Steam discharge control method based on pilot valve adjustment

Abstract

The invention discloses a steam discharge control method based on pilot valve adjustment, and particularly relates to the technical field of steam discharge, which comprises the following steps: determining the actual pressure and expected pressure of a main valve and the set pressure of a pilot valve, and comparing the relationship between the actual pressure of the main valve and the expected pressure of the main valve to obtain the set pressure of the pilot valve. The hysteresis between the actual pressure and the expected pressure of the main valve in the time delay information is determined, a delay transfer function model of the steam system PID controller in the monitoring time period is obtained, a delay factor of the delay transfer function model is obtained, and the response delay of the steam system in the time delay information is determined; the ARMA model is used for modeling the time sequence data of the actual pressure, the change trend of the actual pressure of the main valve in the pressure change information is determined, the potential risk of the steam system is judged, it can be ensured that the system keeps stable operation in various change environments, and excessive adjustment or control failure of the pilot valve is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of steam emission, and more particularly to a steam emission control method based on pilot valve regulation. Background Art

[0002] Existing technologies usually use advanced control technologies such as PID control or model predictive control (MPC). Especially when the steam demand varies greatly, these methods can enable the pilot valve to control the pressure of the steam system more stably. However, in actual applications, the steam system faces many challenges due to factors such as steam demand fluctuations, control system lags, and sensor response delays. Especially when the demand fluctuates greatly, it is often difficult to detect potential risks in a timely manner, which may lead to system failure or instability.

[0003] In order to solve the above two defects, a technical solution is now provided. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a steam emission control method based on pilot valve regulation to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A steam emission control method based on pilot valve regulation specifically comprises the following steps:

[0007] S1: Collect data from various pressure sensors in the steam system to determine the actual pressure of the main valve, the expected pressure, and the set pressure of the pilot valve, and determine the hysteresis between the actual pressure of the main valve and the expected pressure in the time delay information by comparing the relationship between the actual pressure of the main valve and the expected pressure of the main valve;

[0008] S2: a delay transfer function model of the steam system PID controller in the monitoring time period, obtaining a delay factor of the delay transfer function model, and determining the response delay of the steam system in the time delay information;

[0009] S3: Modeling the time series data of actual pressure by using the ARMA model, predicting and analyzing the change trend of actual pressure, and determining the change trend of the actual pressure of the main valve in the pressure change information;

[0010] S4: Through comprehensive analysis of time delay information and pressure change information, an early warning assessment model is constructed to determine the potential risks of the steam system and adjust the set pressure of the pilot valve according to the size of the potential risks.

[0011] In a preferred embodiment, comparing the relationship between the actual pressure of the main valve and the expected pressure of the main valve includes:

[0012] According to the pressure sensor in the steam pipeline, determine the actual pressure of the main valve, and mark the actual pressure of the main valve during the monitoring period as: SJ n , where n = 1, 2, 3, ..., N, N is a positive integer, and n is the number of the actual pressure collected during the monitoring period;

[0013] Obtain the expected pressure of the main valve and mark the expected pressure of the main valve as: QW n ;

[0014] The relationship between the actual pressure and the expected pressure of the main valve is analyzed by the cross-correlation function, and the cross-correlation coefficient between the actual pressure and the expected pressure of the main valve is determined. The calculation formula is: Among them, XG τ It is the correlation coefficient between the actual pressure and the expected pressure of the main valve, τ is the lag time, and τ is a positive integer.

[0015] In a preferred embodiment, determining the hysteresis between the actual pressure of the main valve and the expected pressure in the time delay information includes:

[0016] The hysteresis between the actual pressure of the main valve and the expected pressure in the time delay information is expressed by the correlation coefficient;

[0017] Set the mutual correlation coefficient threshold and the lag time threshold, compare the mutual correlation coefficient threshold with the mutual correlation coefficients at different lag times within the lag time threshold, obtain the mutual correlation coefficients at different lag times greater than the mutual correlation coefficient threshold within the lag time threshold, and re-mark the mutual correlation coefficients at different lag times greater than the mutual correlation coefficient threshold within the lag time threshold as: XG i , where i=1, 2, 3, ..., I, I is a positive integer, and i is the number of the cross-correlation coefficient at different lag times greater than the cross-correlation coefficient threshold;

[0018] Calculate the correlation coefficient using the formula: Among them, LX xg is the correlation coefficient, XG yz is the cross-correlation coefficient threshold.

