Flowmeter output signal filtering method and device
By acquiring the flow meter output signal, determining the fluid state, and selecting appropriate filtering algorithms and parameters, the problem of inaccurate filtering results in existing technologies is solved, achieving higher signal accuracy and stability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NORTH CHINA ELECTRICAL POWER RES INST
- Filing Date
- 2025-12-31
- Publication Date
- 2026-05-12
AI Technical Summary
Existing flow meter output signal filtering schemes cannot adapt to real-time changes in fluid conditions, resulting in inaccurate filtering results and increasing the difficulty for unit operators to judge the unit's status.
By acquiring multiple output signals from the flow meter, the current fluid state is determined, and an appropriate filtering algorithm and parameters are selected for filtering based on the fluid state. This includes training a fluid state detection model and using a deep learning model, as well as selecting Kalman filtering or wavelet filtering algorithms and corresponding parameters for filtering.
It improves the accuracy of filtering results, better eliminates noise interference caused by fluid flow conditions, and ensures signal stability and accuracy.
Smart Images
Figure CN122019967A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of flow meter technology, and in particular to a method and apparatus for filtering flow meter output signals. Background Technology
[0002] Thermal power generating units are a type of equipment that uses fossil fuels (such as coal, oil, and natural gas) to generate electricity. Their working principle involves converting chemical energy into heat energy through fuel combustion, which is then converted into mechanical energy by power machinery such as steam turbines or gas turbines. Finally, the mechanical energy is converted into electrical energy by a generator. During the operation of thermal power generating units, flow monitoring is crucial for ensuring unit safety, improving unit operating efficiency, and maintaining the stability of various operating parameters.
[0003] When using flow meters to monitor the flow rates of various fluids within thermal power generating units, external noise, such as noise from the fluid's own flow state, pipeline mechanical vibration, electromagnetic interference from power equipment, and signal transmission interference, can interfere with the flow meter's output signal. This severely affects the accuracy and stability of the flow meter's output signal, leading to control loop oscillations, increased measurement errors, and even false alarms. Therefore, effectively filtering the flow meter's output signal to obtain more accurate fluid state and flow rate values is crucial.
[0004] Currently, the common practice is to first select a filtering algorithm with fixed parameters, and then filter the flowmeter output signal based on this algorithm. Although existing filtering schemes perform well under stable operating conditions, in actual unit operation, the fluid state changes in real time with the unit load. Since different current fluid states correspond to completely different noise characteristics, using existing filtering schemes to filter the flowmeter output signal cannot guarantee the accuracy of the filtering results, thus increasing the difficulty for unit operators to judge the unit's status. Summary of the Invention
[0005] This application provides a method and apparatus for filtering the output signal of a flow meter. The main purpose is to accurately determine the fluid state based on the signal output by the flow meter, and select an appropriate filtering scheme to filter the output signal of the flow meter based on the determined fluid state, thereby ensuring the accuracy of the filtering result.
[0006] To address the aforementioned technical problems, this application provides the following technical solutions: In a first aspect, this application provides a method for filtering the output signal of a flow meter, the method comprising: Acquire multiple output signals corresponding to the target flow meter; The current fluid state corresponding to the target flow meter is determined based on the multiple output signals; The target filtering scheme corresponding to the target flow meter is determined based on the current fluid state corresponding to the target flow meter, wherein the target filtering scheme includes a target filtering algorithm and target parameters corresponding to the target filtering algorithm; The target filtering algorithm and the target parameters are used to filter multiple output signals to obtain the target filtering result for each output signal.
[0007] Secondly, this application also provides a flow meter output signal filtering device, the device comprising: The acquisition unit is used to acquire multiple output signals corresponding to the target flow meter; The first determining unit is configured to determine the current fluid state corresponding to the target flow meter based on the plurality of output signals; The second determining unit is used to determine the target filtering scheme corresponding to the target flow meter based on the current fluid state corresponding to the target flow meter, wherein the target filtering scheme includes a target filtering algorithm and target parameters corresponding to the target filtering algorithm; A filtering unit is used to filter multiple output signals based on the target filtering algorithm and the target parameters to obtain a target filtering result for each output signal.
[0008] Thirdly, embodiments of this application provide a computer device including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in the first aspect.
[0009] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect.
[0010] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in the first aspect.
