A method and device for detecting valve stickiness

Abstract

The present invention relates to a method and device for detecting valve stickiness, including: obtaining target historical data of a preprocessed control loop within a preset time period in the past; processing MV historical data using a valve stickiness model; establishing a process feature model based on PV historical data and the true opening value of the valve, and obtaining an expression for a first parameter and an expression for a second parameter based on the linear process feature model; performing simulation using the expression for the first parameter and the expression for the second parameter to obtain a simulated PV estimated value, establishing an expression for the mean square error between the PV historical data and the PV estimated value, and establishing an objective function with minimizing the mean square error as the optimization objective; solving the objective function to obtain the optimal stickiness parameter; and determining the corresponding target valve stickiness level according to the optimal stickiness parameter. Compared with the prior art, it not only reduces the amount of calculation but also improves the accuracy of valve stickiness detection.

Description

Technical Field

[0001] The present invention relates to the technical field of valve stickiness detection, and particularly to a valve stickiness detection method and device. Background Art

[0002] Valve stickiness is a common fault in process control, which may cause problems such as oscillation of the controlled variable in the process, thereby deteriorating the control performance of the control loop, affecting the smoothness of production and the product quality. Therefore, an appropriate non-invasive method, namely a valve stickiness detection algorithm, can detect the valve stickiness situation from the daily operation data of the control loop, and give an evaluation of the valve stickiness situation in time to help the operator make decisions in time and reduce its impact on the control performance.

[0003] Currently, the prior art detects valve stickiness by means of graphic fitting.

[0004] However, in the actual industrial process, the calculation amount of the graphic fitting method is relatively large and the accuracy is relatively low. Summary of the Invention

[0005] (I) Technical Problems to be Solved

[0006] In view of the above-mentioned disadvantages and deficiencies of the prior art, the present invention provides a valve stickiness detection method and device, which solves the technical problem of relatively low accuracy existing in the prior art.

[0007] (II) Technical Solutions

[0008] In order to achieve the above object, the main technical solutions adopted by the present invention include:

[0009] In a first aspect, an embodiment of the present invention provides a method for detecting valve stickiness, including: obtaining target historical data of a preprocessed control loop within a preset time period in the past; wherein the target historical data includes PV historical data and MV historical data; processing the MV historical data by using a valve stickiness model to obtain a true valve opening value; wherein the true valve opening value is obtained from stickiness parameters, and the stickiness parameters are used to determine the target valve stickiness level; establishing a linear process characteristic model including a first parameter and a second parameter based on the PV historical data and the true valve opening value, and obtaining an expression of the first parameter and an expression of the second parameter based on the linear process characteristic model; wherein the input data of the linear process characteristic model is the true valve opening value, and the output data of the linear process characteristic model is the PV historical data; performing simulation by using the expression of the first parameter and the expression of the second parameter to obtain a simulated PV estimated value, establishing an expression of the mean square error between the PV historical data and the PV estimated value, and establishing an objective function with minimizing the mean square error as the optimization objective; solving the objective function to obtain an optimal stickiness parameter; and determining the corresponding target valve stickiness level according to the optimal stickiness parameter.

[0010] In a possible embodiment, the stickiness parameters include a static friction parameter and a dynamic friction parameter; the calculation expression of the true valve opening value is as follows:

[0011] ;

[0012] In the formula, represents the true valve opening value at the current moment t ; represents the MV historical data at time t; cum_u represents the external applied force acting on the valve and balancing the frictional force at present; represents the static friction parameter; represents the dynamic friction parameter; abs represents the absolute value; represents the previous moment t- 1 of the true valve opening value.

[0013] In a possible embodiment, the expression of the linear process characteristic model is as follows:

[0014] ;

[0015] In the formula, to respectively represent the first PV historical data to the N th PV historical data; to respectively represent the valve true opening values from the first moment to the N- 1 moment; arepresents the first parameter; b represents the second parameter; to respectively represent the 2nd error caused by noise to the N th error caused by noise.

