CN115099312A - Method, device and storage medium for diagnosing health state of ultrasonic flowmeter - Google Patents
Method, device and storage medium for diagnosing health state of ultrasonic flowmeter Download PDFInfo
- Publication number
- CN115099312A CN115099312A CN202210638407.1A CN202210638407A CN115099312A CN 115099312 A CN115099312 A CN 115099312A CN 202210638407 A CN202210638407 A CN 202210638407A CN 115099312 A CN115099312 A CN 115099312A
- Authority
- CN
- China
- Prior art keywords
- health state
- data set
- health
- basic data
- state parameter
- 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
Abstract
The application discloses a method, a device and a storage medium for diagnosing the health state of an ultrasonic flowmeter. The health state parameters of the ultrasonic flowmeter are obtained; determining a characteristic index set of the health state parameters according to the health state parameters; determining a basic data set according to the characteristic index set; and determining whether an abnormal working condition exists according to the basic data set. This application can satisfy the demand of carrying out all-round monitoring to ultrasonic flowmeter health status through the health status parameter of analysis ultrasonic flowmeter to and evaluate ultrasonic flowmeter health status from a plurality of aspects.
Description
Technical Field
The present application relates to the field of ultrasound flow technologies, and in particular, to a method, an apparatus, and a storage medium for diagnosing a health status of an ultrasound flow meter.
Background
Ultrasonic flow meters, due to their operating mechanism, have high demands on the operating health of the various components. In the process of calculating the acoustic path or acoustic delay, the extremely small calculation deviation can cause serious error problems of flow calculation, and the use of the ultrasonic flowmeter is seriously influenced. Therefore, the realization of complete, comprehensive and reliable diagnosis of the health state of the ultrasonic flowmeter is the key for ensuring the normal work of the ultrasonic flowmeter.
At present, the common method at home and abroad is as follows: and setting fixed sampling time and acquiring an actually measured target time sequence. When the target time sequence is characterized by air speed, sound velocity and the like, calculating the deviation of the indexes and theoretical values, and taking the maximum value or the average value of the calculation result; and when the target time sequence is characterized by a vortex angle, an asymmetric coefficient and the like without theoretical values, calculating the average value or the maximum value of the target time sequence. The calculation results are further compared with an artificially set threshold value, and when the calculation values of the evaluation indexes exceed the threshold value, the abnormal working condition is determined.
In summary, the above method for evaluating the health status of the ultrasonic flowmeter has a problem that one or a few indexes are used for one side. In addition, the threshold of the detection parameter of the ultrasonic flowmeter is set manually, and is influenced by subjective factors, so that errors are easily caused.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method, an apparatus, and a storage medium for diagnosing a health state of an ultrasonic flowmeter, so as to solve the problem in the prior art that the health state of the ultrasonic flowmeter is evaluated according to one or a few indexes one-sidedly.
To achieve the above object, a first aspect of the embodiments of the present application provides a method for diagnosing a health state of an ultrasonic flowmeter, the method including:
acquiring health state parameters of the ultrasonic flowmeter;
determining a characteristic index set of the health state parameters according to the health state parameters;
determining a basic data set according to the characteristic index set;
and determining whether an abnormal working condition exists according to the basic data set.
In embodiments of the present application, the health state parameter may comprise at least one of:
sampling rate, signal gain, signal-to-noise ratio, swirl angle, measured air velocity per channel, and measured flow velocity per channel.
In an embodiment of the present application, the feature index set may include:
distortion degree index, distribution characteristic index, complexity degree index and periodicity index.
In an embodiment of the present application, the distribution characteristic index includes kurtosis and skewness, and the kurtosis satisfies formula (1):
wherein S is 2 Is kurtosis, x i The value of the ith measuring point in the health state parameter time sequence,
the mean value of the values of all the measuring points in the health state parameter time sequence is shown, std is standard normal distribution, and n is the total number of the measuring points;
the skewness satisfies formula (2):
wherein S is 3 The degree of deviation is the degree of deviation,
the mean value of the values of all the measured points in the health state parameter time series, std is a standard normal distribution.
In an embodiment of the present application, the complexity index includes a complexity and a spectral statistical variance, and the complexity satisfies formula (3):
wherein S is 4 For complexity, n is the total number of points, x i The value of the ith measuring point in the health state parameter time sequence, x i-1 The value of the (i-1) th measuring point in the health state parameter time sequence is obtained;
the spectral statistical variance satisfies formula (4):
wherein S is 5 Is the spectral statistical variance, n is the total number of the measuring points, k is the frequency of the sub-signal in the time sequence of the health state parameter, X (k) is the amplitude corresponding to the frequency k after Fourier transformation,
is the mean value of the amplitude of the time series of health state parameters after fourier transformation of the frequency.