[0011] By employing the above-described technical solution, the technical solution provided in this application has at least the following advantages: This application provides a method and apparatus for filtering output signals of a flow meter. After obtaining multiple output signals corresponding to a target flow meter through an output signal filtering application, the application first determines the current fluid state corresponding to the target flow meter based on these signals. Then, it determines a target filtering scheme for the target flow meter based on this current fluid state, specifically determining the target filtering algorithm, target parameters, and the filtering process for the output signals. Finally, it filters the multiple output signals based on the target filtering algorithm and parameters. This involves configuring the target filtering algorithm according to the target parameters and then filtering the output signals according to the configured algorithm, thereby obtaining the target filtering result for each output signal. In this application, the output signal filtering application selects the target filtering algorithm and the target parameters corresponding to the target filtering algorithm based on the current fluid state corresponding to the target flow meter (i.e., the fluid state of the target fluid at the target position in the target pipe at the current moment). Therefore, filtering multiple output signals corresponding to the target flow meter based on the target filtering algorithm and the target parameters can better eliminate the noise caused by the flow state of the target fluid itself, thereby ensuring the accuracy of the filtering results.
[0012] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description
[0013] The above and other objects, features, and advantages of exemplary embodiments of this application will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the drawings, several embodiments of this application are illustrated by way of example and not limitation, with the same or corresponding reference numerals denoteing the same or corresponding parts, wherein: Figure 1 A flowchart of a flowmeter output signal filtering method provided in an embodiment of this application is shown; Figure 2 A flowchart of another flowmeter output signal filtering method provided in an embodiment of this application is shown; Figure 3 This paper shows a block diagram of a flow meter output signal filtering device according to an embodiment of the present application; Figure 4 A block diagram of another flowmeter output signal filtering device provided in an embodiment of this application is shown. Detailed Implementation
[0014] Exemplary embodiments of this application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of this application are shown in the drawings, it should be understood that this application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of this application and to fully convey the scope of this application to those skilled in the art.
[0015] Furthermore, the terms “first,” “second,” and similar terms used in this application do not indicate any order, quantity, or importance, but are merely used to distinguish different parts.
[0016] It should be noted that, unless otherwise stated, the technical or scientific terms used in this application shall have the ordinary meaning as understood by one of ordinary skill in the art to which this application pertains.
[0017] Currently, the common practice is to first select a filtering algorithm with fixed parameters, and then filter the flowmeter output signal based on this algorithm. Although existing filtering schemes perform well under stable operating conditions, in actual unit operation, the fluid state changes in real time with the unit load. Since different current fluid states correspond to completely different noise characteristics, using existing filtering schemes to filter the flowmeter output signal cannot guarantee the accuracy of the filtering results, thus increasing the difficulty for unit operators to judge the unit's status.
[0018] Therefore, in order to accurately determine the fluid state based on the signal output by the flow meter, and to select a suitable filtering scheme to filter the flow meter output signal based on the determined fluid state, thereby ensuring the accuracy of the filtering result, this application provides a flow meter output signal filtering method, such as... Figure 1 As shown.
[0019] 101. Obtain multiple output signals corresponding to the target flow meter.
[0020] The target flow meter is a flow meter installed at a target location on a target pipeline within the target thermal power generating unit. The target flow meter is used to monitor the flow rate of the target fluid within the target pipeline at the target location. The target pipeline can be any pipeline within the target thermal power generating unit, and the target location can be any location on the target pipeline. The target flow meter can be, but is not limited to, any type of vortex flow meter, electromagnetic flow meter, ultrasonic flow meter, etc. The embodiments of this application do not specifically limit this.
[0021] In the embodiments of this application, the execution entity in each step is an output signal filtering application running on the target terminal device, wherein the target terminal device may be, but is not limited to, a computer, tablet computer, laptop computer, etc.
[0022] When staff need to filter the output signal of the target flow meter, the output signal filtering application can first acquire multiple output signals corresponding to the target flow meter. These multiple output signals are multiple analog signals continuously acquired from the target flow meter at a target sampling rate, and then converted from analog to digital to obtain multiple digital signals. The target sampling rate can be, but is not limited to, 500Hz, 1000Hz, etc.
[0023] 102. Determine the current fluid state corresponding to the target flow meter based on multiple output signals.
[0024] The current fluid state corresponding to the target flow meter is the fluid state of the target fluid at the target location in the target pipe at the current moment. Specifically, the current fluid state corresponding to the target flow meter can be one of the following: steady laminar flow, moderate turbulent flow, and severe turbulent flow.
[0025] After acquiring multiple output signals corresponding to the target flow meter, the output signal filtering application can determine the current fluid state corresponding to the target flow meter based on these multiple output signals.
[0026] 103. Determine the target filtering scheme corresponding to the target flow meter based on the current fluid state corresponding to the target flow meter.
[0027] The target filtering scheme includes the target filtering algorithm and the target parameters corresponding to the target filtering algorithm.
[0028] After determining the current fluid state corresponding to the target flow meter, the output signal filtering application can determine the target filtering scheme corresponding to the target flow meter based on the current fluid state corresponding to the target flow meter. That is, it determines the filtering algorithm (i.e., the target filtering algorithm) and the corresponding parameters (i.e., the target parameters corresponding to the target filtering algorithm) for the output signal corresponding to the target flow meter based on the current fluid state corresponding to the target flow meter.
