Industrial fluid parameter substitution measurement method

Abstract

The invention provides an industrial fluid parameter substitution measurement method, and relates to the field of industrial production, the industrial fluid parameter substitution measurement method comprises the following steps: constructing a multi-dimensional dynamic matrix database comprising pressure, flow, valve opening, pipeline diameter, medium density, viscosity and temperature parameters; establishing a bidirectional dynamic substitution algorithm of pressure and flow based on parameter correction logic fused by a hydrodynamic equation and experimental data; mode switching when the sensor breaks down is achieved through a three-level fault diagnosis mechanism, and a self-adaptive correction mechanism is adopted to guarantee the measurement precision. The method is high in reliability: the sensor is seamlessly switched to an alternative mode when a fault occurs, and continuous operation of the system is guaranteed; a theoretical model is combined with experimental data, and the error is controlled within 2%; cost saving: redundant sensor configuration is reduced, and hardware and maintenance cost is reduced; the adaptability is high, and dynamic correction of complex working conditions such as medium parameter change and pipeline aging is supported.

Description

Technical Field

[0001] The present application relates to the field of industrial production, and in particular to an alternative measurement method for industrial fluid parameters. Background Art

[0002] In industrial production and fluid delivery systems, accurately measuring the pressure and flow of media is key to ensuring normal system operation and process control. Currently, traditional pressure and flow measurement methods are independent of each other. When a flow meter or pressure gauge is damaged, production often needs to be stopped for equipment replacement and calibration. This not only reduces production efficiency but may also affect product quality and production continuity. In addition, current monitoring and control systems have the following technical defects:

[0003] (1) Pressure and flow parameter monitoring are strongly coupled but are handled in isolation, and a single sensor failure will cause the system to shut down; (2) Traditional redundant design requires the installation of additional backup instruments, increasing hardware costs by 30%-50%; (3) Existing compensation algorithms do not establish a multi-parameter correlation model, and the calibration error exceeds ±5%; (4) Parameter mapping relationships drift under dynamic conditions, and there is a lack of an adaptive correction mechanism. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide an alternative measurement method for industrial fluid parameters, which can solve the above-mentioned technical problems.

[0005] The present invention provides an alternative measurement method for industrial fluid parameters, including:

[0006] Construct a multi-dimensional dynamic matrix database containing pressure, flow, valve opening, pipe diameter, medium density, viscosity and temperature parameters;

[0007] Based on the parameter correction logic of the fusion of fluid mechanics equations and experimental data, a two-way dynamic substitution algorithm for pressure and flow is established;

[0008] A three-level fault diagnosis mechanism is used to achieve mode switching when a sensor fails, and an adaptive correction mechanism is used to ensure measurement accuracy.

[0009] Preferably, the construction of the multi-dimensional dynamic matrix database includes a theoretical model based on the Bernoulli equation and the Darcy-Weisbach formula; combining historical operation data to form a three-dimensional interpolation matrix containing no less than 100,000 groups of data; and using a sliding window algorithm to achieve real-time data updates, with a data survival period of 90 days.

[0010] Preferably, the bidirectional dynamic substitution algorithm includes: flow substitution mode: based on the pressure difference, valve opening, pipe diameter and Reynolds number, the compensation coefficient is optimized through the radial basis function neural network; pressure substitution mode: a bidirectional LSTM network is used to establish a time series correlation model of pressure-flow-valve opening, and the compensation value calculation error is ≤±1.2%.

[0011] Preferably, the three-level fault diagnosis mechanism includes: first-level diagnosis: detecting sensor communication interruption and immediately switching to alternative mode; second-level diagnosis: identifying data anomalies and starting a self-test program; third-level diagnosis: confirming hardware failure and triggering alarm recording.

[0012] Preferably, the adaptive correction mechanism includes: model drift detection: starting the online learning module when the error of 10 consecutive sets of compensation values ​​is greater than 1.5%; incremental learning algorithm: using the RLS algorithm with a forgetting factor λ=0.95 to update the network weights, and the learning rate η=0.01.

[0013] Preferably, the system initialization phase includes: loading a pre-trained RBF neural network model, including 12 hidden layer nodes and a radial basis function width σ=0.8; initializing a dynamic matrix, and loading the latest 72 hours of historical data to construct a basic mapping relationship.

[0014] Preferably, the real-time data collection and verification include: a main control parameter sampling period of 100ms, an auxiliary parameter update period of 500ms; and data verification rules including pressure value mutation threshold detection and flow rationality verification.

[0015] Preferably, the core algorithm of the dynamic substitution calculation includes: flow compensation calculation: based on the pressure difference, pipeline characteristics and fluid physical parameters, the compensation value is predicted through a neural network; pressure compensation calculation: an improved Elman network is used to process time series data, and the network structure is 8-15-2.

