CN114962318B - Compressor surge control method and device, storage medium and computer equipment - Google Patents

Compressor surge control method and device, storage medium and computer equipment Download PDF

Info

Publication number
CN114962318B
CN114962318B CN202210581452.8A CN202210581452A CN114962318B CN 114962318 B CN114962318 B CN 114962318B CN 202210581452 A CN202210581452 A CN 202210581452A CN 114962318 B CN114962318 B CN 114962318B
Authority
CN
China
Prior art keywords
value
compressor
predicted
controlled
pressure value
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210581452.8A
Other languages
Chinese (zh)
Other versions
CN114962318A (en
Inventor
杨东升
徐永超
王睿
朱叶盛
徐海松
徐沛森
罗重威
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Northeastern University China
Original Assignee
Northeastern University China
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Northeastern University China filed Critical Northeastern University China
Priority to CN202210581452.8A priority Critical patent/CN114962318B/en
Publication of CN114962318A publication Critical patent/CN114962318A/en
Application granted granted Critical
Publication of CN114962318B publication Critical patent/CN114962318B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
    • F04D—NON-POSITIVE-DISPLACEMENT PUMPS
    • F04D27/00—Control, e.g. regulation, of pumps, pumping installations or pumping systems specially adapted for elastic fluids
    • F04D27/02—Surge control
    • F04D27/0246—Surge control by varying geometry within the pumps, e.g. by adjusting vanes
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
    • F04D—NON-POSITIVE-DISPLACEMENT PUMPS
    • F04D27/00—Control, e.g. regulation, of pumps, pumping installations or pumping systems specially adapted for elastic fluids
    • F04D27/02—Surge control
    • F04D27/0253—Surge control by throttling
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
    • Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating

Abstract

The invention discloses a method and a device for controlling compressor surge, a storage medium and computer equipment, relates to the technical field of compressors, and mainly aims to improve the control precision of compressor surge. The method comprises the following steps: acquiring an initial inter-vane gap value, an initial throttle valve opening value, an actual flow value and an actual pressure value corresponding to a compressor to be controlled when surging does not occur; determining a first predicted flow value and a first predicted pressure value corresponding to the outlet gas of the compressor to be controlled based on the initial inter-vane gap value and the initial throttle valve opening value; determining a second predicted flow value and a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment; and adjusting an initial inter-vane gap value and the initial throttle opening value corresponding to the compressor to be controlled based on the second predicted flow value, the preset flow value range, the second predicted pressure value and the preset pressure value range. The invention is suitable for controlling the surge of the compressor.