[0029] 104. Filter multiple output signals based on the target filtering algorithm and target parameters to obtain the target filtering result for each output signal.
[0030] Once the output signal filtering application determines the target filtering scheme corresponding to the target flow meter, that is, after determining the target filtering algorithm and target parameters for filtering the output signal of the target flow meter, it can filter multiple output signals corresponding to the target flow meter based on the target filtering algorithm and target parameters. In other words, it first configures the target filtering algorithm according to the target parameters, and then filters multiple output signals corresponding to the target flow meter according to the configured target filtering algorithm, thereby obtaining the target filtering result for each output signal.
[0031] This application provides a method for filtering output signals of a flow meter. After the output signal filtering application obtains multiple output signals corresponding to a target flow meter, it first determines the current fluid state corresponding to the target flow meter based on these signals. Then, it determines a target filtering scheme based on the current fluid state, specifically determining the target filtering algorithm, target parameters, and the filtering process for the output signals. Finally, it filters the multiple output signals based on the target filtering algorithm and parameters. This involves configuring the target filtering algorithm according to the target parameters and then filtering the output signals to obtain the target filtering result for each output signal. In this embodiment, the output signal filtering application selects the target filtering algorithm and the target parameters corresponding to the target filtering algorithm based on the current fluid state corresponding to the target flow meter (i.e., the fluid state of the target fluid at the target position in the target pipe at the current moment). Therefore, filtering multiple output signals corresponding to the target flow meter based on the target filtering algorithm and the target parameters can better eliminate the noise caused by the flow state of the target fluid itself, thereby ensuring the accuracy of the filtering results.
[0032] To provide a more detailed explanation, this application provides another method for filtering the output signal of a flow meter, as detailed below. Figure 2 As shown.
[0033] 201. Train the fluid state detection model.
[0034] To ensure that the output signal filtering application can accurately determine the current fluid state corresponding to the target flow meter after acquiring multiple output signals, the application needs to pre-train a fluid state detection model. The following will explain in detail how to train and obtain the fluid state detection model.
[0035] (1) Obtain a training sample set, wherein the training sample set contains multiple training samples. For any training sample, the training sample contains multiple sample flow meter output signals and the fluid state corresponding to the multiple sample flow meter output signals.
[0036] (2) Train the deep learning model based on the training sample set until the loss function corresponding to the deep learning model converges to obtain the fluid state detection model.
[0037] The deep learning model can be a model built based on any existing deep learning algorithm, and this application does not specifically limit it.
[0038] The deep learning model is iteratively trained using a training sample set containing multiple training samples. In each round of training, it is determined whether the loss function of the deep learning model has converged. If the loss function converges, the deep learning model obtained after this round of training is identified as the fluid state detection model. If the loss function has not converged, the model parameters of the deep learning model are optimized and adjusted according to the loss function, and the next round of training is carried out based on the optimized and adjusted deep learning model.
[0039] That is, after multiple rounds of iterative training of the deep learning model based on the training sample set, when the loss function of the deep learning model converges, the deep learning model at this time is determined to be a fluid state detection model.
[0040] Because, under certain specific circumstances, even with a large number of iterative training sessions, the loss function of a deep learning model may not converge, in order to avoid endless iterative training of the deep learning model, when it is determined that the loss function of the deep learning model obtained after this round of training has not converged, the following two methods can be used, but are not limited to: 1. If the loss function of the deep learning model has not converged, determine whether the current cumulative iteration training time of the deep learning model based on the training sample set has reached the preset time threshold.
[0041] If the current cumulative training time reaches the preset time threshold, it means that the training time has reached the requirement. At this time, the training can be stopped and the deep learning model obtained after this round of training can be identified as the fluid state detection model.
[0042] If the current cumulative training time has not reached the preset time threshold, then the process can proceed to the next round of training, where the model parameters of the deep learning model are optimized and adjusted according to the loss function, and the optimized and adjusted deep learning model is used as the basis for the next round of training.
[0043] 2. If the loss function of the deep learning model has not converged, determine whether the current cumulative number of iterations of training the deep learning model based on the training sample set has reached the preset threshold.
[0044] If the current cumulative number of training iterations reaches the preset threshold, it means that the required number of training iterations has been reached. At this point, the training iterations can be stopped, and the deep learning model obtained after this round of training can be identified as the fluid state detection model.
[0045] If the current cumulative number of training iterations has not reached the preset threshold, then the process can proceed to the next round of training, where the model parameters of the deep learning model are optimized and adjusted according to the loss function, and the optimized and adjusted deep learning model is used as the basis for the next round of training.
[0046] 202. Obtain multiple output signals corresponding to the target flow meter.
[0047] Regarding step 202, obtaining multiple output signals corresponding to the target flow meter, please refer to the relevant description of step 101 above. This embodiment of the application will not repeat it here.