[0019] In a preferred embodiment, determining the response delay of the steam system in the time delay information includes:

[0020] The response delay of the steam system in the time delay information is represented by the response delay coefficient;

[0021] Determine the delay transfer function model of the steam system PID controller within the monitoring period, and obtain the delay factor of the delay transfer function model. The delay transfer function model is expressed as: Among them, G(s) is the delay transfer function model, γ1, γ2, γ3, ..., γw are high-order terms, is the delay factor;

[0022] The delay time of the delay transfer function model in the monitoring time period is marked as: χm, m=1, 2, 3, ..., M, M is a positive integer, and m is the number of the delay time of the delay transfer function model of the PID controller collected at different times in the monitoring time period;

[0023] Determine the average value and standard deviation of the delay time of the delay transfer function model, and mark the average value and standard deviation of the delay time of the delay transfer function model as: χavg and χstd, where,

[0024] Calculate the response delay coefficient using the following formula: Among them, XY yc is the response delay coefficient.

[0025] In a preferred embodiment, determining the change trend of the actual pressure of the main valve in the pressure change information includes:

[0026] The change trend of the actual pressure of the main valve in the pressure change information is represented by the pressure time series deviation coefficient;

[0027] The time series of actual pressure collected in the last monitoring period is used as the training set, and the ARMA model is trained to determine the order P and Q of the ARMA model. The expression of the trained ARMA model is: Among them, a is a constant term, LSJ r is the actual pressure in the last monitoring period, r=1, 2, 3, …, R, R is a positive integer, p=1, 2, 3, …, P, p is the number of the order P of the ARMA model, q=1, 2, 3, …, Q, q is the number of the order Q of the ARMA model, φ p is the coefficient of the MA part in the ARMA model, θ q is the coefficient of the AR part in the ARMA model, ε r is the white noise term;

[0028] The trained ARMA model is obtained, and the actual pressure in the current detection time period is predicted by the trained ARMA model. The expression for predicting the actual pressure in the current monitoring time period is: Among them, YC R+n To predict the actual pressure of the nth collection in the current time period, YC R+np is the known observation value of the time series data, ε R +nq is the prediction error of time series data;

[0029] The actual pressure predicted during the current monitoring period is marked as: YC n , by calculating and predicting the residual between the actual pressure in the current monitoring period and the actual pressure of the main valve in the actual monitoring period, the pressure time series deviation coefficient is determined. The calculation formula is: Among them, PC yl is the deviation coefficient of the pressure time series.

[0030] In a preferred embodiment, constructing an early warning assessment model includes:

[0031] Through comprehensive analysis of time delay information and pressure change information, the correlation coefficient, response delay coefficient and pressure time series deviation coefficient are weighted and calculated to build an early warning evaluation model and generate an early warning evaluation coefficient. The calculation formula of the early warning evaluation coefficient is: Among them, pg yj is the early warning assessment coefficient, α1, α2, and α3 are the proportional coefficients of the correlation coefficient, the response delay coefficient, and the pressure time series deviation coefficient, respectively. α1, α2, and α3 are all greater than 0.

[0032] In a preferred embodiment, determining the potential risk of the steam system includes:

[0033] Set the warning assessment coefficient threshold, compare the warning assessment coefficient within the monitoring period with the warning assessment coefficient threshold, if the warning assessment coefficient is greater than the warning assessment coefficient threshold, generate a warning signal, if the warning assessment coefficient is less than the warning assessment coefficient threshold, no signal is generated.