Description

Compressor surge control method and device, storage medium and computer equipment
Technical Field
The invention relates to the technical field of compressors, in particular to a method and a device for controlling compressor surge, a storage medium and computer equipment.
Background
The compressor is used as important gas conveying equipment in industrial production and is widely applied to industries such as steel, petroleum, chemical engineering, metallurgy and the like, however, as a kind of inherent defects of fluid machinery, the compressor can generate an unstable state, namely surge when in work, and when the surge occurs, the blade can strongly vibrate and the bearing abrasion is intensified due to the violent fluctuation and periodic oscillation of airflow, the normal operation of other equipment connected with the compressor is influenced, and the stable operation of the equipment is greatly damaged, so that the control on the surge of the compressor becomes particularly important.
At present, surge of the compressor is generally controlled by a differential controller. However, the differential controller can analyze and control only one influencing factor of the compressor to generate the surge phenomenon at a time, the influencing factors of the compressor to generate the surge phenomenon are many, and the influencing factors are related, so that the control method cannot simultaneously control a plurality of influencing factors of the compressor to generate the surge phenomenon, and therefore the control method cannot comprehensively analyze and control the influencing factors of the compressor to generate the surge, and further the control precision of the compressor surge is low.
Disclosure of Invention
The invention provides a method and a device for controlling compressor surge, a storage medium and computer equipment, and mainly aims to improve the control precision of compressor surge.
According to a first aspect of the present invention, there is provided a method of controlling compressor surge, comprising:
obtaining an initial inter-vane gap value and an initial throttle opening value corresponding to a compressor to be controlled when surging does not occur, and an actual flow value and an actual pressure value of outlet gas of the compressor to be controlled corresponding to the initial inter-vane gap value and the initial throttle opening value;
inputting the initial inter-leaf gap value and the initial throttle opening value into a preset multi-output prediction model together to predict the gas at the outlet of the compressor, so as to obtain a first predicted flow value and a first predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled;
determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual flow value and the first predicted flow value, and determining a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual pressure value and the first predicted pressure value;
judging whether the second predicted flow value is within a preset flow value range or not, and judging whether the second predicted pressure value is within a preset pressure value range or not;
if the second predicted flow value is not within the preset flow value range and/or the second predicted pressure value is not within the preset pressure value range, adjusting an initial inter-vane gap value and the initial throttle opening value corresponding to the compressor to be controlled based on the second predicted flow value, the preset flow value range, the second predicted pressure value and the preset pressure value range to prevent the compressor to be controlled from surging at the next moment.
According to a second aspect of the present invention, there is provided a compressor surge control apparatus comprising:
the device comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring an initial inter-vane gap value and an initial throttle opening value corresponding to a compressor to be controlled when surging does not occur, and an actual flow value and an actual pressure value of outlet gas of the compressor to be controlled corresponding to the initial inter-vane gap value and the initial throttle opening value;
the prediction unit is used for inputting the initial inter-vane gap value and the initial throttle valve opening value into a preset multi-output prediction model together for predicting the gas at the outlet of the compressor to obtain a first predicted flow value and a first predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled;
the determining unit is used for determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual flow value and the first predicted flow value, and determining a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual pressure value and the first predicted pressure value;
the judging unit is used for judging whether the second predicted flow value is in a preset flow value range or not and judging whether the second predicted pressure value is in a preset pressure value range or not;
and the adjusting unit is used for adjusting an initial inter-vane gap value and an initial throttle opening value corresponding to the compressor to be controlled based on the second predicted flow value, the preset flow value range, the second predicted pressure value and the preset pressure value range to prevent the compressor to be controlled from surging at the next moment if the second predicted flow value is not in the preset flow value range and/or the second predicted pressure value is not in the preset pressure value range.
According to a third aspect of the present invention, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
obtaining an initial inter-vane gap value and an initial throttle opening value corresponding to a compressor to be controlled when surging does not occur, and an actual flow value and an actual pressure value of outlet gas of the compressor to be controlled corresponding to the initial inter-vane gap value and the initial throttle opening value;
inputting the initial inter-leaf gap value and the initial throttle opening value into a preset multi-output prediction model together to predict the gas at the outlet of the compressor, so as to obtain a first predicted flow value and a first predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled;
determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual flow value and the first predicted flow value, and determining a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual pressure value and the first predicted pressure value;
judging whether the second predicted flow value is in a preset flow value range or not, and judging whether the second predicted pressure value is in a preset pressure value range or not;
if the second predicted flow value is not within the preset flow value range and/or the second predicted pressure value is not within the preset pressure value range, adjusting an initial inter-vane gap value and the initial throttle opening value corresponding to the compressor to be controlled based on the second predicted flow value, the preset flow value range, the second predicted pressure value and the preset pressure value range to prevent the compressor to be controlled from surging at the next moment.
According to a fourth aspect of the present invention, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the program:
obtaining an initial inter-vane gap value and an initial throttle opening value corresponding to a compressor to be controlled when surging does not occur, and an actual flow value and an actual pressure value of outlet gas of the compressor to be controlled corresponding to the initial inter-vane gap value and the initial throttle opening value;
inputting the initial inter-leaf gap value and the initial throttle opening value into a preset multi-output prediction model together to predict the gas at the outlet of the compressor, so as to obtain a first predicted flow value and a first predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled;
determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual flow value and the first predicted flow value, and determining a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual pressure value and the first predicted pressure value;
judging whether the second predicted flow value is in a preset flow value range or not, and judging whether the second predicted pressure value is in a preset pressure value range or not;
if the second predicted flow value is not within the preset flow value range and/or the second predicted pressure value is not within the preset pressure value range, adjusting an initial inter-vane gap value and the initial throttle opening value corresponding to the compressor to be controlled based on the second predicted flow value, the preset flow value range, the second predicted pressure value and the preset pressure value range to prevent the compressor to be controlled from surging at the next moment.
According to the control method, the control device, the storage medium and the computer equipment for compressor surge, compared with the mode that the surge of a compressor is controlled through a differential controller at present, the method obtains an initial inter-vane gap value and an initial throttle valve opening value corresponding to the compressor to be controlled when the compressor is not surged, and an actual flow value and an actual pressure value of outlet gas of the compressor to be controlled corresponding to the initial inter-vane gap value and the initial throttle valve opening value; inputting the initial inter-leaf gap value and the initial throttle opening value into a preset multi-output prediction model together to predict the gas at the outlet of the compressor, so as to obtain a first predicted flow value and a first predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled; then, determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual flow value and the first predicted flow value, and determining a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual pressure value and the first predicted pressure value; meanwhile, judging whether the second predicted flow value is in a preset flow value range or not, and judging whether the second predicted pressure value is in a preset pressure value range or not; finally, if the second predicted flow value is not in the preset flow value range and/or the second predicted pressure value is not in the preset pressure value range, adjusting an initial inter-lobe clearance value and an initial throttle opening value corresponding to the compressor to be controlled based on the second predicted flow value, the preset flow value range, the second predicted pressure value and the preset pressure value range to prevent the compressor to be controlled from surging at the next moment, inputting the initial inter-lobe clearance and the initial throttle opening corresponding to the compressor to be controlled without surging at the current moment into a preset multi-output prediction model for prediction to obtain a first predicted flow value and a first predicted pressure value corresponding to the outlet gas of the compressor to be controlled, determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the first predicted flow value and an actual flow value, determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the first predicted flow value and the actual pressure value, and finally performing differential analysis on the second predicted flow value, the second predicted pressure value and the preset pressure value, and the actual pressure value, and the compressor to control flow value, and the compressor to avoid the influence of the compressor to the flow and the compressor to be controlled, and the compressor to be controlled.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention and do not constitute a limitation of the invention. In the drawings:
FIG. 1 illustrates a flow chart of a method for controlling compressor surge in accordance with an embodiment of the present invention;
FIG. 2 is a flow chart illustrating another method for controlling compressor surge in accordance with an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating a compressor surge control apparatus according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating another compressor surge control apparatus according to an embodiment of the present invention;
fig. 5 shows a physical structure diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The invention will be described in detail hereinafter with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
