Automatic central tuning of compressed air systems

Abstract

The invention relates to a device and a method for centralized control of a compressed air system. In particular, the present invention relates to a method and apparatus for a compressed air system having a centralized controller system that provides an automatic tuning process to achieve optimal tuning parameters for a specific location. Controlling the compressor system includes at least one compressor configured to provide compressed air or gas. The automatic tuning method comprises the steps of collecting initial data by monitoring the compressor system, estimating a new data set by an estimation unit until the estimated data is configured to be different from the initial data, compiling a new parameter set based on the estimated data, validating the new parameter set derived from the estimated data, and tuning the new parameter set based on the validated new parameter set. All steps are repeated until a verification of a new parameter is achieved, a new tuning is applied based on the verified parameter, instructing at least one of the elements in the compressor chamber to perform an action according to the tuning process.

Description

Technical Field

[0001] The present invention relates to an apparatus for centralized control of a compressed air system. In particular, the present invention relates to a method and apparatus for a compressed air system having a centralized controller system that provides an automatic tuning process to achieve optimal tuning parameters for a specific site. Background Art

[0002] Air compressors are used in a variety of industries, such as automotive, manufacturing, construction, and more. They are necessary to power tools and equipment, making them an integral part of any industrial process. However, air compressors can have limitations that can negatively affect their efficiency, energy consumption, and productivity. Fortunately, air compressors are undergoing a revolution with the advent of smart technology, providing improved performance, sustainability, and cost-effectiveness.

[0003] As part of smart technology, artificial intelligence is already helping air compressors achieve optimal performance by using algorithms to monitor and notify users of these systems. AI algorithms can identify patterns in system operation, predicting and preventing potential failures.

[0004] Traditionally, air compressor maintenance is performed on a fixed schedule, which can result in unnecessary downtime and wasted resources. With smart technology, maintenance can be performed based on the actual condition of the compressor. AI technology can analyze the compressor's data to identify potential issues before they become major problems, allowing maintenance to be performed at the right time.

[0005] Predictive maintenance can save time and money by reducing the need for frequent maintenance checks. It can also prevent unexpected equipment failures that can lead to expensive repairs and downtime. In addition, predictive maintenance can increase the life of your air compressor, reducing the need for replacements and lowering costs.

[0006] AI-controlled air compressors can also improve safety in industrial environments. For example, if a tool is not being operated correctly, an AI algorithm on the compressor can detect this and notify the system to shut down, preventing accidents and injuries. Additionally, where noise reduction is the goal, AI technology can help identify the source of noise. This is crucial in workplaces where noise levels can cause hearing damage. Moreover, by reducing overall wear and tear, such as due to vibration, noise reduction will extend the life of the compressor.

[0007] The use of AI in air compressors is still in its early stages, but the potential for growth is huge. As AI technology continues to develop, we should expect more advancements in air compressor technology.

[0008] Air compressors are well known for their high energy consumption. AI algorithms can optimize the operation of compressors, thereby reducing energy usage and costs. Additionally, AI technology can identify when a compressor is not in use and shut it down, thereby reducing energy waste. Energy efficiency is crucial in today's world where energy costs are rising and environmental issues are extremely important. By using AI-controlled air compressors, factories can reduce their energy consumption and carbon emissions, making them more sustainable and environmentally friendly. However, these AI algorithms are not always safe to use. They do not provide any guarantees on system performance or system safety. As a result, these systems cannot be used in practice due to safety concerns.

[0009] Another approach is to combine AI algorithms with existing and proven technologies. According to the present invention, AI algorithms learn from the data of the compressor and adjust its operation to achieve even better efficiency and performance. The performance of multiple compressors working together in a compressed air system can be optimized using central tuning technology including AI support in the compressor system. It considers the system instead of looking at the performance of each individual machine. By using a combination of existing and predictable control schemes with AI technology, safe and high-performance systems can be designed. Proven technology can be tuned to achieve the best possible efficiency through AI algorithms while still considering safety requirements. In addition, AI technology can be used to predict future energy needs, adding valuable information to more advanced control methods to adjust the operating point of the air compressor, thereby further reducing energy consumption.

[0010] Configuring each device in the most efficient way is not a simple task. There are a large number of these systems, making it difficult for humans to improve the optimization of the system. Multiple compressors can be connected in a compressed air system to supply compressed air to the same distribution network. These compressors can have several types, sizes and ages, which can lead to uneven loads and system inefficiencies. There are a large number of different pneumatic networks, which can be divided into different categories according to their structure, size, layout and capacity. The customer may have several requirements for the system in terms of energy efficiency and demand requirements.