[0016] In a possible embodiment, the expression of the mean square error is as follows:

[0017] ;

[0018] ;

[0019] In the formula, MSE represents the mean square error; represents the estimated value corresponding to ; represents the estimated value corresponding to ; represents the estimated value corresponding to ;

[0020] In a possible embodiment, the objective function is solved to obtain the optimal viscous parameter, including: exploring a rough region in the search space of the viscous parameter using a grid search algorithm; refining the search within the rough region using a Bayesian optimization algorithm to obtain the optimal viscous parameter.

[0021] In a possible embodiment, according to the optimal viscous parameter, the corresponding target valve viscous level is determined, including: calculating a valve viscosity quantization index according to the optimal viscous parameter; determining the target index interval where the valve viscosity quantization index is located, and taking the valve viscous level corresponding to the target index interval as the target valve viscous level.

[0022] Second aspect, an embodiment of the present invention provides a valve stickiness detection device, including: an acquisition module, configured to acquire target historical data of a preprocessed control loop within a preset time period in the past; wherein, the target historical data includes PV historical data and MV historical data; a processing module, configured to process the MV historical data by using a valve stickiness model to obtain a true valve opening value; wherein, the true valve opening value is obtained from stickiness parameters, and the stickiness parameters are used to determine a target valve stickiness level; a building module, configured to build a linear process feature model including a first parameter and a second parameter based on the PV historical data and the true valve opening value, and obtain an expression of the first parameter and an expression of the second parameter based on the linear process feature model; wherein, the input data of the linear process feature model is the true valve opening value, and the output data of the linear process feature model is the PV historical data; a simulation module, configured to perform simulation by using the expression of the first parameter and the expression of the second parameter to obtain a simulated PV estimated value, build an expression of the mean square error between the PV historical data and the PV estimated value, and build an objective function with minimizing the mean square error as an optimization target; a solving module, configured to solve the objective function to obtain an optimal stickiness parameter; a determining module, configured to determine a corresponding target valve stickiness level according to the optimal stickiness parameter.

[0023] In a possible embodiment, the stickiness parameters include a static friction parameter and a dynamic friction parameter; the calculation expression of the true valve opening value is as follows:

[0024] ;

[0025] In the formula, represents the true valve opening value at the current moment t ; represents the MV historical data at time t; cum_u represents the external applied force currently acting on the valve and balancing the frictional force; represents the static friction parameter; represents the dynamic friction parameter; abs represents the absolute value; represents the previous moment t- 1 of the true valve opening value.

[0026] In a possible embodiment, the expression of the linear process feature model is as follows:

[0027] ;

[0028] In the formula, to respectively represent the first PV historical data to the N th PV historical data; to respectively represent the true opening value of the valve from the 1st moment to the N- 1st moment; a represents the first parameter; b represents the second parameter; to respectively represent the 2nd error caused by noise to the N th error caused by noise.

[0029] In a possible embodiment, the expression of the mean square error is as follows:

[0030] ;

[0031] ;

[0032] In the formula, MSE represents the mean square error; represents the estimated value corresponding to ; represents the estimated value corresponding to ; represents the estimated value corresponding to ;

[0033] (III) Beneficial effects

[0034] The beneficial effect of the present invention is:

[0035] The embodiment of the present application provides a valve stickiness detection method and device. By acquiring the target historical data of the preprocessed control loop in the past preset time period, where the target historical data includes PV historical data and MV historical data, and processing the MV historical data by using a valve stickiness model to obtain the true opening value of the valve, where the true opening value of the valve is obtained from the stickiness parameter, and the stickiness parameter is used to determine the target valve stickiness level, and establishing a linear process characteristic model including the first parameter and the second parameter based on the PV historical data and the true opening value of the valve, and obtaining the expressions of the first parameter and the second parameter based on the linear process characteristic model; where the input data of the linear process characteristic model is the true opening value of the valve, the output data of the linear process characteristic model is the PV historical data, and simulating by using the expressions of the first parameter and the second parameter to obtain the simulated PV estimated value, and establishing the expression of the mean square error between the PV historical data and the PV estimated value, and establishing an objective function with the minimum mean square error as the optimization target, and solving the objective function to obtain the optimal stickiness parameter, and determining the corresponding target valve stickiness level according to the optimal stickiness parameter. Compared with the prior art, it not only reduces the calculation amount, but also improves the accuracy of valve stickiness detection.

