Oil-free digital energy air compression station monitoring system based on air floating shaft

Abstract

The invention relates to an oil-free digital energy air compression station monitoring system based on an air floating shaft, which comprises a data acquisition module, a communication module, a central processing unit, a monitoring terminal and a control execution module, and is characterized in that the data acquisition module is responsible for acquiring information such as the rotating speed of the air floating shaft, the inlet and outlet pressure and temperature of an air compressor, motor operation parameters and the like in real time; the communication module is used for transmitting the acquired data to the central processing unit; the central processing unit analyzes, processes and stores the received data and generates a corresponding control signal; the monitoring terminal is used for displaying information and receiving an operation instruction; and the control execution module controls the air compression station according to the control signal. According to the system, oil pollution is completely eradicated through an oil-free lubrication air floating shaft technology, and the air quality is guaranteed; accurate monitoring and fault early warning of core components and overall working conditions of the equipment are achieved through intelligent monitoring, and the stability and reliability of the equipment are improved; an operation strategy is intelligently optimized according to actual gas consumption requirements, and energy conservation and consumption reduction are achieved; and remote monitoring and management are supported.

Description

Technical Field

[0001] This invention relates to the technical field of digital energy monitoring, and more particularly to an oil-free digital energy air compressor station monitoring system based on an air-floating shaft. Background Technology

[0002] With the continuous development of industry, air compressor stations play a crucial role in many production fields, providing a stable and reliable compressed air power source for various pneumatic equipment and processes. However, most traditional air compressor stations use oil-lubricated air compressors, which have many drawbacks during operation.

[0003] On the one hand, the lubricating oil in oil-filled air compressors may mix into the compressed air due to leakage or carryover, causing pollution to subsequent air-using equipment and affecting product quality. This problem is particularly prominent in industries with extremely high air quality requirements, such as food, pharmaceuticals, and electronics, and may even lead to serious production accidents and economic losses. In addition, complex oil-gas separation and filtration devices are required to reduce the risk of oil pollution, which increases the complexity of the system and operating costs.

[0004] On the other hand, the monitoring systems of traditional air compressor stations have a relatively low level of intelligence. They typically only monitor and display basic operating parameters such as pressure and temperature, lacking precise, real-time status sensing of core air compressor components such as the air bearing shaft. This makes it difficult to predict potential faults in advance, often resulting in reactive repairs after a fault occurs. This not only prolongs equipment downtime and affects production schedules but also increases repair difficulty and costs as the fault escalates. Furthermore, traditional monitoring systems struggle to accurately assess and optimize the overall energy efficiency of the air compressor station, failing to flexibly adjust the compressor's operating conditions based on dynamic changes in actual air demand. This leads to significant energy waste during operation, hindering the company's energy conservation and emission reduction goals, as well as its efforts to achieve peak carbon emissions and carbon neutrality.

[0005] Furthermore, lubrication and wear issues of key components such as the air bearing shaft in traditional air compressors have always been critical factors affecting equipment reliability and service life. Oil-based lubrication methods cannot completely avoid problems such as oil deterioration and poor lubrication, which in turn affect the stable operation of the air bearing shaft, shorten equipment lifespan, and increase equipment replacement costs and long-term operational burdens for enterprises.

[0006] Against this backdrop, it is particularly urgent and necessary to develop an oil-free digital energy air compressor station monitoring system based on an air-bearing shaft to overcome the shortcomings of traditional air compressor stations in terms of air quality, monitoring intelligence, fault early warning and handling capabilities, energy saving effect, and lubrication and maintenance of key components, so as to meet the urgent needs of modern industry for high performance, high reliability, energy saving and intelligence of air compressor stations. Summary of the Invention

[0007] To address the aforementioned issues, this invention provides an oil-free digital energy air compressor station monitoring system based on an air-bearing shaft. This invention forms a closed-loop intelligent analysis system for air compressor data within the digital energy air compressor station monitoring environment, which not only improves the service life and automation level of air compressor equipment but also enhances the system's comprehensive adaptability to equipment capabilities and data compliance requirements.