[0034] Technical effects and advantages of the present invention:

[0035] The present invention collects data from various pressure sensors in the steam system, analyzes the relationship between the actual pressure of the main valve and the expected pressure, and then obtains time delay information and hysteresis; combines the delay transfer function model of the PID controller to quantify the response delay of the steam system; uses the ARMA model to model the time series of the actual pressure and predicts the pressure change trend. Finally, through comprehensive analysis of the time delay information and the pressure change information, an early warning evaluation model is constructed to timely evaluate the potential risks of the system, adjust the set pressure of the pilot valve according to the risk level, and ensure that the main valve pressure is stable within the target range. The present invention helps to ensure that the system maintains stable operation under various changing environments and avoids excessive adjustment or control failure of the pilot valve. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0037] Figure 1 The figure is a flow chart of a steam emission control method based on pilot valve regulation according to the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] Example 1

[0040] Figure 1 The present invention is a flow chart of a steam emission control method based on pilot valve regulation, which specifically includes the following steps:

[0041] S1: Collect data from various pressure sensors in the steam system to determine the actual pressure of the main valve, the expected pressure, and the set pressure of the pilot valve, and determine the hysteresis between the actual pressure of the main valve and the expected pressure in the time delay information by comparing the relationship between the actual pressure of the main valve and the expected pressure of the main valve;

[0042] S2: a delay transfer function model of the steam system PID controller in the monitoring time period, obtaining a delay factor of the delay transfer function model, and determining the response delay of the steam system in the time delay information;

[0043] S3: Modeling the time series data of actual pressure by using the ARMA model, predicting and analyzing the change trend of actual pressure, and determining the change trend of the actual pressure of the main valve in the pressure change information;

[0044] S4: Through comprehensive analysis of time delay information and pressure change information, an early warning assessment model is constructed to determine the potential risks of the steam system and adjust the set pressure of the pilot valve according to the size of the potential risks.

[0045] By using a pilot valve to control the pressure and flow of the steam system, the stability and reliability of the system can be ensured, and excessive or low pressure can be avoided to threaten the safety of equipment and systems. In the steam system, the main function of the pilot valve is to adjust the opening of the main valve according to the set pressure. The set pressure of the pilot valve will affect the actual pressure of the main valve. By adjusting the pressure of the pilot valve, the opening degree of the main valve can be controlled, thereby indirectly controlling the steam flow and system pressure.

[0046] In the steam system, the set pressure of the pilot valve, the actual pressure of the main valve and the expected pressure of the main valve are closely related control parameters, ensuring that the system can adjust the steam flow according to demand while maintaining the stability of the system pressure. Among them, the set pressure of the pilot valve is used to adjust the pressure control point of the main valve. It is dynamically adjusted according to the error between the actual pressure of the main valve and the expected pressure of the main valve. When the actual pressure of the system is lower than the expected set pressure, the set pressure of the pilot valve will increase to prompt the main valve to open and allow more steam flow; when the actual pressure exceeds the expected pressure, the set pressure will decrease, thereby reducing the steam flow;

[0047] The actual pressure of the main valve refers to the pressure in the system measured by multiple pressure sensors. It is affected by many factors such as pipeline resistance, steam flow, equipment status, etc. The actual pressure of the main valve is continuously monitored and compared with the expected pressure to calculate the error. If the error is large, the control system will adjust the opening of the main valve by adjusting the set pressure of the pilot valve, thereby adjusting the actual pressure to be close to the expected value.

[0048] The expected pressure of the main valve is the pressure value under ideal conditions, which is usually set by the control system according to load demand, process requirements or safety standards. The actual pressure is driven close to the expected value by adjusting the set pressure of the pilot valve.

[0049] In the steam system, the PID controller and MPC (model predictive control) are used to meet the response of large changes in steam demand and improve the performance of the steam system. The PID controller adjusts the pilot valve by measuring the error between the actual pressure and the expected pressure of the main valve, and predicts the changes in steam demand and pressure by using MPC, and makes adjustments in advance according to the predicted results;

[0050] MPC sets the expected pressure for the main valve in advance by predicting demand changes and system dynamics in the future. MPC can better match the steam demand. The PID controller adjusts the control pilot valve according to the error between the expected pressure of the main valve and the actual pressure of the main valve.

[0051] It should be noted that MPC is usually used to deal with system dynamics with regularity or known trends, so it is very suitable for predicting and controlling those regular demand changes. For situations with large demand fluctuations, MPC may find it difficult to accurately predict the future state of the system, resulting in large control errors.