In an embodiment of the present application, the periodicity index satisfies formula (5):
wherein S is 6 Is an autoregressive coefficient, n is the total number of measured points, t is a lag coefficient, std is a standard normal distribution, x i The value of the ith measuring point in the health state parameter time sequence,
is the mean value, x, of the values of all the measured points in the health state parameter time series i+t The value of the i + t measuring point in the health state parameter time sequence.
In an embodiment of the present application, determining whether an abnormal operating condition exists according to the basic data set includes:
acquiring a basic data set;
clustering the basic data set according to a K-means clustering algorithm to determine a clustering result;
and determining abnormal working conditions according to the clustering result.
In an embodiment of the present application, clustering the basic data set according to a K-means clustering algorithm includes:
and clustering the basic data set by combining the maximum mutual information coefficient.
In an embodiment of the present application, the maximum mutual information coefficient satisfies formula (6):
wherein, x is any point in the basic data set, y is another any point in the basic data set, a is the number of grids divided on the x axis, B is the number of grids divided on the y axis, B is a variable, the value of B is the 0.6 power of the data volume of the basic data set, and I (x, y) is mutual information.
In an embodiment of the present application, further comprising:
an alarm threshold is determined from the base data set.
A second aspect of the present application provides an apparatus for diagnosing a health state of an ultrasonic flow meter, comprising:
a memory configured to store instructions; and
a processor configured to recall instructions from the memory and upon execution of the instructions enable implementation of a method for diagnosing a health state of an ultrasonic flow meter according to the above.
A third aspect of the present application provides a machine-readable storage medium having instructions stored thereon for causing a machine to perform the above-described method for diagnosing a health state of an ultrasonic flow meter.
According to the technical scheme, the health state parameters of the ultrasonic flowmeter are obtained, the characteristic index set of the health state parameters is determined according to the health state parameters, the basic data set is determined according to the characteristic index set, and finally whether abnormal working conditions exist or not is determined according to the basic data set. On one hand, the method promotes the basic research of the ultrasonic flowmeter health state diagnosis method, and on the other hand, the method is favorable for accurately evaluating the health state of the ultrasonic flowmeter due to the introduction of an intelligent and data algorithm and the introduction of historical data into real-time detection. The health state parameters of the ultrasonic flowmeter are comprehensively analyzed, the possibility of misreporting the health state of the ultrasonic flowmeter is reduced, and the comprehensiveness and accuracy of monitoring the health state of the ultrasonic flowmeter are improved.
Additional features and advantages of embodiments of the present application will be described in detail in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the embodiments of the disclosure without limiting the embodiments of the disclosure. In the drawings:
FIG. 1 schematically illustrates a flow diagram of a method for diagnosing the health of an ultrasonic flow meter in accordance with an embodiment of the present application;
FIG. 2 is a diagram schematically illustrating a distortion level indicator and a distribution characteristic indicator according to an embodiment of the present application;
FIG. 3 schematically illustrates a diagram of a complexity index according to an embodiment of the present application;
FIG. 4 schematically illustrates a schematic of a periodicity index according to an embodiment of the application;
FIG. 5 schematically illustrates a diagram of clustering a base data set according to an embodiment of the present application;
FIG. 6 schematically illustrates a diagram of determining an alarm threshold according to an embodiment of the present application;
fig. 7 schematically illustrates a structural schematic diagram of an apparatus for diagnosing a health state of an ultrasonic flow meter according to an embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the specific embodiments described herein are only used for illustrating and explaining the embodiments of the present application and are not used for limiting the embodiments of the present application. 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 application.
It should be noted that if directional indications (such as up, down, left, right, front, and back … …) are referred to in the embodiments of the present application, the directional indications are only used to explain the relative positional relationship between the components, the movement situation, and the like in a specific posture (as shown in the drawings), and if the specific posture is changed, the directional indications are changed accordingly.
In addition, if there is a description relating to "first", "second", etc. in the embodiments of the present application, the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present application.
Fig. 1 schematically illustrates a flow diagram of a method for diagnosing a health state of an ultrasonic flow meter according to an embodiment of the application. As shown in fig. 1, embodiments of the present application provide a method for diagnosing the health of an ultrasonic flow meter, which may include the following steps.
In the embodiments of the present application, an ultrasonic flow meter is an instrument for measuring a flow rate by detecting an effect of a fluid flow on an ultrasonic beam or an ultrasonic pulse, and is mainly composed of a transducer and a transducer. The processor extracts a time series of health state parameters of the ultrasonic flow meter from the historical data. The health status parameters may include, but are not limited to, sampling rate, signal gain, signal-to-noise ratio, swirl angle, measured air velocity per channel, and measured flow velocity per channel, among others. The time sequence is a sequence formed by arranging the numerical values of the same statistical index according to the occurrence time sequence. By acquiring the health state parameters of the ultrasonic flowmeter, the health state of the ultrasonic flowmeter can be conveniently and comprehensively evaluated subsequently.
