CN108288043B - Waveform identification method, device and equipment and computer readable storage medium - Google Patents
Waveform identification method, device and equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN108288043B CN108288043B CN201810088580.2A CN201810088580A CN108288043B CN 108288043 B CN108288043 B CN 108288043B CN 201810088580 A CN201810088580 A CN 201810088580A CN 108288043 B CN108288043 B CN 108288043B
- Authority
- CN
- China
- Prior art keywords
- parameter data
- operation parameter
- waveform
- judging
- characteristic
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The embodiment of the invention discloses a waveform identification method, a waveform identification device, waveform identification equipment and a computer readable storage medium, wherein the method comprises the steps of acquiring first operation parameter data of a system; identifying a disturbance time point from the first operation parameter data, and performing normalization processing on the operation parameter data after the disturbance time point to obtain second operation parameter data; grouping the second operation parameter data according to a preset grouping mode and a preset group number, and calculating second-order center distances corresponding to the second operation parameter data of each group one by one; and judging the attenuation characteristic and the vibration characteristic of the corresponding waveform according to each second-order center distance, and matching the waveform according to the attenuation characteristic and the vibration characteristic. The embodiment of the invention can realize automatic identification of the waveform of the disturbance system, and improves the identification accuracy and the identification efficiency, thereby more accurately reflecting the self-adjustment capability of the system.
Description
Technical Field
The embodiment of the invention relates to the technical field of power systems, in particular to a waveform identification method, a waveform identification device, waveform identification equipment and a computer readable storage medium.
Background
Thermal power generation is the main force of modern society power development, and power plant disturbance experiment can inspect whether the unit has the ability of adapting to load change to guarantee the safe and economic operation of electric wire netting, improve power quality and electric wire netting operation level and the fail safe nature of experimental control circuit, can also improve maintainer business quality and operation personnel's adaptability to strain.
Disturbance tests are various, such as a unit fuel regulation system disturbance test, a main steam pressure fixed value changing disturbance test, a unit air supply regulation system disturbance test and a unit coordination control system disturbance test, wherein the unit fuel regulation system disturbance test can improve the anti-interference capability of a fuel regulation system when phenomena such as self-flow and jamming of a powder feeder occur, and can properly adjust various relevant parameters (such as a proportional band, integral time and the like) according to a test result so as to improve the regulation quality; the main steam pressure fixed value disturbance test is changed, so that the adjusting capacity of the fuel adjusting system when the set value is changed can be improved, and each relevant parameter can be properly adjusted according to the test result to improve the adjusting quality; disturbance test measures of the air supply adjusting system of the unit can improve the anti-interference capability of the air supply adjusting system when the opening of the baffle is changed; the disturbance test of the unit coordination control system can improve the adjusting capability of the coordination control system when the load is changed so as to adapt to the requirement of bidding on-line.
In each disturbance experiment, the self-adjusting capability of the system can be well reflected by the variation curve of each parameter of the system along with time after disturbance, so that the identification of the parameter waveform is very critical. At present, when a power plant carries out a unit disturbance experiment, waveform identification and judgment are mainly carried out by human eyes of a tester, so that the accuracy rate and the efficiency of waveform identification are reduced.
In view of the above, how to provide a waveform identification method, apparatus, device and computer readable storage medium to solve the above technical problems becomes a problem to be solved by those skilled in the art at present.
Disclosure of Invention
Embodiments of the present invention provide a waveform identification method, apparatus, device, and computer readable storage medium, which can implement automatic identification of a disturbance system waveform, and improve identification accuracy and identification efficiency, thereby more accurately reflecting the self-adjustment capability of a system.
In order to solve the above technical problem, an embodiment of the present invention provides a waveform identification method, including:
acquiring first operating parameter data of a system;
identifying a disturbance time point from the first operation parameter data, and normalizing the operation parameter data after the disturbance time point to obtain second operation parameter data;
grouping the second operation parameter data according to a preset grouping mode and a preset group number, and calculating second-order center distances corresponding to the second operation parameter data of each group one by one;
and judging the attenuation characteristic and the vibration characteristic of the corresponding waveform according to each second-order center distance, and matching the waveform according to the attenuation characteristic and the vibration characteristic.
Optionally, after acquiring the first operating parameter data of the system, the method further includes:
preprocessing the first operating parameter data to remove a noise signal;
the process of identifying a disturbance time point from the first operating parameter data is:
a disturbance time point is identified from the preprocessed first operating parameter data.