[0048] 203. Determine the current fluid state corresponding to the target flow meter based on multiple output signals.
[0049] After acquiring multiple output signals corresponding to the target flow meter, the output signal filtering application can determine the current fluid state corresponding to the target flow meter based on these multiple output signals.
[0050] Specifically, in this step, the output signal filtering application can determine the current fluid state corresponding to the target flow meter based on multiple output signals from the target flow meter using any of the following three methods: (1) First, calculate the average value corresponding to multiple output signals; second, substitute the multiple output signals, the quantity of the multiple output signals, and the average value into the first preset formula to calculate the standard deviation corresponding to the multiple output signals, wherein the first preset formula is as follows: σ=[1 / N∑(i=1 to N)(x i - x̄) 2 ] Where σ is the standard deviation of the multiple output signals, N is the number of the multiple output signals, and x i Let x be the i-th output signal, and x̄ be the average value of multiple output signals; When the standard deviations corresponding to multiple output signals are less than or equal to the first standard deviation threshold, the current fluid state corresponding to the target flow meter is determined to be a stable laminar flow state; when the standard deviations corresponding to multiple output signals are greater than the first standard deviation threshold and the standard deviations corresponding to multiple output signals are less than or equal to the second standard deviation threshold, the current fluid state corresponding to the target flow meter is determined to be a moderately turbulent flow state; when the standard deviations corresponding to multiple output signals are greater than the second standard deviation threshold, the current fluid state corresponding to the target flow meter is determined to be a severely turbulent flow state; wherein, the first standard deviation threshold and the second standard deviation threshold are determined based on the full scale corresponding to the target flow meter, the first standard deviation threshold = the full scale corresponding to the target flow meter * a, the second standard deviation threshold = the full scale corresponding to the target flow meter * b, where b is greater than a, a can be 2%, 3%, 4%, etc., and b can be 5%, 6%, 7%, etc.
[0051] (2) First, obtain the fluid density, fluid viscosity coefficient, and pipe diameter corresponding to the target flow meter, wherein the fluid density corresponding to the target flow meter is the fluid density of the target fluid, the fluid viscosity coefficient corresponding to the target flow meter is the fluid viscosity coefficient of the target fluid, and the pipe diameter corresponding to the target flow meter is the diameter of the target pipe; second, substitute multiple output signals, the fluid density, fluid viscosity coefficient, and pipe diameter corresponding to the target flow meter into the second preset formula to calculate the fluid Reynolds number corresponding to each output signal, wherein the second preset formula is as follows: Re i =(ρ*x i *D) / μ Among them, Re i Let ρ be the fluid Reynolds number corresponding to the i-th output signal, ρ be the fluid density corresponding to the target flow meter, and x be the fluid density. i Let be the i-th output signal, D be the pipe diameter corresponding to the target flow meter, and μ be the fluid viscosity coefficient corresponding to the target flow meter. It should be noted that when multiple output signals are specifically volumetric flow rate or mass flow rate, multiple output signals need to be converted into flow velocity before being substituted into the second preset formula. Calculate the average fluid Reynolds number corresponding to multiple output signals based on the fluid Reynolds number corresponding to each output signal, that is, calculate the average fluid Reynolds number corresponding to multiple output signals, and determine the calculation result as the average fluid Reynolds number corresponding to multiple output signals; When the average fluid Reynolds number corresponding to multiple output signals is less than or equal to the first fluid Reynolds number threshold, the current fluid state corresponding to the target flow meter is determined to be a steady laminar flow state; when the average fluid Reynolds number corresponding to multiple output signals is greater than the first fluid Reynolds number threshold, and the average fluid Reynolds number corresponding to multiple output signals is less than or equal to the second fluid Reynolds number threshold, the current fluid state corresponding to the target flow meter is determined to be a moderately turbulent flow state; when the average fluid Reynolds number corresponding to multiple output signals is greater than the second fluid Reynolds number threshold, the current fluid state corresponding to the target flow meter is determined to be a severely turbulent flow state; wherein, the second fluid Reynolds number threshold is greater than the first fluid Reynolds number threshold, the first fluid Reynolds number threshold may be, but is not limited to, 1500, 2000, 2500, etc., and the second fluid Reynolds number threshold may be, but is not limited to, 3500, 4000, 4500, etc.
[0052] (3) Input multiple output signals into the fluid state detection model. After receiving multiple output signals, the fluid state detection model can determine the current fluid state corresponding to the target flow meter based on the multiple output signals.
[0053] 204. Determine the target filtering scheme corresponding to the target flow meter based on the current fluid state corresponding to the target flow meter.
[0054] After determining the current fluid state corresponding to the target flow meter, the output signal filtering application can determine the target filtering scheme corresponding to the target flow meter based on the current fluid state. That is, it determines the target filtering algorithm to be used and the target parameters corresponding to the target filtering algorithm based on the current fluid state corresponding to the target flow meter.
