CN115167365A - Board card fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation - Google Patents
Board card fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation Download PDFInfo
- Publication number
- CN115167365A CN115167365A CN202210906196.5A CN202210906196A CN115167365A CN 115167365 A CN115167365 A CN 115167365A CN 202210906196 A CN202210906196 A CN 202210906196A CN 115167365 A CN115167365 A CN 115167365A
- Authority
- CN
- China
- Prior art keywords
- energy spectrum
- wavelet energy
- spectrum entropy
- board card
- analog
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0208—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the configuration of the monitoring system
- G05B23/0213—Modular or universal configuration of the monitoring system, e.g. monitoring system having modules that may be combined to build monitoring program; monitoring system that can be applied to legacy systems; adaptable monitoring system; using different communication protocols
Abstract
The invention provides a board card fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation, and relates to the technical field of electronic controller fault diagnosis. The method comprises the following steps: acquiring an original sensor process signal from a gas turbine controller system, and performing data processing to form an original data set; inputting the original data set into a sensor wavelet energy spectrum entropy calculation model to obtain a sensor wavelet energy spectrum entropy value; selecting wavelet energy spectrum entropy values of all sensors associated with the IO board card, and inputting the wavelet energy spectrum entropy values into an IO board card wavelet energy spectrum entropy calculation model to obtain the wavelet energy spectrum entropy values of the IO board card; and calculating the difference value between the wavelet energy spectrum entropy value of the IO board card and the boundary of a preset normal range, and judging whether the IO board card has a fault. According to the method, the fault state of the IO board card is rapidly diagnosed in an engineering mode, an engineering applicable means is provided for timely identifying the IO board card fault, and an important support is provided for loop fault diagnosis of the gas turbine control system.
Description
Technical Field
The invention relates to the technical field of fault diagnosis of electronic controllers, in particular to a board card fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation.
Background
The gas turbine control system is a complex nonlinear dynamic system formed by a large number of parts according to a certain mode, function and requirement. An electronic controller (DCS system) in a gas turbine control system is the core and key of the whole gas turbine control system. How to effectively diagnose faults of an electronic controller of a fuel control system is a difficult problem in the industry. The conventional fault diagnosis method of the electronic controller based on the BIT technology needs to add a large number of redundant diagnosis circuits in the electronic components, which increases the system cost on one hand and also increases new fault points on the other hand. Different manufacturers of gas turbine control systems have a plurality of professional system diagnosis functions built in their respective DCS systems, and these functions must be checked in engineer operation stations with corresponding authorities, and the information acquisition process is passive, requiring operators to find various alarm information at different positions, and then combining various paper data of paper edition, even needing to actually check the hardware indication state in the DCS cabinet, to judge the fault point of the system. Further determination of the cause of the failure is more of the individual abilities and experience of the engineer. The rapid judgment of the system fault of the gas turbine power plant is severely restricted, and as a result, the unplanned shutdown caused by false alarm of an electronic controller system frequently occurs, and great economic loss is caused to the power plant.
At present, when industrial equipment of a factory is maintained, a mode of 'prevention is mainly adopted, planned maintenance is mainly adopted, and temporary repair is auxiliary' is adopted. Specifically, a factory sets a period of three to five years according to the new and old conditions of industrial equipment, and performs one-time overhaul on all the industrial equipment in the factory, namely, the operation of shutdown, disassembly, maintenance and reinstallation on all the industrial equipment is performed on all the industrial equipment, and whether certain industrial equipment needs to be maintained is not particularly considered, the one-time overhaul period is more than two months, hundreds of professional maintenance personnel are needed, and the total number of all kinds of constructors is nearly thousands of people. During two major repairs, minor repairs are carried out on industrial equipment every two years, namely, the disassembly, maintenance and reinstallation are carried out on auxiliary working equipment in a factory, such as a steam turbine generator unit in a power plant and most of industrial equipment except for other large core equipment, wherein the period is generally dozens of days to two months. Meanwhile, when the factory carries out planned maintenance, the temporary repair is assisted, namely the temporary repair is carried out on the industrial equipment which fails and cannot operate.
