An anti-surge control method for a compressor train

Abstract

The application discloses a kind of anti-surge control methods for compressor unit, specifically relates to the field of compressor unit operation control, the application is deployed pressure, flow, temperature and other various sensor terminals in the installation and commissioning phase of compressor unit, real-time acquisition inlet pressure, flow, exhaust pressure and other working parameters, after acquisition, data is preprocessed, smooth data using moving average filtering method, according to 3σ principle washes abnormal value, according to missing proportion processing missing value and normalization, based on preprocessed data, build operating condition model, combined with inlet flow and exhaust pressure and other parameters, calculate anti-surge threshold in low, medium and high load area, at the same time, use historical data to build exhaust pressure and inlet flow prediction model, predict future state. By comparing predicted value and threshold value to judge surge state, and then adjust inlet and outlet adjusting valve opening, ensure the stable operation of compressor unit, effectively prevent surge phenomenon from occurring, improve the safety and reliability of compressor unit operation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of compressor unit operation control, and more particularly to an anti-surge control method for a compressor unit. BACKGROUND

[0002] In modern industrial systems, compressor units are the core equipment of numerous production processes, with a wide range of applications, covering petroleum and chemical industry, natural gas transportation, refrigeration systems, and power production, etc. For example, in petroleum and chemical industry production, compressor units are used for gas compression, transportation and pressurization, which is an important link to ensure the continuity and stability of the production process; in the process of natural gas transportation, it can increase the gas pressure and realize efficient long-distance transportation.

[0003] With the continuous expansion of industrial production scale and the increasing complexity of production process, the stability, reliability and efficiency of compressor unit operation are increasingly required, however, surge has always been a key factor that hinders the stable operation of compressor units, which is an unstable phenomenon that occurs during the operation of the compressor, its essence is that when the compressor flow is reduced to a certain extent, strong oscillation and backflow of gas flow occur in the compressor, resulting in dramatic fluctuations in pressure, flow and other parameters. At present, in the field of anti-surge control technology, there are many technical solutions, among which the more common one is the control method based on fixed threshold, which sets a fixed surge control threshold according to experience or simple theoretical calculation, and when the compressor operating parameters exceed the threshold, the corresponding control measures are started, and some technologies monitor some operating parameters, such as only focusing on the inlet flow and exhaust pressure, to determine whether surge occurs and adjust the control accordingly.

[0004] However, in actual use, it still has some disadvantages, such as the traditional anti-surge control method has defects in data acquisition and processing, the acquisition of compressor unit operating parameters may not be comprehensive or accurate, it is difficult to obtain multi-dimensional parameters such as cylinder temperature, bearing temperature, inlet pipeline temperature and exhaust pipeline temperature, etc., which cannot accurately reflect the real operating state of the unit, at the same time, in the setting of anti-surge threshold, the previous method often uses fixed threshold or simple empirical formula, without fully considering the differences in operating characteristics of the compressor unit under different conditions, which leads to the threshold cannot accurately reflect the actual surge boundary of the compressor, prone to misjudgment, and cannot timely and effectively prevent surge from occurring, and the traditional method of judging the surge state is relatively single, mainly relying on a few parameters such as inlet flow and exhaust pressure, ignoring other important indicators such as vibration amplitude, and the judgment of surge state is only based on the current data, which may miss the early surge risk and cannot play a predictive role, delaying the starting time of anti-surge control measures. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art, embodiments of the present application provide an anti-surge control method for a compressor unit, which solves the problems raised in the above background art by the following scheme.