[0036] In order to make the above-mentioned objectives, features and advantages to be achieved by the embodiments of the present application more obvious and understandable, the following specifically cites preferred embodiments and describes them in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. 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 related drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 A flow chart of a valve sticking detection method provided by an embodiment of the present application is shown;

[0039] Figure 2 A schematic diagram of a valve viscosity model provided in an embodiment of the present application is shown;

[0040] Figure 3 A schematic diagram of a search space provided in an embodiment of the present application is shown;

[0041] Figure 4 A structural block diagram of a valve viscosity detection device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0042] In order to better explain the present invention and facilitate understanding, the present invention is described in detail below through specific implementation modes in conjunction with the accompanying drawings.

[0043] In addition to the graph fitting method, the existing technology can also use neural network algorithms for valve sticking detection. In addition, if a deep neural network algorithm is to be trained, a large amount of labeled data is required for model training. However, in actual industrial processes, obtaining high-quality labeled data is extremely costly and difficult to obtain.

[0044] Based on this, the embodiments of the present application provide a valve stickiness detection method and device. By obtaining the target historical data of the preprocessed control loop in the past preset time period, where the target historical data includes PV historical data and MV historical data, and processing the MV historical data using a valve stickiness model to obtain the true valve opening value, where the true valve opening value is obtained from the stickiness parameter, and the stickiness parameter is used to determine the target valve stickiness level, and establishing a linear process characteristic model including a first parameter and a second parameter based on the PV historical data and the true valve opening value, and obtaining the expressions of the first parameter and the second parameter based on the linear process characteristic model; where the input data of the linear process characteristic model is the true valve opening value, the output data of the linear process characteristic model is the PV historical data, and using the expressions of the first parameter and the second parameter for simulation to obtain the simulated PV estimated value, and establishing the expression of the mean square error between the PV historical data and the PV estimated value, and establishing an objective function with the minimum mean square error as the optimization target, and solving the objective function to obtain the optimal stickiness parameter, and determining the corresponding target valve stickiness level according to the optimal stickiness parameter. Compared with the prior art, it not only reduces the calculation amount but also improves the accuracy of valve stickiness detection.

[0045] To better understand the above technical solution, the exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present invention can be more clearly and thoroughly understood, and the scope of the present invention can be fully conveyed to those skilled in the art.

[0046] To facilitate the understanding of the embodiments of the present application, some terms related to the embodiments of the present application are explained as follows:

[0047] "PV": It is the English abbreviation of Process Variable, and its Chinese name is the measured value;

[0048] "MV": It is the English abbreviation of Manipulated Variable, and its Chinese name is the output value after the controller operation in the automatic case;

[0049] "Quality code": Its English is Tag Quality, and it represents the flag indicating whether the tag number is a good value.

[0050] Please refer to Figure 1 , Figure 1 which shows the flowchart of a valve stickiness detection method provided by the embodiments of the present application. As Figure 1As shown, the valve stickiness detection method can be executed by a valve stickiness detection device, and the specific device of the valve stickiness detection device can be set according to actual needs. For example, the valve stickiness detection device can be a controller or the like. Specifically, the valve stickiness detection method includes:

[0051] Step S110, obtaining target historical data of a preprocessed control loop in a past preset time period. Among them, the target historical data includes PV historical data and MV historical data.

[0052] It should be understood that the specific process of preprocessing can be set according to actual needs, and the embodiments of the present application are not limited thereto.

[0053] Optionally, obtain historical data of the control loop in a past preset time period, and then perform quality checks on the PV historical data and MV historical data of the loop. At the same time, each value in the historical data has a quality code. When the quality code is a good value, it is considered valid data, and the longest segment of data with the quality codes of both the PV historical data and the MV historical data being good values is extracted for processing. Among them, the specific time period of the past preset time period can be set according to actual needs, and the embodiments of the present application are not limited thereto. For example, the past preset time period can be 24 hours or the like.

