CN-122019967-A - Flowmeter output signal filtering method and device

CN122019967ACN 122019967 ACN122019967 ACN 122019967ACN-122019967-A

Abstract

The application discloses a flowmeter output signal filtering method and device. The method comprises the steps of obtaining a plurality of output signals corresponding to a target flowmeter, determining a current fluid state corresponding to the target flowmeter according to the plurality of output signals, determining a target filtering scheme corresponding to the target flowmeter according to the current fluid state corresponding to the target flowmeter, wherein the target filtering scheme comprises a target filtering algorithm and target parameters corresponding to the target filtering algorithm, and filtering the plurality of output signals based on the target filtering algorithm and the target parameters to obtain a target filtering result corresponding to each output signal.

Inventors

WU JIAWEI
Wang Zhuanpin
MA NING
LI ZHAN
XING ZHIWEI
LIU LEI
KANG JINGQIU

Assignees

华北电力科学研究院有限责任公司
国家电网有限公司

Dates

Publication Date: 20260512
Application Date: 20251231

Claims (10)

1. A method of filtering a flow meter output signal, the method comprising: acquiring a plurality of output signals corresponding to a target flowmeter; determining a current fluid state corresponding to the target flowmeter according to a plurality of output signals; Determining a target filtering scheme corresponding to the target flowmeter according to the current fluid state corresponding to the target flowmeter, wherein the target filtering scheme comprises a target filtering algorithm and target parameters corresponding to the target filtering algorithm; And filtering the plurality of output signals based on the target filtering algorithm and the target parameters to obtain a target filtering result corresponding to each output signal.
2. The method of claim 1, wherein determining the current fluid state corresponding to the target flow meter from the plurality of output signals comprises: calculating average values corresponding to a plurality of output signals; substituting the output signals, the quantity and average value corresponding to the output signals into a first preset formula to calculate standard deviation corresponding to the output signals; when the standard deviation is smaller than or equal to a first standard deviation threshold value, determining that the current fluid state corresponding to the target flowmeter is a steady laminar flow state; when the standard deviation is greater than the first standard deviation threshold and the standard deviation is less than or equal to a second standard deviation threshold, determining that the current fluid state corresponding to the target flowmeter is a moderate turbulence state; And when the standard deviation is larger than the second standard deviation threshold value, determining that the current fluid state corresponding to the target flowmeter is a severe turbulence state.
3. The method of claim 1, wherein determining the current fluid state corresponding to the target flow meter from the plurality of output signals comprises: Acquiring the fluid density, the fluid viscosity coefficient and the pipeline diameter corresponding to the target flowmeter; Substituting the output signals, the fluid density, the fluid viscosity coefficient and the pipeline diameter corresponding to the target flowmeter into a second preset formula to calculate the fluid Reynolds number corresponding to each output signal; Calculating average fluid Reynolds numbers corresponding to a plurality of output signals according to the fluid Reynolds numbers corresponding to each output signal; when the average fluid Reynolds number is smaller than or equal to a first fluid Reynolds number threshold value, determining that the current fluid state corresponding to the target flowmeter is a steady laminar flow state; when the average fluid Reynolds number is larger than the first fluid Reynolds number threshold value and the average fluid Reynolds number is smaller than or equal to the second fluid Reynolds number threshold value, determining that the current fluid state corresponding to the target flowmeter is a medium turbulence state; and when the average fluid Reynolds number is larger than the second fluid Reynolds number threshold, determining that the current fluid state corresponding to the target flowmeter is a severe turbulence state.
4. The method of claim 1, wherein determining the current fluid state corresponding to the target flow meter from the plurality of output signals comprises: And inputting the plurality of output signals into a fluid state detection model to determine the current fluid state corresponding to the target flowmeter, wherein the fluid state detection model is used for determining the current fluid state corresponding to the target flowmeter according to the plurality of output signals.
5. The method according to claim 4, wherein the method further comprises: Obtaining a training sample set, wherein the training sample set comprises a plurality of training samples, and the training samples comprise a plurality of sample flowmeter output signals and fluid states corresponding to the sample flowmeter output signals; performing multiple rounds of iterative training on the deep learning model based on the training sample set, In each training round, judging whether the loss function of the deep learning model is converged or not; if the loss function converges, determining the deep learning model obtained after the training of the round as the fluid state detection model; And if the loss function is not converged, carrying out optimization adjustment on the model parameters of the deep learning model according to the loss function, and entering the next training round based on the optimized and adjusted deep learning model.
6. The method of any of claims 1-5, wherein the determining a target filtering scheme for the target flow meter based on a current fluid state for the target flow meter comprises: When the current fluid state corresponding to the target flowmeter is a steady laminar flow state, determining that the target filtering algorithm is a Kalman filtering algorithm, and the target parameter is a first process noise covariance value; When the current fluid state corresponding to the target flowmeter is a moderate turbulence state, determining that the target filtering algorithm is a wavelet filtering algorithm and a Kalman filtering algorithm, wherein the target parameters are a first wavelet base, a first decomposition layer number, a first threshold function, a first threshold selection rule and a second process noise covariance value; And when the current fluid state corresponding to the target flowmeter is a severe turbulence state, determining that the target filtering algorithm is a wavelet filtering algorithm and a Kalman filtering algorithm, wherein the target parameters are a second wavelet base, a second decomposition layer number, a second threshold function, a second threshold selection rule and a third process noise covariance value.
7. The method of claim 6, wherein filtering the plurality of output signals based on the target filtering algorithm and the target parameter to obtain a target filtering result corresponding to each of the output signals, comprises: When the current fluid state corresponding to the target flowmeter is a stable laminar flow state, calling a preset Kalman filtering module to carry out filtering processing on a plurality of output signals based on the first process noise covariance value so as to obtain a target filtering result corresponding to each output signal; When the current fluid state corresponding to the target flowmeter is a moderate turbulence state, calling a preset wavelet filtering module to carry out filtering processing on a plurality of output signals based on the first wavelet base, the first decomposition layer number, the first threshold function and the first threshold selection rule so as to obtain an intermediate filtering result corresponding to each output signal; and when the current fluid state corresponding to the target flowmeter is a severe turbulence state, calling the preset wavelet filtering module to carry out filtering processing on a plurality of output signals based on the second wavelet base, the second decomposition layer number, the second threshold function and the second threshold selection rule so as to obtain an intermediate filtering result corresponding to each output signal, and calling the preset Kalman filtering module to carry out filtering processing on the intermediate filtering result corresponding to each output signal based on the third process noise covariance value so as to obtain the target filtering result corresponding to each output signal.
8. A flow meter output signal filtering apparatus, said apparatus comprising: The acquisition unit is used for acquiring a plurality of output signals corresponding to the target flowmeter; A first determining unit, configured to determine a current fluid state corresponding to the target flowmeter according to a plurality of output signals; A second determining unit, configured to determine a target filtering scheme corresponding to the target flowmeter according to a current fluid state corresponding to the target flowmeter, where the target filtering scheme includes a target filtering algorithm and a target parameter corresponding to the target filtering algorithm; And the filtering unit is used for carrying out filtering processing on the plurality of output signals based on the target filtering algorithm and the target parameters so as to obtain a target filtering result corresponding to each output signal.
9. A computer device comprising a memory, a processor and a computer program stored on the memory, characterized in that the processor executes the computer program to carry out the steps of the method according to any one of claims 1 to 7.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 7.