[0006] To achieve the above object, the present application provides the following technical scheme: an anti-surge control method for a compressor unit, comprising: S1: sensor deployment: during the installation and commissioning phase of the compressor unit, deploying sensor terminals according to the measurement requirements of various parameters;

[0007] The sensor terminals comprise: a pressure sensor, a flow sensor, a temperature sensor, a rotational speed sensor, and a vibration sensor;

[0008] S2: compressor unit data acquisition: real-time acquisition of compressor unit operating parameters according to the sensor terminals deployed in step S1;

[0009] The compressor unit operating parameters comprise: intake air pressure, intake air flow, exhaust air pressure, exhaust air flow, operating temperature, compressor rotational speed, and vibration amplitude;

[0010] The operating temperature comprises: cylinder temperature, bearing temperature, intake air pipe temperature, and exhaust air pipe temperature;

[0011] S3: data preprocessing: smoothing the compressor unit operating parameters by using a moving average filtering method, checking whether there are abnormal values and missing values in the acquired parameters and performing data cleaning, and performing data normalization processing on the cleaned data to obtain preprocessed data;

[0012] S4: dynamic anti-surge threshold calculation: constructing a compressor unit operating condition model based on the preprocessed data obtained in step S3, taking intake air flow and exhaust air pressure as main variables, and constructing anti-surge thresholds for low load, medium load, and high load of the compressor operation in combination with the operating condition model;

[0013] S5: future state prediction: constructing an exhaust air pressure prediction model and an intake air flow prediction model based on historical operating data, and substituting the preprocessed data obtained in step S3 into the exhaust air pressure prediction model and the intake air flow prediction model to obtain exhaust air pressure prediction values and intake air flow prediction values at future time;

[0014] S6: surge state judgment: comparing the exhaust air pressure prediction values and the intake air flow prediction values obtained in step S5 with the dynamically calculated anti-surge thresholds to judge the surge state of the compressor unit at future time;

[0015] S7: control execution: adjusting the opening degrees of the exhaust air regulating valve and the intake air regulating valve based on the judgment result in step S6 until the comparison result of the exhaust air pressure prediction values and the intake air flow prediction values with the dynamically calculated anti-surge thresholds is a normal operating state.

[0016] Technical effects and advantages of the present application:

[0017] 1、The present application comprehensively collects the working parameters of the compressor unit by deploying various sensors such as pressure, flow, temperature, speed and vibration, covering inlet pressure, inlet flow, outlet pressure, outlet flow, working temperature, compressor speed and vibration amplitude, etc., to ensure that the obtained data can accurately reflect the running state of the unit, and the moving average filtering method is used to smooth the data, combined with the 3σ principle to identify and clean abnormal values, and different methods are used to process missing values according to the missing proportion, and finally the data is normalized, effectively improving the data quality and providing a reliable basis for subsequent analysis and decision-making;

[0018] 2、The present application constructs an operating condition model based on the collected multi-parameter data, takes inlet flow and outlet pressure as main variables, and constructs the corresponding anti-surge threshold calculation formula of the low load area, the medium load area and the high load area combined with the historical operating data of different operating conditions. This dynamic threshold calculation method fully considers the operating characteristics of the compressor under different operating conditions, can more accurately reflect the surge boundary, improves the accuracy and timeliness of surge judgment, and effectively prevents surge from occurring.

[0019] 3、The present application constructs an outlet pressure prediction model and an inlet flow prediction model based on historical operating data, predicts the outlet pressure and inlet flow values at future time based on the prediction model, can predict the surge state of the compressor unit before surge occurs, and effectively prevents surge from occurring. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 It is a schematic diagram of the overall structure of the present application. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0022] As shown in the accompanying drawings Figure 1 A kind of anti-surge control method for compressor unit, comprising:

[0023] S1: sensor deployment: in the installation and debugging phase of compressor unit, according to the measurement requirement of each parameter, deploy sensor terminal;

[0024] The sensor terminal includes: pressure sensor, flow sensor, temperature sensor, speed sensor and vibration sensor;

[0025] It needs to be further explained that the deployment method of the sensor terminal is as follows:

[0026] The pressure sensor and the flow sensor are installed at the inlet of the compressor, and the pressure sensor and the flow sensor are also installed at the outlet of the compressor; the temperature sensor is arranged at the cylinder and the bearing part of the compressor; the rotating speed sensor is installed at the rotating shaft of the motor; the vibration sensor is installed at the casing and the bearing seat; after the installation of the sensors, all the sensors are calibrated to ensure that the measurement accuracy meets the requirements, and the connection between the sensors and the data acquisition module is established to prepare for data acquisition.