[0054] In addition, after extraction, this segment of data needs to meet the following conditions: ensure that there is a certain fluctuation (not a straight line) in this segment of data, and the PV value and the MV value are not always constant; the amount of this segment of data is not less than 200 data points.

[0055] It should be noted here that if the above conditions are not met, the valve stickiness of the loop is not detected, that is, the following steps are not performed.

[0056] In addition, for the case where the amount of data is too large (for example, the amount of data is 200 to 10,000, etc.), on the premise of meeting the amount of data, appropriate resampling can be performed to reduce the amount of computation and further improve the computation efficiency.

[0057] In addition, the PV historical data and the MV historical data can be normalized respectively to reduce problems caused by differences in numerical magnitudes. At the same time, the normalization formula is as follows:

[0058] ;

[0059] In the formula, i represents the i th value; x i represents the i th normalized data (for example, the normalized PV historical data or the normalized MV historical data); X iIndicates the i th historical data (e.g., the i th PV historical data or the i th MV historical data); Indicates the mean value of the historical data. For example, in x i When indicating the i th PV historical data, Indicates the mean value of the PV historical data; for another example, in x i When indicating the i th MV historical data, Indicates the mean value of the MV historical data; Indicates the standard deviation of the historical data. For example, in x i When indicating the i th PV historical data, Indicates the standard deviation of the PV historical data; for another example, in x i When indicating the i th MV historical data, Indicates the standard deviation of the MV historical data.

[0060] Step S120, process the MV historical data using the valve hysteresis model to obtain the true valve opening value. Among them, the true valve opening value is obtained from the hysteresis parameter, and the hysteresis parameter is used to determine the target valve hysteresis level.

[0061] Specifically, valve hysteresis means that the output of the valve cannot change smoothly with the change of the signal from the controller. The valve output may remain unchanged or suddenly jump when the controller signal changes. Due to the existence of the hysteresis phenomenon, there is a difference in the valve output between the forward and reverse strokes of the valve. When the valve movement direction changes, due to the existence of dead zone and static friction, the valve output will remain unchanged, and the unchanged range is S, that is, S represents the change amount of the controller signal, and within this change range, the valve output will remain unchanged; when the controller signal is large enough and the valve output suddenly jumps, the jump size is J, that is, J represents the valve jump range when the valve output suddenly jumps. And, considering the normalized static friction and the normalized dynamic friction The parameters have the following relationship:

[0062] S = + ;

[0063] J= - ;

[0064] In the formula, S、 , and J can all be expressed as percentages of the valve range. Also, in this application, process simulation is used to calculate the static friction and dynamic friction magnitudes of the valve, and then to confirm whether there is stickiness and quantify the stickiness index.

[0065] Also, as Figure 2 shown, the processing procedure of this valve stickiness model is as follows:

[0066] Obtain ; where this represents the MV historical data at time t;

[0067] According to , calculate , and the calculation expression of this is as follows: ; In the formula, cum_u represents the external applied force currently acting on the valve and balancing the frictional force, which comes from the control signal thereof; represents the force remaining on the valve without causing valve movement, and at the start of the simulation, it is defaulted that there is no remaining force on the valve and no external applied force, that is, the initial is 0; represents the true opening value of the valve at the previous moment t- 1;

[0068] Judge whether is greater than ; where abs represents the absolute value;

[0069] If it is determined that is greater than , then calculate and through the following formula, specifically:

[0070] ;

[0071] In the formula, represents the true opening value of the valve at the current moment t ; represents the static friction parameter of the valve; represents the dynamic friction parameter of the valve;

[0072] If it is determined that is less than or equal to , then calculate and through the following formula, specifically:

[0073] 。

[0074] That is to say, according to the valve stickiness model and the MV historical data of the control loop (i.e., Figure 2 in ), the true opening value of the valve (i.e., the output of the true position of the valve) can be obtained. Specifically:

[0075] ;

[0076] In the formula, represents the true opening value of the valve at the current moment t ; represents the MV historical data at time t; cum_u represents the external applied force that balances the frictional force acting on the valve at present; represents the static friction parameter; represents the dynamic friction parameter; abs represents the absolute value; represents the previous moment t- 1 of the true opening value of the valve.