[0011] In order to handle the wide variety of systems in which the compressor can be configured, there are a number of parameters available. These parameters can be technical parameters, such as power, pressure ratio and / or start-up time. Other parameters can include economic parameters, such as investment and / or maintenance costs, or even environmental requirements, such as energy efficiency and / or noise requirements during operation. Taking all these parameters into account and correcting for different system layouts is difficult in practice. The maintenance technician quickly loses a global overview of all possibilities for configuring the system.

[0012] Central tuning requires modifying the control of each compressor, taking into account inter alia the interaction between the compressors, in order to obtain a balanced system and maximum efficiency. Measurement and analysis of system performance, including elements such as pressure, flow rate and energy consumption, is part of the central tuning process. In addition, system characteristics important to the system should also be considered, such as wear, humidity, noise and temperature effects. This is usually done once by a technician when these systems are installed. However, after a period of time, when the machines deteriorate or when the system is changed, the process needs to be repeated.

[0013] AI-assisted central tuning can result in significant energy savings, improved system reliability, and reduced maintenance costs. Although machine learning and AI technologies are rapidly advancing, a skilled technician or engineer with specific expertise and experience in compressed air systems is typically still responsible for central tuning of the compressor system. This is due to several factors. First, compressor systems can be complex and require an understanding of how the various parts of the system work together. Second, the central tuning process includes modifying the compressor controls, which requires a comprehensive understanding of unique compressor models and their control schemes. Finally, central tuning involves optimizing the performance of the entire compressed air system, which requires a holistic perspective of the system and its needs.

[0014] In the present invention, machine learning and AI techniques enable to assist or even take over the complex tuning process. The central tuning process includes analyzing system data, learning the working principle of the system, verifying the necessary parameters, providing suggestions for adjustments to the compressor control and executing it.

[0015] By analyzing data from sensors and other sources, AI algorithms can adjust control parameters in real time to achieve the best possible performance, taking into account factors such as temperature, pressure, and flow rate. They can identify changes in the system that inherently lead to system retuning. This can be done in real time without the need for external interaction or stopping the system to perform benchmarking. Real-time tuning efforts can guarantee that the system will always operate at the best achievable efficiency. As a result, the compressor system's controls will be able to continuously operate at peak efficiency.

[0016] By building in a validation step, it is guaranteed that the new tuning parameters are safe for the system. This avoids downtime or degradation of the system. It allows the generated compressed air to always meet the minimum required air quality required by the user.

[0017] In addition, in the present invention, the AI ​​algorithm can identify the root cause of the fault in advance. By analyzing data from sensors and other sources, the AI ​​algorithm enables technicians to take corrective actions and avoid downtime. Correctly diagnosed faults in the compressor system allow them to be repaired quickly and effectively. The condition of the compressor is monitored in real time, and any signs of impending failure are detected. By analyzing data from sensors and other sources, the AI ​​algorithm can identify patterns indicating the need for maintenance, allowing maintenance to be performed proactively rather than reactively. In a further embodiment, based on the analysis, the maintenance technician is notified of the impending failure.

[0018] Additionally, AI can be used to analyze the performance of compressor systems over time, identifying trends and patterns that can help operators optimize their operations. By analyzing data from sensors and other sources, AI algorithms can provide insights into areas where performance can be improved, such as energy efficiency or reliability. It can recommend where to take additional measures, such as installing additional sensors, changing the system, or replacing the current compressor.

[0019] In summary, AI can be a valuable tool for optimizing compressor system performance, reducing energy consumption, and improving reliability, ultimately leading to cost savings and improved operational efficiency.

[0020] To achieve this behavior, AI algorithms can optimize and control various parameters in the system. The tuning parameters used for the central tuning system can vary depending on the specific compressor system being used.

[0021] The pressure set point parameter determines the desired operating pressure of the compressed air system. A central tuning system adjusts the output pressure of the compressor to match the set point and maintain a consistent pressure throughout the system. In an embodiment of the present invention, the pressure in the inlet and outlet points can be monitored by pressure sensors.

[0022] The load / unload set point parameter determines when the compressor should start and stop operating based on the demand for compressed air. A central tuning system monitors the system's air demand and adjusts parameters affecting the compressor's output accordingly to ensure efficient operation.

[0023] The cycle time parameter controls how often the compressor runs and stops. A central tuning system adjusts the cycle time to minimize energy consumption while still meeting the system's air needs while avoiding compressor problems such as overheating or condensation.

[0024] The central tuning system can optimize the efficiency of the system by adjusting the compressor output to match the demand for compressed air. This helps to reduce energy consumption and extend the life of the compressor system.