[0027] S2: Compressor unit data acquisition: according to the sensor terminal deployed in step S1, real-time acquisition of compressor unit working parameters;

[0028] Specifically, the compressor unit working parameters include inlet pressure, inlet flow, outlet pressure, outlet flow, working temperature, compressor rotating speed and vibration amplitude;

[0029] The working temperature includes cylinder temperature, bearing temperature, inlet pipe temperature and outlet pipe temperature;

[0030] S3: Data preprocessing: using moving average filtering method to smooth the compressor unit working parameters, checking whether there are abnormal values and missing values in the collected parameters and performing data cleaning, and performing data normalization processing on the cleaned data to obtain preprocessed data;

[0031] It needs to be specifically explained that the smoothing processing refers to setting the window size to 5 for the time series data of each parameter, and calculating the average value of the data in the window as the smoothing value of the center data of the window;

[0032] The data cleaning refers to identifying abnormal values based on the 3σ principle of statistics, if the data point deviates from the mean value by more than 3 times the standard deviation, it is considered as an abnormal value, and the mean value of the adjacent data is used to replace it; for missing values, different processing methods are selected according to the missing proportion, when the missing proportion is less than 10%, linear interpolation method is used to fill; when the missing proportion is between 10% and 30%, the missing values are predicted using a regression model; if the missing proportion exceeds 30%, the data segment is discarded.

[0033] S4: Dynamic anti-surge threshold calculation: based on the preprocessed data obtained in step S3, a compressor unit operating condition model is constructed, taking inlet flow and outlet pressure as main variables, combining with the operating condition model, the anti-surge threshold of the compressor in the low load area, the medium load area and the high load area is constructed;

[0034] It needs to be specifically explained that the construction process of the compressor unit operating condition model is as follows:

[0035] Based on the collected intake pressure P in , intake flow rate Q in , exhaust pressure P out , exhaust flow rate Q out , cylinder temperature T cyl , bearing temperature T b , intake pipe temperature T in-pipe , exhaust pipe temperature T out-pipe , compressor speed n, and vibration amplitude A, a multivariate linear regression model is established to model the operating conditions of the compressor unit, with the critical pressure ratio γ cr as the dependent variable, and its expression is:

[0036] γ cr = β0+ β1P in + β2Q in + β3P out + β4Q out + β5T cyl + β6T b + β7T in-pipe + β8T out-pipe + β9n+ β 10 A+ ε

[0037] Where γ cr represents the critical pressure ratio, i.e., the ratio of exhaust pressure to intake pressure, which is an important indicator of whether the compressor is close to the surge state. It reflects the pressure limit at which the compressor can operate stably under different operating conditions. When the actual pressure ratio approaches or exceeds the critical pressure ratio, the compressor is at risk of surging. β0represents the constant term in the regression model, representing the theoretical initial value of the critical pressure ratio when all independent variables are zero. In practical terms, it includes the combined effects of other factors on the critical pressure ratio that are not considered in the model. β1, β2, …, β 10 are the regression coefficients corresponding to the independent variables P in , Q in , P out , Q out , T cyl , T b , T in-pipe , T out-pipe , n, and A. These coefficients represent the degree and direction of the influence of each independent variable on the critical pressure ratio. For example, β1represents the change in the critical pressure ratio γ in for every unit change in the intake pressure P cr , with other independent variables held constant; β2represents the change in the critical pressure ratio γ inThe influence degree of critical pressure ratio is obtained by collecting at least 1000 groups of historical operation data under different working conditions, and fitting by using the least square method, to ensure that the model can accurately reflect the relationship between each parameter and the critical pressure ratio. The error term ε is used to represent the influence of random factors or measurement errors not considered in the model on the dependent variable. The value is also obtained by fitting the historical operation data by using the least square method. Since there are many factors that cannot be accurately modeled in actual operation, the existence of the error term makes the model more consistent with the actual situation.