At present, the method for controlling the surge of the compressor through the differential controller has the advantages that the differential controller can analyze and control only one influencing factor of the compressor which generates the surge phenomenon at each time, the influencing factors of the compressor which generates the surge phenomenon are many, and the influencing factors are related, so the method has low control precision on the surge of the compressor.
In order to solve the above problem, an embodiment of the present invention provides a method for controlling surge of a compressor, as shown in fig. 1, the method including:
101. and acquiring an initial inter-vane gap value and an initial throttle valve opening value corresponding to the compressor to be controlled when surging does not occur, and an actual flow value and an actual pressure value of outlet gas of the compressor to be controlled corresponding to the initial inter-vane gap value and the initial throttle valve opening value.
The actual flow value is the flow value of the gas output from the outlet of the compressor measured at the moment when the gap between the blade tip of the impeller of the compressor and the volute is adjusted to be the initial inter-blade gap, and the actual pressure value is the pressure value of the gas output from the outlet of the compressor measured at the moment when the opening of the valve of the outlet of the compressor is adjusted to be the initial opening value of the throttle valve.
For the embodiment of the invention, when the compressor starts to work, the surge phenomenon cannot occur, the surge phenomenon may occur when the operation time of the compressor is increased, at the moment, the surge of the compressor needs to be inhibited, the compressor to be controlled can be a magnetic suspension compressor, the magnetic suspension compressor adopts a magnetic bearing mode, an axial magnetic suspension thrust bearing is controlled to adjust the blade tip clearance between the blade tip of an impeller of the compressor and a volute, the opening degree of a throttle valve is adjusted, and the stable working point of the system is changed to complete the surge control.
For the embodiment of the invention, in order to overcome the problem of low control precision of compressor surge in the prior art, the embodiment of the invention inputs the initial inter-lobe gap and the initial throttle opening corresponding to the compressor to be controlled, which do not generate surge at the current moment, into the preset multi-output prediction model for prediction to obtain a first predicted flow value and a first predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled, determines a second predicted flow value corresponding to the gas at the outlet of the compressor to be controlled at the next moment based on the first predicted flow value and the actual flow value, determines a second predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled at the next moment based on the first predicted pressure value and the actual pressure value, and finally adjusts the inter-lobe gap and the throttle opening in the compressor to be controlled according to the second predicted pressure value, the preset pressure value range, the second predicted pressure value and the preset flow value range, so as to realize the control of the compressor surge, and avoid the situation that a differential controller can analyze and control the influence of the compressor only can be on one influence factor each time, and further improve the control precision of the compressor surge.
Specifically, the embodiment of the present invention adopts a layered cascade control system to control compressor surge, where the layered cascade control system may specifically be an MPC-PID cascade control system, that is, an inner ring adopts PID control to perform short-period data acquisition such as inter-leaf gap, throttle opening, compressor outlet gas flow and pressure, and inputs the acquired data into an MPC control system of an outer ring to perform compressor surge control, and the MPC-PID cascade control system can achieve good tracking performance and has good robustness when a model is mismatched, thereby improving the control accuracy of compressor surge.
102. And jointly inputting the initial inter-leaf gap value and the initial throttle opening value into a preset multi-output prediction model for predicting the gas at the outlet of the compressor to obtain a first predicted flow value and a first predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled.
For the embodiment of the invention, after an initial inter-leaf gap value and an initial throttle opening value are obtained, in order to prevent the compressor to be controlled from surging, the initial inter-leaf gap value and the initial throttle opening value are input into a preset multi-output prediction model in an MPC control system to predict the gas at the outlet of the compressor, a first predicted flow value and a first predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled are obtained, a second predicted flow value corresponding to the gas at the outlet of the compressor to be controlled at the next moment is determined based on the first predicted flow value and an actual flow value, a second predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled at the next moment is determined based on the first predicted flow value and the actual flow value, whether surging occurs in the compressor to be controlled can be judged based on the second predicted flow value and the second predicted flow value, if surging occurs, the inter-leaf gap and the throttle opening corresponding to the compressor to be controlled are adjusted until the compressor does not occur, and therefore, the preset multi-input multi-output prediction model is adopted, the inter-leaf gap and the relationship between the compressor to be controlled can be capable of considering the compressive clearance and the inter-leaf gap and the surge accuracy of the compressor to be controlled.
103. And determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual flow value and the first predicted flow value, and determining a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual pressure value and the first predicted pressure value.
The next time is a non-occurrence time, that is, the upcoming time may be one minute in the future, 2 minutes in the future, 30 minutes in the future, 1 hour in the future, or the like.
For the embodiment of the invention, after a first predicted flow value and a first predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the current moment are obtained, a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment is calculated based on the first predicted flow value and the actual flow value corresponding to the current moment, a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment is calculated based on the first predicted pressure value and the actual pressure value corresponding to the compressor to be controlled at the current moment, and finally, whether the compressor to be controlled at the next moment can generate the surge phenomenon is determined based on the second predicted flow value and the second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment.
104. And judging whether the second predicted flow value is in a preset flow value range or not, and judging whether the second predicted pressure value is in a preset pressure value range or not.
For the embodiment of the present invention, the preset flow value range and the preset pressure value range may be calculated in advance, a change curve corresponding to the outlet gas flow and the gas pressure when the compressor is in the normal working state may be drawn in advance, the change curve is a reference curve corresponding to the outlet gas flow and the gas pressure of the compressor in the normal working state, the preset flow value range and the preset pressure value range may be determined in the reference curve, and the reference curve may be drawn specifically by the following formula:
Figure BDA0003663989250000081
Figure BDA0003663989250000082
wherein psi s Is to output a set value of dimensionless pressure, phi s Is a set value for outputting a dimensionless mass flow rate,. Phi. (k) is an actual output for outputting a dimensionless pressure at time k (current time), phi. (k) is an actual output for outputting a dimensionless mass flow rate at time k (current time), and phi. (k) is a set value for outputting a dimensionless mass flow rate at time k (current time) r (k + i) represents the reference output at time k + i (the next time) of the dimensionless pressure rise, φ r (k + i) represents the reference output of the dimensionless mass flow at time k + i (the next time), T is the sampling time, T ψ A first time constant, T, representing a reference curve φ Is a second time constant of the reference track, and can be plotted with respect to psi based on the above formula r (k + i) and phi r A reference trajectory curve of (k + i) in which a preset flow value range and a preset pressure value range can be read.
Further, after a preset flow value range and a preset pressure value range are determined, whether a second predicted flow value is within the preset flow value range or not is judged, meanwhile, whether a second predicted pressure value is within the preset pressure value range or not is judged, if any one of the second predicted flow value and the second predicted pressure value is not within the corresponding value range, it is determined that a surge phenomenon will occur in the compressor to be controlled at the next moment, and at the moment, an inter-leaf gap and a throttle opening of the compressor need to be adjusted, so that the compressor is prevented from surging at the next moment.
105. If the second predicted flow value is not within the preset flow value range and/or the second predicted pressure value is not within the preset pressure value range, adjusting an initial inter-vane gap value and the initial throttle opening value corresponding to the compressor to be controlled based on the second predicted flow value, the preset flow value range, the second predicted pressure value and the preset pressure value range to prevent the compressor to be controlled from surging at the next moment.
For the embodiment of the present invention, after determining whether the second predicted flow and the second predicted pressure value are within the corresponding value ranges, if the second predicted flow value is not within the preset flow value range and/or the second predicted pressure value is not within the preset pressure value range, determining an inter-vane gap adjustment range and a throttle opening adjustment range of the compressor based on the second predicted flow value and the preset flow value range and the second predicted pressure value and the preset pressure value range, and finally performing corresponding adjustment on the inter-vane gap and the throttle opening of the compressor based on the inter-vane gap adjustment range and the throttle opening adjustment range until the compressor at the next moment cannot generate the surge phenomenon, so as to input the initial inter-vane gap and the initial throttle opening corresponding to the compressor to be controlled, which do not generate the surge at the current moment, into the preset multi-output prediction model for prediction, obtaining a first predicted flow value and a first predicted pressure value corresponding to the outlet gas of the compressor to be controlled, determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the first predicted flow value and the actual flow value, determining a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the first predicted pressure value and the actual pressure value, and finally adjusting the inter-leaf gap and the throttle opening in the compressor to be controlled according to the second predicted pressure value, the preset pressure value range, the second predicted flow value and the preset flow value range so as to realize the control of the surge of the compressor to be controlled and avoid the condition that a differential controller can only analyze and control one influence factor at each time, the invention can comprehensively analyze and control the compressor surge influence factors, and further can improve the control precision of the compressor surge.
