Turbine compressor full working condition prediction method and system based on digital twinborn simulation

Abstract

The invention discloses a turbine compressor all-condition prediction method and system based on digital twin simulation, and belongs to the technical field of compressor simulation. According to the method, neural network training is carried out on data obtained through mechanism model simulation of key components of a compressor pipe network system and an actual compressor pipe network system experiment data set, characteristic functions of all the components are obtained, and a high-precision target compressor digital twinning dynamic simulation system is established. A user can dynamically simulate and predict the full-cycle working condition of the target compressor pipe network system by setting the boundary condition and the initial condition, and outputs and stores the simulation result. The simulation result comprises dynamic changes of upstream and downstream pressure, temperature and flow of the compressor along with time. Through the digital twin system of the compressor pipe network system, the test working condition of the target compressor pipe network system can be simulated, and dynamic changes of pressure, temperature and flow of the corresponding working condition are obtained; and feature analysis and behavior prediction under complex working conditions can be realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of full-cycle operating condition simulation and prediction of compressor systems, and relates to a method and system for predicting the full operating condition of a turbine compressor based on digital twin simulation. Background Art

[0002] As a core equipment in the industrial field, turbine compressors are widely used in many key industries such as chemical industry, metallurgy, aviation, etc. Their main function is to achieve efficient pressurization and transportation of gas working fluids through coordinated work with pipelines, valves and other devices. In the actual operation process, the adjustment of the control parameters of the compressor pipeline system will cause a variety of different operating conditions, which directly reflect the operating status, performance fluctuations and possible safety hazards of the system. Therefore, in-depth analysis of the system operating conditions can not only grasp the working status of the equipment in real time, but also provide a scientific basis for subsequent maintenance and performance optimization, which is of extremely important practical significance.

[0003] However, the turbine compressor system faces high cost challenges in experimental testing and real-time monitoring due to its complex structure and diverse risk types. In order to effectively reduce this cost and accurately grasp the full working conditions of the compressor system, domestic and foreign scholars have long been committed to the research and development of turbine compressor working condition simulation technology. Although certain research results have been achieved, the existing turbine compressor working condition simulation prediction model still has technical problems such as insufficient prediction accuracy and difficulty in real-time simulation in practical applications, which greatly limits the further application and promotion of simulation technology in compressor system performance analysis and optimization. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art and provide a method and system for predicting the full operating conditions of a turbine compressor based on digital twin simulation, so as to solve the technical problems in the prior art that the existing turbine compressor operating condition simulation prediction model has insufficient prediction accuracy and is difficult to simulate in real time.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: A method for predicting the full working conditions of a turbine compressor based on digital twin simulation includes the following steps: S1, collecting sensor parameters and reading device parameters in the compressor pipe network system; S2, input into the digital twin simulation model of the compressor pipe network system to predict the compressor operating conditions; The acquisition process of the digital twin simulation model of the compressor pipe network system is as follows: S201, performing a compressor multi-operating condition data test to obtain a twin data set; training a neural network through the twin data set to obtain a valve flow resistance characteristic function and a compressor characteristic function; S202, constructing a mechanism simulation model of the compressor pipe network system and performing simulation, wherein the mechanism simulation model includes a compressor simulation module, a pipe network simulation module and a valve simulation module; correcting the valve simulation module by the valve flow resistance characteristic function, and correcting the compressor simulation module by the compressor characteristic function, repeating the simulation until the accuracy of the mechanism simulation model meets the accuracy requirement, otherwise repeating S201, and finally obtaining a digital twin simulation model of the compressor pipe network system; S3, output the predicted compressor operating conditions.

[0006] A further improvement of the present invention is: Preferably, in S1, the sensor parameters include valve pressure, valve temperature, valve flow, compressor inlet flow, compressor inlet temperature, compressor inlet pressure, compressor outlet flow, compressor outlet temperature and compression outlet pressure; the reading device parameters include valve opening, compressor speed and compressor power.