[0052] A monitoring period is set to monitor the actual situation of steam demand to avoid overshoot or oscillation caused by sudden changes in demand. The time delay information and pressure change information of the steam system are collected during the monitoring period. The lag between the actual pressure of the main valve and the expected pressure in the time delay information is expressed by the correlation coefficient, the response delay of the steam system in the time delay information is expressed by the response delay coefficient, and the change trend of the actual pressure of the main valve in the pressure change information is expressed by the pressure time series deviation coefficient.

[0053] It should be noted that the monitoring time period is a specific time period and is set by the staff based on actual conditions.

[0054] The correlation coefficient is used to analyze the relationship between the actual pressure and the expected pressure of the main valve. The advantages of the correlation coefficient include:

[0055] The correlation coefficient can be used to detect the changing relationship between the actual pressure and the expected pressure of the main valve within a period of time, and determine whether the system exhibits atypical and irregular behavior;

[0056] Ability to judge the effectiveness of control algorithms such as PID or MPC in regulating the current steam system, and whether the control algorithm can enhance the stability of the control system;

[0057] According to the results of the autocorrelation anomaly system, it is possible to determine whether the current fluctuation is a change within the normal range, and then decide whether the control strategy needs to be adjusted to prevent the system from over-adjusting, thereby reducing the oscillation caused by lag, over-adjustment, etc. by adjusting the parameters of the control algorithm.

[0058] The logic for obtaining the correlation coefficient is as follows: according to the pressure sensor in the steam pipeline, the actual pressure of the main valve is determined, and the actual pressure of the main valve during the monitoring period is marked as: SJ n , where n = 1, 2, 3, ..., N, N is a positive integer, and n is the number of the actual pressure collected during the monitoring period;

[0059] Obtain the expected pressure of the main valve and mark the expected pressure of the main valve as: QW n ;

[0060] It should be noted that the expected pressure of the main valve is a continuous dynamic adjustment process. The expected pressure of the main valve is determined by MPC and actual conditions. Usually, as the steam demand increases, the expected pressure of the main valve increases, and as the steam demand decreases, the expected pressure of the main valve decreases.

[0061] The relationship between the actual pressure and the expected pressure of the main valve is analyzed by the cross-correlation function, and the cross-correlation coefficient between the actual pressure and the expected pressure of the main valve is determined. The calculation formula is: Among them, XG τis the correlation coefficient between the actual pressure and the expected pressure of the main valve, τ is the lag time, and τ is a positive integer;

[0062] Set the mutual correlation coefficient threshold and the lag time threshold, compare the mutual correlation coefficient threshold with the mutual correlation coefficients at different lag times within the lag time threshold, obtain the mutual correlation coefficients at different lag times greater than the mutual correlation coefficient threshold within the lag time threshold, and re-mark the mutual correlation coefficients at different lag times greater than the mutual correlation coefficient threshold within the lag time threshold as: XG i , where i=1, 2, 3, ..., I, I is a positive integer, and i is the number of the cross-correlation coefficient at different lag times greater than the cross-correlation coefficient threshold;

[0063] It should be noted that the correlation coefficient threshold and the lag time threshold are set by professional staff. The correlation coefficient threshold is used to determine that there is a strong correlation between the expected pressure and the actual pressure of the main valve. The lag time threshold is the lag of the system response time, which usually reflects the lag of the steam system in changing the actual pressure according to the expected pressure. The lag time threshold is usually a smaller value to ensure the timely response speed of the steam system.

[0064] Calculate the correlation coefficient using the formula: Among them, LX xg is the correlation coefficient, XG yz is the cross-correlation coefficient threshold.

[0065] It can be seen from the formula that the larger the correlation coefficient is, the more relevant the relationship between the actual pressure and the expected pressure of the main valve is, which means that the pilot valve has better control over the main valve, the current demand changes may be more regular, and the system can adapt to changes in steam demand.

[0066] The delay transfer function model of the steam system is determined by the PID controller of the steam system during the monitoring period, and the delay factor of the delay transfer function model is obtained. The response delay coefficient is determined by calculating the volatility of the delay factor. The advantages of the response delay coefficient include:

[0067] Although other parameters (such as pressure, flow, temperature, etc.) can provide information about the current state of the system, they may not fully capture the delay characteristics of the system in responding to changes in demand. The response delay coefficient directly reflects the hysteresis effect of the system and its fluctuations, and therefore can more accurately reveal the stability of the system;

[0068] Hysteresis usually causes controller (such as PID controller) response delay, which in turn causes large errors or control instability. By analyzing the response delay coefficient, the hysteresis of the system when facing changes in external demand can be effectively identified.

[0069] The response delay coefficient provides feedback basis for the adjustment of PID controller or MPC controller, and can help identify the delay model of the system and optimize the transfer function and control strategy.

[0070] The acquisition logic of the response delay coefficient is: determine the delay transfer function model of the steam system PID controller within the monitoring time period, obtain the delay factor of the delay transfer function model, and the delay transfer function model is expressed as: Among them, G(s) is the delay transfer function model, γ1, γ2, γ3, ..., γw are high-order terms, is the delay factor;

[0071] The delay time of the delay transfer function model in the monitoring time period is marked as: χm, m=1, 2, 3, ..., M, M is a positive integer, and m is the number of the delay time of the delay transfer function model of the PID controller collected at different times in the monitoring time period;

[0072] Determine the average value and standard deviation of the delay time of the delay transfer function model, and mark the average value and standard deviation of the delay time of the delay transfer function model as: χavg and χstd, where,

[0073] It should be noted that the delay transfer function model of the steam system's PID controller during the monitoring period will continue to change with the changes in steam demand, so the delay factor will also change with time and demand changes. This change reflects the lag characteristics of the control process when the system responds to different changes in steam demand.

[0074] Calculate the response delay coefficient using the following formula: Among them, XY yc is the response delay coefficient.

[0075] It can be seen from the formula that the larger the response delay coefficient, the more significant the difference in response speed at different time points within the monitoring period, which may lead to frequent over- and under-adjustment, inaccurate control signals, and thus affect the performance of the equipment, indicating that the mismatch between steam supply and demand may be higher.

[0076] The ARMA model is used to model the time series data of actual pressure, predict and analyze the changing trend of actual pressure. By training an ARMA model based on actual pressure, the deviation and error between the model and actual pressure are identified, and the pressure time series deviation coefficient is obtained. The advantages of the pressure time series deviation coefficient include:

[0077] The ARMA model can capture the autoregressive (AR) and moving average (MA) characteristics in time series data, thereby accurately describing the historical behavior and potential patterns of the system. This makes it possible to predict the actual pressure based on historical data and optimize the control strategy.

[0078] The ARMA model can capture long-term dependencies and short-term fluctuations in time series data. It is particularly suitable for data with time correlation (such as periodic fluctuations, trends, etc.) and can more accurately reflect the dynamic characteristics of the steam system.

[0079] The ARMA model provides the ability to predict the future behavior of actual pressure, which is especially important for advanced control strategies such as MPC. By combining the ARMA model with PID control, the system response can be predicted and adjusted more accurately, improving control accuracy and response speed.

[0080] The logic for obtaining the pressure time series deviation coefficient is as follows: using the actual pressure time series collected in the previous monitoring period as a training set, training is performed through the ARMA model, and the orders P and Q of the ARMA model are determined. The expression of the trained ARMA model is obtained as follows: Among them, a is a constant term, LSJ r is the actual pressure in the last monitoring period, r=1, 2, 3, …, R, R is a positive integer, p=1, 2, 3, …, P, p is the number of the order P of the ARMA model, q=1, 2, 3, …, Q, q is the number of the order Q of the ARMA model, φ p is the coefficient of the MA part in the ARMA model, θ q is the coefficient of the AR part in the ARMA model, ε r is the white noise term;

[0081] The trained ARMA model is obtained, and the actual pressure in the current detection time period is predicted by the trained ARMA model. The expression for predicting the actual pressure in the current monitoring time period is: Among them, YC R+n To predict the actual pressure of the nth collection in the current time period, YC R+ np is the known observation value of the time series data, ε R+ nq is the prediction error of time series data;

[0082] The actual pressure predicted during the current monitoring period is marked as: YC n , by calculating and predicting the residual between the actual pressure in the current monitoring period and the actual pressure of the main valve in the actual monitoring period, the pressure time series deviation coefficient is determined. The calculation formula is: Among them, PC yl is the deviation coefficient of the pressure time series.