[0025] By optimizing these kinds of parameters, a central tuning system can ensure that the compressor system operates at its maximum efficiency while still meeting the demand for compressed air.

[0026] In the prior art, attempts to alleviate the problems associated with optimizing performance of multiple compressors working together in a compressed air system are described in the following patents.

[0027] Chinese patent application No. CN113741174 discloses an adaptive pressure control algorithm for a reciprocating natural gas compressor. When the gas lift compressor is working, the gas collection and pressurization can be achieved by using a PID control algorithm and logical judgment on the exhaust pressure of the gas lift compressor. When each well is working, a set of PID controller parameters matching the compressor needs to be set. On the basis of conventional PID controller parameters, the PID controller parameters can be automatically adjusted according to the changes in the working characteristics of the well site. In the intelligent control algorithm with the parameters in the optimal state, the online parameter self-correction of the PID controller is realized through fuzzy control technology.

[0028] WO2023001903A1 discloses a method for providing at least one design configuration of a compressed air system including at least two compressors connected in parallel, wherein the method comprises the following steps. A computer receives component data, wherein the component data comprises a compressor list containing a plurality of compressors of different types. A computer generates a bifurcated data structure. The computer generates compressed air system configuration data specifying a compressed air system configuration, in which two compressors from the compressor list are connected in parallel. The computer calculates at least one quality value for at least one of the compressed air system configurations based on the compressed air system configuration and at least one technical parameter of the compressor of the compressed air system configuration, wherein the at least one quality value specifies the quality of the compressed air system configuration with respect to a quality standard preferably predefined by a user. The computer provides at least one compressed air system configuration, which has at least one associated quality value in each case.

[0029] US20160245273 relates to an electronic control device for a component for compressed air generation, compressed air processing, compressed air storage and / or compressed air distribution, wherein the electronic control device relies on one or more models as component-related models, which contain information related to the structure or behavior of the component in order to determine, simulate or evaluate operation-related data, and for evaluation purposes, perform open-loop control, closed-loop control, diagnosis and / or monitoring of the component, or perform determination, provision, prediction or optimization of operation data, operation states, operation modes, operation behaviors and / or operation effects based on the models in a specific evaluation routine, and wherein current or historical structure information operation data, operation states and / or measurement / sensor values ​​of the component that are at least partially available in the electronic control device are used as initial values.

[0030] The present invention enables the tuning process to be performed on a separate device or server and by calculating optimized parameters without any simulation. The combination of measured data and a priori models is used to improve the parameters of the system. In the prior art, for the purpose of monitoring in optimization, the PI settings are manipulated or iterative adaptive model simulations are used.

[0031] The commissioning of a compressed air system is a critical process to ensure its efficient operation and performance. During commissioning, various parameters associated with the components of the system need to be tuned to achieve the desired output. In the prior art, this process is manual and time-consuming, requiring a skilled technician to make repeated adjustments and verify the results. The present invention addresses this challenge by introducing an automated tuning system that significantly reduces commissioning time and continually improves the overall performance of the compressed air system. Summary of the invention

[0032] One of the objects of the present invention is to provide a method for optimally and efficiently managing a compressor system.

[0033] It is an object of the present invention to provide an automated tuning method for a compressed gas system to determine optimal parameters that help improve performance, reduce maintenance costs and provide a more stable control system.

[0034] Another object of the present invention is to reduce or eliminate the amount of time a technician needs to spend on the tuning process.

[0035] Another object of the invention is to provide a central tuning which determines the most efficient parameters independently of the adjustments in the system and the specific conditions on site, thereby keeping the system in optimal working conditions at all times, regardless of changes in the system.

[0036] The present invention shows an automatic tuning algorithm that can tune various parameters of a system related to the operation of the system. In order to make the tuning process more efficient (streamline) when commissioning, the central tuning process reduces the amount of time a technician needs to spend when commissioning. Central tuning proposes to automatically tune these types of parameters based on an algorithm that reads the required inputs from the operation control unit. The central automatic tuning process determines the optimal tuning parameters for a specific site.

[0037] The present invention relates to an automatic tuning system for compressed air systems, which is specifically designed to make the tuning process more efficient when commissioning. The system utilizes algorithms and data collected from a centralized controller to predict and implement optimal tuning parameters for a specific site, thereby reducing the time and effort required by technicians during commissioning. By continuously learning and applying tuning parameters, the system ensures the most efficient operation of the compressed air system, resulting in increased energy savings and improved performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings serve only for the purpose of illustrating a device for haemostasis testing, the advantages of which over the prior art have been outlined above and will be briefly explained below.

