vector machine | |
| Vladov et al. | Neural Network Modeling of Helicopters Turboshaft Engines at Flight Modes Using an Approach Based on" Black Box" Models. | |
| Zhang et al. | A prediction method for exhaust gas temperature of marine diesel engine based on LSTM | |
| Yu et al. | Remaining useful life prediction based on multi-scale residual convolutional network for aero-engine | |
| CN116521406A (en) | Method for detecting anomaly of non-overrun flight parameter data of aero-engine based on residual gate GRU-VAE model | |
| CN115469550A (en) | Digital twin-based aircraft engine operation maintenance method and system | |
| Wang et al. | A novel scheme for intelligent fault diagnosis of marine diesel engine using the multi-information fusion technology | |
| Tao et al. | A state and fault prediction method based on RBF neural networks | |
| Liu et al. | Fault diagnosis and prediction method for valve clearance of diesel engine based on linear regression | |
| Kozlenko et al. | Software implemented fault diagnosis of natural gas pumping unit based on feedforward neural network | |
| Sun et al. | Anomaly detection of marine diesel engine valve system based on Mahalanobis distance | |
| He et al. | Canonical correlation analysis and key performance indicator based fault detection scheme with application to marine diesel supercharging systems | |
| Kocak et al. | Condition monitoring and fault diagnosis of a marine diesel engine with machine learning techniques | |
| Tsaganos et al. | Fault detection and diagnosis of two-stroke low-speed marine engine with machine learning algorithms |
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 |