[0008] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A monitoring system for an oil-free digital energy air compressor station based on an air-bearing shaft is provided, comprising: The data acquisition module is used to collect information such as the air bearing shaft speed, air compressor inlet and outlet pressures, temperature, and motor operating parameters in the oil-free digital energy air compressor station in real time. A communication module, connected to the data acquisition module, is used to transmit the acquired data to the central processing unit; The central processing unit, connected to the communication module, is used to analyze, process and store the received data, dynamically generate the optimal control strategy based on the real-time status of the air compressor, and generate corresponding control signals based on the control strategy. The monitoring terminal, connected to the central processing unit, is used to display various information and statuses of the monitoring system, as well as to receive operation commands input by the user. The control execution module is connected to the central processing unit and controls the operation of the air compressor station according to the control signal, and dynamically adjusts the operating parameters of the air compressor unit according to the optimization strategy.

[0009] Preferably, the data acquisition module includes multiple sensors, which are used to detect the radial vibration displacement and axial displacement of the air bearing shaft, the exhaust temperature of the air compressor, current and voltage, respectively.

[0010] Preferably, the communication module uses wireless communication and the OPC UA protocol to realize data interaction between modules.

[0011] Preferably, the central processing unit includes a data processing subunit and a storage subunit. The data processing subunit performs real-time analysis and diagnosis of the collected data by constructing an air compressor capacity prediction model, and the storage subunit is used to store historical data and control strategy information. The air compressor capacity prediction model is used to calculate the air compressor's equipment capacity score by comprehensively considering various operating conditions of the air compressor. The specific calculation method for the equipment capacity score is as follows: ; in, This represents the equipment capability score of the i-th air compressor, where μ represents the equipment error coefficient. This represents the preliminary equipment capacity score calculated by the air compressor capacity prediction model. This represents a matrix of real-time status data for air compressor equipment. This represents the equipment degradation weighting coefficient, used to adjust the impact of equipment health degradation, and Delay(t) represents the equipment health degradation function.

[0012] Preferably, the monitoring terminal has a graphical interface that can intuitively display the operating parameter curves, equipment status indicators, and alarm information of the air compressor station, and supports remote access and control functions.

[0013] Preferably, the control execution module includes a frequency converter, a solenoid valve controller, and a cooling system controller. The control execution module controls the operating conditions of each air compressor in the air compressor station by adjusting the motor speed, controlling the valve opening, and starting or stopping the cooling equipment.

[0014] Preferably, an alarm module is also included, which is connected to the central processing unit, and is used to issue an audible and visual alarm signal when an abnormal situation is detected, such as when the air compressor air bearing shaft is overspeeding, the pressure is abnormal, or the temperature is too high, so as to remind the operator to deal with it in time.

[0015] Preferably, a feedback adjustment module is also included. This module is connected to the data acquisition module and the central processing unit. The feedback adjustment module compares the real-time status data of the air compressor with the optimal control strategy generated by the central processing unit, calculates the feedback error between the real-time status data and the optimal control strategy, and adjusts the air compressor output when the feedback error exceeds a preset threshold. When the feedback error is less than the preset threshold, it indicates a large deviation between the optimal control state and the actual state, and the central processing unit adjusts the air compressor output. When the feedback error is less than the preset threshold, it indicates that the current control effect is close to expectations, and the air compressor maintains its current output without adjustment.

[0016] The beneficial effects of this invention are as follows: 1. This monitoring system comprehensively and in real-time monitors the air bearing shaft speed, air compressor inlet and outlet pressures, temperature, and motor operating parameters through its data acquisition module. It can accurately perceive the status of core components and the overall operating condition of the equipment. Utilizing advanced data analysis and processing algorithms, it can promptly detect abnormal fluctuations in operating parameters and provide early and accurate warnings of potential faults.