[0039] The drawings are not meant to limit the scope of protection defined in the claims, nor should the scope defined in the claims be interpreted by referring to the drawings alone without resorting to the technical disclosure in the specification of the present invention.

[0040] Figure 1 is an overall perspective view of a compressor system according to the present invention.

[0041] Figure 2 is a diagram showing an operating state of a compressor system according to the present invention.

[0042] Figure 3 is a flow chart illustrating an algorithm loop according to the present invention.

[0043] Reference Parts List

[0044] 100 compressor systems

[0045] 101, 102, 103 compressors

[0046] 104, 105, 106 local controller

[0047] 107 air net volume

[0048] 110 Flow Sensor

[0049] 111 Consumers

[0050] 112 Central Controller

[0051] 113 Compressor Room DETAILED DESCRIPTION

[0052] Figure 1 A compressor system 100 according to an illustrative embodiment of the present invention is shown. The compressor system 100 includes a compressor room 113 and a control unit. In an embodiment of the present invention, the control unit includes a central controller 112 or at least one local controller 104, 105, 106 for the operation of the elements in the compressor system 100. The elements include compressors 101, 102, 103, and in an embodiment of the present invention, the compressor room 113 also includes other elements, such as dryers, coolers, sensors, filters, heaters and valves. The compressor room 113 also includes an airnet volume 107 for compressed gas, as a space within an existing pipeline or container.

[0053] The compressor room 113 includes local controllers 104, 105, 106. These local controllers 104, 105, 106 are configured to manage compressors 101, 102, 103. In an embodiment of the present invention, the local controllers 104, 105, 106 are limited to one compressor and some other elements in the compressor system 100. In some embodiments of the present invention, the local controllers 104, 105, 106 can also control other compressors 101, 102, 103 connected in series to the main compressor to which they are connected. Management means that operating parameters or states can be checked, controlled, monitored, set and / or verified, or any other manipulation can be performed to affect the operation of the compressor. In an embodiment of the present invention, the tasks performed by the central controller 112 can alternatively be performed remotely, such as a cloud server. In addition, each local controller 104, 105, 106 can be embedded in each compressor 101, 102, 103 or located outside each compressor.

[0054] In an embodiment of the present invention, a flow sensor 110 sends a signal to the control unit. The flow sensor 110 monitors the air network volume 107 .

[0055] Figure 2 The operating states of the compressor system 100 according to the present invention are shown. The plant using compressed air gets a signal from a central control algorithm on a control unit or cloud server as an auto-tuning algorithm. The auto-tuning process is initiated manually or based on a predetermined schedule when the system is online. Once triggered, the system proceeds through a series of steps to estimate, verify and apply the optimal tuning parameters for the compressed air system.

[0056] The system starts by collecting real-time data from various sensors and static compressor parameters from P&I charts. The data collection phase is necessary to detect the current operating conditions of the compressed air system and is used as input for the subsequent tuning steps. Most compressors have outlet sensors and some defined characteristics. These characteristics may include, but are not limited to, speed limits of the motor, valve positions, pressure differences across elements in the compressor. All of this information may contribute to the data that should be collected for the auto-tuning process.

[0057] For each compressor 101, 102, 103, there is a model with parameters that can be tuned per se. These parameters include different timings of the state machine, settings related to filtering of the collected data, tuning of local controller settings such as parameters of the PI loop, calibration settings and management limits for pressure, flow, temperature and humidity measurements.

[0058] Similar groups of settings exist for other machines associated with the compressor system 100, such as, but not limited to, dryers, refrigerators, chillers, and energy recovery systems.

[0059] It takes a certain amount of time to transition between the states of the compressors 101, 102, 103. The states involved in the estimation of the transition time are:

[0060] - Main states: "Stop (off)", "Unloaded (on but not producing)" and "Loaded (on and producing)"

[0061] - Substates: The Main state can be further divided into two other states: the Prepare substate and the Ready substate. In the Prepare substate phase, the compressor is already in its Main state, but there are some auxiliary processes ongoing that prevent an immediate change to another state.

[0062] - Transition states between any of the main states, these are: starting, stopping, loading, unloaded, loading from stop, stopping from load.

[0063] In addition to these states, there is a stop state that is not estimated, including a transition state from any state to stop. If necessary, the transition from stop to stop can be included in the transition estimate.

[0064] Using data and historical information collected from previously installed sites, the system employs complex algorithms to estimate the optimal set of tuning parameters for the specific site and current operating conditions. Several approaches can be used, including neural networks, optimization algorithms, engineer-designed heuristics, or system identification techniques. In one embodiment, the optimization technique is a Moving Range Estimator (MHE).