[0083] It can be seen from the formula that the larger the pressure time series deviation coefficient is, the more likely it is that the steam demand may fluctuate significantly and the model may not be able to respond in time. This may mean that the system's feedback mechanism does not adjust the pilot valve or main valve pressure in a timely or accurate manner, resulting in the steam system being unable to respond quickly to changing demand or external disturbances.

[0084] Through comprehensive analysis of time delay information and pressure change information, the correlation coefficient, response delay coefficient and pressure time series deviation coefficient are weighted and calculated to build an early warning evaluation model and generate an early warning evaluation coefficient. The calculation formula of the early warning evaluation coefficient is: Among them, pg yj is the early warning assessment coefficient, α1, α2, and α3 are the proportional coefficients of the correlation coefficient, the response delay coefficient, and the pressure time series deviation coefficient, respectively. α1, α2, and α3 are all greater than 0.

[0085] Set the early warning assessment coefficient threshold, and compare the early warning assessment coefficient within the monitoring time period with the early warning assessment coefficient threshold. If the early warning assessment coefficient is greater than the early warning assessment coefficient threshold, a warning signal is generated, and the staff adjusts the set pressure of the pilot valve to ensure that the main valve pressure can be stabilized within the target range. If the early warning assessment coefficient is less than the early warning assessment coefficient threshold, no signal is generated, indicating that the steam system can meet the response to large changes in steam demand by using PID controller and MPC (model predictive control).

[0086] The present invention collects data from various pressure sensors in the steam system, analyzes the relationship between the actual pressure of the main valve and the expected pressure, and then obtains time delay information and hysteresis; combines the delay transfer function model of the PID controller to quantify the response delay of the steam system; uses the ARMA model to model the time series of the actual pressure and predicts the pressure change trend. Finally, through comprehensive analysis of the time delay information and the pressure change information, an early warning evaluation model is constructed to timely evaluate the potential risks of the system, adjust the set pressure of the pilot valve according to the risk level, and ensure that the main valve pressure is stable within the target range. The present invention helps to ensure that the system maintains stable operation under various changing environments and avoids excessive adjustment or control failure of the pilot valve.

[0087] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0088] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0089] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0090] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0091] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0092] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0093] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0094] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A steam emission control method based on pilot valve regulation, characterized in that: The specific steps include: S1: Collect data from various pressure sensors in the steam system to determine the actual pressure of the main valve, the expected pressure, and the set pressure of the pilot valve, and determine the hysteresis between the actual pressure of the main valve and the expected pressure in the time delay information by comparing the relationship between the actual pressure of the main valve and the expected pressure of the main valve; S2: a delay transfer function model of the steam system PID controller within the monitoring time period, obtaining a delay factor of the delay transfer function model, and determining the response delay of the steam system in the time delay information; S3: Modeling the time series data of actual pressure by using the ARMA model, predicting and analyzing the change trend of actual pressure, and determining the change trend of the actual pressure of the main valve in the pressure change information; S4: Through comprehensive analysis of time delay information and pressure change information, an early warning assessment model is constructed to determine the potential risks of the steam system and adjust the set pressure of the pilot valve according to the size of the potential risks.

2. A steam emission control method based on pilot valve regulation according to claim 1, characterized in that: Compare the actual pressure of the main valve with the expected pressure of the main valve, including: According to the pressure sensor in the steam pipeline, determine the actual pressure of the main valve, and mark the actual pressure of the main valve during the monitoring period as: SJ n , where n = 1, 2, 3, ..., N, N is a positive integer, and n is the number of the actual pressure collected during the monitoring period; Obtain the expected pressure of the main valve and mark the expected pressure of the main valve as: QW n ; The relationship between the actual pressure and the expected pressure of the main valve is analyzed by the cross-correlation function, and the cross-correlation coefficient between the actual pressure and the expected pressure of the main valve is determined. The calculation formula is: Among them, XG τ It is the correlation coefficient between the actual pressure and the expected pressure of the main valve, τ is the lag time, and τ is a positive integer.