Optionally, the process of preprocessing the first operation parameter data is as follows:
and preprocessing the first operation parameter data by adopting a filtering processing and smoothing processing method.
Optionally, the process of determining the attenuation characteristic and the vibration characteristic of the corresponding waveform according to each second-order center distance is as follows:
judging the attenuation characteristic of the corresponding waveform according to each second-order center distance, judging whether the attenuation characteristic is convergence, if so, acquiring the operation parameter data in the unstable interval from the second operation parameter data, and judging the vibration characteristic of the corresponding waveform according to the operation parameter data in the unstable interval; otherwise, judging the vibration characteristics of the corresponding waveforms according to the second operation parameter data.
Optionally, the process of determining the attenuation characteristic of the corresponding waveform according to each second-order center distance is as follows:
and judging the attenuation characteristics of the corresponding waveforms according to the empirical value comparison method, the step-by-step comparison method or the first-stage and last-stage comparison methods.
Optionally, the process of determining the vibration characteristic of the corresponding waveform according to the operation parameter data in the unstable interval is as follows:
and judging whether the ratio of the data positioned on the same side of the balance position in the operation parameter data in the unstable interval to the total number of the operation parameter data in the unstable interval is in the range of [0.2,0.8], if so, judging that the vibration characteristic of the corresponding waveform is vibration, otherwise, judging that the vibration characteristic of the corresponding waveform is non-vibration.
Optionally, the method further includes:
extracting a waveform characteristic value according to the waveform obtained by matching;
and calculating the performance index of the system according to the first operation parameter data and the waveform characteristic value.
The embodiment of the invention correspondingly provides a waveform identification device, which comprises:
the system comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is used for acquiring first operation parameter data of a system and preprocessing the first operation parameter data;
the normalization module is used for identifying a disturbance time point from the preprocessed first operation parameter data and normalizing the operation parameter data positioned after the disturbance time point to obtain second operation parameter data;
the calculation module is used for grouping the second operation parameter data according to a preset grouping mode and a preset group number and calculating second-order center distances corresponding to the second operation parameter data of each group one by one;
and the identification module is used for judging the attenuation characteristic and the vibration characteristic of the corresponding waveform according to each second-order center distance and matching the waveform according to the attenuation characteristic and the vibration characteristic.
An embodiment of the present invention provides a waveform identification device, including:
a memory for storing a computer program;
a processor for implementing the steps of the waveform identification method as described above when executing the computer program.
An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the waveform identification method as described above.
The embodiment of the invention provides a waveform identification method, a device, equipment and a computer readable storage medium, wherein a disturbance time point is identified from acquired first operation parameter data, and fluctuation is generated after a system is disturbed, so that normalization processing is performed on operation parameter data after the disturbance time point to acquire second operation parameter data, second operation parameter data are grouped, second-order center distance of each group of data is calculated, attenuation characteristics and vibration characteristics of corresponding waveforms are determined according to each second-order center distance, and the waveforms are matched according to the attenuation characteristics and the vibration characteristics, so that the waveform identification is realized. The embodiment of the invention can realize automatic identification of the waveform of the disturbance system, and compared with the prior art, the identification accuracy and the identification efficiency are both improved, thereby more accurately reflecting the self-adjusting capability of the system.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed in the prior art and the embodiments 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 is a schematic flow chart of a waveform identification method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a waveform identification apparatus according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention provide a waveform identification method, apparatus, device, and computer-readable storage medium, which can implement automatic identification of a disturbance system waveform, and improve identification accuracy and identification efficiency, thereby more accurately reflecting self-adjustment capability of a system.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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 some, but not all, embodiments of the present invention. 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.
Referring to fig. 1, fig. 1 is a flowchart illustrating a waveform identification method according to an embodiment of the present invention.
The method comprises the following steps:
s11: acquiring first operating parameter data of a system;
it should be noted that, in the embodiment of the present invention, after the system (a certain subsystem or certain subsystems) is disturbed, the first operating parameter data of the system may be acquired at preset time intervals, for example, at 10s intervals.
Further, after acquiring the first operation parameter data of the system at S11, the method further includes:
preprocessing the first operation parameter data to remove noise signals;
specifically, since the acquired first operation parameter data includes interference signals such as noise, the first operation parameter data needs to be preprocessed to remove the interference signals such as background noise.