[0016] Beneficial effects of the present invention:

[0017] The present invention provides an industrial fluid parameter substitution measurement method, which includes constructing a multidimensional dynamic matrix database containing pressure, flow, valve opening, pipe diameter, medium density, viscosity and temperature parameters; establishing a bidirectional dynamic substitution algorithm for pressure and flow based on parameter correction logic that integrates fluid mechanics equations and experimental data; realizing mode switching when a sensor fails through a three-level fault diagnosis mechanism, and adopting an adaptive correction mechanism to ensure measurement accuracy; the present invention has high reliability: seamless switching to the substitution mode when a sensor fails to ensure continuous operation of the system; improved accuracy: combining theoretical models with experimental data, the error is controlled within 2%; cost savings: reducing redundant sensor configuration, reducing hardware and maintenance costs; strong adaptability: supporting dynamic correction of complex working conditions such as medium parameter changes and pipeline aging. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 Flowchart of the present invention. DETAILED DESCRIPTION

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Generally, the components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0021] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for protection, but merely represents selected embodiments of the present application. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments in the present application without creative work are within the scope of protection of the present application.

[0022] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not require further definition or explanation in subsequent drawings.

[0023] In the description of this application, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, or are the orientations or positional relationships in which the product of this application is typically placed when in use. These terms are intended only to facilitate the description of this application and simplify the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limitations on this application. Furthermore, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0024] Furthermore, terms such as "horizontal," "vertical," and "overhanging" do not necessarily imply that a component must be absolutely horizontal or overhanging, but rather that it can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but rather that it can be slightly tilted.

[0025] It should also be noted that, in the description of this application, unless otherwise expressly specified or limited, the terms "disposed," "installed," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0026] like Figure 1 As shown, an embodiment of the present application provides an industrial fluid parameter replacement measurement method, including constructing a multi-dimensional dynamic matrix database containing pressure, flow, valve opening, pipe diameter, medium density, viscosity and temperature parameters; establishing a bidirectional dynamic replacement algorithm for pressure and flow based on parameter correction logic that integrates fluid mechanics equations and experimental data; realizing mode switching when a sensor fails through a three-level fault diagnosis mechanism, and adopting an adaptive correction mechanism to ensure measurement accuracy.

[0027] In a single-stream medium pipeline, a dynamic matrix database is constructed based on the following parameters: input parameters: PT1 pressure value (P1), PT2 pressure value (P2), flowmeter FT value (Q), valve opening (K), and pipeline diameter (D); output parameters: pressure-flow mapping relationship matrix M (P1, P2, Q, K, D).

[0028] A theoretical model is established based on the fluid mechanics equations (Bernoulli equation, Darcy-Weisbach formula), and correction coefficients are fitted with experimental data to form a multidimensional matrix database covering all working conditions. In order to cover the working conditions more comprehensively, other parameters such as medium density (ρ), viscosity (μ) and temperature (T) can be considered to form a more complex multidimensional matrix.

[0029]

[0030] In this embodiment, the construction of the multidimensional dynamic matrix database includes a theoretical model based on the Bernoulli equation and the Darcy-Weisbach formula; combining historical operation data to form a three-dimensional interpolation matrix containing no less than 100,000 groups of data; and using a sliding window algorithm to achieve real-time data updates, with a data survival period of 90 days.

[0031] In this embodiment, the bidirectional dynamic substitution algorithm includes: flow substitution mode: based on the pressure difference, valve opening, pipe diameter and Reynolds number, the compensation coefficient is optimized through the radial basis function neural network; pressure substitution mode: a bidirectional LSTM network is used to establish a time series correlation model of pressure-flow-valve opening, and the compensation value calculation error is ≤±1.2%.

[0032] Specifically, the basic equation: (Valve Flow Equation)

[0033] Among them C ν is the valve flow coefficient, G is the specific gravity of the medium, ΔP=P1-P2;

[0034] Extended model: Introducing pipeline friction coefficient λ and Reynolds number Re to correct the effect of non-ideal fluid:

[0035] (Darcy's formula + local resistance correction); where A is the pipe cross-sectional area, L is the pipe length, and K is the valve resistance.

[0036] Experimental data fitting, optimize λ and K values ​​through measured data, and generate the revised ΔP-QK relationship matrix.

[0037] 3. Dynamic matrix construction method

[0038] Data collection: within the valve opening range K = 0-100%, collect P1, P2, Q, D data in 5% steps;

[0039] Normalization processing:

[0040] Matrix filling: Main matrix dimensions: K×D×ΔP→Q; radial basis function (RBF) neural network interpolation is used to fill missing data.

[0041] In this embodiment, the three-level fault diagnosis mechanism includes: first-level diagnosis: detecting sensor communication interruption and immediately switching to alternative mode; second-level diagnosis: identifying data anomalies and starting a self-test program; third-level diagnosis: confirming hardware failure and triggering alarm recording.