[0007] Preferably, in S201, the twin data set includes a valve test data set and a compressor test data set; the valve flow resistance characteristic function is obtained by training the neural network with the valve test data set, and the compressor characteristic function is obtained by training the neural network with the compressor test data set.

[0008] Preferably, in S201, the opening of the compressor inlet regulating valve (4) is used as a variable, and the pressure loss of the inlet regulating valve (4) is used as an output parameter to obtain a valve test data set; the opening of the compressor outlet regulating valve (7) is used as a variable, and the compressor operating condition is used as an output parameter to obtain a compressor characteristic function.

[0009] Preferably, during the S202 simulation process, the valve flow resistance characteristic function is placed in the valve simulation module for simulation, and the compressor characteristic function is placed in the compressor simulation module until both the valve simulation module and the compressor simulation module meet the accuracy requirements. If the accuracy requirements are not met, S201 is re-executed to obtain new valve flow resistance characteristic function and compressor characteristic function.

[0010] Preferably, during the simulation process S202, the control equations corresponding to the three simulation modules are decoupled from each other, and the parameters between the three simulation modules are transferred to each other.

[0011] Preferably, the parameters are transmitted to each other as follows: the input flow of the pipe network simulation module is the output of the compressor simulation module or the valve simulation module, and the output of the pipe network simulation module is the input pressure of the compressor or the valve.

[0012] Preferably, during the simulation process of S202, the simulation result data is imported into the twin data set of S201.

[0013] Preferably, in S3, the digital twin simulation model of the compressor pipeline network system can also simulate the typical operating conditions of the compressor pipeline network system, obtain the target process characteristics of the compressor pipeline network system, and control the compressor pipeline network system based on the target process characteristics; the target process characteristics include compressor temperature, pressure and flow.

[0014] A turbine compressor full-operating condition prediction system based on digital twin simulation, including a hardware part and a software part, wherein the hardware part includes a physical model of the compressor pipe network, a data acquisition and transmission device, and a computer control system; The physical model is used to carry out a multi-operating condition test of the compressor; The data acquisition and transmission device is used to collect data from the physical model and transmit the control instructions of the computer control system to the physical model of the compressor pipe network; The computer control system is used to build and obtain a digital twin simulation model of the compressor pipe network system, simulate the compressor pipe network system through the digital twin simulation model of the compressor pipe network system, and predict the compressor operating condition.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses a method for predicting the full working conditions of a turbine compressor based on digital twin simulation. The method collects sensor parameters and reading device parameters in the compressor pipe network system in real time, and transmits the real-time parameters to the digital twin simulation model of the compressor pipe network system. Through the digital twin simulation model of the compressor pipe network system, the working conditions can be simulated in real time, and the target working conditions can be achieved. The control parameters or coefficients are fed back to the entire compressor pipe network system. By controlling the relevant parameters of the compressor pipe network system, the compressor pipe network system can achieve the target working conditions. In the digital twin simulation model of the compressor pipe network system, the digital twin technology has high-fidelity modeling and simulation characteristics, which can achieve high-fidelity reproduction of all working conditions, and through real-time data interaction, it can achieve high-reliability simulation prediction of unknown working conditions, avoiding the high cost of full-condition experimental research. Based on digital twin technology, efficient simulation of turbine compressors in all working conditions has broad application prospects in the fields of optimizing test processes and control strategies, real-time monitoring and risk assessment. It can realize real-time simulation and prediction of the full-cycle operating conditions of the compressor system, visualize the prediction results, save and analyze the parameters, which has guiding significance for process optimization and process design, and facilitates obtaining the full operating condition map of the target system at a lower cost.

[0016] Furthermore, this method conducts neural network training on key parameters of valves and compressors based on the mechanism model, realizes the identification of key parameters by training test data of full-cycle operating conditions, and obtains a digital twin simulation system of the compressor pipeline system with high simulation accuracy. The research method is advanced and innovative.