Further, in the embodiment of the present invention, the first operation parameter data may be preprocessed by using a filtering process and a smoothing process.
It should be noted that, a filtering process is adopted to remove the noise signal, and then a smoothing process (for example, a sliding average method) is used to process the denoised first operation parameter data, so as to remove the abnormal value interference in the data, so as to further optimize the obtained data.
S12: identifying a disturbance time point from the first operation parameter data, and carrying out normalization processing on the operation parameter data after the disturbance time point to obtain second operation parameter data;
it should be noted that, after the first operation parameter data is preprocessed, the process of identifying the disturbance time point from the first operation parameter data is specifically to identify the disturbance time point from the preprocessed first operation parameter data.
Specifically, the time point of each parameter setting value being manually changed is identified from the preprocessed first operation parameter data, that is, the disturbance time point is identified, and after the disturbance time point is determined, the system performs self-adjustment from the disturbance time point, so that each operation parameter data after the disturbance time point is obtained from the preprocessed first operation parameter data, and the operation parameter data is normalized, so that each operation parameter data after the normalization is in the range of [0,1 ].
S13: grouping the second operation parameter data according to a preset grouping mode and a preset group number, and calculating second-order center distances corresponding to the second operation parameter data of each group one by one;
specifically, after the second operation parameter data is obtained, the second operation parameter data is grouped, and specifically, the second operation parameter data may be divided into a preset group number according to an equal interval grouping or incremental grouping manner, for example, the total number of the second operation parameter data is n, the preset group number is 5, and the preset grouping manner is an equal interval grouping manner, so that the number of each group of data is n/5 rounded. After grouping is completed, the second-order center distance corresponding to the specific data in each group is calculated according to the specific data in each group, so that a group of second-order center distances is obtained, wherein the second-order center distances, namely variances, can well reflect the fluctuation size of a random variable near the mean value of the random variable, and the bigger the variance is, the bigger the fluctuation is.
S14: and judging the attenuation characteristic and the vibration characteristic of the corresponding waveform according to each second-order center distance, and matching the waveform according to the attenuation characteristic and the vibration characteristic.
It should be noted that, in the present application, whether a corresponding waveform has an attenuation characteristic is determined according to each second-order center distance, and then a vibration characteristic of the waveform is determined, and then the waveform can be matched according to the attenuation characteristic and the vibration characteristic, so that the waveform identification of the disturbance system is realized.
Further, the process of determining the attenuation characteristic and the vibration characteristic of the corresponding waveform according to each second-order center distance in the step S14 may specifically be:
judging the attenuation characteristic of the corresponding waveform according to each second-order center distance, judging whether the attenuation characteristic is convergence, if so, acquiring the operation parameter data in the unstable interval from the second operation parameter data, and judging the vibration characteristic of the corresponding waveform according to the operation parameter data in the unstable interval; otherwise, judging the vibration characteristics of the corresponding waveform according to the second operation parameter data.
It should be noted that whether the corresponding waveform converges or not can be determined by each second-order center distance, if the waveform converges, the waveform tends to be stable gradually, at this time, the second operation parameter data can be cut by a first-end stage comparison method, so as to obtain an unstable region, wherein the first-end stage comparison method is that the last second-order center distance is two orders of magnitude smaller than the first second-order center distance, and the division point between the stable region and the unstable region can be determined according to the method, so as to obtain the unstable region.
In addition, the vibration characteristics are identified through the unstable interval, so that the system error can be effectively reduced, and the identification accuracy can be improved.
Specifically, the process of determining the vibration characteristic of the corresponding waveform according to the operation parameter data in the unstable interval may specifically be:
and judging whether the ratio of the data positioned on the same side of the balance position in the operation parameter data in the unstable interval to the total number of the operation parameter data in the unstable interval is in the range of [0.2,0.8], if so, judging that the vibration characteristic of the corresponding waveform is vibration, otherwise, judging that the vibration characteristic of the corresponding waveform is non-vibration.
It should be noted that, when the attenuation characteristic of the waveform is convergence, an unstable region is obtained, and for the operation parameter data in the unstable region, when 20% to 80% of the data is on the same side of the equilibrium position, curve vibration is indicated, that is, the vibration characteristic of the waveform is vibration, and the waveform can be determined to be vibration attenuation by combining the determined attenuation characteristic (convergence); if the data on the same side of the equilibrium position is less than 20% of the total data in the unstable region or greater than 80% of the total data in the unstable region, the vibration characteristic of the waveform is determined to be non-vibration, and the waveform can be determined to be non-periodic convergence by combining the determined attenuation characteristic (convergence).