3. A steam emission control method based on pilot valve regulation according to claim 2, characterized in that: Determine the hysteresis between the actual pressure and the expected pressure of the main valve in the time delay information, including: The hysteresis between the actual pressure of the main valve and the expected pressure in the time delay information is expressed by the correlation coefficient; Set the mutual correlation coefficient threshold and the lag time threshold, compare the mutual correlation coefficient threshold with the mutual correlation coefficients at different lag times within the lag time threshold, obtain the mutual correlation coefficients at different lag times greater than the mutual correlation coefficient threshold within the lag time threshold, and re-mark the mutual correlation coefficients at different lag times greater than the mutual correlation coefficient threshold within the lag time threshold as: XG i , where i=1, 2, 3, ..., I, I is a positive integer, and i is the number of the cross-correlation coefficient at different lag times greater than the cross-correlation coefficient threshold; Calculate the correlation coefficient using the formula: Among them, LX xg is the correlation coefficient, XG yz is the cross-correlation coefficient threshold.

4. A steam emission control method based on pilot valve regulation according to claim 3, characterized in that: Determine the response delay of the steam system in the time delay information, including: The response delay of the steam system in the time delay information is represented by the response delay coefficient; Determine the delay transfer function model of the steam system PID controller within the monitoring period, and obtain the delay factor of the delay transfer function model. The delay transfer function model is expressed as: Where G(s) is the delay transfer function model, γ1, γ2, γ3, ..., γ w is a high-order term, e -χs is the delay factor; The delay time of the delay transfer function model during the monitoring period is marked as: m , m=1, 2, 3, ..., M, M is a positive integer, and m is the number of the delay time of the PID controller delay transfer function model collected at different times within the monitoring time period; Determine the mean and standard deviation of the delay time of the delay transfer function model and label the mean and standard deviation of the delay time of the delay transfer function model as: χ avg and χ std ,in, Calculate the response delay coefficient using the following formula: Among them, XY yc is the response delay coefficient.

5. A steam emission control method based on pilot valve regulation according to claim 4, characterized in that: Determine the change trend of the actual pressure of the main valve in the pressure change information, including: The change trend of the actual pressure of the main valve in the pressure change information is represented by the pressure time series deviation coefficient; The time series of actual pressure collected in the last monitoring period is used as the training set, and the ARMA model is trained to determine the order P and Q of the ARMA model. The expression of the trained ARMA model is: Among them, a is a constant term, LSJ r is the actual pressure in the last monitoring period, r=1, 2, 3, …, R, R is a positive integer, p=1, 2, 3, …, P, p is the number of the order P of the ARMA model, q=1, 2, 3, …, Q, q is the number of the order Q of the ARMA model, φ p is the coefficient of the MA part in the ARMA model, θ q is the coefficient of the AR part in the ARMA model, ε r is the white noise term; The trained ARMA model is obtained, and the actual pressure in the current detection time period is predicted by the trained ARMA model. The expression for predicting the actual pressure in the current monitoring time period is: Among them, YC R+n To predict the actual pressure of the nth collection in the current time period, YC R+n-p is the known observation value of the time series data, ε R+n-q is the prediction error of time series data; The actual pressure predicted during the current monitoring period is marked as: YC n , by calculating and predicting the residual between the actual pressure in the current monitoring period and the actual pressure of the main valve in the actual monitoring period, the pressure time series deviation coefficient is determined. The calculation formula is: Among them, PC yl is the deviation coefficient of the pressure time series.

6. A steam emission control method based on pilot valve regulation according to claim 5, characterized in that: Construct an early warning assessment model, including: Through comprehensive analysis of time delay information and pressure change information, the correlation coefficient, response delay coefficient and pressure time series deviation coefficient are weighted and calculated to build an early warning evaluation model and generate an early warning evaluation coefficient. The calculation formula of the early warning evaluation coefficient is: Among them, pg yj is the early warning assessment coefficient, α1, α2, and α3 are the proportional coefficients of the correlation coefficient, the response delay coefficient, and the pressure time series deviation coefficient, respectively. α1, α2, and α3 are all greater than 0.

7. A steam emission control method based on pilot valve regulation according to claim 6, characterized in that: Determine potential risks to the steam system, including; Set the warning assessment coefficient threshold, compare the warning assessment coefficient within the monitoring period with the warning assessment coefficient threshold, if the warning assessment coefficient is greater than the warning assessment coefficient threshold, generate a warning signal, if the warning assessment coefficient is less than the warning assessment coefficient threshold, no signal is generated.

Images