[0017] Furthermore, this method uses neural network training to obtain the characteristic functions of key components of the compressor pipeline system to replace the mechanism model to build a digital twin simulation system, and obtains the full-cycle operating data of the compressor through dynamic simulation. It can achieve high-precision simulation while avoiding the high cost of full-operating condition test research, and is advanced and practical.

[0018] The present invention also discloses a turbine compressor full operating condition prediction system based on digital twin simulation, which is a compressor pipeline system full operating condition prediction device based on digital twin, including a hardware part and a software part; the hardware part is an acquisition and control system composed of a pipeline system and pressure sensors, temperature sensors, flow sensors, signal collection and processing equipment and computers; 3) the software part is a digital twin simulation system of the target compressor pipeline system; 4) the digital twin simulation system is used to dynamically simulate and predict the full-cycle operating conditions of the compressor pipeline system, and the simulation prediction results are output and stored. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a technical block diagram of the present invention; Figure 2 This is the structural diagram of the compressor pipe network system test equipment; Figure 3 It is the dynamic simulation result under normal working conditions of the compressor pipe network system; Figure 4 It is the dynamic simulation result under the surge condition of the compressor pipe network system; Among them, 1-physical model; 2-data acquisition and transmission device; 3-computer control system; 4-compressor inlet regulating valve; 5-compressor; 6-pipeline network; 7-compressor outlet regulating valve; 8-monitoring point; 9-prediction result; 10-full cycle operating condition map. DETAILED DESCRIPTION

[0020] The present invention is further described in detail below in conjunction with the accompanying drawings: Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0021] A first aspect of the present invention discloses a method for predicting the full working conditions of a turbine compressor based on digital twin simulation, the method comprising the following steps: Step 1: derive a mechanism simulation model of the compressor pipe network system through the mechanism model. The simulation model of the compressor pipe network system includes a compressor simulation module, a pipe network simulation module and a valve simulation module.

[0022] In this step, the specific mechanism model refers to the published patent CN 115356096 A.

[0023] In this step, the mechanism model building platform can be any basic data building platform or language, such as MATLAB, C language or Java.

[0024] Step 2, conduct relevant working condition tests in the physical model 1 of the compressor pipe network system, use the opening of the compressor inlet regulating valve 4 and the opening of the compressor outlet regulating valve 7 as control parameters, conduct multi-working condition tests in the compressor pipe network system, and obtain a test data set; the test data set includes a valve test data set and a compressor test data set. Train the neural network with the valve test data set and the valve experimental data set in the compressor pipe network system to obtain the valve flow resistance characteristic function (describing the relationship between pressure loss and flow rate when the fluid passes through the valve); train the neural network with the compressor test data set and the compressor experimental data set in the compressor pipe network system to obtain the compressor characteristic function (using the compressor outlet valve opening as a variable, and using a specific functional formula to describe the performance and operating characteristics of the compressor); When training the neural network, the number of hidden neurons of the BP neural network is selected as 10, so that the simulation error of the trained compressor digital twin model is minimized.

[0025] Step 3, bring the valve flow resistance characteristic function into the valve simulation module, bring the compressor characteristic function into the compressor simulation module, and simulate the valve simulation module and the compressor simulation module. If the simulation result accuracy of the two simulation modules meets the set standards, execute step 4, otherwise repeat step 2, and re-obtain the valve flow resistance characteristic function and the compressor characteristic function through neural network learning.

[0026] Step 4, bring the valve flow resistance characteristic function and compressor characteristic function that meet the accuracy requirements into the compressor pipe network digital twin simulation system, realize the full working condition simulation of the target compressor system through the user-designed working conditions and corresponding boundary conditions, realize the parameter transfer between the three simulation modules and the decoupling of the control equations, and obtain the compressor pipe network system digital twin simulation model; specifically, the input parameters of the compressor simulation module and the valve simulation module are pressure, and the output parameter is flow; the input parameter of the pipe network simulation module is flow, and the output parameter is pressure. Connect the pipe network simulation module between the compressor and the valve module, and the input flow required by the pipe network simulation module is provided by the compressor or valve, and the pressure output by the pipe network module is used as the input parameter of the compressor or valve.