[0077] Step S130: Establish a linear process characteristic model including a first parameter and a second parameter based on the PV historical data and the true opening value of the valve, and obtain the expressions of the first parameter and the second parameter based on the linear process characteristic model. Among them, the input data of the linear process characteristic model is the true opening value of the valve, and the output data of the linear process characteristic model is the PV historical data.

[0078] Specifically, the PV historical data (i.e., the actual measured value PV of the process) can be used as the output y of the linear process characteristic model, and the true opening value of the valve after the valve through the stickiness model specified by the valve stickiness algorithm u can be used as the input signal of the linear system. Also, for the convenience of calculation, the linear process characteristic model can adopt a first-order ARX model. Assume that the output of the process y and the input u have the following relationship at t moment (ignoring the influence of time delay). Specifically:

[0079] ;

[0080] Similarly, at other moments, there is:

[0081] ;

[0082] ; ...

[0083] ;

[0084] And the system of equations can be written in matrix form as:

[0085] ;

[0086] In the formula, to respectively represent the 1st PV historical data to the N th PV historical data; to respectively represent the true opening values of the valve at the 1st moment to the N- th 1 moment; a represents the first parameter; b represents the second parameter; to respectively represent the 2nd error caused by noise to the N th error caused by noise, that is to are the errors caused by noise.

[0087] Let , , and , the equation is briefly recorded as: .

[0088] In addition, since the true opening value of the valve is and function of, the expressions of the first parameter a and the second parameter b can be obtained by the least squares method, that is, the expressions of the first parameter a and the second parameter b are both functions related to and .

[0089] Step S140, perform simulation using the expressions of the first parameter and the second parameter, obtain the simulated PV estimated value, establish the expression of the mean square error between the PV historical data and the PV estimated value, and establish the objective function with the minimum mean square error as the optimization goal.

[0090] Specifically, after obtaining the expressions of the first parameter and the second parameter, use the obtained parameters for simulation. At a certain moment t, the simulated estimated output is:

[0091] ;

[0092] In the formula, denotes the estimated value corresponding to ;

[0093] Also, the calculation error of the simulation is:

[0094] ;

[0095] Also, the overall error equation is:

[0096] ;

[0097] Also, the calculated mean square error MSE is:

[0098] ;

[0099] In the formula, MSE denotes the mean square error between the PV historical data and the PV estimated value; n is the length of; denotes the estimated value corresponding to; denotes the estimated value corresponding to; denotes the estimated value corresponding to.

[0100] In addition, the mean square error MSE can be set to the minimum as the optimization objective. Given and are known, can be calculated by the least squares method, and the objective function can be denoted as:

[0101] .

[0102] Step S150, solve the objective function to obtain the optimal viscous parameter.

[0103] Specifically, use the grid search algorithm to explore a rough area within the search space of the viscous parameter; use the Bayesian optimization algorithm to refine the search within the rough area to obtain the optimal viscous parameter.

[0104] For example, the search space can be set as follows:

[0105] First, the valve cannot be completely stationary, so the sum of the dynamic friction and the static friction of the valve is less than the range between the maximum and minimum values of MV S max = MV max - MVmin , + ≤ S max . Among them, and are both greater than or equal to 0.

[0106] Secondly, the static friction is not less than the dynamic friction, that is ≤ .

[0107] Also, according to the above conditions, a search space for the viscous parameter as shown in Figure 3 can be constructed, and the rough area of this search space can be a plane triangle range as shown in Figure 3 . Also, within the search spaces of and , according to the given accuracy, generally 1% can be used to evenly divide the search space into several grid points.

[0108] Subsequently, perform the selection step: After setting the search space, 4 groups of data within the parameter space can be randomly selected for parameter calculation and saved. Based on these data as the initial training data, a Gaussian process model is trained, and the Gaussian process model can adopt a squared exponential kernel, and the hyperparameters of the squared exponential kernel are estimated by maximizing the marginal likelihood function.