And 102, determining a characteristic index set of the health state parameters according to the health state parameters.
In the embodiment of the present application, in order to fully evaluate the health status of the ultrasonic flow meter, the processor analyzes the health status parameter from four aspects. The health state parameters may include, but are not limited to, sampling rate, signal gain, signal-to-noise ratio, swirl angle, measured air velocity per channel, and measured flow rate per channel, among others. The characteristic index set is a set of distortion degree index, distribution characteristic index, complexity degree index and periodicity index of a health state parameter of the ultrasonic flowmeter. The health state of the ultrasonic flowmeter can be comprehensively diagnosed by acquiring the health state parameters and determining the characteristic index set of the health state parameters.
And 103, determining a basic data set according to the characteristic index set.
In the embodiment of the present application, the ultrasonic flow meters are usually a plurality of cooperative tasks, and in a specific application process, the health states of the plurality of ultrasonic flow meters need to be monitored, so that the processor can determine the basic data set according to the characteristic index set. The basic data set is a set of distortion degree indexes, distribution characteristic indexes, complexity degree indexes and periodicity indexes of one health state parameter of a plurality of ultrasonic flowmeters. By determining the basic data set, the health states of the ultrasonic flowmeters can be diagnosed according to the characteristic indexes of the ultrasonic flowmeters, and the efficiency of monitoring the health states of the ultrasonic flowmeters is improved.
And step 104, determining whether an abnormal working condition exists according to the basic data set.
In an embodiment of the present application, the processor may determine whether an abnormal operating condition exists based on the underlying data set. Abnormal conditions may include, but are not limited to, pipe blockage, component damage. The processor can obtain a basic data set, cluster the basic data set according to a K-means clustering algorithm combined with a maximum mutual information coefficient, determine a clustering result, and determine an abnormal working condition according to the clustering result, so that whether the abnormal working condition occurs or not can be judged more accurately. The basic data set is clustered through a K-means clustering algorithm combined with the maximum mutual information coefficient, so that the characteristic index under the abnormal working condition is more accurately identified.
According to the technical scheme, the health state parameters of the ultrasonic flowmeter are obtained, the characteristic index set of the health state parameters is determined according to the health state parameters, the basic data set is determined according to the characteristic index set, and finally whether abnormal working conditions exist or not is determined according to the basic data set. On one hand, the method promotes the basic research of the ultrasonic flowmeter health state diagnosis method, and on the other hand, the method is favorable for accurately evaluating the health state of the ultrasonic flowmeter due to the introduction of an intelligent and data algorithm and the introduction of historical data into real-time detection. The health state parameters of the ultrasonic flowmeter are comprehensively analyzed, the possibility of misreporting the health state of the ultrasonic flowmeter is reduced, and the comprehensiveness and accuracy of monitoring the health state of the ultrasonic flowmeter are improved.
In an embodiment of the present application, the health status parameter may include at least one of:
sampling rate, signal gain, signal-to-noise ratio, swirl angle, measured air velocity per channel, and measured flow velocity per channel.
In particular, the processor may acquire a state of health parameter of the ultrasonic flow meter. The sampling rate, also called sampling speed, is the number of samples per second that are extracted from a continuous signal and made up into a discrete signal. The signal gain is the ratio of the ultrasonic flow meter signal output to the signal input. The signal-to-noise ratio is the ratio between the maximum undistorted sound signal intensity generated by the sound source and the simultaneous noise intensity, and can reflect whether the pipeline is blocked or not. The swirl angle refers to an angle measured according to different flow states of gas in the ultrasonic flowmeter, the swirl angle is usually small under stable flow, and the condition of large swirl angle indicates that the flow state control of the ultrasonic flowmeter is unstable and turbulent flow occurs. The acoustic channel is an ultrasonic channel formed by mounting a pair of transducers on a measured pipeline or channel. The measured gas velocity for each channel is the gas flow velocity for each channel of the ultrasonic flow meter. The measured flow rate for each channel is the fluid flow rate for each channel of the ultrasonic flow meter. By collecting a plurality of health state parameters of the ultrasonic flowmeter, the health state of the ultrasonic flowmeter can be conveniently and comprehensively evaluated from a plurality of aspects in a follow-up manner.
In an embodiment of the present application, the feature index set may include:
distortion degree index, distribution characteristic index, complexity degree index and periodicity index.
Specifically, the processor may analyze the health status parameter from four aspects, namely, determine a distortion level indicator, a distribution characteristic indicator, a complexity level indicator, and a periodicity indicator of the health status parameter. The distortion level indicator may be used to evaluate a degree of dispersion of the health status indicator, thereby determining a degree to which the time series of the health status parameter deviates from a true value. Fig. 2 schematically shows a distortion level indicator and a distribution characteristic indicator according to an embodiment of the present application. As shown in fig. 2, line 1 is the actually measured air velocity of each channel, and line 2 is the measured air velocity of each channel in the normal state. In one example, the processor may determine the distortion level indicator from the measured air velocity of each channel of the ultrasonic flow meter. The distortion degree index satisfies formula (7):
wherein S is 1 Is a distortion degree index, i.e. the mean value of the time series of the health state parameters, n is the total number of the measuring points, VOG i Measured air velocity, VOG, of each acoustic channel actually measured for the ith station i ′ The air velocity is measured for each channel theoretically at the ith station.
The distribution characteristic indicator may be used to characterize a distribution of values over a time series of segments of the health state parameter. In one example, the ultrasonic flow meter remains relatively stable in its distribution profile of the time series of state of health parameters during normal operating conditions. The complexity index is used for describing the complexity of the health state parameter time series, wherein the complexity index comprises two numerical values, namely complexity and spectral statistical variance. The complexity is used for describing the number of wave crests and wave troughs in the time sequence of the health state parameter. The spectral statistical variance is used to describe the difference in the frequency distribution of the sub-signals in the time series of the health state parameter. The periodicity index refers to an index describing the periodicity of the time series of the health state parameter. By analyzing the six characteristic indexes of the health state parameter of the ultrasonic flowmeter, the health state of the ultrasonic flowmeter can be accurately diagnosed from multiple aspects.
In the embodiment of the present application, the distribution characteristic index includes kurtosis and skewness, and the kurtosis satisfies formula (1):
wherein S is 2 Is kurtosis, x i The value of the ith measuring point in the health state parameter time sequence,
the average value of all measuring points in the health state parameter time sequence is std, the std is standard normal distribution, and n is the total number of the measuring points;
the skewness satisfies formula (2):
wherein S is 3 The degree of deviation is the degree of deviation,
the mean value of the values of all the measured points in the health state parameter time series, std is a standard normal distribution.
Specifically, the standard normal distribution satisfies formula (8):
wherein the content of the first and second substances,std is the standard normal distribution, x i The value of the ith measuring point in the health state parameter time sequence,
is the average value of the values of all the measuring points in the health state parameter time sequence, and n is the total number of the measuring points.
Fig. 2 schematically shows a distortion level indicator and a distribution characteristic indicator according to an embodiment of the present application. As shown in fig. 2, line 1 is the actually measured air velocity of each channel, and line 2 is the measured air velocity of each channel in the normal state. In an embodiment of the present application, the processor may determine the distribution characteristic indicator of the health status parameter time series according to the acquired health status parameter time series. The distribution characteristic indicator may be used to characterize the distribution of values over a time series of segments of the health state parameter. In one example, the ultrasonic flow meter maintains a relatively stable distribution characteristic of the time series of state of health parameters during normal operating conditions. Therefore, under the condition that the ultrasonic flowmeter is in a healthy working state, the distribution mode of the health state parameter time sequence measurement points is kept relatively stable, namely, the kurtosis and the skewness change in a certain region. Kurtosis is a statistic describing how steep the distribution of all values in the population. Skewness is a measure of the direction and extent of skew of a statistical data distribution. And under the condition that the values of the kurtosis and the skewness deviate from the conventional values, the abnormal working condition of the ultrasonic flowmeter is shown to be possible. By determining the distribution characteristic index, the operating state of the ultrasonic flow meter can be judged from the characteristics of the numerical distribution of the health state parameter time series.
In the embodiment of the present application, the complexity index includes complexity and a spectrum statistical variance, and the complexity satisfies formula (3):
wherein S is 4 For complexity, n is the total number of points, x i For the ith measuring point in the health state parameter time sequenceValue of (a), x i-1 The value of the ith-1 measuring point in the health state parameter time sequence is obtained;
the spectral statistical variance satisfies formula (4):
wherein S is 5 Is the spectral statistical variance, n is the total number of the measuring points, k is the frequency of the sub-signal in the time sequence of the health state parameter, X (k) is the amplitude corresponding to the frequency k after Fourier transformation,
is the mean value of the amplitude of the time series of health state parameters after fourier transformation of the frequency.
Specifically, x (k) satisfies formula (9):
wherein X (k) is the amplitude corresponding to the frequency k after Fourier transform, n is the total number of the measuring points, x i The value of the ith measuring point in the health state parameter time sequence.
In an embodiment of the present application, the processor may determine the complexity index of the health status parameter time series according to the acquired health status parameter time series. The complexity index is used for describing the complexity of the health state parameter time series, wherein the complexity index comprises two numerical values, namely complexity and spectral statistical variance. Fig. 3 schematically shows a schematic diagram of a complexity indicator according to an embodiment of the application. As shown in fig. 3, line 3 is the measured air velocity of each channel in the normal state, and line 4 is the measured air velocity of each channel actually measured. The complexity is used for describing the number of wave crests and wave troughs in the time sequence of the health state parameter. The spectral statistical variance is used to describe the difference in the frequency distribution of the sub-signals in the time series of the health state parameter. In one example, the frequency k of the sub-signal in the health state parameter time series is processed by fourier transform. The fourier transform may transform the signal from the time domain to the frequency domain, and may further analyze the health status parameter and study the frequency domain characteristics of the health status parameter from the frequency domain. The time domain is a mathematical function or a physical signal versus time. The frequency domain is a coordinate system used in describing the characteristics of a signal in terms of frequency. When the ultrasonic flowmeter is in a healthy working state, the complexity of the time sequence of the parameters of the healthy state is kept at a low level, namely, the wave crests and the wave troughs are few. Therefore, when the complexity and the spectral statistical variance are large, the working state of the ultrasonic wave can be judged to be abnormal. Through the analysis of the complexity index of the health state parameter time sequence, the running state of the ultrasonic flowmeter can be judged according to the complexity of the health state parameter time sequence and the numerical value of the spectral statistical variance.
In the embodiment of the present application, the periodicity index satisfies formula (5):
wherein S is 6 Is a periodic index, i.e. an autoregressive coefficient, n is the total number of measured points, t is a lag coefficient, std is a standard normal distribution, x i The value of the ith measuring point in the health state parameter time sequence,
is the mean value, x, of the values of all the measured points in the health state parameter time series i+t The value of the (i + t) th measuring point in the health state parameter time sequence is obtained.
Specifically, fig. 4 schematically shows a schematic diagram of a periodicity index according to an embodiment of the present application. As shown in fig. 4, line 5 is the actually measured air velocity of each channel, and line 6 is the measured air velocity of each channel in the normal state. In an embodiment of the present application, the processor may determine a periodicity indicator of the time series of health status parameters according to the obtained time series of health status parameters. When the lag coefficient is a fixed value, under the condition of larger autoregressive coefficient, the health state parameter time sequence does not have obvious periodic regularity. Therefore, for the health state index with the periodic rule, the abnormal working condition of the ultrasonic flowmeter can be judged under the condition that the autoregressive coefficient is large. By analyzing the periodic indexes of the health state parameter time sequence, the running state of the ultrasonic flowmeter can be judged according to the periodic rule of the health state parameter time sequence.
In the embodiment of the present application, determining whether an abnormal operating condition exists according to the basic data set includes:
acquiring a basic data set;
clustering the basic data set according to a K-means clustering algorithm, and determining a clustering result;
and determining abnormal working conditions according to the clustering result.
Specifically, the processor may cluster the underlying data set according to a K-means (K-means) clustering algorithm to determine whether an abnormal operating condition exists. The K-means clustering algorithm judges the similar relation of different samples by calculating the distance between the samples, and puts the similar samples into the same category. In general, a conventional K-means clustering algorithm determines its similarity using euclidean distance, where euclidean distance refers to the true distance between two points in a multidimensional space or the natural length of a vector. Clustering is carried out by combining a K-means clustering algorithm with a maximum mutual information coefficient based on a basic data set formed by carrying out characteristic index analysis on a large number of health state parameter time sequences of the ultrasonic flowmeter. The processor may obtain the number N of dimensions and categories of the underlying dataset, where a dimension is the number of independent parameters in the mathematics. The number of categories N refers to the category of the health state, and for example, the health state of the ultrasonic flow meter may be classified into healthy, good, and unhealthy, and then the number of categories is 3. The processor may divide the health status parameters into K clusters, i.e., randomly select K parameters as initial cluster centers, then calculate the distance between each parameter and the initial cluster center, and assign each parameter to the cluster center closest to the parameter. Every time a parameter is assigned, the cluster center of the cluster is recalculated based on the existing parameters in the cluster until no further change in cluster center occurs or no parameter can be reassigned to a different cluster center.
And under the condition of calculating the maximum mutual information coefficient, recalculating the clustering center instead of the Euclidean distance. Fig. 5 schematically shows a schematic diagram of clustering a base data set according to an embodiment of the present application. As shown in fig. 5, in one example, the processor may perform a dimensionality reduction process on the clustering result through a Principal Components Analysis (PCA) technique, thereby displaying the clustering result. And (5) clustering the data in the basic data set by taking N as 2 and the dimensionality as 6. Compared with the clustering result when the ultrasonic flowmeter is in a healthy state, the characteristic index of the healthy state parameter under the abnormal working condition is a small sample, so that the class with a small number of displayed clustering results is regarded as abnormal. It should be noted that the number of clusters K increases as the number N of health status categories of the ultrasonic flow meter increases. Clustering is carried out by combining a K-means clustering algorithm with a maximum mutual information coefficient, and the relation between nonlinear parameters can be introduced, so that the abnormal working condition can be determined comprehensively and accurately.
In the embodiment of the present application, clustering the basic data set according to the K-means clustering algorithm includes:
and clustering the basic data set by combining the maximum mutual information coefficient.
In particular, the processor may cluster the underlying data set by incorporating the maximum mutual information coefficient. The traditional K-means clustering algorithm clusters data through Euclidean distance, and under the condition that the data have a nonlinear relation, the traditional K-means clustering algorithm cannot cluster the data, so that the maximum mutual information coefficient is required to be introduced to cluster the data with the nonlinear relation, and the requirement of clustering the data with different relations is met. In one example, in the case where the maximum mutual information coefficient is calculated, the cluster center is recalculated instead of the euclidean distance. By clustering the basic data set in combination with the maximum mutual information coefficient, the characteristic indexes in the basic data set can be comprehensively analyzed.
In the embodiment of the present application, the maximum mutual information coefficient satisfies formula (6):
wherein, x is any point in the basic data set, y is another any point in the basic data set, a is the number of grids divided on the x axis, B is the number of grids divided on the y axis, B is a variable, the value of B is the 0.6 power of the data volume of the basic data set, and I (x, y) is mutual information.
Specifically, mutual information I (x, y) of two points x and y satisfies formula (10):
wherein, I (x, y) is mutual information, x is an arbitrary point in the basic data set, y is another arbitrary point in the basic data set, and p (x, y) is the joint probability of the two points x and y.
The processor may cluster the underlying data set by incorporating the maximum mutual information coefficient. The traditional K-means clustering algorithm clusters data through Euclidean distance, and under the condition that the data have a nonlinear relation, the traditional K-means clustering algorithm cannot cluster the data, so that the maximum mutual information coefficient is required to be introduced to cluster the data with the nonlinear relation, and the requirement of clustering the data with different relations is met. By clustering the basic data set in combination with the maximum mutual information coefficient, the characteristic indexes in the basic data set can be comprehensively analyzed.
In the embodiment of the present application, the method may further include:
an alarm threshold is determined from the base data set.
In particular, fig. 6 schematically illustrates a schematic diagram of determining an alarm threshold according to an embodiment of the present application. As shown in fig. 6, in the embodiment of the present application, the processor may perform statistics on the clustering result, so as to determine the alarm threshold. In an actual use process, a plurality of ultrasonic flowmeters are generally used, clustering is performed according to a basic data set formed by feature index sets of health state parameters of the plurality of ultrasonic flowmeters, and the maximum value and the minimum value of the feature indexes are determined according to a clustering result, so that an alarm threshold value of the feature indexes is determined. In one example, an abnormal condition may be determined when the characteristic indicator falls outside of a threshold range. When the characteristic index falls within the threshold range, a normal condition may be determined. Further, in the case where a new characteristic index occurs, when the new characteristic index falls outside the threshold range, it may be determined as an abnormal condition. When the new characteristic index falls within the threshold range, a normal condition may be determined. It should be noted that the alarm threshold may be changed according to the change of the value of the characteristic index of the basic data set. The alarm threshold value is continuously updated according to the clustering result obtained in real time, so that the requirement of accurately diagnosing the health state of the ultrasonic flowmeter under different working conditions can be met.
Fig. 7 schematically illustrates a block diagram of an apparatus for diagnosing a health state of an ultrasonic flow meter according to an embodiment of the present application. As shown in fig. 7, an embodiment of the present application provides an apparatus for diagnosing a health state of an ultrasonic flowmeter, which may include:
a memory 710 configured to store instructions; and
a processor 720 configured to invoke the instructions from the memory 710 and when executing the instructions is capable of implementing the method for diagnosing the health of an ultrasonic flow meter described above.
Specifically, in the embodiment of the present application, the processor 720 may be configured to:
acquiring health state parameters of the ultrasonic flowmeter;
determining a characteristic index set of the health state parameters according to the health state parameters;
determining a basic data set according to the characteristic index set;
and determining whether the abnormal working condition exists according to the basic data set.
In embodiments of the present application, the health state parameter may comprise at least one of:
sampling rate, signal gain, signal-to-noise ratio, swirl angle, measured air velocity per channel, and measured flow velocity per channel.
In an embodiment of the present application, the feature index set may include:
distortion degree index, distribution characteristic index, complexity degree index and periodicity index.
In an embodiment of the present application, the distribution characteristic index includes kurtosis and skewness, and the kurtosis satisfies formula (1):
wherein S is 2 Is kurtosis, x i The value of the ith measuring point in the health state parameter time sequence,
the mean value of the values of all the measuring points in the health state parameter time sequence is shown, std is standard normal distribution, and n is the total number of the measuring points;
the skewness satisfies formula (2):
wherein S is 3 In order to obtain the degree of skewness,
the mean value of the values of all the measured points in the health state parameter time series, std is a standard normal distribution.
In an embodiment of the present application, the complexity index includes a complexity and a spectral statistical variance, and the complexity satisfies formula (3):
wherein S is 4 For complexity, n is the total number of points, x i The value of the ith measuring point in the health state parameter time sequence, x i-1 For the i-1 st in the time series of the health state parameterMeasuring the value of a point;
the spectral statistical variance satisfies formula (4):
wherein S is 5 Is the spectral statistical variance, n is the total number of the measuring points, k is the frequency of the sub-signal in the time sequence of the health state parameter, X (k) is the amplitude corresponding to the frequency k after Fourier transformation,
is the mean value of the amplitude of the time series of health state parameters after fourier transformation of the frequency.
In an embodiment of the present application, the periodicity index satisfies formula (5):
wherein S is 6 Is an autoregressive coefficient, n is the total number of measured points, t is a lag coefficient, std is a standard normal distribution, x i The value of the ith measuring point in the health state parameter time sequence,
is the mean value, x, of the values of all the measured points in the time series of the health status parameter i+t The value of the i + t measuring point in the health state parameter time sequence.
Further, the processor 720 may be further configured to:
acquiring a basic data set;
clustering the basic data set according to a K-means clustering algorithm to determine a clustering result;
and determining abnormal working conditions according to the clustering result.
Further, the processor 720 may be further configured to:
and clustering the basic data set by combining the maximum mutual information coefficient.
In an embodiment of the present application, the maximum mutual information coefficient satisfies formula (6):
wherein, x is any point in the basic data set, y is another any point in the basic data set, a is the number of grids divided on the x axis, B is the number of grids divided on the y axis, B is a variable, the value of B is the 0.6 power of the data volume of the basic data set, and I (x, y) is mutual information.
Further, the processor 720 may be further configured to:
an alarm threshold is determined from the base data set.
According to the technical scheme, the health state parameters of the ultrasonic flowmeter are obtained, the characteristic index set of the health state parameters is determined according to the health state parameters, the basic data set is determined according to the characteristic index set, and finally whether abnormal working conditions exist or not is determined according to the basic data set. On one hand, the method promotes the basic research of the ultrasonic flowmeter health state diagnosis method, and on the other hand, the method is favorable for accurately evaluating the health state of the ultrasonic flowmeter due to the introduction of an intelligent and data algorithm and the introduction of historical data into real-time detection. The health state parameters of the ultrasonic flowmeter are comprehensively analyzed, the possibility of misreporting the health state of the ultrasonic flowmeter is reduced, and the comprehensiveness and accuracy of monitoring the health state of the ultrasonic flowmeter are improved.
Embodiments of the present application also provide a machine-readable storage medium having instructions stored thereon for causing a machine to perform the above-described method for diagnosing a health state of an ultrasonic flow meter.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that 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 the process, method, article, or apparatus that comprises the element.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art to which the present application pertains. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (12)
1. A method for diagnosing the health of an ultrasonic flow meter, the method comprising:
acquiring health state parameters of the ultrasonic flowmeter;
determining a characteristic index set of the health state parameters according to the health state parameters;
determining a basic data set according to the characteristic index set;
and determining whether an abnormal working condition exists according to the basic data set.
2. The method of claim 1, wherein the health state parameter comprises at least one of:
sampling rate, signal gain, signal-to-noise ratio, swirl angle, measured air velocity per channel, and measured flow velocity per channel.
3. The method of claim 1, wherein the set of feature metrics comprises:
distortion degree index, distribution characteristic index, complexity degree index and periodicity index.
4. The method according to claim 3, wherein the distribution characteristic index includes a kurtosis and a skewness, and the kurtosis satisfies formula (1):
wherein S is 2 Is kurtosis, x i The value of the ith measuring point in the health state parameter time sequence,
the mean value of the values of all the measuring points in the health state parameter time sequence is shown, std is standard normal distribution, and n is the total number of the measuring points;
the skewness satisfies formula (2):
wherein S is 3 In order to obtain the degree of skewness,
the mean value of the values of all the measured points in the health state parameter time series, std is a standard normal distribution.
5. The method of claim 3, wherein the complexity index comprises a complexity and a spectral statistical variance, the complexity satisfying equation (3):
wherein S is 4 For complexity, n is the total number of points, x i The value of the ith measuring point in the health state parameter time sequence, x i-1 The value of the (i-1) th measuring point in the health state parameter time sequence is obtained;
the spectral statistical variance satisfies formula (4):
wherein S is 5 Is the spectral statistical variance, n is the total number of the measuring points, k is the frequency of the sub-signal in the time sequence of the health state parameter, X (k) is the amplitude corresponding to the frequency k after Fourier transformation,
is the mean value of the fourier transformed amplitudes of the frequency of the time series of health state parameters.