[0027] In this step, the mechanism simulation model of the compressor pipe network system and the twin data are combined so that the conservation laws in the compressor simulation process can be corrected through the physical mechanism model, and the digital twin data-driven technology is used to obtain a digital twin hybrid model based on the above-mentioned compressor pipe network dynamic simulation system based on physical principles. Specifically, a series hybrid modeling method is used to first solve the mechanism model to obtain the mechanism output result, and then the data-driven model is used to correct the mechanism output result, and finally the digital twin simulation result is output.

[0028] In this step, the mechanism model of the compressor is obtained through conservation of mass, conservation of momentum, and conservation of energy, and the data is driven by twin data 3. Twin data comes from temperature, pressure, flow and other data collected by physical entity sensors. The transmission of "physical quantity-electrical signal-data" is realized through sensors, A / D converters, and data acquisition software, and recorded in the computer. The above data is used as a training data set for data-driven modeling in the digital twin hybrid model. The twin data in the present invention is the actual data obtained by the above-mentioned entity model 1, and further the valve flow resistance characteristic function and compressor characteristic function obtained by neural network training.

[0029] Step 5: Simulate a typical operating condition of "start-up-air supply-standby-air supply" of the target compressor through the digital twin simulation model of the compressor pipeline system, obtain the process characteristics of the target compressor system and analyze its control means, wherein the compressor process characteristics include compressor temperature, pressure and flow.

[0030] Step 6. During the operation of the physical model of the compressor pipeline system, the full-cycle operating condition control parameters of the target compressor system are input into the digital twin simulation model of the compressor pipeline system to realize the full-cycle operating condition simulation prediction of the target system. At the same time, according to the prediction results, once surge conditions or other conditions are found in the physical operation model of the compressor pipeline system, the digital twin simulation model of the compressor pipeline system can output control parameters to control the valve.

[0031] It should be noted that the above-mentioned simulation process will continuously generate relevant simulation data as twin data. The relevant parameters obtained by the simulation can be brought into the data test set, and the valve flow resistance characteristic function and the compressor characteristic function can be continuously updated. The mechanism simulation model is further corrected to obtain a continuously updated digital twin simulation model of the compressor pipeline system.

[0032] The input and output parameters of the target system are transmitted to the computer through sensors and reading devices to realize visualization of prediction results, data storage and drawing of full-cycle operating condition maps. The sensors and reading devices include compressor inlet and outlet pressure sensors, compressor outlet flow sensor, speed reading device, power reading device, opening reading devices at each valve and atmospheric temperature and pressure sensors.

[0033] The second aspect of the present invention discloses a turbo compressor full operating condition prediction system based on digital twin simulation, see Figure 1 , including a hardware part and a software part arranged in the hardware system, a physical model of the compressor pipe network system, a data acquisition and transmission device 2 and a computing control system; a software part is arranged in the computer control system, and the software part includes a mechanism modeling module and a digital twin simulation system of the compressor pipe network system.

[0034] Figure 2 The structural diagram of the device described in the present invention is given, which is divided into a physical model 1 of the compressor pipe network system, a data acquisition and transmission device, and a computer system. The physical model of the compressor pipe network system consists of a compressor inlet regulating valve 4, a turbine compressor 5, a compressor downstream pipe network 6, a compressor outlet regulating valve 7, and various signal test points 8. Specifically, a compressor inlet regulating valve 4 is provided on the inlet pipe of the turbine compressor 5, the outlet of the turbine compressor 5 is connected to the compressor downstream pipe 6, and the compressor outlet regulating valve 7 is provided on the compressor downstream pipe 6. Test points are provided between the compressor inlet regulating valve 4, the compressor inlet regulating valve 4 and the turbine compressor 5, the inlet of the compressor downstream pipe 6, and the compressor outlet regulating valve 7; pressure sensors are respectively arranged at the inlet and outlet of the turbine compressor 5, a flow sensor, a speed monitoring device, and a power monitoring device are arranged at the outlet of the turbine compressor 5, and an opening reading device, and a temperature and pressure sensor for the atmospheric environment are arranged at each valve.