Of course, when the attenuation characteristic of the waveform is non-convergence, for the operation parameter data (i.e. the second operation parameter data) in the whole region, when 20% -80% of the data are on the same side of the equilibrium position, curve vibration is illustrated, that is, the vibration characteristic of the waveform is vibration, and the waveform can be determined to be vibration divergence by combining the determined attenuation characteristic (non-convergence); if the data on the same side of the equilibrium position is less than 20% of the total number of the second operation parameter data or greater than 80% of the total number of the second operation parameter data, the vibration characteristic of the waveform is specified as non-vibration, and the waveform can be specified as non-periodic divergence in combination with the above-specified attenuation characteristic (non-convergence).
Specifically, the process of determining the attenuation characteristic of the corresponding waveform according to each second-order center distance may specifically be:
and judging the attenuation characteristics of the corresponding waveforms according to an empirical value comparison method, a step-by-step comparison method or a first-stage and last-stage comparison method.
It should be noted that the empirical value comparison method compares the obtained last second-order center distance with a preset empirical value, and determines that the waveform converges when the last second-order center distance is smaller than the preset empirical value, where the preset empirical value may be 10-4. The step-by-step comparison method is that the waveform is judged to be convergent if each second-order center distance is smaller than the previous second-order center distance. And in the first-stage and last-stage comparison method, the last second-stage center distance is two orders of magnitude smaller than the first second-stage center distance, and the waveform is judged to be converged. That is, any one of the above methods may be employed in the present application to determine the attenuation characteristics of the corresponding waveform. Of course, besides the three methods, other methods may be used to determine the attenuation characteristic of the waveform, and the purpose of the embodiment of the present invention may be achieved without any particular limitation in the present application.
Further, the method further comprises:
extracting a waveform characteristic value according to the waveform obtained by matching;
and calculating the performance index of the system according to the first operation parameter data and the waveform characteristic value.
It should be noted that, in the present application, the performance index of the system may also be automatically calculated, so as to improve the calculation accuracy and efficiency of the performance index.
Specifically, after the waveform is matched in S14, the waveform characteristic value of the waveform is extracted, and the peak and trough are determined by performing a difference method twice adjacent to each other to determine a minimum value and a maximum value, thereby determining the peak and trough value. And because filtering processing and smoothing processing can not eliminate the burr noise, so that a plurality of interference points exist in each obtained extreme value, each peak-valley value needs to be screened to remove the interference value and the abnormal value so as to obtain the accurate peak-valley value. In addition, for the curve with the increased set value, the first extreme value is a peak, otherwise, the first extreme value is a trough, the next extreme value appears behind the determined extreme value, and the next extreme value is the maximum value of the rear extreme values, so that a group of extreme values is obtained.
It should be noted that, the adjacent difference algorithm in this application refers to the dispersion of the second derivative,wherein the calculation relation of the first adjacent difference is
ynIs the value of the nth data point, yn+1Is the value of the n +1 th data point, thus obtaining a group of y'n. The second adjacent difference is a group y 'obtained by subtracting the first adjacent difference according to the calculated relational expression'nAnd performing subtraction again to obtain corresponding y ″)n. If the second difference is greater than 0, the position is concave and has a minimum value; otherwise, if the result is less than 0, it is convex and has a maximum value.
After obtaining a group of peak-to-valley values, calculating performance indexes of the system, wherein when the waveform is vibration convergence, the performance indexes comprise an attenuation rate, an overshoot, a steady-state error, an adjustment time and the like, and each performance index is calculated as follows:
attenuation rate:
wherein, y1Indicating the first extreme point, y, of the quantity to be regulated3A third extreme point representing the regulated quantity;
overshoot:
wherein, y∞Representing the stable final value of the regulated quantity after disturbance;
steady state error: e.g. of the typess＝r-y∞Wherein r represents a set value disturbance amount;
adjusting the time tsSatisfies y (t), wherein | y (t) -y∞|≤|y∞|×5％，t＞ts. That is, by substituting y (t) into the relational expression one by one, the intersection point y (t) between the stable section and the unstable section is found, and t at this time is taken as ts。
In addition, for non-periodic convergence, the performance indexes of the system comprise overshoot, steady-state error and adjustment time, and the calculation method of each performance index is the same as that of the overshoot, the steady-state error and the adjustment time in the periodic convergence.