[0017] 2. Through optimized system architecture and integrated monitoring and management, this system organically integrates the operation control, parameter monitoring, and fault diagnosis functions of oil-free air compressors, forming a highly collaborative and stable operating system. Efficient communication and timely, accurate data sharing between modules ensure that the air compressor station can stably cope with various operating condition changes and emergencies, enhancing the overall system's anti-interference capability and reliability. This provides a solid and reliable compressed air power guarantee for enterprise production, reducing the probability of serious consequences such as production line paralysis due to air compressor station failures, and effectively supporting the enterprise's continuous and large-scale production operations.

[0018] 3. The equipped monitoring terminal supports remote access and control functions. Operators do not need to be physically present on-site; they can view the real-time operating status, historical data, and alarm information of the air compressor station anytime, anywhere via the network, and can remotely issue operating commands, achieving convenient and efficient management of the air compressor station. This is especially suitable for enterprises with multiple air compressor stations distributed in different areas, effectively reducing the cost and difficulty of manual inspections and management, improving operational management level and response speed, and realizing intelligent, unmanned, or minimally staffed operation modes of the air compressor station, further reducing the enterprise's human resource investment and operating costs.

[0019] The oil-free digital energy air compressor station monitoring system based on air-bearing shafts demonstrates significant advantages in air quality assurance, intelligence, energy saving, equipment maintenance, operational stability, and remote management. It can effectively solve many problems existing in traditional air compressor stations, has broad market application prospects and important promotion and application value, and can bring huge economic and social benefits to the production and operation of industrial enterprises. Attached Figure Description

[0020] Figure 1 This is a framework diagram of an oil-free digital energy air compressor station monitoring system based on an air-floating shaft, according to the present invention. Detailed Implementation

[0021] Please see Figure 1 As shown, this invention relates to an oil-free digital energy air compressor station monitoring system based on an air-bearing shaft, comprising: The data acquisition module is used to collect information such as the air bearing shaft speed, air compressor inlet and outlet pressures, temperature, and motor operating parameters in the oil-free digital energy air compressor station in real time. A communication module, connected to the data acquisition module, is used to transmit the acquired data to the central processing unit; The central processing unit, connected to the communication module, is used to analyze, process and store the received data, dynamically generate the optimal control strategy based on the real-time status of the air compressor, and generate corresponding control signals based on the control strategy. The monitoring terminal, connected to the central processing unit, is used to display various information and statuses of the monitoring system, as well as to receive operation commands input by the user. The control execution module is connected to the central processing unit and controls the operation of the air compressor station according to the control signal, and dynamically adjusts the operating parameters of the air compressor unit according to the optimization strategy.

[0022] The data acquisition module includes multiple sensors, which are used to detect the radial vibration displacement and axial displacement of the air bearing shaft, the exhaust temperature of the air compressor, current and voltage.

[0023] High-precision radial vibration sensors and axial displacement sensors are installed at the air bearing shaft of each oil-free air compressor to monitor the operating status of the air bearing shaft in real time. Their measurement accuracy is ±0.001mm, and the sampling frequency is 10kHz. Simultaneously, pressure transmitters and temperature sensors are installed on the inlet and outlet pipes of the air compressor to monitor air pressure and temperature parameters. The pressure transmitter has a measurement range of 0 - 1.6MPa and an accuracy of ±0.2%, while the temperature sensor has a measurement range of -20℃ to 120℃ and an accuracy of ±0.5℃. Furthermore, current transformers and voltage transformers are installed at the input of the drive motor to monitor the motor's current and voltage. The current transformer has a measurement range of 0-300A and an accuracy of ±0.5%, while the voltage transformer has a measurement range of 0-440V and an accuracy of ±0.5%. All sensors are connected to the data acquisition module via wired connections. The data acquisition module uses an industrial-grade distributed data acquisition unit with multi-channel input and high-speed data acquisition and processing capabilities. It can simultaneously acquire multiple types of sensor signals and perform preliminary data preprocessing operations such as filtering and range conversion.

[0024] The collected radial vibration displacement, axial displacement, air compressor exhaust temperature, current, and voltage of the air bearing shaft need to be preprocessed and transformed into a unified input feature set for subsequent modeling. Since the data comes from multiple sources with different timestamps, data granularity, and formats, time alignment, normalization, and missing value imputation are required to ensure the data can be fused into a standardized feature vector.