[0035] Specifically, the flow sensor described in the present invention is a conical throttle and a pitot tube, and the temperature sensor is a thermometer.

[0036] The data acquisition and transmission device 2 is used to transmit the sensor signals of each test point to the digital twin simulation model of the compressor pipe network system in the digital twin platform, and at the same time transmit the control parameters set in the digital twin simulation model of the compressor pipe network system to the physical model of the compressor pipe network system. In the compressor performance test, the compressor operating point is migrated by changing the opening of the compressor inlet regulating valve 4 and the compressor outlet regulating valve 7. In the compressor pipe network system, sensors are placed at the inlet and outlet of the valve and the compressor, and the test data of the system under different working conditions are obtained. The sensor at each test point transmits the compressor test signal to the twin data 3 through the data acquisition and transmission device 2. Various sensors are connected to the data acquisition software in the computer through the signal conversion device based on the ModBus communication protocol. When the compressor pipe network system is tested, the valve opening, compressor speed and power, pressure, temperature and flow data are collected by the sensor, input into the computer through the A / D converter, and collected by the computer software, and finally the compressor pipe network system data with pressure, temperature and flow changing over time are formed. Based on the collected data, the working condition prediction of the compressor pipe network system can be realized through the trained digital twin simulation model of the compressor pipe network system.

[0037] In the digital twin simulation model of the compressor pipe network system, through the relevant configuration of the computer, the operating condition prediction results 9 and the full-cycle operating condition map 10 can be displayed.

[0038] The present invention can further realize valve control through software by using the prediction results of the working conditions of the digital twin simulation model of the compressor pipe network system. Specifically, the valve control instruction is input into the digital twin platform and input into the physical entity 1 through the data acquisition and transmission device. Through the ModBus communication protocol and register, the computer software outputs the communication instruction and relay to realize the control of the regulating valve, and inputs the valve control signal into the compressor outlet regulating valve 7 to realize the change of the action of the compressor outlet regulating valve 7 and change the compressor working condition. Through the above process, the performance test of the compressor pipe network system under various working conditions can be carried out, and the test data of the pressure, temperature and flow at the compressor and the boundary can be collected and processed.

[0039] By training the neural network with the data obtained from the simulation of the mechanism model of the key components of the compressor pipe network system and the actual compressor pipe network system experimental data set, the characteristic functions of each component are obtained, and a high-precision digital twin dynamic simulation system for the target compressor is established. By setting boundary conditions and initial conditions, users can realize the dynamic simulation and prediction of the full-cycle operating conditions of the target compressor pipe network system, and output and store the simulation results. The simulation results include the dynamic changes of the upstream and downstream pressures, temperatures, and flows of the compressor over time. Through the digital twin system of the compressor pipe network system, the test conditions of the target compressor pipe network system can be simulated to obtain the dynamic changes of the corresponding operating conditions pressure, temperature, and flow; feature analysis and behavior prediction under complex conditions can also be realized.

[0040] The following is further described in conjunction with specific embodiments: Example Step 1: Build a digital twin model of the compressor pipeline system, and perform digital twin modeling of the target compressor system through physical entity 1 and twin data 3.

[0041] Step 2: To improve the simulation accuracy of the compressor module digital twin system, the key components of the mechanism model are optimized through BP neural network training. The compressor power, speed, inlet gas temperature and pressure, and outlet gas pressure are used as input parameters of the compressor module digital twin system, and the compressor output gas mass flow rate is used as the output parameter. The weights of each layer of the neural network are updated by calculating the error between the sample output value and the target value. The training is stopped by iterating until the error of the output value meets the requirements or the number of learning times reaches the maximum number of learning times; a modular model of the compressor and throttle valve based on the BP neural network is obtained.