According to the control method for compressor surge, compared with the mode that the surge of the compressor is controlled through a differential controller at present, the method obtains an initial inter-vane gap value and an initial throttle opening value corresponding to the compressor to be controlled when no surge occurs, and an actual flow value and an actual pressure value of outlet gas of the compressor to be controlled corresponding to the initial inter-vane gap value and the initial throttle opening value; inputting the initial inter-leaf gap value and the initial throttle opening value into a preset multi-output prediction model together to predict the gas at the outlet of the compressor, so as to obtain a first predicted flow value and a first predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled; then, determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual flow value and the first predicted flow value, and determining a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual pressure value and the first predicted pressure value; meanwhile, judging whether the second predicted flow value is in a preset flow value range or not, and judging whether the second predicted pressure value is in a preset pressure value range or not; finally, if the second predicted flow value is not in the preset flow value range and/or the second predicted pressure value is not in the preset pressure value range, adjusting an initial inter-leaf gap value and an initial throttle opening value corresponding to the compressor to be controlled based on the second predicted flow value, the preset flow value range, the second predicted pressure value and the preset pressure value range to prevent the compressor to be controlled from surging, inputting the initial inter-leaf gap and the initial throttle opening corresponding to the compressor to be controlled, which do not surging at the current moment, into a preset multi-output prediction model for prediction to obtain a first predicted flow value and a first predicted pressure value corresponding to the outlet gas of the compressor to be controlled, determining a second predicted value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the first predicted flow value and the actual flow value, and determining a second predicted pressure value and a pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the first predicted flow value and the actual flow value, thereby realizing the comprehensive control of the compressor to avoid the influence of the compressor to the flow value and the flow control of the compressor to be controlled, and the compressor, and the flow value of the compressor to be controlled.
Further, in order to better explain the process of controlling the compressor surge, as a refinement and an extension of the above embodiment, an embodiment of the present invention provides another method for controlling the compressor surge, as shown in fig. 2, the method includes:
201. and acquiring an initial inter-vane gap value and an initial throttle opening value corresponding to the compressor to be controlled when no surge occurs, and an actual flow value and an actual pressure value of outlet gas of the compressor to be controlled corresponding to the initial inter-vane gap value and the initial throttle opening value.
Specifically, a measuring tool is used for measuring the inter-leaf gap value and the throttle valve opening value corresponding to the compressor to be controlled at the current moment, and meanwhile, a flow sensor is used for measuring the actual mass flow value and the actual pressure value corresponding to the outlet gas of the compressor at the current moment.
202. And jointly inputting the initial inter-blade gap value and the initial throttle valve opening value into a preset multi-output prediction model to predict the gas at the outlet of the compressor, so as to obtain a first predicted flow value and a first predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled.
For the embodiment of the present invention, in order to predict the first predicted flow value and the first predicted pressure value corresponding to the outlet gas of the compressor at the current time by using the preset multi-output prediction model, the preset multi-output prediction model needs to be constructed first, and the specific method for constructing the preset multi-output prediction model is as follows: acquiring a sample inter-vane gap value and a sample throttle opening value corresponding to a sample compressor, and an actual sample flow value and an actual sample pressure value of the sample compressor outlet gas corresponding to the sample inter-vane gap value and the sample throttle opening value; inputting the sample inter-leaf gap value and the sample throttle opening value into a preset initial multi-output prediction model together for predicting the gas at the outlet of the sample compressor to obtain a predicted sample flow value and a predicted sample pressure value corresponding to the gas at the outlet of the sample compressor; determining a loss function corresponding to the preset initial multi-output prediction model based on the actual sample flow value, the predicted sample flow value, the actual sample pressure value and the predicted sample pressure value; and constructing the preset multi-output prediction model based on the loss function.
Specifically, firstly, a measuring tool is used for measuring a sample interlobe gap and a sample throttle opening corresponding to a sample compressor, meanwhile, a flow sensor installed at an outlet of the compressor is used for measuring an actual sample flow value corresponding to outlet gas of the compressor, a pressure sensor installed at the outlet of the compressor is used for measuring an actual sample pressure value corresponding to outlet gas of the compressor, then, the sample interlobe gap and the sample throttle opening are input into a preset initial multi-output prediction model to obtain a predicted sample flow value and a predicted sample pressure value corresponding to outlet gas of the sample compressor, a loss function corresponding to the preset initial multi-output prediction model is constructed by comparing the size between the predicted sample flow value and the actual sample flow value and the size between the predicted sample pressure value and the actual sample pressure value, and parameters corresponding to the preset initial multi-output prediction model are continuously updated based on the loss function until the loss value corresponding to the loss function is minimum, and the updated parameters are parameters corresponding to the preset multi-output prediction model.
For the embodiment of the present invention, after the preset multi-output prediction model is constructed, a first predicted flow value and a first predicted pressure value corresponding to a compressor to be controlled are determined by using the prediction multi-output prediction model based on the initial interlobe gap and the initial throttle opening, and based on this, step 202 specifically includes: respectively carrying out normalization processing on the initial inter-vane gap value and the initial throttle valve opening value to obtain a processed initial inter-vane gap value and a processed initial throttle valve opening value; and inputting the processed initial inter-leaf gap value and the processed initial throttle opening value into a preset multi-output prediction model together for predicting the gas at the outlet of the compressor to obtain a first predicted flow value and a first predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled.
Specifically, in order to reduce the calculation difficulty of the preset multi-output prediction model and further improve the prediction accuracy of the preset multi-output prediction model, normalization processing needs to be performed on the initial inter-vane gap value and the initial throttle opening value, that is, the initial inter-vane gap value is divided by the preset gap standard value to obtain a normalized initial inter-vane gap value, meanwhile, the initial throttle opening value is divided by the preset opening standard value to obtain a normalized initial throttle opening value, and finally, the normalized initial inter-vane gap value and the normalized initial throttle opening value are input into the preset multi-output prediction model to be predicted to obtain a first predicted mass flow value and a first predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the current moment, wherein the method for predicting the mass flow value and the pressure value by using the prediction multi-output prediction model specifically comprises the following steps: inputting the processed initial interlobe gap value and the processed initial throttle opening value into a hidden layer through an input layer of the preset neural network model, and extracting features output by the hidden layer; inputting the output characteristics of the hidden layer into the output layer, and extracting a first predicted flow value and a first predicted pressure value which are output by the output layer and correspond to the outlet gas of the compressor to be controlled.
The preset multi-output prediction model may be a preset LSTM model, and the preset LSTM model includes an input layer, a hidden layer, and an output layer.
Specifically, the processed initial inter-leaf gap and the processed initial throttle opening are input to a hidden layer through an input layer of a preset LSTM model, and the result output through the hidden layer is:
f(W 1 x+b 1 )
the output result is the characteristic that the processed initial interlobe gap and the processed initial throttle opening are fully connected through a preset LSTM model and before the softmax layer is input, x is the processed initial interlobe gap and the processed initial throttle opening, w 1 For the weight of the hidden layer, the connection coefficients of the LSTM model are also preset, b 1 For the bias coefficient of the hidden layer, the f function may generally adopt a sigmoid function or a tanh function, as follows:
sigmoid(x)＝1/(1+e- x )
tanh(x)＝(e x -e -x )/(e 1 +e -x )
further, after the processed initial interlobe gap and the processed initial throttle opening degree are input to a hidden layer through an input layer of a multilayer sensor model to obtain an output result of the hidden layer, the output result is input to an output layer, namely a softmax layer of the multilayer sensor, a first predicted flow value and a first predicted pressure value are output through the output layer, and the obtained recommendation result is:
softmax(W 2 f(W 1 x+b 1 )+b 2 )
wherein, W 2 As weight coefficients of the output layer, b 2 The first predicted flow value and the first predicted pressure value can be output through the output layer of the preset LSTM model as the bias coefficient of the output layer.
203. And determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual flow value and the first predicted flow value, and determining a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual pressure value and the first predicted pressure value.
For the embodiment of the present invention, in order to determine whether a surge phenomenon occurs at the next moment of the compressor to be controlled, a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment needs to be determined, based on which step 203 specifically includes: determining a first prediction coefficient corresponding to the outlet gas flow of the compressor to be controlled; subtracting the actual flow value from the first predicted flow value to obtain a first predicted error value corresponding to the outlet gas flow of the compressor to be controlled; multiplying the first prediction error value by the first prediction coefficient to obtain a first prediction balance value corresponding to the outlet gas flow of the compressor to be controlled; and adding the first predicted balance value and the first predicted flow value to obtain a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment.
Specifically, the second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment may be calculated by the following formula:
φ p (k+i)＝φ m (k)+k φ (φ(k)-φ m (k))