[0109] Subsequently, perform the evaluation step: The Gaussian process model and the acquisition function can be used to select new parameter combinations for evaluation, and the next sampling point is obtained and added to the training data. Among them, the expected improvement EI function can be selected as the acquisition function.

[0110] Finally, perform the iterative process: Repeat the selection step and the evaluation step until the maximum number of iterations is reached, stop the optimization, and finally obtain the optimal viscous parameter. Among them, the viscous parameter includes the static friction parameter and the dynamic friction parameter .

[0111] Step S160, determine the corresponding target valve viscous level according to the optimal viscous parameter.

[0112] Optionally, calculate the valve viscosity quantization index according to the optimal viscous parameter; determine the target index interval where the valve viscosity quantization index is located, and use the valve viscous level corresponding to the target index interval as the target valve viscous level. Among them, the specific intervals of each index interval can be set according to actual needs, and the embodiments of this application are not limited thereto.

[0113] For example, when it is determined that the valve has a serious sticking problem, the sticking index should be large, and vice versa, the sticking index is small. And, the formula for quantifying the valve sticking index is as follows:

[0114] ;

[0115] 。

[0116] In the formula, represents the valve stickiness quantization index; represents the stickiness sensitivity index; f represents the total valve friction.

[0117] In addition, when the valve stickiness quantization index is greater than or equal to 0 and less than or equal to 0.3, the valve stickiness level can be judged as none; when the valve stickiness quantization index is greater than 0.3 and less than or equal to 0.5, the valve stickiness level can be judged as weak; when the valve stickiness quantization index is greater than 0.5 and less than or equal to 0.7, the valve stickiness level can be judged as medium; when the valve stickiness quantization index is greater than 0.7 and less than or equal to 1, the valve stickiness level can be judged as strong.

[0118] In summary, by means of the technical solution of the present application, the present application obtains target historical data of the preprocessed control loop in a past preset time period, where the target historical data includes PV historical data and MV historical data, and processes the MV historical data using a valve stickiness model to obtain a true valve opening value, where the true valve opening value is obtained from stickiness parameters, and the stickiness parameters are used to determine the target valve stickiness level, and a linear process characteristic model including a first parameter and a second parameter is established based on the PV historical data and the true valve opening value, and based on the linear process characteristic model, expressions of the first parameter and the second parameter are obtained; wherein, the input data of the linear process characteristic model is the true valve opening value, the output data of the linear process characteristic model is the PV historical data, and simulations are performed using the expressions of the first parameter and the second parameter to obtain a simulated PV estimated value, and an expression of the mean square error between the PV historical data and the PV estimated value is established, and an objective function with the minimum mean square error as the optimization objective is established, and the objective function is solved to obtain the optimal stickiness parameter, and according to the optimal stickiness parameter, the corresponding target valve stickiness level is determined. Compared with the prior art, it not only reduces the calculation amount, but also improves the accuracy of valve stickiness detection.

[0119] It should be understood that the above valve stickiness detection method is only exemplary, and those skilled in the art can make various deformations according to the above method, and the deformed solutions also belong to the protection scope of the present application.

[0120] Please refer to Figure 4 , Figure 4The structure block diagram of a valve sticking detection device 400 provided in an embodiment of the present application is shown. It should be understood that the valve sticking detection device 400 can execute each step in the above method embodiment. The specific functions of the valve sticking detection device 400 can be found in the description above. To avoid repetition, the detailed description is appropriately omitted here. The valve sticking detection device 400 includes at least one software function module that can be stored in a memory in the form of software or firmware or solidified in the operating system (OS) of the valve sticking detection device 400. Specifically, the valve sticking detection device 400 includes:

[0121] The acquisition module 410 is used to acquire the target historical data of the preprocessed control loop in the past preset time period; wherein the target historical data includes PV historical data and MV historical data;

[0122] The processing module 420 is used to process the MV historical data using a valve viscosity model to obtain a valve real opening value; wherein the valve real opening value is obtained by a viscosity parameter, and the viscosity parameter is used to determine a target valve viscosity level;

[0123] Establishing module 430, for establishing a linear process characteristic model including a first parameter and a second parameter based on the PV historical data and the actual valve opening value, and obtaining an expression of the first parameter and an expression of the second parameter based on the linear process characteristic model; wherein the input data of the linear process characteristic model is the actual valve opening value, and the output data of the linear process characteristic model is the PV historical data;

[0124] A simulation module 440 is used to perform simulation using the expression of the first parameter and the expression of the second parameter to obtain a simulated PV estimate, establish an expression of a mean square error between the PV historical data and the PV estimate, and establish an objective function with the minimum mean square error as an optimization target;

[0125] A solution module 450 is used to solve the objective function to obtain the optimal viscosity parameter;

[0126] The determination module 460 is used to determine the corresponding target valve viscosity level according to the optimal viscosity parameter.

[0127] In a possible embodiment, the viscosity parameter includes a static friction parameter and a dynamic friction parameter; the calculation expression of the actual valve opening value is as follows:

[0128] ;

[0129] In the formula, Indicates the current time t The actual valve opening value; Represents the MV historical data at time t; cum_u Represents the external applied force currently acting on the valve and balancing the frictional force; Represents the static friction parameter; Represents the dynamic friction parameter; abs Represents the absolute value; Represents the previous moment t- The true opening value of the valve at 1.

[0130] In a possible embodiment, the expression of the linear process characteristic model is as follows:

[0131] ;

[0132] In the formula, To Respectively represent the 1st PV historical data to the N th PV historical data; To Respectively represent the valve true opening values from the 1st moment to the N- 1st moment; a Represents the first parameter; b Represents the second parameter; To Respectively represent the 2nd error caused by noise to the N th error caused by noise.

[0133] In a possible embodiment, the expression of the mean square error is as follows:

[0134] ;

[0135] ;

[0136] In the formula, MSE Represents the mean square error; Represents the estimated value corresponding to ; Represents the estimated value corresponding to ; Represents the estimated value corresponding to ;

[0137] Since the device described in the above embodiments of the present invention is the device used to implement the method of the above embodiments of the present invention, based on the method described in the above embodiments of the present invention, those skilled in the art can understand the specific structure and variations of the device, so it will not be elaborated here. Any device used in the method of the above embodiments of the present invention belongs to the scope protected by the present invention.

[0138] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0139] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions.

[0140] It should be noted that the words "a" or "an" preceding a component do not exclude the existence of a plurality of such components. The present invention can be implemented by means of hardware including several different components and by means of a properly programmed computer. Among the several devices listed, several of these devices can be embodied by the same hardware. The use of the words first, second, third, etc. is only for the convenience of expression and does not indicate any order. These words can be understood as part of the component name.

[0141] In addition, it should be noted that in the description of this specification, the descriptions of terms such as "an embodiment", "some embodiments", "embodiments", "examples", "specific examples", or "some examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0142] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications after learning the basic creative concepts. Therefore, the technical solutions should be construed as including the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0143] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the technical solution of the present invention and its equivalent technologies, the present invention should also cover these modifications and variations.

Claims

1. A method for detecting valve stickiness, characterized in that Including: Obtain the target historical data of the preprocessed control loop in the past preset time period; wherein, the target historical data includes PV historical data and MV historical data; Process the MV historical data using a valve stiction model to obtain the true valve opening value; wherein, the true valve opening value is obtained from the stiction parameters, and the stiction parameters are used to determine the target valve stiction level; Based on the PV historical data and the true valve opening value, establish a linear process characteristic model including a first parameter and a second parameter, and based on the linear process characteristic model, obtain the expressions of the first parameter and the second parameter; wherein, the input data of the linear process characteristic model is the true valve opening value, and the output data of the linear process characteristic model is the PV historical data; Use the expressions of the first parameter and the second parameter for simulation to obtain a simulated PV estimated value, and establish an expression for the mean square error between the PV historical data and the PV estimated value, and establish an objective function with the minimum mean square error as the optimization goal; Solve the objective function to obtain the optimal stiction parameters; Determine the corresponding target valve stiction level according to the optimal stiction parameters; The stiction parameters include a static friction parameter and a dynamic friction parameter; the calculation expression of the true valve opening value is as follows: ； wherein, represents the true opening value of the valve at the current moment; t of the valve; represents the historical MV data at time t; cum_u represents the external force currently acting on the valve and balancing the frictional force; represents the static friction parameter; represents the dynamic friction parameter; abs represents the absolute value; represents the previous moment t- 1 of the true opening value of the valve; The expression of the linear process characteristic model is as follows: ； Wherein, to respectively represent the 1st PV historical data to the N th PV historical data; to respectively represent the valve true opening values at the 1st moment to the N- th moment; a represents the first parameter; b represents the second parameter; to respectively represent the 2nd error caused by noise to the N th error caused by noise.