[0042] Step 3, during dynamic simulation, the compressor simulation module and the regulating valve simulation module in the digital twin model quickly solve the characteristic flow, and the pipe network module solves the local pressure. The two types of modules appear alternately, and the output parameters are mutually solving input conditions. At the same time, the real-time simulation results such as the compressor flow, the pressure before and after the compressor, and the valve flow are compared and analyzed with the physical sensor test results and output, realizing the function of real-time simulation and monitoring of test data. The real-time prediction of the actual compressor system achieved by the present invention has important prospects in the application of compressor system fault diagnosis and safety protection. In addition to real-time reading of physical sensor parameters, in the application of digital twin system design and optimization of unknown working conditions, the user can design boundary conditions such as valve opening and perform dynamic simulation. According to the simulation analysis results, based on the principles of efficiency, safety and economy, the control conditions and process flow of each component are optimized to provide guidance for the design of actual working conditions.

[0043] The digital twin system of the compressor pipe network system is used to dynamically simulate and predict the surge condition. According to compressor theory, surge is caused by excessive resistance downstream of the compressor and the inability of the compressor to give the working fluid enough energy to leave the system. At this time, the downstream pipe network pressure is temporarily higher than the compressor outlet pressure, the flow rate decreases, and even backflow occurs, which causes pressure fluctuations and the system enters a surge condition. In actual working conditions, when the valve opening downstream of the compressor decreases and the resistance of the pipe network downstream of the compressor increases, the system will enter a surge condition.

[0044] In a dynamic simulation study, the valve opening is gradually adjusted as follows: Under normal working conditions, the outlet valve opening is closed from 1 to 0.6 at 20s, changing the working conditions of the compressor system. Due to the decrease in the outlet valve opening, the compressor outlet pressure rises, the flow rate decreases, and the change is step-shaped, which is consistent with the valve opening. The pressure change lags behind the flow change, which is in line with the working mechanism of the compressor; at 40s, the outlet valve is closed from 0.6 to 0.4, and the compressor outlet pressure further rises and the flow rate further decreases; under surge working conditions, the outlet valve opening is closed from 1 to 0.5 at 20s, changing the working conditions of the compressor system. Due to the decrease in the outlet valve opening, the compressor outlet pressure rises, the flow rate decreases, and the change is step-shaped, which is consistent with the valve opening; at 40s, the outlet valve opening is closed from 0.5 to 0.2, and the system enters a surge state, and the pressure and flow rate fluctuate periodically. The pressure fluctuation is consistent with the flow fluctuation period, and the pressure fluctuation lags behind the flow fluctuation.

[0045] Figure 3 , Figure 4 The dynamic simulation results of pressure and flow rate under normal working condition and surge working condition of the compressor pipe network system described in the present invention are given. It can be seen that when the compressor outlet regulating valve is gradually closed from fully open, the compressor working condition changes, the working point moves left along the performance curve, and the outlet pressure gradually rises; when the compressor outlet regulating valve is closed to a sufficiently small level, the compressor enters a surge state, and the compressor pressure and flow rate both fluctuate periodically. This example fully proves that the compressor system digital twin system described in the present invention can simulate and study the surge characteristics of the compressor.

[0046] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more. In the description of the present invention, the first feature "above" or "below" the second feature may include the first and second features being in direct contact, or the first and second features not being in direct contact but being in contact through another feature between them.

[0047] In the description of the present invention, “on”, “over” and “above” a first feature from a second feature includes the first feature being directly above and obliquely above the second feature, or simply means that the first feature is horizontally higher than the second feature.