wherein phi p (k + i) represents a second predicted flow value, φ m (k) Representing a first predicted streamThe magnitude, phi (k), represents the actual flow value, k φ And expressing a first prediction coefficient, and substituting the first prediction coefficient, the actual flow value and the first prediction flow value into the formula to calculate a second prediction flow value corresponding to the outlet gas of the compressor to be controlled at the next moment.
Further, in order to determine whether a surge phenomenon occurs at the next moment of the compressor to be controlled, a second predicted pressure value corresponding to outlet gas of the compressor to be controlled at the next moment needs to be determined, and based on this, step 203 specifically includes: determining a second prediction coefficient corresponding to the outlet gas pressure of the compressor to be controlled; subtracting the actual pressure value from the first predicted pressure value to obtain a second predicted error value corresponding to the outlet gas pressure of the compressor to be controlled; multiplying the second prediction error value by the second prediction coefficient to obtain a second prediction balance value corresponding to the outlet gas pressure of the compressor to be controlled; and adding the second predicted balance value and the first predicted pressure value to obtain a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment.
Specifically, the second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment can be calculated by the following formula:
ψ p (k+i)＝ψ m (k)+k ψ (ψ(k)-ψ m (k))
wherein psi p (k + i) represents a second predicted pressure value, ψ m (k) Representing a first predicted pressure value, # k representing an actual pressure value, k ψ And expressing a second prediction coefficient, and substituting the second prediction coefficient, the actual pressure value and the first prediction pressure value into the formula to calculate a second prediction pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment.
204. And judging whether the second predicted flow value is in a preset flow value range or not, and judging whether the second predicted pressure value is in a preset pressure value range or not.
Specifically, a preset flow value range and a preset pressure value range may be determined in the drawn reference curve track, after the preset flow value range and the preset pressure value range are determined, it is determined whether the second predicted flow value is within the preset flow value unit, meanwhile, it is determined whether the second predicted pressure value is within the preset pressure value range, if any one of the second predicted flow value and the second predicted pressure value is not within the corresponding value unit, it is determined that a surge phenomenon will occur in the compressor to be controlled at the next moment, and the compressor is prevented from surging by adjusting an inter-lobe gap and a throttle opening of the compressor.
Further, after determining whether the second predicted flow value is within a preset flow value range and determining whether the second predicted pressure value is within a preset pressure value range, the method further includes: and if the second predicted flow value is within the preset flow value range and the second predicted pressure value is within the preset pressure value range, determining that the compressor to be controlled cannot surge at the next moment.
Specifically, if the second predicted flow value is within the preset flow value unit and the second predicted pressure value is within the preset pressure value range, it is determined that the compressor to be controlled cannot surge at the next moment, and the inter-vane gap and the opening degree of the throttle valve of the compressor do not need to be adjusted.
205. And if the second predicted flow value is not in the preset flow value range and/or the second predicted pressure value is not in the preset pressure value range, calculating an inter-leaf gap value range and a throttle opening value range for preventing the surge of the compressor to be controlled by using a preset control function based on the second predicted flow value, the preset flow value range, the second predicted pressure value and the preset pressure value range.
For the embodiment of the present invention, after determining whether the second predicted flow value is within the preset flow value range and determining whether the second predicted pressure value is within the preset pressure value range, if any one of the second predicted flow value and the second predicted pressure value is not within the corresponding value range, it indicates that surge is about to occur in the compressor to be controlled at the next moment, and based on this, it is first necessary to determine the adjustable range of the inter-vane gap and the adjustable range of the throttle opening, and specifically, the inter-vane gap value range and the throttle opening value range may be calculated by using the following formulas:
Figure BDA0003663989250000161
Figure BDA0003663989250000162
wherein, J 1 (k) Performance index representing dimensionless pressure, J 2 (k) Performance index representing dimensionless mass flow, P is prediction time domain, M is control time domain, deltau u 1 Output increment, deltau u, at the current time representing a dimensionless pressure 2 Indicating the output increment of the dimensionless mass flow at the current moment, psi r (k + i) denotes a reference output at the time k + i (next time) of dimensionless pressure rise, ψ m (k + i) represents a second predicted pressure value, phi r (k + i) represents the reference output of the dimensionless mass flow at time k + i (the next time), phi m (k + i) represents a second predicted flow value, and the surge control problem can be transformed into the following optimization problem, taking into account the range of parameters of the compressor operation:
minλ 1 J 1 (k)+λ 2 J 2 (k)
s.t.u(k)＝Δu(k)+u(k-1)
u 1min ≤u 1 ≤u 1max
k tmin ≤k t ≤k tmax
0≤u 2 ≤100％
φ min ≤φ m (k+i)≤φ max
ψ min ≤ψ m (k+i)≤ψ max
wherein λ is 1 Is a weight coefficient, λ, of a performance index of dimensionless pressure 2 Weight coefficient, u, representing a performance index of a non-measured mass flow 1 Denotes the interlobal space, u 1min For negative maximum blade tip clearance adjustment of the compressor, u 2max For maximum forward tip clearance adjustment, k, of the compressor t Indicating throttle opening, k tmin Is the minimum adjustment amount of the throttle valve opening of the compressor, k tmax For maximum adjustment of the throttle opening of the compressor, phi min And phi max The minimum value and the maximum value of the compressor output dimensionless mass flow are respectively; phi, phi min And psi max The minimum value and the maximum value of the dimensionless pressure output by the compressor are respectively, so that the value range of the inter-leaf gap and the value range of the opening degree of the throttle valve for preventing the surge of the compressor to be controlled can be determined according to the mode, and a user adjusts the inter-leaf gap and the opening degree of the throttle valve of the compressor to be controlled based on the value range of the inter-leaf gap and the value range of the opening degree of the throttle valve.
206. And adjusting an initial inter-vane gap value and the initial throttle valve opening value corresponding to the compressor to be controlled based on the inter-vane gap value range and the throttle valve opening value range to prevent the compressor to be controlled from surging at the next moment.
Specifically, after obtaining the inter-leaf gap value range and the throttle opening value range, the MCD-PID control system needs to adjust an initial inter-leaf gap value and the initial throttle opening value corresponding to the compressor to be controlled based on the inter-leaf gap value range and the throttle opening value range, and a specific adjustment method is that the MCD-PID control system drives the opening of the throttle valve based on current, and at this time, a current interference signal is generated, so that the PID controller can suppress the current interference information, and at the same time, drives the adjustment of the inter-leaf gap by the voltage applied to the electromagnetic coil, and at this time, a voltage interference signal is generated, so that the PID controller can suppress the voltage interference information, thereby more accurately controlling the inter-leaf gap and the throttle opening, and preventing the compressor from surging.
According to the control method, the control device, the storage medium and the computer equipment for compressor surge, compared with the mode that the surge of a compressor is controlled through a differential controller at present, the method obtains an initial inter-vane gap value and an initial throttle valve opening value corresponding to the compressor to be controlled when the compressor is not surged, and an actual flow value and an actual pressure value of outlet gas of the compressor to be controlled corresponding to the initial inter-vane gap value and the initial throttle valve opening value; inputting the initial inter-vane gap value and the initial throttle valve opening value into a preset multi-output prediction model together for predicting gas at the outlet of the compressor to obtain a first predicted flow value and a first predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled; then, determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual flow value and the first predicted flow value, and determining a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual pressure value and the first predicted pressure value; meanwhile, judging whether the second predicted flow value is in a preset flow value range or not, and judging whether the second predicted pressure value is in a preset pressure value range or not; finally, if the second predicted flow value is not in the preset flow value range and/or the second predicted pressure value is not in the preset pressure value range, adjusting an initial inter-vane gap value and an initial throttle opening value corresponding to the compressor to be controlled based on the second predicted flow value, the preset flow value range, the second predicted pressure value and the preset pressure value range to prevent the compressor to be controlled from surging, so that a first predicted flow value and a first predicted pressure value corresponding to outlet gas of the compressor to be controlled are obtained by inputting the initial inter-vane gap and the initial throttle opening corresponding to the compressor to be controlled without surging at the current moment into a preset multi-output prediction model for prediction, and determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the first predicted flow value and the actual flow value, determining a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the first predicted pressure value and the actual pressure value, and finally adjusting the inter-leaf gap and the opening of the throttle valve in the compressor to be controlled according to the second predicted pressure value and the preset pressure value range as well as the second predicted flow value and the preset flow value range, so that the control of the surge of the compressor to be controlled is realized, and the condition that a differential controller only can analyze and control one influence factor at each time is avoided.
Further, as a specific implementation of fig. 1, an embodiment of the present invention provides a compressor surge control device, as shown in fig. 3, the device includes: an acquisition unit 31, a prediction unit 32, a determination unit 33, a judgment unit 34, and an adjustment unit 35.
The obtaining unit 31 may be configured to obtain an initial inter-vane gap value and an initial throttle opening value corresponding to the compressor to be controlled when no surge occurs, and an actual flow value and an actual pressure value of the outlet gas of the compressor to be controlled corresponding to the initial inter-vane gap value and the initial throttle opening value.
The prediction unit 32 may be configured to input the initial inter-vane gap value and the initial throttle opening value into a preset multi-output prediction model together to perform prediction on compressor outlet gas, so as to obtain a first predicted flow value and a first predicted pressure value corresponding to the compressor outlet gas to be controlled.