[0038] The low load area refers to the intake flow rate Q in <300m 3 The low load area exhaust pressure anti-surge threshold P th1 The calculation formula is:

[0039] P th1 = a1Q in + a2P in + a3T in-pipe + a4n + b1;

[0040] The low load area intake flow rate anti-surge threshold Q th1 The calculation formula is:

[0041] Q th1 = c1P out + c2T out-pipe + c3A + d1;

[0042] Where P th1 refers to the low load area exhaust pressure anti-surge threshold, which is the critical value of the exhaust pressure for judging whether the compressor will surge when running at low load. When the actual exhaust pressure exceeds this threshold, the compressor has the risk of entering the surge state. Q th1 refers to the low load area intake flow rate anti-surge threshold, which is used to measure whether the intake flow rate is within a safe range under low load conditions. If the actual intake flow rate is lower than this threshold, it may cause surging. a1, a2, a3, a4, b1, c1, c2, c3, d1 are coefficients determined by analyzing and fitting the historical operation data in the low load area. These coefficients reflect the influence weight and direction of each related parameter on the anti-surge threshold. For example, a1 represents that in the low load area, the intake flow rate Q in changes by one unit, and the change amount of the exhaust pressure anti-surge threshold P th1 ; c1 represents the influence degree of the exhaust pressure P out on the intake flow rate anti-surge threshold Q th1 . The value is obtained based on statistical analysis and mathematical fitting of a large amount of low load area actual operation data to ensure the accuracy of threshold calculation.

[0043] The medium load area refers to 300m 3 / h ≤ Q in ≤ 700 m 3 / h, the exhaust pressure anti-surge threshold P th2 The calculation formula is:

[0044] P th2 = e1Q in + e2P in + e3Q out + e4T cyt + f1;

[0045] The intake flow anti-surge threshold Q th2 The calculation formula is:

[0046] Q th2 = g1P out + g2T b + g3n + h1;

[0047] wherein P th2 and Q th2 respectively refer to the exhaust pressure anti-surge threshold and the intake flow anti-surge threshold in the medium load area, which are important basis for judging whether the compressor is in surge in the medium load operation condition, e1, e2, e3, e4, f1, g1, g2, g3, h1 are coefficients determined by analyzing and fitting the historical operation data in the medium load area, similar to the coefficients in the low load area, which quantify the influence of each parameter on the anti-surge threshold in the medium load area, for example, e3 represents the influence degree of the exhaust flow Q out on the exhaust pressure anti-surge threshold P th2 in the medium load area, g2 represents the influence degree of the bearing temperature Tb on the intake flow anti-surge threshold Q th2 in the medium load area, etc., and the values thereof are determined according to the actual operation data characteristics of the medium load area.

[0048] The high load area refers to Q in > 700 m 3 / h, the exhaust pressure anti-surge threshold P th3 in the high load area, and the calculation formula is:

[0049] P th3 = i1Q in + i2P in + i3Q out + i4T out-pipe + j1;

[0050] The intake flow anti-surge threshold Q th3 in the high load area, and the calculation formula is:

[0051] Q th3 = k1P out + k2A + k3n + l1;

[0052] where Pth3 and Qth3 represent the exhaust pressure anti-surge threshold and the intake flow anti-surge threshold in the high load region, respectively, which are used to define the pressure and flow range for safe operation of the compressor in the high load condition, i1, i2, i3, i4, j1, k1, k2, k3, and l1 are coefficients determined by analyzing and fitting the historical operation data in the high load region, reflecting the action relationship of each parameter on the anti-surge threshold in the high load condition. For example, i4 represents the influence degree of the exhaust pipe temperature T out-pipe on the exhaust pressure anti-surge threshold P th3 , k2 represents the influence degree of the vibration amplitude A on the intake flow anti-surge threshold Q th3 , and so on. The values thereof are based on the analysis and fitting of the actual operation data in the high load region, ensuring that the threshold can adapt to the characteristics of the high load condition.