In the combustion engine power generation industry, this routine maintenance mode of operation is not suitable for electronic controller systems, represented by DCS. The DCS system is composed of high-precision and high-density electronic components/chips, the working principle and failure mechanism of various components are completely different, the failure mode is often 'sudden', and the problem of fault detection cannot be effectively solved at all only by means of daily checking means and testing means. In the daily operation process of the gas turbine, the temperature of the combustion chamber is the most important control monitoring parameter, and the stability and consistency of the group of parameters (the 9F unit is 31 measuring points which are arranged in a circumferential mode) are directly related to whether the unit can continue to operate or not; once the measured value distortion caused by the analog IO board card fault occurs, the machine may need to be stopped immediately, and the result is very serious.
The problem in the industry is always to study a data-driven fault diagnosis method for an IO board card of an electronic controller, and how to conveniently and quickly judge the IO board card fault of the electronic controller and find a fault diagnosis method which can be realized by engineering.
Disclosure of Invention
The invention aims to provide a board fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation aiming at the defects of the prior art, so as to solve the problem of engineering fault diagnosis of an analog IO board of an electronic controller in a gas turbine control system.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
the invention provides a board fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation, which is used for carrying out fault diagnosis on an IO board on analog quantity of a gas turbine electronic controller, and comprises the following steps:
acquiring original sensor process signals from a gas turbine electronic controller system, and performing data preprocessing to form an original signal data set, wherein the sensor process signals comprise temperature process signals, pressure process signals and flow process signals;
inputting signals in the original signal data set into a sensor wavelet energy spectrum entropy calculation model to obtain signal wavelet energy spectrum entropy values of each sensor;
selecting signal wavelet energy spectrum entropy values of all sensors associated with the analog quantity IO board card, and inputting the selected signal wavelet energy spectrum entropy values into an analog quantity IO board card wavelet energy spectrum entropy calculation model to obtain wavelet energy spectrum entropy values of the analog quantity IO board card;
and calculating the difference value between the wavelet energy spectrum entropy value of the analog IO board card and the preset boundary line of the normal interval range of the wavelet energy spectrum entropy value, and judging whether the analog IO board card has a fault according to the difference value, thereby realizing fault diagnosis of the analog IO board card.
Optionally, raw temperature process signals for the respective temperature sensors are obtained from the gas turbine electronic controller system in OPC UA industrial protocols.
Optionally, real-time temperature process signals of all temperature sensors associated with the thermocouple IO board card are acquired from the gas turbine electronic controller DCS system through an OPC UA industrial protocol interface from the gas turbine electronic controller system, and the data preprocessing includes an operation of removing redundant samples, an operation of removing abnormal samples, and a data normalization operation.
Optionally, the sensor wavelet energy spectrum entropy calculation model is as follows:
projecting any signal x (t) to wavelet space of different scales to obtain detail signals under different scales:
in the above formula, C j (k) And d j (k) Respectively a low-frequency component coefficient and a high-frequency component coefficient;
assuming that the length of the time series is N, the result of each wavelet transform of the signal x (t) at the time of the j-th layer k is expressed as:
D＝{D j (k)},k＝1,…,N,j＝1,…,J
E jk ＝|D j (k)| 2 the j decomposition scale is the corresponding wavelet energy spectrumEntropy of wavelet energy spectrum of (E) j ＝∑ j |D j (k)| 2 Time interval T, and then power P j ，
According to the energy distribution condition of the wavelet transform coefficient in different scales, calculating the wavelet energy spectrum entropy value W of the sensor signal in different scales EE Comprises the following steps:
W EE ＝-∑ j P j log 2 P j 。
optionally, the analog IO board wavelet energy spectrum entropy calculation model is as follows:
wherein, W IO-card For the wavelet energy spectrum entropy value of the analog quantity IO board card,
is the wavelet energy spectrum entropy value, k, of the sensor corresponding to the ith channel of the analog IO board card i Is the weighted weight of the ith channel, and m is the total number of sensors associated with the analog IO board card.
Optionally, whether the analog IO board card fails is determined according to the following formula:
F IOcard =1, if W IO-card >W highlimit
Wherein, F IOcard Identification bits for fault judgment of analog IO boards, at F IOcard If =1, judging that the analog IO board card has a fault;
W high limit for the preset highest limit of the normal range of the wavelet energy spectrum entropy value, the difference value between the wavelet energy spectrum entropy value of the analog IO board card and the preset boundary line of the normal range of the wavelet energy spectrum entropy value is larger than zero, namely W IO-card >W high limit In the case of (A), F IOcard ＝1。
The beneficial effects of the invention include:
the invention provides a board card fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation, which comprises the following steps: acquiring original sensor process signals from a gas turbine electronic controller system, and performing data preprocessing to form an original signal data set, wherein the sensor process signals comprise temperature process signals, pressure process signals and flow process signals; inputting signals in the original signal data set into a sensor wavelet energy spectrum entropy calculation model to obtain signal wavelet energy spectrum entropy values of each sensor; selecting signal wavelet energy spectrum entropy values of all sensors associated with the analog IO board card, and inputting the selected signal wavelet energy spectrum entropy values into an analog IO board card wavelet energy spectrum entropy calculation model to obtain the wavelet energy spectrum entropy values of the analog IO board card; and calculating the difference value between the wavelet energy spectrum entropy value of the analog IO board card and the boundary line of the preset normal interval range of the wavelet energy spectrum entropy value, and judging whether the analog IO board card has a fault according to the difference value, thereby realizing fault diagnosis of the analog IO board card. The method can be used for rapidly diagnosing the fault state of the analog IO board card in an engineering mode, provides an engineering applicable means for identifying the fault of the analog IO board card of the electronic controller in time, and provides an important support for fault diagnosis of the control system loop of the gas turbine.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed for the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 shows a schematic flowchart of a board fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation according to an embodiment of the present invention;
fig. 2 is a schematic diagram illustrating an actual operation flow of the board fault diagnosis method based on the wavelet energy spectrum entropy calculation of the sensor signal according to the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be 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 given herein without making any creative effort, shall fall within the protection scope of the present invention.
The electronic controller in the gas turbine control system is a complex system formed by highly integrated electronic components, and the BIT-based fault diagnosis method is high in implementation cost, and a newly-added fault diagnosis loop increases the complexity of the system on one hand and additionally increases the fault probability of the system on the other hand. Data-based fault diagnosis methods are a recent research hotspot. However, the data-based fault diagnosis method requires a large number of high-quality fault samples for algorithm training and verification. The inability to generate enough fault samples at the industrial site (which is easily understood to mean that if the fault samples at the industrial site are abundant, the process is not mature and wide industrial application is impossible), results in that data-based fault diagnosis methods often perform well only in a laboratory environment and cannot be really used at the industrial site.
In order to solve the problems, the invention provides a convenient and feasible analog IO board card fault diagnosis method.
Fig. 1 is a schematic flowchart illustrating a board fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation according to an embodiment of the present invention, and as shown in fig. 1, the board fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation according to the present invention is used for performing fault diagnosis on an IO board of an analog quantity of a gas turbine electronic controller, and the method includes:
The sensor process signals include temperature process signals, pressure process signals, and flow process signals. The raw sensor process signals are obtained, for example, from a 9F unit gas turbine electronic controller system using natural gas fuel.
And 102, inputting signals in the original signal data set into a sensor wavelet energy spectrum entropy calculation model to obtain signal wavelet energy spectrum entropy values of each sensor.
103, selecting signal wavelet energy spectrum entropy values of all sensors associated with the analog quantity IO board card, and inputting the selected signal wavelet energy spectrum entropy values into an analog quantity IO board card wavelet energy spectrum entropy calculation model to obtain the wavelet energy spectrum entropy values of the analog quantity IO board card.
And step 104, calculating a difference value between the wavelet energy spectrum entropy value of the analog IO board card and a preset boundary line of a normal interval range of the wavelet energy spectrum entropy value, and judging whether the analog IO board card has a fault according to the difference value, so that fault diagnosis of the analog IO board card is realized.
Based on the fact that an IO board card of analog quantity of an electronic controller fails, the state of a sensor signal acquired by the board card is abnormal, and the first reaction that the IO board card fails is the abnormal sensor signal. The method can be used for rapidly diagnosing the fault state of the analog IO board card in an engineering mode, provides an engineering applicable means for identifying the analog IO board card fault of the electronic controller in time, and provides an important support for the fault diagnosis of the control system loop of the gas turbine.
Optionally, the raw temperature process signals of the respective temperature sensors are obtained from an OPC Server data source connected to the gas turbine electronic controller system in OPC UA industrial protocol from the gas turbine electronic controller system.
Optionally, real-time temperature process signals of all temperature sensors associated with the thermocouple IO board card are obtained from the gas turbine electronic controller DCS system through an OPC UA industrial protocol interface from the gas turbine electronic controller system, and the data preprocessing includes a redundant sample elimination operation, an abnormal sample removal operation, and a data normalization operation, and converts the data into a gaussian distribution form with 0 mean value and 1 variance.
Optionally, the sensor wavelet energy spectrum entropy calculation model is as follows:
projecting any signal x (t) to wavelet space of different scales to obtain detail signals under different scales:
in the above formula, C j (k) And d j (k) Respectively a low-frequency component coefficient and a high-frequency component coefficient;
assuming that the time series length is N, the result of each wavelet transform of the signal x (t) at the j-th layer k time is represented as:
D＝{D j (k)},k＝1,…,N,j＝1,…,J
E jk ＝|D j (k)| 2 for the corresponding wavelet energy spectrum, the entropy of the wavelet energy spectrum on the j decomposition scale is E j ＝∑ j |D j (k)| 2 Time interval T, and then power P j ，
According to the energy distribution condition of the wavelet transform coefficient in different scales, calculating the wavelet energy spectrum entropy value W of the sensor signal in different scales EE Comprises the following steps:
W EE ＝-∑ j P j log 2 P j 。
optionally, the analog IO board wavelet energy spectrum entropy calculation model is as follows:
wherein, W IO-card For the wavelet energy spectrum entropy value of the analog quantity IO board card,
is the wavelet energy spectrum entropy value k of the sensor corresponding to the ith channel of the analog IO board card i Is the addition of the ith channelAnd the weight m is the total number of the sensors associated with the analog IO board card.
Optionally, whether the analog IO board card fails is determined according to the following formula:
F IOcard =1, if W IO-card >W highlimit
Wherein, F IOcard Identification bits for fault judgment of analog IO boards, at F IOcard When the analog quantity IO board card is out of order 1, judging that the analog quantity IO board card fails;
W high limit for the preset maximum limit of the normal range of the wavelet energy spectrum entropy value, the difference value between the wavelet energy spectrum entropy value of the analog quantity IO board card and the preset boundary line of the normal range of the wavelet energy spectrum entropy value is larger than zero, namely W IO-card >W high limit In the case of (A), F IOcard ＝1。
Fig. 2 shows an actual operation flow diagram of the board card fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation provided by the embodiment of the present invention. The specific fault diagnosis process of the analog quantity IO board of the actual gas turbine control system is shown in fig. 2.
After an analog quantity IO board card based on an electronic controller breaks down, the state of a sensor signal acquired by the board card is abnormal, such as sudden numerical value jump (step fault), restoration to normal (pulse fault) after the sudden numerical value jump, continuous numerical value increase or decrease (time change/temperature drift fault), periodic interference in the numerical value (often because a strong electric induction signal is mixed in the board card), or signal stability deterioration (white noise interference, often because of poor contact or abnormal grounding). The first reaction of the IO board card failure is that the sensor signals are abnormal, when the data collected by the sensor is abnormally changed, the wavelet energy spectrum entropy of the sensor is correspondingly abnormally changed, so that the wavelet energy spectrum entropy of the IO board card is abnormally jumped, and when the wavelet energy spectrum entropy of the board card exceeds the normal interval range, the board card failure can be judged. The method can be used for rapidly diagnosing the fault state of the analog IO board card in an engineering mode, provides an engineering applicable means for identifying the fault of the analog IO board card of the electronic controller in time, and provides an important support for fault diagnosis of the control system loop of the gas turbine.
The above embodiments are merely illustrative of the technical concept and features of the present invention, and the purpose thereof is to enable those skilled in the art to understand the content of the present invention and implement the present invention, and not to limit the scope of the present invention, and all equivalent changes or modifications made according to the spirit of the present invention should be covered in the scope of the present invention.
Claims (6)
1. A board fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation is used for carrying out fault diagnosis on an IO board on an analog quantity of a gas turbine electronic controller, and comprises the following steps:
acquiring original sensor process signals from a gas turbine electronic controller system, and performing data preprocessing to form an original signal data set, wherein the sensor process signals comprise temperature process signals, pressure process signals and flow process signals;
inputting the signals in the original signal data set into a sensor wavelet energy spectrum entropy calculation model to obtain signal wavelet energy spectrum entropy values of each sensor;
selecting signal wavelet energy spectrum entropy values of all sensors associated with the analog quantity IO board card, and inputting the selected signal wavelet energy spectrum entropy values into an analog quantity IO board card wavelet energy spectrum entropy calculation model to obtain the wavelet energy spectrum entropy values of the analog quantity IO board card;
and calculating a difference value between the wavelet energy spectrum entropy value of the analog IO board card and a preset boundary line of a normal interval range of the wavelet energy spectrum entropy value, and judging whether the analog IO board card has a fault according to the difference value, thereby realizing fault diagnosis of the analog IO board card.
2. The board fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation of claim 1, wherein raw temperature process signals of each temperature sensor are obtained from the gas turbine electronic controller system by OPC UA industrial protocol.
3. The board fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation of claim 2, wherein real-time temperature process signals of all temperature sensors associated with a thermocouple IO board are obtained from a gas turbine electronic controller DCS system through an OPC UA industrial protocol interface from the gas turbine electronic controller system, and the data preprocessing includes a redundant sample elimination operation, an abnormal sample removal operation, and a data normalization operation.
4. The board card fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation of claim 1, wherein a sensor wavelet energy spectrum entropy calculation model is as follows:
projecting any signal x (t) to wavelet space of different scales to obtain detail signals under different scales:
in the above formula, C j (k) And d j (k) Respectively a low-frequency component coefficient and a high-frequency component coefficient;
assuming that the length of the time series is N, the result of each wavelet transform of the signal x (t) at the time of the j-th layer k is expressed as:
D＝{D j (k)},k＝1,…,N,j＝1,…,J
E jk ＝|D j (k)| 2 for the corresponding wavelet energy spectrum, the entropy of the wavelet energy spectrum on the j decomposition scale is E j ＝∑ j |D j (k)| 2 Time interval T, and then power P j ，
According to the energy distribution condition of the wavelet transform coefficient in different scales, calculating the wavelet energy spectrum entropy value W of the sensor signal in different scales EE Comprises the following steps:
W EE ＝-∑ j P j log 2 P j 。
5. the board card fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation of claim 4 is characterized in that an analog IO board card wavelet energy spectrum entropy calculation model is as follows:
wherein, W IO-card Is the wavelet energy spectrum entropy value of the analog IO board card,
is the wavelet energy spectrum entropy value k of the sensor corresponding to the ith channel of the analog IO board card i Is the weighted weight of the ith channel, and m is the total number of sensors associated with the analog IO board.