The determining unit 33 may be configured to determine a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next time based on the actual flow value and the first predicted flow value, and determine a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next time based on the actual pressure value and the first predicted pressure value.
The determining unit 34 may be configured to determine whether the second predicted flow value is within a preset flow value range, and determine whether the second predicted pressure value is within a preset pressure value range.
The adjusting unit 35 may be configured to adjust an initial inter-vane gap value and the initial throttle opening value corresponding to the compressor to be controlled based on the second predicted flow value, the preset flow value range, the second predicted pressure value, and the preset pressure value range if the second predicted flow value is not within the preset flow value range and/or the second predicted pressure value is not within the preset pressure value range, so as to prevent the compressor to be controlled from surging at the next time.
In a specific application scenario, in order to determine a first predicted flow value and a first predicted pressure value corresponding to the outlet gas of the compressor to be controlled, as shown in fig. 4, the prediction unit 32 includes a processing module 321 and a prediction module 322.
The processing module 321 may be configured to perform normalization processing on the initial inter-vane gap value and the initial throttle opening value, respectively, to obtain a processed initial inter-vane gap value and a processed initial throttle opening value.
The prediction module 322 may be configured to input the processed initial inter-vane gap value and the processed initial throttle opening value to a preset multi-output prediction model together to perform prediction on compressor outlet gas, so as to obtain a first predicted flow value and a first predicted pressure value corresponding to the compressor outlet gas to be controlled.
In a specific application scenario, in order to determine a first predicted flow value and a first predicted pressure value corresponding to the outlet gas of the compressor to be controlled, the prediction module 322 may be specifically configured to input the processed initial inter-leaf gap value and the processed initial throttle opening value to a hidden layer through an input layer of the preset neural network model, and extract a feature output by the hidden layer.
The prediction module 322 may be specifically configured to input the feature output by the hidden layer to the output layer, and extract a first predicted flow value and a first predicted pressure value corresponding to the outlet gas of the compressor to be controlled, which are output by the output layer.
In a specific application scenario, in order to construct the preset multi-output prediction model, the apparatus further includes a construction unit 36.
The obtaining unit 31 may further be configured to obtain a sample inter-vane gap value and a sample throttle opening value corresponding to a sample compressor, and an actual sample flow rate value and an actual sample pressure value of the sample compressor outlet gas corresponding to the sample inter-vane gap value and the sample throttle opening value.
The predicting unit 32 may be further configured to input the sample inter-vane gap value and the initial sample throttle opening value to a preset initial multi-output prediction model together to perform sample compressor outlet gas prediction, so as to obtain a predicted sample flow value and a predicted sample pressure value corresponding to the sample compressor outlet gas.
The determining unit 33 may be further configured to determine a loss function corresponding to the preset initial multi-output prediction model based on the actual sample flow value and the predicted sample flow value, and the actual sample pressure value and the predicted sample pressure value.
The constructing unit 36 may be configured to construct the preset multi-output prediction model based on the loss function.
In a specific application scenario, in order to determine a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next time, the determining unit 33 includes a determining module 331, a subtracting module 332, a multiplying module 333, and an adding module 334.
The determining module 331 may be configured to determine a first prediction coefficient corresponding to the outlet gas flow of the compressor to be controlled.
The subtracting module 332 may be configured to subtract the actual flow value from the first predicted flow value to obtain a first predicted error value corresponding to the outlet gas flow of the compressor to be controlled.
The multiplying module 333 may be configured to multiply the first prediction error value and the first prediction coefficient to obtain a first prediction balance value corresponding to the outlet gas flow of the compressor to be controlled.
The adding module 334 may be configured to add the first predicted balance value and the first predicted flow value to obtain a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next time.
In a specific application scenario, in order to determine a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next time based on the actual pressure value and the first predicted pressure value, the determining module 331 may be further configured to determine a second prediction coefficient corresponding to the outlet gas pressure of the compressor to be controlled.
The subtracting module 332 may be further configured to subtract the actual pressure value from the first predicted pressure value to obtain a second predicted error value corresponding to the outlet gas pressure of the compressor to be controlled.
The multiplying module 333 may be further configured to multiply the second prediction error value and the second prediction coefficient to obtain a second prediction balance value corresponding to the outlet gas pressure of the compressor to be controlled.
The adding module 334 may be further configured to add the second predicted balance value to the first predicted pressure value, so as to obtain a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next time.
In a specific application scenario, in order to adjust the initial inter-vane gap value and the initial throttle opening value corresponding to the compressor to be controlled, the adjusting unit 35 includes a calculating module 351 and an adjusting module 352.
The calculating module 351 may be configured to calculate, based on the second predicted flow value, the preset flow value range, the second predicted pressure value, and the preset pressure value range, an inter-vane gap value range and a throttle opening value range for preventing surge of the compressor to be controlled by using a preset control function.
The adjusting module 352 may be configured to adjust an initial inter-vane gap value and an initial throttle opening value corresponding to the compressor to be controlled based on the inter-vane gap value range and the throttle opening value range.
In a specific application scenario, in order to determine whether the inter-vane gap and the throttle opening of the compressor need to be adjusted, the determining unit 33 may be further configured to determine that the compressor to be controlled cannot surge at the next moment if the second predicted flow value is within the preset flow value range and the second predicted pressure value is within the preset pressure value range.
It should be noted that, other corresponding descriptions of the functional modules related to the control device for compressor surge according to the embodiment of the present invention may refer to the corresponding description of the method shown in fig. 1, and are not repeated herein.
Based on the method shown in fig. 1, correspondingly, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the following steps: obtaining an initial inter-vane gap value and an initial throttle opening value corresponding to a compressor to be controlled when surging does not occur, and an actual flow value and an actual pressure value of outlet gas of the compressor to be controlled corresponding to the initial inter-vane gap value and the initial throttle opening value; inputting the initial inter-vane gap value and the initial throttle valve opening value into a preset multi-output prediction model together for predicting gas at the outlet of the compressor to obtain a first predicted flow value and a first predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled; determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual flow value and the first predicted flow value, and determining a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual pressure value and the first predicted pressure value; judging whether the second predicted flow value is within a preset flow value range or not, and judging whether the second predicted pressure value is within a preset pressure value range or not; if the second predicted flow value is not within the preset flow value range and/or the second predicted pressure value is not within the preset pressure value range, adjusting an initial inter-vane gap value and the initial throttle opening value corresponding to the compressor to be controlled based on the second predicted flow value, the preset flow value range, the second predicted pressure value and the preset pressure value range to prevent the compressor to be controlled from surging at the next moment.
Based on the above embodiments of the method shown in fig. 1 and the apparatus shown in fig. 3, an embodiment of the present invention further provides an entity structure diagram of a computer device, as shown in fig. 5, where the computer device includes: a processor 41, a memory 42, and a computer program stored on the memory 42 and executable on the processor, wherein the memory 42 and the processor 41 are both arranged on a bus 43 such that when the processor 41 executes the program, the following steps are performed: obtaining an initial inter-vane gap value and an initial throttle opening value corresponding to a compressor to be controlled when surging does not occur, and an actual flow value and an actual pressure value of outlet gas of the compressor to be controlled corresponding to the initial inter-vane gap value and the initial throttle opening value; inputting the initial inter-vane gap value and the initial throttle valve opening value into a preset multi-output prediction model together for predicting gas at the outlet of the compressor to obtain a first predicted flow value and a first predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled; determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual flow value and the first predicted flow value, and determining a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual pressure value and the first predicted pressure value; judging whether the second predicted flow value is within a preset flow value range or not, and judging whether the second predicted pressure value is within a preset pressure value range or not; if the second predicted flow value is not within the preset flow value range and/or the second predicted pressure value is not within the preset pressure value range, adjusting an initial inter-vane gap value and the initial throttle opening value corresponding to the compressor to be controlled based on the second predicted flow value, the preset flow value range, the second predicted pressure value and the preset pressure value range to prevent the compressor to be controlled from surging at the next moment.