6. The method of claim 3, wherein the periodicity index satisfies equation (5):
wherein S is 6 Is an autoregressive coefficient, n is the total number of measured points, t is a lag coefficient, std is a standard normal distribution, x i The value of the ith measuring point in the health state parameter time sequence,
is the mean value, x, of the values of all the measured points in the health state parameter time series i+t The value of the (i + t) th measuring point in the health state parameter time sequence is obtained.
7. The method of claim 1, wherein determining from the base dataset whether an abnormal condition exists comprises:
acquiring the basic data set;
clustering the basic data set according to a K-means clustering algorithm to determine a clustering result;
and determining abnormal working conditions according to the clustering result.
8. The method of claim 7, wherein clustering the base data set according to a K-means clustering algorithm comprises:
and clustering the basic data set by combining the maximum mutual information coefficient.
9. The method of claim 8, wherein the maximum mutual information coefficient satisfies formula (6):
wherein, x is any point in the basic data set, y is another any point in the basic data set, a is the number of grids divided on the x axis, B is the number of grids divided on the y axis, B is a variable, the value of B is the 0.6 power of the data volume of the basic data set, and I (x, y) is mutual information.
10. The method of claim 1, further comprising:
an alarm threshold is determined from the base data set.
11. An apparatus for diagnosing the health of an ultrasonic flow meter, comprising:
a memory configured to store instructions; and
a processor configured to recall the instructions from the memory and upon execution of the instructions is capable of implementing the method for diagnosing ultrasonic flow meter health according to any one of claims 1 to 10.
12. A machine-readable storage medium having instructions stored thereon for causing a machine to perform the method for diagnosing the health of an ultrasonic flow meter according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210638407.1A CN115099312A (en) | 2022-06-07 | 2022-06-07 | Method, device and storage medium for diagnosing health state of ultrasonic flowmeter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210638407.1A CN115099312A (en) | 2022-06-07 | 2022-06-07 | Method, device and storage medium for diagnosing health state of ultrasonic flowmeter |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115099312A true CN115099312A (en) | 2022-09-23 |
Family
ID=83289457
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210638407.1A Pending CN115099312A (en) | 2022-06-07 | 2022-06-07 | Method, device and storage medium for diagnosing health state of ultrasonic flowmeter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115099312A (en) |
-
2022
- 2022-06-07 CN CN202210638407.1A patent/CN115099312A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11048729B2 (en) | Cluster evaluation in unsupervised learning of continuous data | |
| CA2318093C (en) | Ultrasensitive surveillance of sensors and processes | |
| JP6987030B2 (en) | Analytical method for system and machine tool abnormalities or machining work | |
| CA2402631C (en) | Generalized lensing angular similarity operator | |
| US8903757B2 (en) | Proactive information technology infrastructure management | |
| CN110068435B (en) | Vibration analysis system and method | |
| CN116592951B (en) | Intelligent cable data acquisition method and system | |
| JP2008501959A (en) | Method and computer program for determining operating parameters in rolling bearings and rolling bearings which can be evaluated thereby | |
| CN102483738A (en) | Determining a seasonal effect in temporal data | |
| JPWO2004068078A1 (en) | State determination method, state prediction method and apparatus | |
| CA2439734A1 (en) | Method and apparatus for determining the health of a component using condition indicators | |
| JP3426905B2 (en) | Method of detecting abnormal sound, method of determining abnormality of machine using the detected value, method of detecting similarity of vibration wave, and voice recognition method using the detected value | |
| CN109976986B (en) | Abnormal equipment detection method and device | |
| US20030028349A1 (en) | System for monitoring non-coincident, nonstationary process signals | |
| US11265232B2 (en) | IoT stream data quality measurement indicator and profiling method and system therefor | |
| CN115099312A (en) | Method, device and storage medium for diagnosing health state of ultrasonic flowmeter | |
| JPWO2019026193A1 (en) | Information processing device, information processing system, information processing method, and program | |
| CN115757073A (en) | System risk identification method and device, electronic equipment and storage medium | |
| US4334282A (en) | Testing apparatus | |
| CN114996257A (en) | Data amount abnormality detection method, device, medium, and program product | |
| CN114090949A (en) | Robust vibration signal characteristic value calculation method | |
| CN109684970B (en) | Window length determination method for moving principal component analysis of structural dynamic response | |
| CN114294183A (en) | Fan blade fault monitoring method and device and fan | |
| CN104808643B (en) | A kind of control loop non-linear detection method based on improved double-spectrum analysis | |
| He et al. | Signal nonstationary degree evaluation method based on moving statistics theory |
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 |