[0055] Specifically, in this step, the output signal filtering application determines the target filtering scheme corresponding to the target flow meter based on the current fluid state of the target flow meter as follows: When the current fluid state corresponding to the target flow meter is a steady laminar flow state, the target filtering algorithm is determined to be the Kalman filtering algorithm, and the target parameter is the first process noise covariance value. The value of the first process noise covariance value can be, but is not limited to, 0.001, 0.002, 0.003, etc. When the current fluid state corresponding to the target flowmeter is moderate turbulence, the target filtering algorithm is determined to be wavelet filtering and Kalman filtering. The target parameters are the first wavelet basis, the first decomposition level, the first threshold function, the first threshold selection rule, and the second process noise covariance. The first wavelet basis can be, but is not limited to, the sym6 wavelet basis, etc.; the first decomposition level can be, but is not limited to, 3, 4, 5, etc.; the first threshold function can be, but is not limited to, a soft threshold function, etc.; the first threshold selection rule can be, but is not limited to, an unbiased risk estimation threshold selection rule, etc.; and the second process noise covariance is greater than the first process noise covariance. The value of the second process noise covariance can be, but is not limited to, 0.04, 0.05, 0.06, etc. The first wavelet basis, the first decomposition level, the first threshold function, the first threshold selection rule, and the second process noise covariance are obtained through statistical analysis of historical moderate turbulence data corresponding to the target fluid. When the current fluid state corresponding to the target flowmeter is a state of severe turbulence, the target filtering algorithm is determined to be a wavelet filtering algorithm and a Kalman filtering algorithm. The target parameters are the second wavelet basis, the second decomposition level, the second threshold function, the second threshold selection rule, and the third process noise covariance value. Among them, the second wavelet basis can be, but is not limited to, the Bior 3.7 wavelet basis, etc.; the second decomposition level can be, but is not limited to, 3, 4, 5, etc.; the second threshold function can be, but is not limited to, a soft threshold function, etc.; the second threshold selection rule can be, but is not limited to, an unbiased risk estimation threshold selection rule, etc.; the third process noise covariance value is greater than the second process noise covariance value, and the value of the third process noise covariance value can be, but is not limited to, 0.5, 0.7, 1.0, etc. The second wavelet basis, the second decomposition level, the second threshold function, the second threshold selection rule, and the third process noise covariance value are obtained by statistical analysis of the historical severe turbulence data corresponding to the target fluid.
[0056] 205. Based on the target filtering algorithm and target parameters, filter multiple output signals to obtain the target filtering result corresponding to each output signal.
[0057] Once the output signal filtering application determines the target filtering scheme corresponding to the target flow meter, that is, after determining the target filtering algorithm and target parameters for filtering the output signal of the target flow meter, it can filter multiple output signals corresponding to the target flow meter based on the target filtering algorithm and target parameters. In other words, it first configures the target filtering algorithm according to the target parameters, and then filters multiple output signals corresponding to the target flow meter according to the configured target filtering algorithm, thereby obtaining the target filtering result for each output signal.
[0058] Specifically, in this step, the output signal filtering application performs filtering processing on multiple output signals based on the target filtering algorithm and target parameters to obtain the target filtering result corresponding to each output signal. The specific process is as follows: When the current fluid state corresponding to the target flow meter is a stable laminar flow state, the preset Kalman filter module is called based on the first process noise covariance value to filter multiple output signals. That is, the preset Kalman filter module is first configured according to the first process noise covariance value, and then the configured preset Kalman filter module is called to filter multiple output signals, thereby obtaining the target filtering result corresponding to each output signal. When the current fluid state corresponding to the target flow meter is a moderately turbulent state, a preset wavelet filter module is first invoked to filter multiple output signals based on the first wavelet basis, the first decomposition level, the first threshold function, and the first threshold selection rule. That is, the preset wavelet filter module is first configured according to the first wavelet basis, the first decomposition level, the first threshold function, and the first threshold selection rule, and then the configured preset wavelet filter module is invoked to filter multiple output signals, thereby obtaining the intermediate filtering result corresponding to each output signal. Then, a preset Kalman filter module is invoked based on the second process noise covariance value to filter the intermediate filtering result corresponding to each output signal. That is, the preset Kalman filter module is first configured according to the second process noise covariance value, and then the configured preset Kalman filter module is invoked to filter the intermediate filtering result corresponding to each output signal, thereby obtaining the target filtering result corresponding to each output signal. When the current fluid state corresponding to the target flow meter is a state of severe turbulence, the preset wavelet filter module is first invoked to filter multiple output signals based on the second wavelet basis, the second decomposition level, the second threshold function, and the second threshold selection rule. That is, the preset wavelet filter module is first configured according to the second wavelet basis, the second decomposition level, the second threshold function, and the second threshold selection rule, and then the configured preset wavelet filter module is invoked to filter multiple output signals, thereby obtaining the intermediate filtering result corresponding to each output signal. Then, the preset Kalman filter module is invoked based on the third process noise covariance value to filter the intermediate filtering result corresponding to each output signal. That is, the preset Kalman filter module is first configured according to the third process noise covariance value, and then the configured preset Kalman filter module is invoked to filter the intermediate filtering result corresponding to each output signal, thereby obtaining the target filtering result corresponding to each output signal.