According to the technical scheme, the method comprises the steps of obtaining an initial inter-vane gap value and an initial throttle opening value corresponding to the compressor to be controlled when no surge occurs, and obtaining an actual flow value and an actual pressure value of outlet gas of the compressor to be controlled corresponding to the initial inter-vane gap value and the initial throttle opening value; inputting the initial inter-leaf gap value and the initial throttle opening value into a preset multi-output prediction model together to predict the gas at the outlet of the compressor, so as to obtain a first predicted flow value and a first predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled; then, determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual flow value and the first predicted flow value, and determining a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual pressure value and the first predicted pressure value; meanwhile, judging whether the second predicted flow value is in a preset flow value range or not, and judging whether the second predicted pressure value is in a preset pressure value range or not; finally, if the second predicted flow value is not in the preset flow value range and/or the second predicted pressure value is not in the preset pressure value range, adjusting an initial inter-leaf gap value and an initial throttle opening value corresponding to the compressor to be controlled based on the second predicted flow value, the preset flow value range, the second predicted pressure value and the preset pressure value range to prevent the compressor to be controlled from surging at the next moment, inputting the initial inter-leaf gap and the initial throttle opening corresponding to the compressor to be controlled, which do not surging at the current moment, into a preset multi-output prediction model for prediction to obtain a first predicted flow value and a first predicted pressure value corresponding to the outlet gas of the compressor to be controlled, determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the first predicted flow value and the actual flow value, determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the first predicted flow value and the actual pressure value, and determining a second predicted flow value and a second predicted pressure value to be controlled at the next moment to control the outlet gas of the compressor to be controlled, and the compressor to avoid the influence of the compressor to the flow value and the compressor to be controlled, and the compressor to avoid the influence of the compressor to be controlled flow value of the compressor to be controlled.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A method of controlling compressor surge, comprising:
obtaining an initial inter-vane gap value and an initial throttle valve opening value corresponding to a compressor to be controlled when surging does not occur, and an actual flow value and an actual pressure value of outlet gas of the compressor to be controlled corresponding to the initial inter-vane gap value and the initial throttle valve opening value;
inputting the initial inter-vane gap value and the initial throttle valve opening value into a preset multi-output prediction model together for predicting gas at the outlet of the compressor to obtain a first predicted flow value and a first predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled;
determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual flow value and the first predicted flow value, and determining a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual pressure value and the first predicted pressure value;
judging whether the second predicted flow value is within a preset flow value range or not, and judging whether the second predicted pressure value is within a preset pressure value range or not;
if the second predicted flow value is not within the preset flow value range and/or the second predicted pressure value is not within the preset pressure value range, adjusting an initial inter-vane gap value and the initial throttle opening value corresponding to the compressor to be controlled based on the second predicted flow value, the preset flow value range, the second predicted pressure value and the preset pressure value range to prevent the compressor to be controlled from surging at the next moment.
2. The method of claim 1, wherein the jointly inputting the initial inter-vane gap value and the initial throttle opening value into a preset multi-output prediction model for compressor outlet gas prediction to obtain a first predicted flow value and a first predicted pressure value corresponding to the compressor outlet gas to be controlled comprises:
respectively carrying out normalization processing on the initial inter-leaf gap value and the initial throttle opening value to obtain a processed initial inter-leaf gap value and a processed initial throttle opening value;
and inputting the processed initial inter-leaf gap value and the processed initial throttle opening value into a preset multi-output prediction model together for predicting the gas at the outlet of the compressor to obtain a first predicted flow value and a first predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled.
3. The method according to claim 2, wherein the preset multi-output prediction model is a preset neural network model and includes an input layer, a hidden layer and an output layer, and the step of inputting the processed initial inter-vane gap value and the processed initial throttle valve opening value into the preset multi-output prediction model together to perform compressor outlet gas prediction to obtain a first predicted flow value and a first predicted pressure value corresponding to the compressor outlet gas to be controlled includes:
inputting the processed initial interlobe gap value and the processed initial throttle opening value into a hidden layer through an input layer of the preset neural network model, and extracting features output by the hidden layer;
inputting the output characteristics of the hidden layer into the output layer, and extracting a first predicted flow value and a first predicted pressure value which are output by the output layer and correspond to the outlet gas of the compressor to be controlled.
4. The method of claim 1, wherein prior to said inputting the initial inter-vane gap value and the initial throttle opening value together into a pre-set multi-output prediction model for compressor outlet gas prediction, obtaining a first predicted flow value and a first predicted pressure value corresponding to the compressor outlet gas to be controlled, the method further comprises:
acquiring a sample inter-vane gap value and a sample throttle opening value corresponding to a sample compressor, and an actual sample flow value and an actual sample pressure value of the sample compressor outlet gas corresponding to the sample inter-vane gap value and the sample throttle opening value;
inputting the sample inter-leaf gap value and the sample throttle opening value into a preset initial multi-output prediction model together for predicting the gas at the outlet of the sample compressor to obtain a predicted sample flow value and a predicted sample pressure value corresponding to the gas at the outlet of the sample compressor;
determining a loss function corresponding to the preset initial multi-output prediction model based on the actual sample flow value, the predicted sample flow value, the actual sample pressure value and the predicted sample pressure value;
and constructing the preset multi-output prediction model based on the loss function.
5. The method of claim 1, wherein the determining a second predicted flow value for the compressor outlet gas to be controlled at a next time based on the actual flow value and the first predicted flow value comprises:
determining a first prediction coefficient corresponding to the outlet gas flow of the compressor to be controlled;
subtracting the actual flow value from the first predicted flow value to obtain a first predicted error value corresponding to the outlet gas flow of the compressor to be controlled;
multiplying the first prediction error value by the first prediction coefficient to obtain a first prediction balance value corresponding to the outlet gas flow of the compressor to be controlled;
adding the first predicted balance value and the first predicted flow value to obtain a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment;
the determining a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual pressure value and the first predicted pressure value includes:
determining a second prediction coefficient corresponding to the outlet gas pressure of the compressor to be controlled;
subtracting the actual pressure value from the first predicted pressure value to obtain a second predicted error value corresponding to the outlet gas pressure of the compressor to be controlled;
multiplying the second prediction error value by the second prediction coefficient to obtain a second prediction balance value corresponding to the outlet gas pressure of the compressor to be controlled;
and adding the second predicted balance value and the first predicted pressure value to obtain a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment.
6. The method of claim 1, wherein the adjusting the initial inter-vane gap value and the initial throttle opening value corresponding to the compressor to be controlled based on the second predicted flow value, the preset flow value range, the second predicted pressure value, and the preset pressure value range comprises:
calculating an interlobe clearance value range and a throttle opening value range for preventing surging of the compressor to be controlled by using a preset control function based on the second predicted flow value, the preset flow value range, the second predicted pressure value and the preset pressure value range;
and adjusting an initial inter-vane gap value and the initial throttle opening value corresponding to the compressor to be controlled based on the inter-vane gap value range and the throttle opening value range.
7. The method of claim 1, wherein after determining whether the second predicted flow value is within a preset flow range and determining whether the second predicted pressure value is within a preset pressure range, the method further comprises:
and if the second predicted flow value is within the preset flow value range and the second predicted pressure value is within the preset pressure value range, determining that the compressor to be controlled cannot surge at the next moment.
8. A compressor surge control apparatus, comprising:
the device comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring an initial inter-vane gap value and an initial throttle opening value corresponding to a compressor to be controlled when surging does not occur, and an actual flow value and an actual pressure value of outlet gas of the compressor to be controlled corresponding to the initial inter-vane gap value and the initial throttle opening value;
the prediction unit is used for inputting the initial inter-leaf gap value and the initial throttle opening value into a preset multi-output prediction model together to predict the gas at the outlet of the compressor so as to obtain a first predicted flow value and a first predicted pressure value corresponding to the gas at the outlet of the compressor to be controlled;
the determining unit is used for determining a second predicted flow value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual flow value and the first predicted flow value, and determining a second predicted pressure value corresponding to the outlet gas of the compressor to be controlled at the next moment based on the actual pressure value and the first predicted pressure value;
the judging unit is used for judging whether the second predicted flow value is in a preset flow value range or not and judging whether the second predicted pressure value is in a preset pressure value range or not;
and the adjusting unit is used for adjusting an initial inter-vane gap value and an initial throttle opening value corresponding to the compressor to be controlled based on the second predicted flow value, the preset flow value range, the second predicted pressure value and the preset pressure value range to prevent the compressor to be controlled from surging at the next moment if the second predicted flow value is not in the preset flow value range and/or the second predicted pressure value is not in the preset pressure value range.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
10. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program realizes the steps of the method of any of claims 1 to 7 when executed by the processor.
CN202210581452.8A 2022-05-26 2022-05-26 Compressor surge control method and device, storage medium and computer equipment Active CN114962318B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210581452.8A CN114962318B (en) 2022-05-26 2022-05-26 Compressor surge control method and device, storage medium and computer equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210581452.8A CN114962318B (en) 2022-05-26 2022-05-26 Compressor surge control method and device, storage medium and computer equipment