[0025] The data preprocessing process consists of three core steps: time alignment, normalization, and missing value imputation, to ensure data quality and consistency.

[0026] The communication module uses wireless communication and the OPC UA protocol to achieve data interaction between modules.

[0027] The communication module employs industrial wireless access points and client network cards based on Wi-Fi 6 technology to wirelessly connect the data acquisition module and the central processing unit. Multiple industrial wireless access points are deployed throughout the air compressor station workshop to ensure signal coverage of the entire station area. The wireless access points and client network cards utilize a highly secure OPC UA encrypted transmission protocol to guarantee the security and reliability of data transmission. The communication bandwidth reaches 120Mbps, sufficient to meet the transmission requirements of large amounts of real-time data.

[0028] The central processing unit includes a data processing subunit and a storage subunit. The data processing subunit performs real-time analysis and diagnosis of the collected data by constructing an air compressor capacity prediction model. The storage subunit is used to store historical data and control strategy information. The central processing unit utilizes a high-performance industrial server equipped with two 3.5GHz multi-core processors, 64GB of RAM, and 2TB of solid-state drive storage, running customized monitoring system software. The data processing subunit performs real-time analysis and diagnosis of the collected data by constructing an air compressor capacity prediction model, including SVM-based fault diagnosis algorithms, multiple linear regression energy efficiency analysis algorithms, and Kalman filtering and PCA system condition monitoring algorithms.

[0029] Fault Diagnosis Algorithm: A machine learning-based fault diagnosis algorithm is used to extract and analyze features from the collected air bearing shaft vibration and temperature signals. For example, the Support Vector Machine (SVM) algorithm is used to train and classify the time-domain and frequency-domain features of the radial and axial displacement signals of the air bearing shaft, establishing a fault feature model. This model can accurately identify early wear and instability of the air bearing shaft, as well as overheating and overpressure faults in the air compressor. The fault diagnosis accuracy is significantly improved compared to traditional methods, enabling precise early warning and diagnosis of equipment faults.

[0030] Energy efficiency analysis algorithm: A multiple linear regression algorithm is used, with parameters such as the air compressor's input power, inlet and outlet pressures, flow rate, and motor current and voltage as input variables, to establish an energy efficiency analysis model. This model can calculate the air compressor's specific power and other energy efficiency indicators in real time and compare them with historical best energy efficiency data. This accurately assesses the real-time operating energy efficiency status of the air compressor station, providing accurate data support for subsequent energy-saving optimization control. Energy efficiency analysis errors are effectively controlled, significantly improving the accuracy of energy efficiency assessment.

[0031] System status monitoring algorithm: A Kalman filter algorithm is used to filter various collected operating parameters in real time, removing noise interference from the signal and improving the accuracy and reliability of the data. Simultaneously, a data-driven principal component analysis (PCA) algorithm is employed to perform dimensionality reduction and feature extraction on the processed data, enabling comprehensive and real-time monitoring of the overall system status of the air compressor station. This allows for the timely detection of abnormal fluctuations and trend changes during system operation, providing a stable and reliable data foundation for fault diagnosis and energy efficiency analysis. The stability and reliability of system status monitoring are effectively improved compared to traditional methods.

[0032] The storage sub-unit uses a combination of relational databases and time-series databases to store historical operating data, fault records, energy efficiency assessment reports, and control strategies. The data storage period can reach more than 10 years, providing sufficient data support for the long-term operation and data analysis of the system.

[0033] The air compressor capacity prediction model is used to calculate the air compressor's equipment capacity score by comprehensively considering various operating conditions of the air compressor. The specific calculation method for the equipment capacity score is as follows: ; in, This represents the equipment capability score of the i-th air compressor, where μ represents the equipment error coefficient. This represents the preliminary equipment capacity score calculated by the air compressor capacity prediction model. This represents a matrix of real-time status data for air compressor equipment. This represents the equipment degradation weighting coefficient, used to adjust the impact of equipment health degradation, and Delay(t) represents the equipment health degradation function.