6. The board card fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation according to claim 5,
judging whether the analog IO board card fails according to the following formula:
F IOcard =1, if W IO-card >W high limit
Wherein, F IOcard Identification bits for fault judgment of analog IO boards, at F IOcard If =1, judging that the analog IO board card has a fault;
W high limit for the preset maximum limit of the normal range of the wavelet energy spectrum entropy value, the difference value between the wavelet energy spectrum entropy value of the analog quantity IO board card and the preset boundary line of the normal range of the wavelet energy spectrum entropy value is larger than zero, namely W IO-card >W high limit In the case of (2), F IOcard ＝1。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210906196.5A CN115167365A (en) | 2022-07-29 | 2022-07-29 | Board card fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210906196.5A CN115167365A (en) | 2022-07-29 | 2022-07-29 | Board card fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115167365A true CN115167365A (en) | 2022-10-11 |
Family
ID=83477743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210906196.5A Pending CN115167365A (en) | 2022-07-29 | 2022-07-29 | Board card fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115167365A (en) |
-
2022
- 2022-07-29 CN CN202210906196.5A patent/CN115167365A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5625574A (en) | Method and data processing system for monitoring operating states of a technical plant | |
| EP1982301B1 (en) | Method of condition monitoring | |
| CN104390657B (en) | A kind of Generator Unit Operating Parameters measurement sensor fault diagnosis method and system | |
| WO2005071620A2 (en) | Method and apparatus to diagnose mechanical problems in machinery | |
| CN112487910A (en) | Fault early warning method and system for nuclear turbine system | |
| KR20170038348A (en) | Fault diagnosis system and fault diagnosis method in dynamic equipment | |
| CN107291991B (en) | Early defect early warning method for wind turbine generator based on dynamic network sign | |
| CN108154166A (en) | A kind of fan intelligent fault diagnosis system and method | |
| CN113742932A (en) | Method for predicting and diagnosing faults of gearbox of wind turbine generator | |
| CN115167366A (en) | Board card fault diagnosis method based on weighted square sum of sensor signal residual sequence | |
| CN114971351A (en) | Equipment multi-index health condition assessment method based on entropy method | |
| CN114519382A (en) | Nuclear power plant key operation parameter extraction and abnormity monitoring method | |
| CN113064017A (en) | State maintenance system and state detection method for power generation equipment | |
| CN114577470A (en) | Fault diagnosis method and system for fan main bearing | |
| CN115167365A (en) | Board card fault diagnosis method based on sensor signal wavelet energy spectrum entropy calculation | |
| Cao et al. | Remaining useful life prediction of wind turbine generator bearing based on EMD with an indicator | |
| CN110794683A (en) | Wind power gear box state evaluation method based on deep neural network and kurtosis characteristics | |
| WO2023273378A1 (en) | Bolt fault diagnosis method and apparatus | |
| CN117908520A (en) | Board card fault diagnosis method based on sensor signal autoregressive moving average model | |
| Tutiv'en et al. | Wind turbine main bearing condition monitoring via convolutional autoencoder neural networks | |
| Fumagalli et al. | Agile diagnostic tool based on electrical signature analysis | |
| CN115167181A (en) | Sensor signal processing method for fault simulation of gas turbine electronic controller board card | |
| CN114687930A (en) | Wind turbine generator fault early warning closed-loop management and control system and method | |
| CN117687390A (en) | Thermocouple bus network fault diagnosis method for electronic controller of gas turbine | |
| CN114442543A (en) | Computer monitoring method suitable for early warning of hydropower station fault |
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 |