[0053] S5: Future state prediction: based on the historical operation data, an exhaust pressure prediction model and an intake flow prediction model are constructed, and the preprocessed data obtained in step S3 are respectively substituted into the exhaust pressure prediction model and the intake flow prediction model to obtain the exhaust pressure prediction value and the intake flow prediction value at the future time;

[0054] It should be further explained that the exhaust pressure prediction model is as follows:

[0055]

[0056] where P out (k+1) represents the exhaust pressure prediction value at the k+1 time, which is the key result of the model output and provides an important reference for subsequent exhaust valve adjustment, P out (k) represents the actual exhaust pressure at the k time, reflecting the continuity of the exhaust pressure in the time sequence, which influences the prediction value at the next time, represents the autoregressive coefficient, measuring the influence degree of the exhaust pressure at the k time on the exhaust pressure prediction value at the k+1 time, and the value range is generally between -1 and 1, which is determined by historical data training, θ1 represents the moving average coefficient, describing the influence of the error term ε(k) at the k time on the exhaust pressure prediction value at the k+1 time, reflecting the action of past random interference on the current prediction, and ε(k) represents the error term at the k time, including random factors or measurement errors that are not considered by the model, and so on. P in (k), Q in (k), T in-pipe(k), n(k), A(k) are the intake pressure, intake flow, intake pipeline temperature, compressor speed and vibration amplitude at k time, which affect the exhaust pressure from different aspects and are important input variables of the model, u1(k), u2(k), u3(k), u4(k), u5(k) are the coefficients of the intake pressure, intake flow, intake pipeline temperature, compressor speed and vibration amplitude, which are used to quantify the influence weight of each parameter on the exhaust pressure prediction value at k+1 time.

[0057] The intake flow prediction model is as follows:

[0058] Q in (k+1) = λ1Q in (k) + δ1ξ(k) + w1(k)P in (k) + w2(k)P out (k) + w3(k)T in-pipe (k) + w4(k)n(k) + w5(k)A(k)

[0059] wherein Q in (k+1) represents the intake flow prediction value at k+1 time, which is the key result of the model output, used to predict the intake flow of the compressor at the future time, and the control system can plan the adjustment strategy in advance according to the prediction value to ensure that the intake flow is in a reasonable range and effectively prevent surge, Q in (k) is the actual intake flow at k time, reflecting the current intake state of the compressor. It is used as the input of the autoregressive part, embodies the continuity and inertia of the intake flow in the time series, and means that the intake flow at the next time is closely related to the current intake flow. λ1 refers to the autoregressive coefficient, which is used to measure the influence degree of the intake flow at k time on the intake flow prediction value at k+1 time, and its value range is usually between-1 and 1. It is determined by statistical analysis and model training on a large amount of historical running data. If λ1 is close to 1, it indicates that the intake flow has strong autocorrelation in time, that is, the current intake flow has a greater influence on the next time. If λ1 is close to 0, it indicates that the autocorrelation is weak. δ1 refers to the moving average coefficient, which describes the influence of the error term ξ(k) at k time on the intake flow prediction value at k+1 time. It reflects the influence degree of random interference or unmodeled factors at past times on the current prediction. It is also obtained by data training. The size of δ1 determines the dependence degree of the model on historical errors. Reasonable adjustment of the coefficient helps to improve the prediction accuracy of the model. ξ(k) refers to the error term at k time, which represents the influence of random factors or measurement errors not considered in the model on the dependent variable. In the actual running process, there are many factors that cannot be accurately modeled, such as sudden changes in gas composition, small pipeline blockage, etc. These factors will cause deviations between the model prediction value and the actual value. The introduction of the error term makes the model more in line with the actual situation. Pin (k) refers to the intake air pressure at time k, the change of which directly affects the inflow of gas, and in turn affects the intake air flow. For example, if the intake air pressure rises, the intake air flow will generally increase under other conditions, so it is one of the important influencing factors in the model, w1(k) refers to the intake air pressure P in (k) refers to the corresponding coefficient, which is used to quantify the influence weight of the intake air pressure at time k on the predicted value of the intake air flow at time k+1, and its value is determined through data fitting and optimization algorithm, reflecting the specific correlation strength between the intake air pressure and the intake air flow, P out (k) refers to the exhaust pressure at time k, which indirectly affects the intake air flow. When the exhaust pressure is too high, it may hinder the inflow of gas, resulting in a decrease in intake air flow, and vice versa, a decrease in exhaust pressure may help increase the intake air flow, w2(k) refers to the exhaust pressure P out (k) refers to the corresponding coefficient, which is used to measure the influence degree of the exhaust pressure at time k on the predicted value of the intake air flow at time k+1, reflecting the quantitative relationship between the exhaust pressure and the intake air flow, T in-pipe (k) refers to the intake air pipeline temperature at time k, which affects the density and volume of gas, and in turn affects the intake air flow. For example, if the intake air pipeline temperature rises, the gas density decreases, and under the same intake air pressure, it may cause the intake air flow to change, w3(k) refers to the intake air pipeline temperature T in-pipe (k) refers to the corresponding coefficient, which is used to determine the influence weight of the intake air pipeline temperature at time k on the predicted value of the intake air flow at time k+1, n(k) refers to the compressor speed at time k, which directly affects the gas suction capacity. Increasing the speed will generally increase the intake air flow, which is one of the important operating variables for adjusting the intake air flow, w4(k) refers to the corresponding coefficient of the compressor speed n(k), which is used to quantify the influence degree of the compressor speed at time k on the predicted value of the intake air flow at time k+1. A(k) refers to the vibration amplitude at time k, which reflects the running stability and mechanical state of the compressor. Abnormal vibration may mean that there is a fault or unstable working condition inside the compressor, which in turn affects the intake air flow. For example, excessive vibration may cause the pipeline connection to loosen, the sealing performance to decrease, and other problems, which indirectly affect the intake air flow. w5(k) refers to the corresponding coefficient of the vibration amplitude A(k), which is used to measure the influence weight of the vibration amplitude at time k on the predicted value of the intake air flow at time k+1.