[0034] Assuming the equipment performs well initially, but with increased usage, the air compressor pressure may gradually decrease and the equipment temperature may rise, leading to a decline in equipment efficiency. In this case, Delay(t) will increase over time, thereby dynamically adjusting the capability score to more accurately reflect the actual performance of the equipment.

[0035] To ensure the device capability model can adapt to changes in device status, an incremental learning strategy is introduced. Specifically, when new device status data arrives, the model is not trained from scratch, but updated by fine-tuning the existing model. This reduces computational resource consumption while ensuring the model's real-time performance.

[0036] To enhance the adaptability of the strategy, an innovative equipment capacity degradation adjustment term is introduced. Long-term use of equipment may lead to capacity degradation (such as aging of the air bearing shaft, decrease in air compressor output pressure, and increase in current load), which affects the equipment's performance. To handle this degradation, a dynamically adjusted degradation factor, Delay(t), is added to the strategy gradient method. This factor changes dynamically based on the equipment's usage duration and state changes. The formula for the degradation adjustment term is as follows: , in: It is in state Select action Strategies; It is a state Take action below The value function, This indicates the long-term benefit of taking a certain action in this state; It is the control coefficient for the recession factor; As the equipment is used for longer periods of time, An increase indicates a gradual decline in the equipment's capabilities.

[0037] The key to incremental learning is to fine-tune the model using only the new data each time it arrives. With each update, the model updates its weights through mini-batch learning, without retraining the entire model. This allows the device capability model to quickly adapt to changes in device status, improving prediction accuracy.

[0038] One of the outputs of the central processing unit is a capacity score for the air compressor. It is a The vector represents the capability of each air compressor i under the current conditions, ranging from [0,1]. The closer it is to 1, the stronger the working capability of the equipment, the higher the score, and the better the working efficiency and health status of the equipment.

[0039] By combining the air bearing shaft status with the air compressor equipment status data, a model was used to generate an equipment capacity score. To adapt to long-term changes in equipment health status, a degradation function and a regularization term were introduced, enabling the equipment capacity score to be dynamically adjusted. Furthermore, an incremental learning strategy was employed to ensure the model can adapt to changes in equipment status in real time, thereby improving the accuracy of equipment capacity prediction.

[0040] The monitoring terminal has a graphical interface that can intuitively display the operating parameter curves, equipment status indicators and alarm information of the air compressor station, and supports remote access and control functions.

[0041] A 55-inch high-definition monitoring display screen is installed in the central control room of the air compressor station as the monitoring terminal. Multiple workstation computers are also provided to facilitate detailed data analysis and the issuance of operational commands by operators. The monitoring terminal is connected to the central processing unit via a local area network, using the TCP / IP communication protocol for data exchange. The communication bandwidth is 1000Mbps, ensuring real-time monitoring and rapid operational response. The graphical interface of the monitoring terminal is designed using visual development tools, intuitively displaying the real-time operating parameters of each air compressor, such as air bearing shaft speed, inlet and outlet pressure, temperature curves, and motor power. Different colors and flashing effects are used to provide alarm prompts for abnormal conditions. Simultaneously, operators can remotely view historical operating data, fault diagnosis reports, and energy efficiency analysis results through the monitoring terminal, and adjust control strategies and system parameters as needed.

[0042] The control execution module includes a frequency converter, a solenoid valve controller, and a cooling system controller. The control execution module controls the operating conditions of each air compressor in the air compressor station by adjusting the motor speed, controlling the valve opening, and starting or stopping the cooling equipment.

[0043] The control execution module mainly includes a frequency converter, solenoid valve controller, and cooling system controller for each air compressor. The frequency converter is a product from a well-known brand, with a power range of 150kW and a speed regulation accuracy of ±0.1%. It can precisely adjust the motor speed according to the control signals issued by the central processing unit, achieving stepless speed regulation control of the air compressor. The solenoid valve controller controls the opening of the air compressor's intake valve, exhaust valve, and cooling system valves. It uses 24V DC solenoid valves with a response time of 50ms, enabling rapid response to control signals and ensuring the loading and unloading of the air compressor and the normal operation of the cooling system. The cooling system controller automatically adjusts the cooling fan speed and cooling water flow rate based on signals from the temperature sensor, ensuring the air compressor operates within a suitable temperature range.

[0044] The central processing unit (CPU) acts like a smart brain, using real-time collected parameters such as compressed air pressure, temperature, and flow rate, combined with historical operating data and preset control logic, to perform in-depth data analysis and calculations. It then precisely issues commands to each actuator, enabling coordinated operation. In actual operation, multiple air compressors work together to meet the air demand of large-scale production. Based on the real-time status of each unit and changes in overall air consumption, the CPU creates a scientific operating sequence: during periods of low demand, some air compressors are ordered to switch to low-speed standby or stop operating, while the remaining units maintain low air supply under inverter control, ready to respond to immediate changes in air demand; during peak demand periods, standby units quickly start up, and all air compressors, under the overall coordination of the CPU, either accelerate via inverters or regulate air intake via solenoid valves, working together to increase air supply and ensure a stable supply of compressed air. This fully demonstrates the high efficiency and intelligence of multi-component coordinated control, maximizing the overall operational efficiency of the air compressor station. The central processing unit issues instructions to each execution component based on real-time data and preset strategies. Each component responds and executes the instructions, ultimately achieving stable and efficient operation of the air compressor system.

[0045] The system also includes a feedback adjustment module, which is connected to the data acquisition module and the central processing unit. The feedback adjustment module compares the real-time status data of the air compressor with the optimal control strategy generated by the central processing unit, calculates the feedback error between the real-time status data and the optimal control strategy, and adjusts the output of the air compressor by the central processing unit when the feedback error is greater than a preset threshold. When the feedback error is less than the preset threshold, it means that the current control effect is close to the expectation, and the air compressor maintains its current output without adjustment.

[0046] The following is the working principle of the air compressor station monitoring system of this invention: When the air compressor station starts up, the central processing unit first performs a self-test on the entire monitoring system, checking the connection status of each module and the operation of the hardware to ensure normal system function. Then, the data acquisition module begins initializing and configuring each sensor, calibrating the sensor's zero point and range, and establishing communication connections with the sensors. The communication module also begins establishing a wireless network connection to ensure uninterrupted data transmission. The central processing unit loads pre-stored control strategies and algorithm models, preparing to receive and process data. The monitoring terminal displays the system startup screen and prompts the operator that the system is initializing.

[0047] During the operation of the air compressor station, the data acquisition module collects data from various sensors in real time according to a set sampling frequency. This includes information such as the vibration displacement of the air bearing shaft, the pressure and temperature at the air compressor inlet and outlet, and the current and voltage of the motor. After preliminary processing, the collected data is transmitted to the central processing unit in real time via the communication module according to a set data packet format and transmission protocol. For example, the radial vibration sensor of the air bearing shaft collects 10,000 data points per second. These data points are packaged into groups of 100, with timestamps and device identification information added, and then transmitted to the central processing unit via a wireless network to ensure data integrity and real-time performance.

[0048] After receiving the data, the central processing unit immediately parses and stores the data, storing the real-time data in the time-series database. Then, the fault diagnosis algorithm is activated to extract and analyze the vibration signals of the air bearing shaft. Using the SVM fault diagnosis model trained on a large amount of historical fault data, the currently collected vibration signal features are classified and identified. For example, when the air bearing shaft experiences early wear, the amplitude of a specific frequency band in the frequency domain of its vibration signal will change. The fault diagnosis algorithm can accurately detect this change and match it with the fault features in the model, thereby accurately determining that the air bearing shaft has a wear fault and assessing its severity. The fault diagnosis results are sent to the monitoring terminal as alarm information and simultaneously recorded in the database, providing a basis for subsequent maintenance.

[0049] Meanwhile, the energy efficiency analysis algorithm uses a multiple linear regression model to calculate energy efficiency indicators such as the specific power of the air compressor in real time, based on collected parameters such as the air compressor's input power, inlet and outlet pressures, flow rate, and motor current and voltage. For example, by statistically analyzing the operating data of the air compressor under different load conditions over a period of time, an energy efficiency model is established. When the actual operating energy efficiency of the air compressor is lower than a set threshold, the energy efficiency analysis algorithm triggers an energy-saving optimization control process. The central processing unit generates corresponding control signals based on the energy efficiency analysis results and sends them to the control execution module, such as adjusting the output frequency of the inverter and reducing the motor speed, so that the air compressor's air supply matches the actual air demand, thereby achieving energy-saving operation.

[0050] The system status monitoring algorithm employs a Kalman filter to perform real-time filtering on various collected operating parameters, removing noise interference from the signals and improving the accuracy and reliability of the data. For example, signals collected by temperature sensors may exhibit fluctuations and noise due to environmental interference and other factors. The Kalman filter can effectively smooth the temperature curve and extract the true temperature change trend. Then, the PCA algorithm is used to perform dimensionality reduction and feature extraction on the processed data, transforming multi-dimensional operating parameters into several principal component features, enabling comprehensive and real-time monitoring of the overall system status of the air compressor station. When abnormal fluctuations occur in the system status, such as a sudden drop in the air compressor's supply pressure or an abnormal increase in motor current, the system status monitoring algorithm can detect these changes promptly and issue alarm signals to remind operators to take appropriate measures.

[0051] Monitoring and Operation Response: The monitoring terminal displays real-time operating status information of the air compressor station, including real-time parameter curves for each air compressor, equipment status indicators (such as running, stopped, faulty, etc.), alarm information lists, and energy efficiency analysis results. Operators can view detailed equipment operating data and historical trends through the monitoring terminal to gain a comprehensive understanding of the air compressor station's operation. For example, when the monitoring terminal issues an alarm for air bearing wear, operators can immediately view the fault diagnosis report to understand the specific location and severity of the fault. Then, based on the maintenance manual and system prompts, they can arrange for maintenance personnel to perform targeted repairs, such as replacing the air bearing or adjusting the air bearing clearance, to ensure the normal operation of the equipment.

[0052] Meanwhile, operators can send operation commands to the central processing unit via the monitoring terminal based on production needs and system operation status, such as starting or stopping a specific air compressor, adjusting the air supply pressure setpoint, and modifying control strategies. Upon receiving the operation commands, the central processing unit performs safety and rationality checks and then sends the corresponding control signals to the control execution module, enabling remote control and management of the air compressor station. For example, during peak production periods, as air demand increases, operators can send commands via the monitoring terminal to increase the number of operating air compressors or increase their operating load to ensure a stable supply of compressed air; during off-peak production periods, the number of operating air compressors or their operating load can be reduced to achieve energy-saving operation.

[0053] The central processing unit (CPU) periodically performs in-depth mining and analysis of stored historical operating data, continuously optimizing fault diagnosis models, energy efficiency analysis models, and system control strategies by combining advanced digital signal processing algorithms. For example, by learning and training on newly added fault data, the accuracy and adaptability of fault diagnosis algorithms are further improved; based on changes in gas demand and energy price fluctuations at different times, the weight parameters of the energy efficiency analysis model and energy-saving control strategies are adjusted to ensure that the air compressor station always maintains optimal operating conditions. The CPU predicts the real-time capacity status of each air compressor using an air compressor capacity prediction model to dynamically adjust the operating parameters of that air compressor. A feedback adjustment module is set up to compare the real-time status data of the air compressor with the optimal control strategy generated by the CPU, calculating the feedback error between the real-time status data and the optimal control strategy. When the feedback error is greater than a preset threshold, it indicates a large deviation between the optimal control state and the actual state, and the CPU adjusts the output of the air compressor; when the feedback error is less than the preset threshold, it indicates that the current control effect is close to expectations, and the air compressor maintains its current output without adjustment. It can automatically and dynamically adjust the algorithm model and control parameters according to the aging of the equipment and changes in the operating environment, ensuring long-term stable operation and performance improvement of the system.

[0054] Overall, this system solves many problems existing in traditional air compressor stations, has significant economic and social benefits, and can be widely used in various industrial production fields.

[0055] The above embodiments are merely descriptions of preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made by those skilled in the art to the technical solutions of the present invention without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. A monitoring system for an oil-free digital energy air compressor station based on an air-bearing shaft, characterized in that, include: The data acquisition module is used to collect information such as the air bearing shaft speed, air compressor inlet and outlet pressures, temperature, and motor operating parameters in the oil-free digital energy air compressor station in real time. A communication module, connected to the data acquisition module, is used to transmit the acquired data to the central processing unit; The central processing unit, connected to the communication module, is used to analyze, process and store the received data, dynamically generate the optimal control strategy based on the real-time status of the air compressor, and generate corresponding control signals based on the control strategy. The monitoring terminal, connected to the central processing unit, is used to display various information and statuses of the monitoring system, as well as to receive operation commands input by the user. The control execution module is connected to the central processing unit and controls the operation of the air compressor station according to the control signal, and dynamically adjusts the operating parameters of the air compressor unit according to the optimization strategy.

2. The oil-free digital energy air compressor station monitoring system based on an air-bearing shaft according to claim 1, characterized in that, The data acquisition module includes multiple sensors, which are used to detect the radial vibration displacement and axial displacement of the air bearing shaft, the exhaust temperature of the air compressor, current and voltage.

3. The oil-free digital energy air compressor station monitoring system based on an air-bearing shaft according to claim 1, characterized in that, The communication module uses wireless communication and the OPC UA protocol to achieve data interaction between modules.

4. The oil-free digital energy air compressor station monitoring system based on an air-bearing shaft according to claim 1, characterized in that, The central processing unit includes a data processing subunit and a storage subunit. The data processing subunit performs real-time analysis and diagnosis of the collected data by constructing an air compressor capacity prediction model. The storage subunit is used to store historical data and control strategy information. The air compressor capacity prediction model is used to calculate the air compressor's equipment capacity score by comprehensively considering various operating conditions of the air compressor. The specific calculation method for the equipment capacity score is as follows: ； in, This represents the equipment capability score of the i-th air compressor, where μ represents the equipment error coefficient. This represents the preliminary equipment capacity score calculated by the air compressor capacity prediction model. This represents a matrix of real-time status data for air compressor equipment. This represents the equipment degradation weighting coefficient, used to adjust the impact of equipment health degradation, and Delay(t) represents the equipment health degradation function.

5. A monitoring system for an oil-free digital energy air compressor station based on an air-bearing shaft according to claim 1, characterized in that, The monitoring terminal has a graphical interface that can intuitively display the operating parameter curves, equipment status indicators, and alarm information of the air compressor station, and supports remote access and control functions.

6. The oil-free digital energy air compressor station monitoring system based on an air-bearing shaft according to claim 1, characterized in that, The control execution module includes a frequency converter, a solenoid valve controller, and a cooling system controller. The control execution module controls the operating conditions of each air compressor in the air compressor station by adjusting the motor speed, controlling the valve opening, and starting or stopping the cooling equipment.

7. The oil-free digital energy air compressor station monitoring system based on an air-bearing shaft according to claim 1, characterized in that, It also includes an alarm module connected to the central processing unit, which is used to issue an audible and visual alarm signal when an abnormal situation is detected, such as when the air compressor air bearing shaft is overspeeding, the pressure is abnormal, or the temperature is too high, so as to remind the operator to deal with it in time.

8. A monitoring system for an oil-free digital energy air compressor station based on an air-bearing shaft according to claim 1, characterized in that, It also includes a feedback adjustment module, which is connected to the data acquisition module and the central processing unit. The feedback adjustment module is used to compare the real-time status data of the air compressor with the optimal control strategy generated by the central processing unit, and calculate the feedback error between the real-time status data of the air compressor and the optimal control strategy. When the feedback error is greater than a preset threshold, it indicates that the deviation between the optimal control state and the actual state is large, and the output of the air compressor is adjusted by the central processing unit. When the feedback error is less than the preset threshold, it indicates that the current control effect is close to the expectation, and the air compressor maintains its current output without adjustment.

Images