[0059] Furthermore, as a response to the above Figure 1 and Figure 2In addition to the implementation of the method shown, another embodiment of this application also provides a flow meter output signal filtering device. This device embodiment corresponds to the foregoing method embodiment. For ease of reading, this device embodiment will not repeat the details of the foregoing method embodiment, but it should be clear that the device in this embodiment can implement all the contents of the foregoing method embodiment. This device is used to accurately determine the fluid state based on the signal output by the flow meter, and select a suitable filtering scheme to filter the flow meter output signal according to the determined fluid state, thereby ensuring the accuracy of the filtering result. Specifically, as shown... Figure 3 As shown, the device includes: Acquisition unit 31 is used to acquire multiple output signals corresponding to the target flow meter; The first determining unit 32 is used to determine the current fluid state corresponding to the target flow meter based on the plurality of output signals; The second determining unit 33 is used to determine the target filtering scheme corresponding to the target flow meter based on the current fluid state corresponding to the target flow meter, wherein the target filtering scheme includes a target filtering algorithm and target parameters corresponding to the target filtering algorithm; The filtering unit 34 is used to filter multiple output signals based on the target filtering algorithm and the target parameters to obtain the target filtering result corresponding to each output signal.
[0060] Furthermore, such as Figure 4 As shown, the first determining unit 32 is specifically used to: calculate the average value corresponding to multiple output signals; Substitute the multiple output signals, the quantity and average value of the multiple output signals into the first preset formula to calculate the standard deviation of the multiple output signals; When the standard deviation is less than or equal to the first standard deviation threshold, the current fluid state corresponding to the target flow meter is determined to be 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 the second standard deviation threshold, the current fluid state corresponding to the target flow meter is determined to be a moderately turbulent state. When the standard deviation is greater than the second standard deviation threshold, the current fluid state corresponding to the target flow meter is determined to be a state of severe turbulence.
[0061] Furthermore, such as Figure 4 As shown, the first determining unit 32 is specifically used to: obtain the fluid density, fluid viscosity coefficient and pipe diameter corresponding to the target flow meter; Substitute the multiple output signals, the fluid density, fluid viscosity coefficient, and pipe diameter corresponding to the target flow meter into the second preset formula to calculate the fluid Reynolds number corresponding to each output signal; Calculate the average fluid Reynolds number corresponding to multiple output signals based on the fluid Reynolds number corresponding to each output signal; When the average fluid Reynolds number is less than or equal to the first fluid Reynolds number threshold, the current fluid state corresponding to the target flow meter is determined to be a steady laminar flow state. When the average fluid Reynolds number is greater than the first fluid Reynolds number threshold and the average fluid Reynolds number is less than or equal to the second fluid Reynolds number threshold, the current fluid state corresponding to the target flow meter is determined to be a moderately turbulent state. When the average fluid Reynolds number is greater than the second fluid Reynolds number threshold, the current fluid state corresponding to the target flow meter is determined to be a state of severe turbulence.
[0062] Furthermore, such as Figure 4 As shown, the first determining unit 32 is specifically used to: input multiple output signals into the fluid state detection model to determine the current fluid state corresponding to the target flow meter, wherein the fluid state detection model is used to determine the current fluid state corresponding to the target flow meter based on the multiple output signals.
[0063] Furthermore, such as Figure 4 As shown, the device also includes: Training unit 35 is used to acquire a training sample set, wherein the training sample set contains multiple training samples, and the training samples contain multiple sample flow meter output signals and fluid states corresponding to the multiple sample flow meter output signals. The deep learning model is trained iteratively through multiple rounds based on the aforementioned training sample set; wherein... In each round of training, it is determined whether the loss function of the deep learning model has converged; If the loss function converges, the deep learning model obtained after this round of training is determined as the fluid state detection model; If the loss function fails to converge, the model parameters of the deep learning model are optimized and adjusted according to the loss function, and the optimized deep learning model is then used to enter the next round of training.