[0060] It should be further explained that the coefficients in the exhaust pressure and flow prediction model, such as the coefficients in the exhaust pressure prediction model θ1, u1(k)-u5(k) and λ1, δ1, w1(k)-w5(k) in the intake air flow prediction model are mainly obtained through parameter estimation of historical operation data, and the least squares method is used for estimation;

[0061] The least square method is as follows:

[0062] Taking the exhaust pressure prediction model as an example, a large amount of historical operation data is collected, including P out (k), P in (k), Q in (k), T in-pipe (k), n(k), A(k) and other parameters, and the actual measurement values are substituted into the exhaust pressure prediction model formula to construct the objective function:

[0063]

[0064] Where n is the number of data samples, and the coefficient value that minimizes the objective function S is calculated as the estimated value of the model coefficient, and the coefficients of the exhaust flow prediction model are calculated using the same principle;

[0065] The error terms such as ε(k), ξ(k) in the exhaust pressure and flow prediction model include random factors and measurement errors that are not considered in the model, and the mean and variance of the error terms are calculated through statistical analysis of historical operation data. For example, in a period of time, record the difference between the model prediction value and the actual measurement value each time, and use these differences as sample data of the error term to calculate the mean μ and variance σ 2 In subsequent model calculations, it is assumed that the error term follows a normal distribution with mean μ and variance σ 2 , i.e. ε(k) ~ N(μ, σ 2 ), ω(k) ~ N(μ, σ 2 ), which is used for model calculation.

[0066] S6: Surge state judgment: the exhaust pressure prediction value and the intake flow prediction value obtained in step S5 are compared with the dynamically calculated anti-surge threshold to judge the surge state of the compressor unit at the future time;

[0067] The method of the surge judgment is as follows:

[0068] When the intake flow Q in is less than the intake flow anti-surge threshold Q th of the corresponding working condition, and the exhaust pressure P out is greater than the exhaust pressure anti-surge threshold P th of the corresponding working condition, it is determined that the compressor unit will enter a surge state; otherwise, it is determined that the compressor unit will be in a normal operation state. In addition, auxiliary judgment is made in combination with the vibration amplitude. When the vibration amplitude A exceeds 2 times the standard deviation of the average value of the normal operation range, even if the operating parameters do not completely exceed the anti-surge threshold range, it is determined that there is a risk of surge, and the anti-surge control measures are started in advance.

[0069] S7: Control execution: based on the result of the judgment in step S6, adjust the opening degree of the exhaust regulating valve and the intake regulating valve until the comparison result of the exhaust pressure prediction value and the intake flow prediction value with the dynamically calculated anti-surge threshold value is the normal operating state.