The embodiment of the invention provides a waveform identification method, which is characterized in that a disturbance time point is identified from obtained first operation parameter data, and fluctuation is generated after a system is disturbed, so that the operation parameter data after the disturbance time point is subjected to normalization processing to obtain second operation parameter data, the second operation parameter data are grouped, the second-order center distance of each group of data is calculated, the attenuation characteristic and the vibration characteristic of a corresponding waveform are determined according to each second-order center distance, and the waveform is matched according to the attenuation characteristic and the vibration characteristic, so that the waveform identification is realized. The embodiment of the invention can realize automatic identification of the waveform of the disturbance system, and compared with the prior art, the identification accuracy and the identification efficiency are both improved, thereby more accurately reflecting the self-adjusting capability of the system.
It should be further noted that the embodiment of the present invention may also implement the calculation of the system performance index, may get rid of the dependence on manual calculation, save human resources, and improve the calculation accuracy and the working efficiency.
Correspondingly, the embodiment of the invention also discloses a waveform identification device, and particularly refers to fig. 2. On the basis of the above-described embodiment:
the device includes:
the system comprises a preprocessing module 1, a data acquisition module and a data processing module, wherein the preprocessing module is used for acquiring first operation parameter data of the system and preprocessing the first operation parameter data;
the normalization module 2 is used for identifying a disturbance time point from the preprocessed first operation parameter data and normalizing the operation parameter data after the disturbance time point to obtain second operation parameter data;
the calculation module 3 is used for grouping the second operation parameter data according to a preset grouping mode and a preset group number and calculating second-order center distances corresponding to the second operation parameter data of each group one by one;
and the identification module 4 is used for judging the attenuation characteristic and the vibration characteristic of the corresponding waveform according to each second-order center distance and matching the waveform according to the attenuation characteristic and the vibration characteristic.
It should be noted that, the waveform identification device provided in the embodiment of the present invention can automatically identify the waveform of the disturbance system during the use process, and compared with the prior art, both the identification accuracy and the identification efficiency are improved, so that the self-adjustment capability of the system is more accurately reflected.
In addition, for a specific description of the waveform identification apparatus according to the embodiment of the present invention, please refer to the above method embodiment, which is not described herein again.
On the basis of the above embodiments, an embodiment of the present invention provides a waveform identification apparatus, including:
a memory for storing a computer program;
a processor for implementing the steps of the waveform identification method as described above when executing a computer program.
It should be noted that the embodiments of the present invention have the same beneficial effects as the above method embodiments, and for the specific description of the waveform identification apparatus related to the embodiments of the present invention, reference is made to the above method embodiments, and details of the method embodiments are not repeated herein.
On the basis of the above embodiments, the present invention provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the above waveform identification method.
It should be noted that the embodiments of the present invention have the same beneficial effects as the above method embodiments, and for the specific description of the waveform identification apparatus related to the embodiments of the present invention, reference is made to the above method embodiments, and details of the method embodiments are not repeated herein.
It is further noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A method of waveform identification, comprising:
acquiring first operating parameter data of a system;
identifying a disturbance time point from the first operation parameter data, and normalizing the operation parameter data after the disturbance time point to obtain second operation parameter data;
grouping the second operation parameter data according to a preset grouping mode and a preset group number, and calculating second-order center distances corresponding to the second operation parameter data of each group one by one;
judging the attenuation characteristic and the vibration characteristic of the corresponding waveform according to each second-order center distance, and matching the waveform according to the attenuation characteristic and the vibration characteristic; wherein:
the process of determining the attenuation characteristic and the vibration characteristic of the corresponding waveform according to each second-order center distance is as follows:
judging the attenuation characteristic of the corresponding waveform according to each second-order center distance, judging whether the attenuation characteristic is convergence, if so, acquiring the operation parameter data in the unstable interval from the second operation parameter data, and judging the vibration characteristic of the corresponding waveform according to the operation parameter data in the unstable interval; otherwise, judging the vibration characteristics of the corresponding waveforms according to the second operation parameter data;
the process of judging the vibration characteristics of the corresponding waveform according to the operation parameter data in the unstable interval is as follows:
and judging whether the ratio of the data positioned on the same side of the balance position in the operation parameter data in the unstable interval to the total number of the operation parameter data in the unstable interval is in the range of [0.2,0.8], if so, judging that the vibration characteristic of the corresponding waveform is vibration, otherwise, judging that the vibration characteristic of the corresponding waveform is non-vibration.