[0064] Furthermore, such as Figure 4 As shown, the second determining unit 33 is specifically used to: when the current fluid state corresponding to the target flow meter is a steady laminar flow state, determine that the target filtering algorithm is a Kalman filtering algorithm, and the target parameter is the first process noise covariance value; When the current fluid state corresponding to the target flow meter is a moderately turbulent state, the target filtering algorithm is determined to be a wavelet filtering algorithm and a Kalman filtering algorithm, and the target parameters are a first wavelet basis, a first decomposition level, a first threshold function, a first threshold selection rule, and a second process noise covariance value. When the current fluid state corresponding to the target flow meter is a state of severe turbulence, the target filtering algorithm is determined to be a wavelet filtering algorithm and a Kalman filtering algorithm, and the target parameters are a second wavelet basis, a second decomposition level, a second threshold function, a second threshold selection rule, and a third process noise covariance value.
[0065] Furthermore, such as Figure 4 As shown, the filtering unit 34 is specifically used to: when the current fluid state corresponding to the target flow meter is a steady laminar flow state, call the preset Kalman filter module to filter multiple output signals based on the first process noise covariance value to obtain the target filtering result corresponding to each output signal; When the current fluid state corresponding to the target flow meter is a moderately turbulent state, a preset wavelet filtering module is invoked based on the first wavelet basis, the first decomposition level, the first threshold function, and the first threshold selection rule to filter multiple output signals, thereby obtaining an intermediate filtering result corresponding to each output signal; and a preset Kalman filtering module is invoked based on the second process noise covariance value to filter the intermediate filtering result corresponding to each output signal, thereby obtaining a target filtering result corresponding to each output signal. When the current fluid state corresponding to the target flow meter is a state of severe turbulence, the preset wavelet filtering module is invoked based on the second wavelet basis, the second decomposition level, the second threshold function, and the second threshold selection rule to filter multiple output signals to obtain an intermediate filtering result corresponding to each output signal; the preset Kalman filtering module is invoked based on the third process noise covariance value to filter the intermediate filtering result corresponding to each output signal to obtain a target filtering result corresponding to each output signal.
[0066] This application provides a method and apparatus for filtering output signals of a flow meter. After the output signal filtering application obtains multiple output signals corresponding to a target flow meter, it first determines the current fluid state corresponding to the target flow meter based on the multiple output signals. Then, it determines the target filtering scheme corresponding to the target flow meter based on the current fluid state, that is, it determines the target filtering algorithm, the target filtering algorithm, and the target parameters corresponding to the target filtering algorithm based on the current fluid state. Finally, it filters the multiple output signals corresponding to the target flow meter based on the target filtering algorithm and the target parameters. Specifically, it first configures the target filtering algorithm according to the target parameters, and then filters the multiple output signals corresponding to the target flow meter according to the configured target filtering algorithm, thereby obtaining the target filtering result for each output signal. In this embodiment, the output signal filtering application selects the target filtering algorithm and the target parameters corresponding to the target filtering algorithm based on the current fluid state corresponding to the target flow meter (i.e., the fluid state of the target fluid at the target position in the target pipe at the current moment). Therefore, filtering multiple output signals corresponding to the target flow meter based on the target filtering algorithm and the target parameters can better eliminate the noise caused by the flow state of the target fluid itself, thereby ensuring the accuracy of the filtering results. This application provides a computer device, including a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the flow meter output signal filtering method described above.
[0067] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the flow meter output signal filtering method described above.
[0068] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the flow meter output signal filtering method described above.
[0069] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can 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, etc.) containing computer-usable program code.
[0070] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can 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, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0071] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0072] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0073] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0074] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0075] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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 technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0076] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0077] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can 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, etc.) containing computer-usable program code.
[0078] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A method for filtering the output signal of a flow meter, characterized in that, The method includes: Acquire multiple output signals corresponding to the target flow meter; The current fluid state corresponding to the target flow meter is determined based on the multiple output signals; The target filtering scheme corresponding to the target flow meter is determined based on the current fluid state corresponding to the target flow meter, wherein the target filtering scheme includes a target filtering algorithm and target parameters corresponding to the target filtering algorithm; The target filtering algorithm and the target parameters are used to filter multiple output signals to obtain the target filtering result for each output signal.
2. The method according to claim 1, characterized in that, Determining the current fluid state corresponding to the target flow meter based on the plurality of output signals includes: Calculate the average value corresponding to the multiple output signals; Substitute the multiple output signals, the quantity and average value of the multiple output signals into the first preset formula to calculate the standard deviation of the multiple output signals; When the standard deviation is less than or equal to the first standard deviation threshold, the current fluid state corresponding to the target flow meter is determined to be 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 the second standard deviation threshold, the current fluid state corresponding to the target flow meter is determined to be a moderately turbulent state. When the standard deviation is greater than the second standard deviation threshold, the current fluid state corresponding to the target flow meter is determined to be a state of severe turbulence.