[0042] In this embodiment, the adaptive correction mechanism includes: model drift detection: when the error of 10 consecutive sets of compensation values ​​is greater than 1.5%, the online learning module is started; incremental learning algorithm: the RLS algorithm with a forgetting factor λ=0.95 is used to update the network weights, and the learning rate η=0.01.

[0043] In this embodiment, the system initialization stage includes: loading a pre-trained RBF neural network model, including 12 hidden layer nodes and a radial basis function width σ=0.8; initializing a dynamic matrix, and loading the latest 72 hours of historical data to construct a basic mapping relationship.

[0044] In this embodiment, the real-time data collection and verification include: the main control parameter sampling period is 100ms, the auxiliary parameter update period is 500ms; the data verification rules include pressure value mutation threshold detection and flow rationality verification.

[0045] In this embodiment, the core algorithm of the dynamic substitution calculation includes: flow compensation calculation: based on the pressure difference, pipeline characteristics and fluid physical parameters, the compensation value is predicted through a neural network; pressure compensation calculation: an improved Elman network is used to process time series data, and the network structure is 8-15-2.

[0046] Specifically, traffic replacement (when FT is damaged): Q comp =fRBF(P1,P2,K,D);

[0047] Pressure replacement (when PT1 / PT2 is damaged):

[0048] Specifically, scenario: PT1 is damaged and P1 needs to be compensated.

[0049] enter:

[0050] P2=0.5MPa,Q=600m 3 / h, K=20%, D=100mm

[0051] ρ=1000kg / m 3 , μ=0.001Pa·s, T=20℃

[0052] step:

[0053] (1) Calculate ΔP:

[0054]

[0055] (2) Compensation P1:

[0056] P1=0.5+0.32=0.82MPa;

[0057] (3) RBF optimization output:

[0058] Result: System output P1 = 0.80 MPa (error < ± 1.5%).

[0059] The above are merely preferred embodiments of the present application and are not intended to limit the present application. Those skilled in the art will readily appreciate that various modifications and variations are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A method for measuring industrial fluid parameters by substitution, characterized in that: include Construct a multi-dimensional dynamic matrix database containing pressure, flow, valve opening, pipe diameter, medium density, viscosity and temperature parameters; Based on the parameter correction logic of the fusion of fluid mechanics equations and experimental data, a two-way dynamic substitution algorithm for pressure and flow is established; A three-level fault diagnosis mechanism is used to achieve mode switching when a sensor fails, and an adaptive correction mechanism is used to ensure measurement accuracy.

2. The industrial fluid parameter substitution measurement method according to claim 1, characterized in that: The construction of the multi-dimensional dynamic matrix database includes a theoretical model based on the Bernoulli equation and the Darcy-Weisbach formula; combining historical operating data to form a three-dimensional interpolation matrix containing no less than 100,000 groups of data; and using a sliding window algorithm to achieve real-time data updates, with a data survival period of 90 days.

3. The industrial fluid parameter substitution measurement method according to claim 1, characterized in that: The bidirectional dynamic substitution algorithm includes: flow substitution mode: based on the pressure difference, valve opening, pipe diameter and Reynolds number, the compensation coefficient is optimized through the radial basis function neural network; pressure substitution mode: a bidirectional LSTM network is used to establish a time series association model of pressure-flow-valve opening, and the compensation value calculation error is ≤±1.2%.

4. The industrial fluid parameter substitution measurement method according to claim 1, characterized in that: The three-level fault diagnosis mechanism includes: first-level diagnosis: detecting sensor communication interruption and immediately switching to alternative mode; second-level diagnosis: identifying data anomalies and starting a self-test program; third-level diagnosis: confirming hardware failure and triggering alarm recording.

5. The industrial fluid parameter substitution measurement method according to claim 1, characterized in that: The adaptive correction mechanism includes: model drift detection: when the error of 10 consecutive compensation value groups is greater than 1.5%, the online learning module is started; incremental learning algorithm: the RLS algorithm with a forgetting factor λ=0.95 is used to update the network weights, and the learning rate η=0.

01.

6. The industrial fluid parameter substitution measurement method according to claim 1, characterized in that: The system initialization phase includes: loading a pre-trained RBF neural network model, including 12 hidden layer nodes and a radial basis function width σ=0.8; initializing a dynamic matrix, and loading the latest 72 hours of historical data to construct a basic mapping relationship.

7. The industrial fluid parameter substitution measurement method according to claim 1, characterized in that: The real-time data acquisition and verification include: the main control parameter sampling period is 100ms, the auxiliary parameter update period is 500ms; the data verification rules include pressure value mutation threshold detection and flow rationality verification.

8. The industrial fluid parameter substitution measurement method according to claim 1, characterized in that: The core algorithm of the dynamic substitution calculation includes: flow compensation calculation: based on the pressure difference, pipeline characteristics and fluid physical parameters, the compensation value is predicted through a neural network; pressure compensation calculation: an improved Elman network is used to process time series data, and the network structure is 8-15-2.

Images