[0048] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0049] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0050] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0051] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting the full working conditions of a turbine compressor based on digital twin simulation, characterized in that: The following steps are involved: S1, collecting sensor parameters and reading device parameters in the compressor pipe network system; S2, input into the digital twin simulation model of the compressor pipe network system to predict the compressor operating conditions; The acquisition process of the digital twin simulation model of the compressor pipe network system is as follows: S201, performing a compressor multi-operating condition data test to obtain a twin data set; training a neural network through the twin data set to obtain a valve flow resistance characteristic function and a compressor characteristic function; S202, constructing a mechanism simulation model of the compressor pipe network system and performing simulation, wherein the mechanism simulation model includes a compressor simulation module, a pipe network simulation module and a valve simulation module; correcting the valve simulation module by the valve flow resistance characteristic function, and correcting the compressor simulation module by the compressor characteristic function, repeating the simulation until the accuracy of the mechanism simulation model meets the accuracy requirement, otherwise repeating S201, and finally obtaining a digital twin simulation model of the compressor pipe network system; S3, output the predicted compressor operating conditions.

2. A method for predicting the full working conditions of a turbine compressor based on digital twin simulation according to claim 1, characterized in that: In S1, the sensor parameters include valve pressure, valve temperature, valve flow, compressor inlet flow, compressor inlet temperature, compressor inlet pressure, compressor outlet flow, compressor outlet temperature and compression outlet pressure; the reading device parameters include valve opening, compressor speed and compressor power.

3. A method for predicting full working conditions of a turbine compressor based on digital twin simulation according to claim 1, characterized in that: In S201, the twin data set includes a valve test data set and a compressor test data set; the valve flow resistance characteristic function is obtained by training the neural network through the valve test data set, and the compressor characteristic function is obtained by training the neural network through the compressor test data set.

4. A method for predicting the full working conditions of a turbine compressor based on digital twin simulation according to claim 2, characterized in that: In S201, the opening of the compressor inlet regulating valve (4) is used as a variable, and the pressure loss of the inlet regulating valve (4) is used as an output parameter to obtain a valve test data set; the opening of the compressor outlet regulating valve (7) is used as a variable, and the compressor operating condition is used as an output parameter to obtain a compressor characteristic function.

5. The method for predicting the full working conditions of a turbine compressor based on digital twin simulation according to claim 1 is characterized in that: During the S202 simulation process, the valve flow resistance characteristic function is placed in the valve simulation module for simulation, and the compressor characteristic function is placed in the compressor simulation module until both the valve simulation module and the compressor simulation module meet the accuracy requirements. If the accuracy requirements are not met, S201 is re-executed to obtain new valve flow resistance characteristic function and compressor characteristic function.

6. A method for predicting full working conditions of a turbine compressor based on digital twin simulation according to claim 1, characterized in that: During the simulation process S202, the control equations corresponding to the three simulation modules are decoupled from each other, and the parameters between the three simulation modules are transmitted to each other.

7. A method for predicting the full working conditions of a turbine compressor based on digital twin simulation according to claim 6, characterized in that: The parameters are transmitted to each other as follows: the input flow of the pipe network simulation module is the output of the compressor simulation module or the valve simulation module, and the output of the pipe network simulation module is the input pressure of the compressor or the valve.

8. A method for predicting full working conditions of a turbine compressor based on digital twin simulation according to claim 1, characterized in that: During the simulation process of S202, the simulation result data is imported into the twin data set of S201.

9. The method for predicting the full working conditions of a turbine compressor based on digital twin simulation according to claim 1 is characterized in that: In S3, the digital twin simulation model of the compressor pipe network system can also simulate the typical working conditions of the compressor pipe network system, obtain the target process characteristics of the compressor pipe network system, and control the compressor pipe network system based on the target process characteristics; The target process characteristics include compressor temperature, pressure and flow.

10. A turbine compressor full operating condition prediction system based on digital twin simulation, characterized in that: It comprises a hardware part and a software part, wherein the hardware part comprises a physical model of a compressor pipe network (1), a data acquisition and transmission device (2) and a computer control system (3); The physical model (1) is used to carry out a multi-operating condition test of a compressor; The data acquisition and transmission device (2) is used to acquire data from the physical model (1) and transmit control instructions of the computer control system to the physical model (1) of the compressor pipe network; The computer control system is used to build and obtain a digital twin simulation model of the compressor pipe network system, simulate the compressor pipe network system through the digital twin simulation model of the compressor pipe network system, and predict the compressor operating condition.

Images