2. The method of claim 1, wherein the obtaining the first operating parameter data of the system is followed by:
preprocessing the first operating parameter data to remove a noise signal;
the process of identifying a disturbance time point from the first operating parameter data is:
a disturbance time point is identified from the preprocessed first operating parameter data.
3. The waveform identification method of claim 2, wherein the pre-processing of the first operational parameter data comprises:
and preprocessing the first operation parameter data by adopting a filtering processing and smoothing processing method.
4. The method according to claim 1, wherein said determining the attenuation characteristic of the corresponding waveform according to each of the second-order center distances comprises:
judging the attenuation characteristics of the corresponding waveforms according to an empirical value comparison method, a step-by-step comparison method or a first-stage and last-stage comparison method; wherein:
the empirical value comparison method is to compare the obtained last second-order center distance with a preset empirical value, and when the last second-order center distance is smaller than the preset empirical value, the waveform convergence is determined; the step-by-step comparison method is characterized in that each second-order center distance is compared with the previous second-order center distance, and when each second-order center distance is smaller than the previous second-order center distance, the waveform convergence is determined; the first-and-last-stage comparison method is characterized in that the last second-order center distance is compared with the first second-order center distance, and when the last second-order center distance is two orders of magnitude smaller than the first second-order center distance, the waveform convergence is determined.
5. The waveform identification method according to any one of claims 1 to 4, characterized in that the method further comprises:
extracting a waveform characteristic value according to the waveform obtained by matching;
and calculating the performance index of the system according to the first operation parameter data and the waveform characteristic value.
6. A waveform recognition apparatus, comprising:
the system comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is used for acquiring first operation parameter data of a system and preprocessing the first operation parameter data;
the normalization module is used for identifying a disturbance time point from the preprocessed first operation parameter data and normalizing the operation parameter data positioned after the disturbance time point to obtain second operation parameter data;
the calculation module is used for grouping the second operation parameter data according to a preset grouping mode and a preset group number and calculating second-order center distances corresponding to the second operation parameter data of each group one by one;
the identification module is used for judging the attenuation characteristic and the vibration characteristic of the corresponding waveform according to each second-order center distance and matching the waveform according to the attenuation characteristic and the vibration characteristic; wherein:
the process of determining the attenuation characteristic and the vibration characteristic of the corresponding waveform according to each second-order center distance is as follows:
judging the attenuation characteristic of the corresponding waveform according to each second-order center distance, judging whether the attenuation characteristic is convergence, if so, acquiring the operation parameter data in the unstable interval from the second operation parameter data, and judging the vibration characteristic of the corresponding waveform according to the operation parameter data in the unstable interval; otherwise, judging the vibration characteristics of the corresponding waveforms according to the second operation parameter data;
the process of judging the vibration characteristics of the corresponding waveform according to the operation parameter data in the unstable interval is as follows:
and judging whether the ratio of the data positioned on the same side of the balance position in the operation parameter data in the unstable interval to the total number of the operation parameter data in the unstable interval is in the range of [0.2,0.8], if so, judging that the vibration characteristic of the corresponding waveform is vibration, otherwise, judging that the vibration characteristic of the corresponding waveform is non-vibration.
7. A waveform identification device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the waveform identification method according to any one of claims 1 to 5 when executing the computer program.
8. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the waveform recognition method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810088580.2A CN108288043B (en) | 2018-01-30 | 2018-01-30 | Waveform identification method, device and equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810088580.2A CN108288043B (en) | 2018-01-30 | 2018-01-30 | Waveform identification method, device and equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108288043A CN108288043A (en) | 2018-07-17 |
| CN108288043B true CN108288043B (en) | 2021-11-26 |
Family
ID=62836104
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810088580.2A Active CN108288043B (en) | 2018-01-30 | 2018-01-30 | Waveform identification method, device and equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108288043B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5613015A (en) * | 1992-11-12 | 1997-03-18 | Fuji Xerox Co., Ltd. | Image signal analyzing system and coding system |
| CN103064063A (en) * | 2011-10-21 | 2013-04-24 | 中国人民解放军海军航空工程学院 | Poly-phase code radar signal waveform automatic identification method based on continuous wave Doppler (CWD) feature |
| CN103517000A (en) * | 2012-06-29 | 2014-01-15 | 京瓷办公信息***株式会社 | Image forming apparatus |
| CN103795144A (en) * | 2013-11-22 | 2014-05-14 | 深圳供电局有限公司 | Method for identifying disturbance occurrence time of power system based on fault recording data |
| CN106441843A (en) * | 2016-09-19 | 2017-02-22 | 南京科远自动化集团股份有限公司 | Rotating machinery fault waveform recognition method |
-
2018
- 2018-01-30 CN CN201810088580.2A patent/CN108288043B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5613015A (en) * | 1992-11-12 | 1997-03-18 | Fuji Xerox Co., Ltd. | Image signal analyzing system and coding system |
| CN103064063A (en) * | 2011-10-21 | 2013-04-24 | 中国人民解放军海军航空工程学院 | Poly-phase code radar signal waveform automatic identification method based on continuous wave Doppler (CWD) feature |
| CN103517000A (en) * | 2012-06-29 | 2014-01-15 | 京瓷办公信息***株式会社 | Image forming apparatus |
| CN103795144A (en) * | 2013-11-22 | 2014-05-14 | 深圳供电局有限公司 | Method for identifying disturbance occurrence time of power system based on fault recording data |
| CN106441843A (en) * | 2016-09-19 | 2017-02-22 | 南京科远自动化集团股份有限公司 | Rotating machinery fault waveform recognition method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108288043A (en) | 2018-07-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109213654B (en) | Anomaly detection method and device | |
| CN111199018B (en) | Abnormal data detection method and device, storage medium and electronic equipment | |
| WO2022111265A1 (en) | Information alerting method and device, and storage medium | |
| US10331810B2 (en) | Method for determining a model of an output quantity of a technical system | |
| CN111953299B (en) | Fault detection method, device and system of photovoltaic module | |
| CN112629585A (en) | Equipment on-line monitoring method and device based on multi-dimensional parameter estimation | |
| CN110702986B (en) | Method and system for dynamically generating self-adaptive signal search threshold in real time | |
| CN107276779B (en) | Monitoring method, system and equipment | |
| CN116994416B (en) | Fan operation fault early warning method and system based on artificial intelligence | |
| CN113868953B (en) | Multi-unit operation optimization method, device and system in industrial system and storage medium | |
| CN115685949A (en) | Method and device for adjusting data sampling frequency in discrete machining production process | |
| CN113626767A (en) | Fan power limit identification method, system, equipment and storage medium | |
| CN108288043B (en) | Waveform identification method, device and equipment and computer readable storage medium | |
| CN117029968A (en) | Traffic data diagnosis method, system, storage medium and electronic equipment | |
| CN117591964B (en) | Electric power intelligent analysis method based on artificial intelligence | |
| CN114812796A (en) | Equipment condition evaluation method and related equipment | |
| CN117666406A (en) | Multi-parameter synchronous dynamic signal acquisition method and system based on edge calculation | |
| CN113255927A (en) | Logistic regression model training method and device, computer equipment and storage medium | |
| CN117061271A (en) | Bus communication automatic regulating method for fire-fighting product | |
| CN115051384B (en) | Frequency modulation performance evaluation method, device, equipment and medium | |
| CN115041544A (en) | Method and device for detecting abnormality of stamping part and storage medium | |
| CN113552444A (en) | Online setting method and device for leakage current characteristic threshold | |
| CN115454804A (en) | Detection method and device for structured query language and electronic equipment | |
| CN113052938A (en) | Method and device for constructing boiler energy efficiency curve | |
| CN113326252B (en) | Database parameter adjusting method and device and electronic equipment |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200509 Address after: No. 10, Huanghe East Road, Zhengdong New District, Zhengzhou City, Henan Province Applicant after: State Power Investment Group Henan Electric Power Co., Ltd Applicant after: TECHNOLOGY INFORMATION CENTER OF STATE POWER INVESTMENT CORPORATION HENAN POWER Co.,Ltd. Address before: 450001 gas power plant, No. 100 Indus street, hi tech Development Zone, Henan, Zhengzhou Applicant before: TECHNOLOGY INFORMATION CENTER OF STATE POWER INVESTMENT CORPORATION HENAN POWER Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |