An air compressor monitoring system and method based on digital twin refined modeling

Abstract

The present application discloses an air compressor monitoring system and method based on digital twin refined modeling. The system includes: a data acquisition module, a model training module, a simulation module and a monitoring module; the data acquisition module is connected to the model training module to collect state parameters of the air compressor during operation and obtain a state parameter training set; the model training module is also connected to the simulation module to construct a digital twin parameter model based on the state parameter training set; the simulation module is also connected to the monitoring module to perform simulation based on the digital twin parameter model to obtain a parameter optimization model and determine the optimal interval of each parameter; the monitoring module is used to perform real-time monitoring based on the parameter optimization model and adjust the operating state parameters of the air compressor to the optimal interval of each parameter. The present application can save the material cost required for large-scale experiments, improve economic benefits, effectively monitor abnormal changes in current parameters, and issue alarms in time to prevent accidents.

Description

Technical Field

[0001] The present application relates to the field of control and monitoring technology, and specifically to an air compressor monitoring system and method based on digital twin refined modeling. Background Art

[0002] Currently, in the coal industry, air compressors are crucial airflow supply devices, and their operational stability and reliability significantly impact underground production. Failure to operate the compressor properly can hinder the operation of underground equipment and, in severe cases, lead to safety accidents, impacting coal mine production safety. Furthermore, a lack of monitoring of compressor operating parameters can easily lead to compressor failures. Monitoring compressor operating parameters can improve operational reliability.

[0003] Therefore, it is necessary to design an air compressor virtual platform system based on digital twin refined modeling to effectively supervise the air compressor operation process, timely discover the current operation problems of the air compressor, prevent the air compressor from malfunctioning, and solve the problem of monitoring the air compressor operation process. Summary of the Invention

[0004] The present application provides an air compressor monitoring system and method based on digital twin refined modeling, which accurately reconstructs the twin model of the air compressor system and realizes parameter optimization and real-time monitoring of energy consumption of the air compressor.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] An air compressor monitoring system based on digital twin refined modeling includes: a data acquisition module, a model training module, a simulation module, and a monitoring module;

[0007] The data acquisition module is connected to the model training module, and the data acquisition module is used to collect state parameters of the air compressor during operation to obtain a state parameter training set;

[0008] The model training module is also connected to the simulation module, and the model training module is used to construct a digital twin parameter model based on the state parameter training set;

[0009] The simulation module is also connected to the supervision module, and is used to perform simulation based on the digital twin parameter model to obtain a parameter optimization model and determine the optimal range of each parameter;

[0010] The monitoring module is used to perform real-time monitoring based on the parameter optimization model, and simultaneously adjust the operating status parameters of the air compressor to the optimal range of each parameter.

[0011] Preferably, the data acquisition module includes: a first acquisition unit and a second acquisition unit;

[0012] The state parameters include a first acquired data set and a second acquired data set;

[0013] The first acquisition unit is used to collect lubricating oil temperature, lubricating oil pressure, cooling water temperature, water pump pipeline pressure, exhaust temperature and main pipe pressure to obtain the first acquisition data set;

[0014] The second acquisition unit is used to acquire motor temperature, motor shaft vibration, host voltage and host current to obtain the second acquisition data set.

[0015] Preferably, the model training module includes: a first computer, a second computer and a first central processing unit;

[0016] The first computer is used to receive and analyze the first collected data set to obtain a parameter variation pattern;

[0017] The second computer is used to receive and analyze the second acquired data set to obtain a parameter change relationship;

[0018] The first central processing unit is used to construct the digital twin parameter model based on the parameter change law and the parameter change relationship.

[0019] Preferably, the simulation module includes a second central processing unit;

[0020] The second central processing unit is used to perform simulation based on the digital twin parameter model to obtain the parameter optimization model;

[0021] The second central processing unit is also used to perform simulation based on the digital twin parameter model to obtain simulation working parameters, input the simulation working parameters into the parameter optimization model for simulation, and obtain the optimal range of each parameter.

[0022] Preferably, the supervision module includes: a status monitoring device and an automatic adjustment device;

[0023] The state monitoring device is used to determine whether the air compressor has abnormal operation or failure based on the parameter optimization model and the state parameters;

[0024] The automatic adjustment device is used to adjust the operating state parameters of the air compressor to the optimal range of each parameter.

[0025] This application also provides an air compressor supervision method based on digital twin refined modeling, comprising the following steps:

[0026] Collecting state parameters of the air compressor during operation to obtain a state parameter training set;

[0027] Building a digital twin parameter model based on the state parameter training set;

[0028] Perform simulation based on the digital twin parameter model to obtain a parameter optimization model and determine the optimal range of each parameter;

[0029] Real-time monitoring is performed based on the parameter optimization model, and the operating status parameters of the air compressor are adjusted to the optimal range of each parameter.

[0030] Preferably, the state parameters include: lubricating oil temperature, lubricating oil pressure, cooling water temperature, water pump pipeline pressure, exhaust temperature, main pipe pressure, motor temperature, motor shaft vibration, host voltage and host current.

[0031] Preferably, the method for determining the optimal interval of each parameter is:

[0032] Simulation is performed based on the digital twin parameter model to obtain simulated working parameters, and the simulated working parameters are input into the parameter optimization model for simulation to obtain the optimal range of each parameter.

[0033] The beneficial effects of this application are:

[0034] This application can analyze the operating status of the air compressor through computer model simulation, save the material cost required for large-scale experiments, and improve economic benefits. In addition, the air compressor digital twin parameter model can effectively predict the mutual change relationship between the various parameters of the air compressor. When a certain parameter of the air compressor changes abnormally, the air compressor digital twin parameter model can effectively monitor the abnormal changes of the current parameter and issue an alarm in time to prevent accidents in the operation of the air compressor, affect production safety, and cause economic losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solution of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0036] Figure 1 This is a structural diagram of an air compressor monitoring system based on digital twin refined modeling in an embodiment of the present application;

[0037] Figure 2 This is a schematic diagram of the workflow of the data acquisition module in the embodiment of the present application;

[0038] Figure 3 This is a schematic diagram of the workflow of the model training module in the embodiment of the present application;

[0039] Figure 4 This is a schematic diagram of the workflow of the simulation module in the embodiment of the present application;

[0040] Figure 5 This is a flow chart of the optimization method of the parameter optimization model in the embodiment of the present application;

[0041] Figure 6 This is a schematic diagram of the workflow of the supervision module in the embodiment of the present application;

[0042] Figure 7 This is a flow chart of an air compressor monitoring method based on digital twin refined modeling in an embodiment of the present application. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0044] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0045] Example 1

[0046] In this embodiment 1, Figure 1 As shown, an air compressor monitoring system based on digital twin refined modeling includes: a data acquisition module, a model training module, a simulation module and a monitoring module.

[0047] The data acquisition module is connected to the model training module and is used to collect state parameters during air compressor operation to obtain a state parameter training set. The data acquisition module includes a first acquisition unit and a second acquisition unit. In this embodiment, the first acquisition unit includes a first collector, a second collector, and a third collector, and the second acquisition unit includes a fourth collector and a fifth collector. The first collector is used to collect lubricating oil temperature and lubricating oil pressure, the second collector is used to collect cooling water temperature and water pump pipeline pressure, the third collector is used to collect exhaust temperature and main pipe pressure, the fourth collector is used to collect motor temperature and motor shaft vibration, and the fifth collector is used to collect machine voltage and main machine current.

[0048] like Figure 2As shown, the workflow of the data acquisition module includes: using the first acquisition unit and the second acquisition unit to collect state parameters that affect the normal operation of the air compressor during operation, establishing an air compressor digital twin parameter model based on the collected state parameters, and then monitoring the operating parameters of the air compressor in real time, and feeding the air compressor operating parameters back to the model training module through the collector, wherein the first acquisition unit is used to collect lubricating oil temperature, lubricating oil pressure, cooling water temperature, water pump pipeline pressure, exhaust temperature and main pipe pressure to obtain a first acquisition data set; the second acquisition unit is used to collect motor temperature, motor shaft vibration, host voltage and host current to obtain a second acquisition data set.

[0049] The model training module is also connected to the simulation module and is used to construct a digital twin parameter model based on the state parameter training set; the model training module includes: a first computer, a second computer and a first central processing unit; the first computer is used to receive and analyze the first acquisition data set to obtain the parameter change law; the second computer is used to receive and analyze the second acquisition data set to obtain the parameter change relationship; the first central processing unit is used to construct the digital twin parameter model based on the parameter change law and the parameter change relationship.

[0050] like Figure 3 As shown, the workflow of the model training module includes: using the first computer and the second computer to supplement the first data set and the second data set of the air compressor; then, continuously adjusting the operating status of the air compressor, adjusting the air compressor to a slightly abnormal working state, and feeding back the data to the air compressor digital twin parameter model, so that the air compressor digital twin parameter model records the parameter change characteristics of the air compressor when the air compressor shows an abnormal trend; finally, the first central processor establishes the air compressor digital twin parameter model based on a large amount of data under different conditions and working conditions of the air compressor.

[0051] The simulation module is also connected to the supervision module and is used to perform simulation based on the digital twin parameter model to obtain a parameter optimization model and simultaneously determine the optimal range of each parameter. The simulation module includes a second central processing unit (CPU). The second CPU is used to perform simulation based on the digital twin parameter model to obtain the parameter optimization model. The second CPU is also used to simulate based on the digital twin parameter model to obtain simulation operating parameters, input the simulation operating parameters into the parameter optimization model for simulation, and obtain the optimal range of each parameter. In this embodiment, the second CPU selects two processors for interactive collaboration, namely the first processor and the second processor.

[0052] like Figure 4As shown, the workflow of the simulation module includes: using the digital twin parameter model of the air compressor to perform simulation, adjusting the water pump pipeline pressure and the host voltage and current, where the water pump pipeline pressure is related to the water pump power, and adjusting the water pump pipeline pressure is the water pump power adjustment, analyzing the changing relationship between the lubricating oil temperature, lubricating oil pressure, cooling water temperature, exhaust temperature, main pipe pressure and motor temperature and motor shaft vibration. The main pipe pressure is the pressure at the output gas, that is, the gas output pressure during the air compressor air supply process. The lubricating oil temperature, lubricating oil pressure, cooling water temperature, exhaust temperature, and main pipe pressure are output to the first processor, and the motor temperature and motor shaft vibration are output to the second processor. During the processing, the two processors complete data interaction and joint processing, build an air compressor parameter optimization model and optimize it, simulate based on the digital twin parameter model, obtain simulated working parameters, input the simulated working parameters into the parameter optimization model for simulation, and obtain the optimal range of each parameter.

[0053] like Figure 5 As shown, the optimization method of the air compressor parameter optimization model in this embodiment includes: obtaining a parameter optimization model through the air compressor digital twin parameter model, taking the water pump pipeline pressure, host voltage and host current parameters in the air compressor parameter optimization model as input, adjusting the air compressor to this working parameter, collecting lubricating oil temperature, lubricating oil pressure, cooling water temperature, water pump pipeline pressure, exhaust temperature and main pipe pressure, and inputting their data into the first industrial computer; collecting the motor temperature, motor shaft vibration, host voltage and host current during the operation of the air compressor, and inputting their data into the second industrial computer; the industrial computer will calculate the difference between the actual value of the above parameters and the theoretical value in the parameter optimization model, and judge whether the deviation is within the error range. If the parameter is within the error range, the current parameter optimization result is reliable and can be used for promotion and use. If the current deviation value is large and exceeds the error range, the parameter name, simulation value and actual output value will be output, and the technical personnel will analyze the cause and re-perform simulation analysis in the air compressor digital twin parameter model to obtain the parameter optimization model.

[0054] The monitoring module is used to perform real-time monitoring based on the parameter optimization model and adjust the operating parameters of the air compressor to the optimal range of each parameter. The monitoring module includes a status monitoring device and an automatic adjustment device. The status monitoring device is used to determine whether the air compressor is operating abnormally or malfunctioning based on the parameter optimization model and the status parameters; the automatic adjustment device is used to adjust the operating parameters of the air compressor to the optimal range of each parameter.

[0055] like Figure 6As shown, the workflow of the supervision module includes: during the operation of the air compressor, the water pump pipeline pressure, lubricating oil temperature, lubricating oil pressure, cooling water temperature, exhaust temperature, main pipe pressure, motor temperature, motor shaft vibration, host voltage and host current are all output in real time, and the current operating parameters are read and compared with the current optimal range of each parameter. If the current parameters are abnormal, an alarm is triggered and the machine is shut down in time to prevent safety hazards caused by operation under equipment failure conditions. The host current and voltage are read, and the host power is calculated. The host energy consumption can be judged based on the host power to achieve parameter optimization and energy consumption monitoring of the air compressor. The air compressor energy consumption forecast is as follows:

[0056] P=UI

[0057] W=APt

[0058] In the formula, P is the host power, U is the host voltage, I is the host current, W is the power consumption of the air compressor, t is the working time, and A is the power compensation coefficient. In actual work, the power consumption generated by the air compressor is greater than the host power. According to the actual situation, A is usually taken as 1.1-1.5.

[0059] Example 2

[0060] In the second embodiment, Figure 7 As shown in FIG, an air compressor monitoring method based on digital twin refined modeling includes the following steps:

[0061] S1. Collect the state parameters of the air compressor during operation to obtain a state parameter training set; use the first acquisition unit and the second acquisition unit to collect the state parameters that affect the normal operation of the air compressor during operation, and establish an air compressor digital twin parameter model based on the collected state parameters. Then, monitor the operating parameters of the air compressor in real time, and feed the air compressor operating parameters back to the model training module through the collector, wherein the first acquisition unit is used to collect lubricating oil temperature, lubricating oil pressure, cooling water temperature, water pump pipeline pressure, exhaust temperature and main pipe pressure to obtain a first acquisition data set; the second acquisition unit is used to collect motor temperature, motor shaft vibration, host voltage and host current to obtain a second acquisition data set.

[0062] S2. Construct a digital twin parameter model based on the state parameter training set; use the first computer and the second computer to supplement the first data set and the second data set of the air compressor; then, continuously adjust the operating state of the air compressor, adjust the air compressor to a slightly abnormal working state, and feed the data back to the digital twin parameter model of the air compressor, so that the digital twin parameter model of the air compressor records the parameter change characteristics of the air compressor when the air compressor shows an abnormal trend; finally, the first central processing unit establishes the digital twin parameter model of the air compressor based on a large amount of data under different conditions and working conditions of the air compressor.

[0063] S3. Perform simulation based on the digital twin parameter model to obtain a parameter optimization model and determine the optimal range of each parameter; use the digital twin parameter model of the air compressor to perform simulation, adjust the water pump pipeline pressure and the host voltage and host current, where the water pump pipeline pressure is related to the water pump power, and adjusting the water pump pipeline pressure is the water pump power adjustment, and analyze the changing relationship between the lubricating oil temperature, lubricating oil pressure, cooling water temperature, exhaust temperature, main pipe pressure and motor temperature and motor shaft vibration. The main pipe pressure is the pressure at the output gas, that is, the gas output pressure during the air compressor air supply process. The lubricating oil temperature, lubricating oil pressure, cooling water temperature, exhaust temperature, and main pipe pressure are output to the first processor, and the motor temperature and motor shaft vibration are output to the second processor. During the processing, the two processors complete data interaction and joint processing, construct an air compressor parameter optimization model and optimize it, simulate based on the digital twin parameter model to obtain simulated working parameters, input the simulated working parameters into the parameter optimization model for simulation, and obtain the optimal range of each parameter.

[0064] S4. Real-time monitoring is performed based on the parameter optimization model, and the operating status parameters of the air compressor are adjusted to the optimal range of each parameter. The workflow of the supervision module includes: during the operation of the air compressor, the water pump pipeline pressure, lubricating oil temperature, lubricating oil pressure, cooling water temperature, exhaust temperature, main pipe pressure, motor temperature, motor shaft vibration, host voltage and host current are all output in real time; the current operating parameters are read and compared with the current optimal range of each parameter; if the current parameters are abnormal, an alarm is issued in time and the machine is shut down to prevent safety hazards caused by operation under equipment failure conditions; the host current and voltage are read, the host power is calculated, and the host energy consumption can be determined based on the host power, thereby realizing parameter optimization and energy consumption monitoring of the air compressor. The air compressor energy consumption prediction is as follows:

[0065] P=UI

[0066] W=APt

[0067] In the formula, P is the host power, U is the host voltage, I is the host current, W is the power consumption of the air compressor, t is the working time, and A is the power compensation coefficient. In actual work, the power consumption generated by the air compressor is greater than the host power. According to the actual situation, A is usually taken as 1.1-1.5.

[0068] The embodiments described above are merely descriptions of the preferred embodiments of the present application and do not limit the scope of the present application. Without departing from the design spirit of the present application, various modifications and improvements made to the technical solutions of the present application by ordinary technicians in this field should fall within the scope of protection determined by the claims of the present application.

Claims

1. An air compressor monitoring system based on digital twin refined modeling, characterized by: include: Data acquisition module, model training module, simulation module and supervision module; The data acquisition module is connected to the model training module, and the data acquisition module is used to collect state parameters of the air compressor during operation to obtain a state parameter training set; The model training module is also connected to the simulation module, and the model training module is used to construct a digital twin parameter model based on the state parameter training set; The simulation module is also connected to the supervision module, and is used to perform simulation based on the digital twin parameter model to obtain a parameter optimization model and determine the optimal range of each parameter; The monitoring module is used to perform real-time monitoring based on the parameter optimization model and adjust the operating state parameters of the air compressor to the optimal range of each parameter; The data acquisition module includes: a first acquisition unit and a second acquisition unit; The state parameters include a first acquired data set and a second acquired data set; The first acquisition unit is used to collect lubricating oil temperature, lubricating oil pressure, cooling water temperature, water pump pipeline pressure, exhaust temperature and main pipe pressure to obtain the first acquisition data set; The second acquisition unit is used to collect motor temperature, motor shaft vibration, host voltage and host current to obtain the second acquisition data set; The model training module includes: a first computer, a second computer and a first central processing unit; The first computer is used to receive and analyze the first collected data set to obtain a parameter variation pattern; The second computer is used to receive and analyze the second acquired data set to obtain a parameter change relationship; The first central processing unit is used to construct the digital twin parameter model based on the parameter change law and the parameter change relationship; The simulation module includes a second central processing unit; The second central processing unit is used to perform simulation based on the digital twin parameter model to obtain the parameter optimization model; The second central processing unit is further configured to perform simulation based on the digital twin parameter model to obtain simulation operating parameters, and input the simulation operating parameters into the parameter optimization model for simulation to obtain the optimal range of each parameter; The workflow of the simulation module includes: using the digital twin parameter model of the air compressor to perform simulation, adjusting the water pump pipeline pressure and the host voltage and current, where the water pump pipeline pressure is related to the water pump power, and adjusting the water pump pipeline pressure is the water pump power regulation, analyzing the changing relationship between the lubricating oil temperature, lubricating oil pressure, cooling water temperature, exhaust temperature, main pipe pressure and motor temperature and motor shaft vibration. The main pipe pressure is the pressure at the output gas, that is, the gas output pressure during the air compressor air supply process. The lubricating oil temperature, lubricating oil pressure, cooling water temperature, exhaust temperature, and main pipe pressure are output to the first processor, and the motor temperature and motor shaft vibration are output to the second processor. During the processing, the two processors complete data interaction and joint processing, build an air compressor parameter optimization model and optimize it, simulate based on the digital twin parameter model to obtain simulated working parameters, input the simulated working parameters into the parameter optimization model for simulation, and obtain the optimal range of each parameter; The optimization method of the air compressor parameter optimization model includes: obtaining a parameter optimization model through the air compressor digital twin parameter model, taking the water pump pipeline pressure, host voltage and host current parameters in the air compressor parameter optimization model as input, adjusting the air compressor to this working parameter, collecting lubricating oil temperature, lubricating oil pressure, cooling water temperature, water pump pipeline pressure, exhaust temperature and main pipe pressure, and inputting their data into the first industrial computer; collecting the motor temperature, motor shaft vibration, host voltage and host current during the operation of the air compressor, and inputting their data into the second industrial computer; the industrial computer will calculate the difference between the actual value of the above parameters and the theoretical value in the parameter optimization model, and judge whether the deviation is within the error range. If the parameter is within the error range, the current parameter optimization result is reliable and can be used for promotion and use. If the current deviation value is large and exceeds the error range, the parameter name, simulation value and actual output value will be output, and the technical personnel will analyze the cause and re-perform simulation analysis in the air compressor digital twin parameter model to obtain the parameter optimization model; The supervision module includes: a state monitoring device and an automatic adjustment device; The state monitoring device is used to determine whether the air compressor has abnormal operation or failure based on the parameter optimization model and the state parameters; The automatic adjustment device is used to adjust the operating state parameters of the air compressor to the optimal range of each parameter.

2. An air compressor monitoring method based on digital twin refined modeling, the air compressor monitoring method is applied to the air compressor monitoring system according to claim 1, characterized in that: The following steps are involved: Collecting state parameters of the air compressor during operation to obtain a state parameter training set; Building a digital twin parameter model based on the state parameter training set; Perform simulation based on the digital twin parameter model to obtain a parameter optimization model and determine the optimal range of each parameter; Real-time monitoring is performed based on the parameter optimization model, and the operating status parameters of the air compressor are adjusted to the optimal range of each parameter.

3. The air compressor monitoring method based on digital twin refined modeling according to claim 2 is characterized in that: The state parameters include: lubricating oil temperature, lubricating oil pressure, cooling water temperature, water pump pipeline pressure, exhaust temperature, main pipe pressure, motor temperature, motor shaft vibration, main engine voltage and main engine current.

4. The air compressor monitoring method based on digital twin refined modeling according to claim 2 is characterized in that: The method for determining the optimal interval of each parameter is: Simulation is performed based on the digital twin parameter model to obtain simulated working parameters, and the simulated working parameters are input into the parameter optimization model for simulation to obtain the optimal range of each parameter.

Images