2. The valve stickiness detection method according to claim 1, wherein The expression of the mean square error is as follows: ； ； In the formula, MSE represents the mean square error; represents the estimated value corresponding to ; represents the estimated value corresponding to the ; represents the estimated value corresponding to the .

3. The valve stickiness detection method according to claim 1, characterized in that, The solving the objective function to obtain the optimal stiction parameters includes: Use a grid search algorithm to explore a rough area in the search space of the stiction parameters; Use a Bayesian optimization algorithm to refine the search within the rough area to obtain the optimal stiction parameters.

4. The valve stickiness detection method according to claim 1, characterized in that The optimal stiction parameters include an optimal static friction parameter and an optimal dynamic friction parameter; the determining the corresponding target valve stiction level according to the optimal stiction parameters includes: Calculate a valve stiction quantization index according to the optimal stiction parameters; wherein, the calculation expression of the valve stiction quantization index is as follows: ； In the formula, represents the valve viscosity quantization index; represents the viscosity sensitivity index; f represents the total valve friction, and it is the root mean square value of the sum of the square of the optimal static friction parameter and the square of the optimal dynamic friction parameter; Determine the target index interval where the valve stiction quantization index is located, and use the valve stiction level corresponding to the target index interval as the target valve stiction level.

5. A valve stickiness detection device, characterized in that, Including: An acquisition module for acquiring the target historical data of the preprocessed control loop in the past preset time period; wherein, the target historical data includes PV historical data and MV historical data; A processing module for processing the MV historical data using a valve stiction model to obtain the true valve opening value; wherein, the true valve opening value is obtained from the stiction parameters, and the stiction parameters are used to determine the target valve stiction level; A building module, configured to build a linear process feature model including a first parameter and a second parameter based on the PV historical data and the true valve opening value, and obtain an expression of the first parameter and an expression of the second parameter based on the linear process feature model; wherein, the input data of the linear process feature model is the true valve opening value, and the output data of the linear process feature model is the PV historical data; A simulation module, configured to perform simulation by using the expression of the first parameter and the expression of the second parameter, obtain a simulated PV estimated value, build an expression of the mean square error between the PV historical data and the PV estimated value, and build an objective function with the minimum mean square error as the optimization objective; A solving module, configured to solve the objective function to obtain an optimal viscous parameter; A determining module, configured to determine a corresponding target valve viscous level according to the optimal viscous parameter; The viscous parameter includes a static friction parameter and a dynamic friction parameter; the calculation expression of the true valve opening value is as follows: ； In the formula, represents the true opening value of the valve at the current moment; t the MV historical data at time t; represents the external force currently acting on the valve and balancing the frictional force; cum_u the static friction parameter; the dynamic friction parameter; represents the absolute value; abs represents the previous moment the true opening value of the valve at time 1; t- 1 The expression of the linear process feature model is as follows: ； Wherein, to respectively represent the 1st PV historical data to the N th PV historical data; to respectively represent the true opening values of the valve at the 1st moment to the N- th moment; a represents the first parameter; b represents the second parameter; to respectively represent the 2nd error caused by noise to the N th error caused by noise.

6. The valve stickiness detection device according to claim 5, characterized in that, The expression of the mean square error is as follows: ； ； Wherein, MSE represents the mean square error; represents the estimated value corresponding to ; represents the estimated value corresponding to the said ; represents the estimated value corresponding to the said ;

Images