Publications (2)

Publication Number Publication Date
CN114962318A CN114962318A (en) 2022-08-30
CN114962318B true CN114962318B (en) 2023-03-21

Family

ID=82971913

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210581452.8A Active CN114962318B (en) 2022-05-26 2022-05-26 Compressor surge control method and device, storage medium and computer equipment

Country Status (1)

Country Link
CN (1) CN114962318B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117588437B (en) * 2024-01-18 2024-04-12 山东豪迈机械制造有限公司 Anti-asthma compensation method and system for centrifugal compressor

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100451311C (en) * 2007-07-05 2009-01-14 东北大学 Combustion controlling device and controlling method for mini combustion turbine
CN109058151A (en) * 2018-07-13 2018-12-21 西安工程大学 A kind of Control Methods for Surge Prevention in Centrifugal Compressors based on prediction model
CN110056530B (en) * 2019-04-30 2020-11-27 沈阳透平机械股份有限公司 Anti-surge control method and system
CN110848166B (en) * 2019-11-13 2021-05-07 西北工业大学 Axial flow compressor surge frequency prediction method
CN113339310B (en) * 2021-07-19 2022-09-13 东北大学 Compressor surge prediction control method based on magnetic suspension axial position control

Also Published As

Publication number Publication date
CN114962318A (en) 2022-08-30

Similar Documents

Publication Publication Date Title
EP2062104B1 (en) Dynamic controller utilizing a hybrid model
EP2107439B1 (en) Method and system for the design and implementation of optimal multivariable model predictive controllers for fast-sampling constrained dynamic systems
CN114962318B (en) Compressor surge control method and device, storage medium and computer equipment
JP2005535130A (en) Methods, systems, and media for handling misrepresented measurement data in modern process control systems
Toscano et al. A new heuristic approach for non-convex optimization problems
Wang et al. Markov nonlinear system estimation for engine performance tracking
JP2001152875A (en) Method and system for compensating measurement error
Saushev et al. Solution of problems of parametric optimization and control of electric drives state based on information about operability area boundary
CN117029968A (en) Traffic data diagnosis method, system, storage medium and electronic equipment
CN113361048B (en) Reliability prediction method and device for gas turbine blade, and electronic device
Ou et al. An optimal design algorithm of the SPRT chart for minimizing weighted ATS
CN116734968A (en) Flow coefficient verification method, device, equipment and storage medium
JP5749041B2 (en) Active feedback control device and program
Silva et al. Multiobjective optimization using variable complexity modelling for control system design
JP2018142200A (en) State estimation method and state estimation device
US11710500B2 (en) Abnormality degree calculation system and method
Brzhozovskii et al. Realization of electrical signal monitoring of metal surface modification by means of low-temperature plasma treatment
CN111752149B (en) Design method of digital repetitive controller for designated time attraction of servo motor
CN110988787B (en) Method for realizing optimal direction finding angle measurement based on cluster analysis in wireless signal direction finding monitoring
JP2021189514A (en) Mass flow controller and hunting suppressing method
CN116821588B (en) Reactor working condition judging and predicting method based on DSMF fusion algorithm
CN116362300B (en) Regional power grid abnormal disturbance quantity prediction method, device, medium and electronic equipment
CN117711523A (en) Method and device for determining gas emission concentration
JP5865138B2 (en) Method and apparatus for determining control parameters
CN115762687B (en) Fitting method and device of material performance curve, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20220830

Assignee: Dongneng (Shenyang) Energy Engineering Technology Co.,Ltd.

Assignor: Northeastern University

Contract record no.: X2023210000291

Denomination of invention: Control methods, devices, storage media, and computer equipment for compressor surge

Granted publication date: 20230321

License type: Common License

Record date: 20231207

EE01 Entry into force of recordation of patent licensing contract