3. The method according to claim 1, characterized in that, Determining the current fluid state corresponding to the target flow meter based on the plurality of output signals includes: Obtain the fluid density, fluid viscosity coefficient, and pipe diameter corresponding to the target flow meter; Substitute the multiple output signals, the fluid density, fluid viscosity coefficient, and pipe diameter corresponding to the target flow meter into the second preset formula to calculate the fluid Reynolds number corresponding to each output signal; Calculate the average fluid Reynolds number corresponding to multiple output signals based on the fluid Reynolds number corresponding to each output signal; When the average fluid Reynolds number is less than or equal to the first fluid Reynolds number threshold, the current fluid state corresponding to the target flow meter is determined to be a steady laminar flow state. When the average fluid Reynolds number is greater than the first fluid Reynolds number threshold and the average fluid Reynolds number is less than or equal to the second fluid Reynolds number threshold, the current fluid state corresponding to the target flow meter is determined to be a moderately turbulent state. When the average fluid Reynolds number is greater than the second fluid Reynolds number threshold, the current fluid state corresponding to the target flow meter is determined to be a state of severe turbulence.
4. The method according to claim 1, characterized in that, Determining the current fluid state corresponding to the target flow meter based on the plurality of output signals includes: Multiple output signals are input into a fluid state detection model to determine the current fluid state corresponding to the target flow meter, wherein the fluid state detection model is used to determine the current fluid state corresponding to the target flow meter based on the multiple output signals.
5. The method according to claim 4, characterized in that, The method further includes: Obtain a training sample set, wherein the training sample set contains multiple training samples, and the training samples contain multiple sample flow meter output signals and fluid states corresponding to the multiple sample flow meter output signals; The deep learning model is trained iteratively through multiple rounds based on the aforementioned training sample set; wherein... In each round of training, it is determined whether the loss function of the deep learning model has converged; If the loss function converges, the deep learning model obtained after this round of training is determined as the fluid state detection model; If the loss function fails to converge, the model parameters of the deep learning model are optimized and adjusted according to the loss function, and the optimized deep learning model is then used to enter the next round of training.
6. The method according to any one of claims 1-5, characterized in that, The step of determining the target filtering scheme corresponding to the target flow meter based on the current fluid state of the target flow meter includes: When the current fluid state corresponding to the target flow meter is a steady laminar flow state, the target filtering algorithm is determined to be the Kalman filtering algorithm, and the target parameter is the first process noise covariance value. When the current fluid state corresponding to the target flow meter is a moderately turbulent state, the target filtering algorithm is determined to be a wavelet filtering algorithm and a Kalman filtering algorithm, and the target parameters are a first wavelet basis, a first decomposition level, a first threshold function, a first threshold selection rule, and a second process noise covariance value. When the current fluid state corresponding to the target flow meter is a state of severe turbulence, the target filtering algorithm is determined to be a wavelet filtering algorithm and a Kalman filtering algorithm, and the target parameters are a second wavelet basis, a second decomposition level, a second threshold function, a second threshold selection rule, and a third process noise covariance value.
7. The method according to claim 6, characterized in that, The step of filtering multiple output signals based on the target filtering algorithm and the target parameters to obtain a target filtering result corresponding to each output signal includes: When the current fluid state corresponding to the target flow meter is a steady laminar flow state, a preset Kalman filter module is invoked based on the first process noise covariance value to filter multiple output signals to obtain the target filtering result corresponding to each output signal. When the current fluid state corresponding to the target flow meter is a moderately turbulent state, a preset wavelet filtering module is invoked based on the first wavelet basis, the first decomposition level, the first threshold function, and the first threshold selection rule to filter multiple output signals, thereby obtaining an intermediate filtering result corresponding to each output signal; and a preset Kalman filtering module is invoked based on the second process noise covariance value to filter the intermediate filtering result corresponding to each output signal, thereby obtaining a target filtering result corresponding to each output signal. When the current fluid state corresponding to the target flow meter is a state of severe turbulence, the preset wavelet filtering module is invoked based on the second wavelet basis, the second decomposition level, the second threshold function, and the second threshold selection rule to filter multiple output signals to obtain an intermediate filtering result corresponding to each output signal; the preset Kalman filtering module is invoked based on the third process noise covariance value to filter the intermediate filtering result corresponding to each output signal to obtain a target filtering result corresponding to each output signal.
8. A flow meter output signal filtering device, characterized in that, The device includes: The acquisition unit is used to acquire multiple output signals corresponding to the target flow meter; The first determining unit is configured to determine the current fluid state corresponding to the target flow meter based on the plurality of output signals; The second determining unit is used to determine the target filtering scheme corresponding to the target flow meter based on the current fluid state corresponding to the target flow meter, wherein the target filtering scheme includes a target filtering algorithm and target parameters corresponding to the target filtering algorithm; A filtering unit is used to filter multiple output signals based on the target filtering algorithm and the target parameters to obtain a target filtering result for each output signal.
9. A computer device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.