[0070] Secondly: in the drawings of the disclosed embodiments, only the structures involved in the disclosed embodiments are involved, other structures can refer to the usual design, and in the case of no conflict, the same embodiment and different embodiments of the present application can be combined with each other;

[0071] Finally: the above only describes the preferred embodiments of the present application and is not used to limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A surge control method for compressor units, characterized in that, include: S1: Sensor Deployment: During the installation and commissioning phase of the compressor unit, sensor terminals are deployed according to the measurement requirements of each parameter; The sensor terminal includes: a pressure sensor, a flow sensor, a temperature sensor, a speed sensor, and a vibration sensor; S2: Compressor unit data acquisition: Based on the sensor terminals deployed in step S1, the operating parameters of the compressor unit are acquired in real time; The compressor unit's operating parameters include inlet pressure, inlet flow rate, exhaust pressure, exhaust flow rate, operating temperature, compressor speed, and vibration amplitude. The operating temperature includes cylinder temperature, bearing temperature, intake manifold temperature, and exhaust manifold temperature; S3: Data preprocessing: The moving average filtering method is used to smooth the operating parameters of the compressor unit, check for outliers and missing values ​​in the collected parameters and clean the data, and then normalize the cleaned data to obtain preprocessed data. S4: Calculation of dynamic anti-surge threshold: Based on the preprocessed data obtained in step S3, a compressor unit operating condition model is constructed. With intake flow and exhaust pressure as the main variables, and combined with the operating condition model, anti-surge thresholds for the low-load, medium-load, and high-load areas of compressor operation are constructed. The compressor unit operating condition model includes: based on the collected intake pressure P in Intake flow rate Q in Exhaust pressure P out Exhaust flow rate Q out Cylinder temperature T cyl Bearing temperature T b Intake pipe temperature T in−pipe Exhaust pipe temperature T out−pipe A compressor unit operating condition model was established using a multiple linear regression model based on 10 operating parameters, including compressor speed n, vibration amplitude A, and critical pressure ratio γ. cr As the dependent variable, its expression is: ； Where, γ cr The critical pressure ratio refers to the ratio of exhaust pressure to intake pressure. β0 is a constant term in the regression model, representing the theoretical initial value of the critical pressure ratio when all independent variables are zero. β1, β2, ..., β 10 These are the corresponding independent variables P in Q in P out Q out T cyl T b T in−pipe T out−pipe The regression coefficients of A, n, and A, with ε representing the error term, used to indicate the impact of random factors or measurement errors not considered in the model on the dependent variable; S5: Future state prediction: Based on historical operating data, construct exhaust pressure prediction model and intake flow prediction model, and substitute the preprocessed data obtained in step S3 into the exhaust pressure prediction model and intake flow prediction model respectively to obtain the exhaust pressure prediction value and intake flow prediction value at future time. S6: Surge state judgment: Compare the predicted values ​​of exhaust pressure and intake flow obtained in step S5 with the dynamically calculated anti-surge threshold to judge the surge state of the compressor unit at future moments. S7: Control Execution: Based on the judgment result in step S6, adjust the opening of the exhaust regulating valve and the intake regulating valve until the comparison result of the exhaust pressure prediction value and the intake flow prediction value with the dynamically calculated anti-surge threshold is in normal operating condition.

2. The anti-surge control method for compressor units according to claim 1, characterized in that: The smoothing process refers to setting the window size to 5 for the time series data of each parameter, and calculating the average value of the data within the window as the smoothing value of the center data of the window. The data cleaning process involves identifying outliers using the statistical 3σ principle. If a data point deviates from the mean by more than three standard deviations, it is considered an outlier and replaced with the mean of adjacent data. For missing values, different processing methods are selected based on the missing percentage. When the missing percentage is less than 10%, linear interpolation is used for filling. When the missing percentage is between 10% and 30%, a regression model is used to predict the missing values. If the missing percentage exceeds 30%, the data segment is discarded.