Description

Flowmeter output signal filtering method and device Technical Field The application relates to the technical field of flowmeters, in particular to a flowmeter output signal filtering method and device. Background The thermal generator set is a device combination for generating electricity by using fossil fuel (such as coal, petroleum, natural gas and the like), and the working principle is that chemical energy is converted into heat energy through fuel combustion, then the heat energy is converted into mechanical energy through a power machine such as a steam turbine or a gas turbine, and finally the mechanical energy is converted into electric energy through a generator. In the operation process of the thermal generator set, flow monitoring is a key for guaranteeing the safety of the set, improving the operation efficiency of the set and maintaining the stability of various operation parameters of the set. In the process of using the flowmeter to monitor the corresponding flow of various fluids in the thermal generator set, noise caused by the flowing state of the fluid, external noise such as pipeline mechanical vibration, electromagnetic interference of power equipment, signal transmission interference and the like can cause the output signal of the flowmeter to be interfered, the accuracy and stability of the output signal of the flowmeter are seriously affected, the oscillation of a control loop and the increase of metering errors are caused, and even the false alarm of a system is caused. Therefore, how to perform effective filtering processing on the flow meter output signal is important to obtain more accurate fluid conditions and flow values. At present, a filtering algorithm with fixed parameters is generally selected, and then filtering processing is carried out on the flowmeter output signal based on the filtering algorithm with fixed parameters. Although the existing filtering scheme performs well under stable working conditions, in actual operation of the unit, the random group load of the fluid state changes in real time, and as different current fluid states correspond to completely different noise characteristics, the filtering processing is carried out on the output signals of the flowmeter by adopting the existing filtering scheme, the accuracy of a filtering result cannot be ensured, and therefore a certain difficulty is increased for unit operators to judge the unit state. Disclosure of Invention The embodiment of the application provides a method and a device for filtering output signals of a flowmeter, which mainly aim to accurately judge the fluid state according to the output signals of the flowmeter, select a proper filtering scheme to filter the output signals of the flowmeter according to the judged fluid state, and further ensure the accuracy of filtering results. In order to solve the technical problems, the embodiment of the application provides the following technical scheme: in a first aspect, the present application provides a method of filtering a flow meter output signal, the method comprising: acquiring a plurality of output signals corresponding to a target flowmeter; determining a current fluid state corresponding to the target flowmeter according to a plurality of output signals; Determining a target filtering scheme corresponding to the target flowmeter according to the current fluid state corresponding to the target flowmeter, wherein the target filtering scheme comprises a target filtering algorithm and target parameters corresponding to the target filtering algorithm; And filtering the plurality of output signals based on the target filtering algorithm and the target parameters to obtain a target filtering result corresponding to each output signal. In a second aspect, the present application also provides a flow meter output signal filtering apparatus, the apparatus comprising: The acquisition unit is used for acquiring a plurality of output signals corresponding to the target flowmeter; A first determining unit, configured to determine a current fluid state corresponding to the target flowmeter according to a plurality of output signals; A second determining unit, configured to determine a target filtering scheme corresponding to the target flowmeter according to a current fluid state corresponding to the target flowmeter, where the target filtering scheme includes a target filtering algorithm and a target parameter corresponding to the target filtering algorithm; And the filtering unit is used for carrying out filtering processing on the plurality of output signals based on the target filtering algorithm and the target parameters so as to obtain a target filtering result corresponding to each output signal. In a third aspect, embodiments of the present application provide a computer device comprising a memory, a processor and a computer program stored on the memory, the processor executing the computer program to carry out the steps of the method of the first a