3. The anti-surge control method for compressor units according to claim 1, characterized in that: The low-load zone refers to the intake airflow Q. in <300 m³ / h, low-load zone exhaust pressure anti-surge threshold P th1 The calculation formula is: ； Low-load area intake flow anti-surge threshold Q th1 The calculation formula is: ； Where P th1 Q refers to the anti-surge threshold of exhaust pressure in the low-load zone. th1 The inlet flow rate anti-surge threshold in the low-load zone refers to the coefficients a1, a2, a3, a4, b1, c1, c2, c3, d1 determined by analyzing and fitting historical operating data in the low-load zone. The medium load zone refers to 300 m³ / h ≤ Q in ≤700m³ / h, anti-surge threshold P for exhaust pressure in medium load zone th2 The calculation formula is: ； Intake flow rate anti-surge threshold Q in medium load zone th2 The calculation formula is: ； Where P th2 and Q th2 These refer to the anti-surge threshold of exhaust pressure in the medium load zone and the anti-surge threshold of intake flow rate in the medium load zone, respectively. e1, e2, e3, e4, f1, g1, g2, g3, h1 are coefficients determined by analyzing and fitting historical operating data in the medium load zone. The high-load area refers to Q in >700m³ / h, high-load area exhaust pressure anti-surge threshold P th3 The calculation formula is: ； High-load area intake flow rate anti-surge threshold Q th3 The calculation formula is: ； Where P th3 and Q th3 These refer to the anti-surge thresholds for exhaust pressure and intake flow in the high-load zone, respectively. i1, i2, i3, i4, j1, k1, k2, k3, l1 are coefficients determined by analyzing and fitting historical operating data in the high-load zone.

4. The anti-surge control method for compressor units according to claim 3, characterized in that: The exhaust pressure prediction model is as follows: ； Among them, P out (k+1) represents the predicted exhaust pressure at time k+1, P out (k) refers to the actual exhaust pressure at time k, φ1 refers to the autoregression coefficient, θ1 refers to the moving average coefficient, ε(k) refers to the error term at time k, and P in (k), Q in (k), T in−pipe (k), n(k), and A(k) represent the intake pressure, intake flow rate, intake pipe temperature, compressor speed, and vibration amplitude at time k, respectively, while u1(k), u2(k), u3(k), u4(k), and u5(k) are the coefficients of the intake pressure, intake flow rate, intake pipe temperature, compressor speed, and vibration amplitude, respectively.

5. The anti-surge control method for compressor units according to claim 1, characterized in that: The intake flow prediction model is as follows: ； Among them, Q in (k+1) represents the predicted intake flow rate at time k+1, Q in (k) represents the actual intake flow rate at time k, λ1 refers to the autoregressive coefficient, δ1 refers to the moving average coefficient, ξ(k) refers to the error term at time k, and P in (k) refers to the intake pressure at time k, and w1(k) refers to the intake pressure P. in The coefficient corresponding to (k), P out (k) refers to the exhaust pressure at time k, and w2(k) refers to the exhaust pressure P. out The coefficient corresponding to (k), T in−pipe (k) refers to the intake pipe temperature at time k, and w3(k) refers to the intake pipe temperature T. in−pipe (k) refers to the coefficient corresponding to the compressor speed at time k, n(k) refers to the compressor speed at time k, w4(k) refers to the coefficient corresponding to the compressor speed n(k), A(k) refers to the vibration amplitude at time k, and w5(k) refers to the coefficient corresponding to the vibration amplitude A(k).

6. The anti-surge control method for compressor units according to claim 4, characterized in that: The method for determining surge condition is as follows: When the intake flow rate Q in The intake flow rate is less than the anti-surge threshold Q under the corresponding operating conditions. th And the exhaust pressure P out Exhaust pressure greater than the anti-surge threshold P under the corresponding operating condition th If the compressor unit is in a surge state, it is determined that it will enter a surge state; otherwise, it is determined that the compressor unit will be in normal operation. At the same time, the vibration amplitude is used as an auxiliary judgment. When the vibration amplitude A exceeds twice the standard deviation of the average value of the normal operation range, even if the operating parameters do not completely exceed the anti-surge threshold range, it is determined that there is a surge risk, and anti-surge control measures are initiated in advance.

Images