[0065] In an embodiment of the invention, the neural network is trained using unsupervised learning and / or deep reinforcement learning.

[0066] Unsupervised learning techniques, such as clustering, anomaly detection, and principal component analysis (PCA), can be used to detect faults in compressor systems. These methods can be applied to sensor data from the compressor system to identify patterns that deviate from normal operating conditions, indicating potential faults.

[0067] In addition, deep reinforcement learning can be used to optimize the control of the compressor system, thereby improving efficiency and reducing energy consumption. In an embodiment of the present invention, the compressor system is modeled as an environment, and the DRL agent learns to take actions (e.g., adjust the speed of the compressor) to maximize the reward signal (e.g., minimize energy consumption). By learning from experience and exploring different control strategies, the DRL agent can learn to achieve better performance than traditional control methods.

[0068] In addition, unsupervised learning techniques such as PCA and clustering can be used to analyze large amounts of sensor data from compressor systems to identify patterns and trends in performance. By analyzing the data in an unsupervised manner, patterns can be identified that may not be obvious using traditional analysis methods. This information can be used to improve the performance of the compressor system, optimize maintenance schedules, and identify energy-saving opportunities.

[0069] In summary, both unsupervised learning and DRL are valuable tools for the present invention in the analysis and control of compressor systems, providing insights into performance and opportunities for optimization.

[0070] The algorithm also has a combination of KPIs as a reward function and can control the tuning parameters of the central controller 112 and the local controllers 104, 105, 106. The KPI parameters can consist of the following metrics:

[0071] -Energy consumption metrics (energy consumption, idle hours, total blowdown flow, average network pressure drop, etc.)

[0072] - Wear-specific metrics (total operating time, total time at low rpm (as this can be dangerous for some compressors with integrated dryers), total starts / stops, total idle cycles, average acceleration, vibration, exposure to moisture, etc.)

[0073] - Metrics for maintenance costs (total operating time, maximum downtime duration per unit, exposure to heat, etc.)

[0074] - Measures for the overall performance of the air network volume 107 (pressure deviation from a set value or from a set segment, number of air network shutdowns, violations of air network humidity, etc.)

[0075] The estimated tuning parameters are subjected to a validation process to ensure their validity and stability. There are several criteria for validating the parameters, including:

[0076] - Check that the parameters remain consistent for new data sets, indicating stability.

[0077] -Simulate the performance of the system with new parameters and compare the results to determine energy savings.

[0078] - In an embodiment of the invention, the expertise of a maintenance technician is involved, who can provide approval or feedback on the proposed parameters.

[0079] -Based on models learned from lab and field locations, through safety filters.

[0080] If the validation process confirms the suitability of the calculated tuning parameters, they are presented to the user for approval, or applied directly to the compressed air system without user intervention. Where remote monitoring and control is possible, the application may be performed remotely, eliminating the need for an on-site visit.

[0081] For the new parameter set, a small simulation can be started. If the new parameter set provides better results in the simulation than the old parameters, the new parameter set is exchanged with the old parameters. The uncertainty error of the simulation is applied as a tolerance measure. This depends on the location and simplification of the simulator.

[0082] The auto-tuning process is designed to be iterative, continuously monitoring and learning the performance of the system. If the applied tuning parameters are not optimal or the operating conditions of the system change significantly, the auto-tuning process is repeated, ensuring that the compressed air system is always operating at its peak efficiency.

[0083] The automatic tuning system can adjust a wide range of parameters to optimize the performance of the compressed air system.

[0084] The system can regulate the compressor system to maintain the correct pressure required for a specific application. This involves setting the optimum operating pressure, taking into account safety margins and implementing automatic back-up plans in the event of any problems within the control chain.

[0085] Each compressor 101, 102, 103 has various tunable parameters, including state machine timing, data filtering settings, and tuning of local controller parameters such as PI loop parameters. Additionally, calibration settings and operating limits for pressure, flow, temperature, and humidity measurements can be fine-tuned.

[0086] The control unit plays an important role in determining which machines run at which operating point. The automatic tuning system can adjust the parameters that affect the action of the control unit, such as the group of machines running, the switching timing, and the reaction speed of the control action.

[0087] Controlling valve position within a compressed air delivery system significantly affects efficiency. The Auto-Tune system optimizes valve position to improve overall system performance.

[0088] The automatic tuning system controls a compressor room 113 housing at least one compressor 101, 102, 103. Each compressor is equipped internally or externally with a local controller 104, 105, 106 communicating with the control unit.

[0089] Figure 3 It is shown that the auto-tuning logic follows a structured and iterative approach to continuously optimize the compressed air system. It involves data collection, estimation, verification and application of tuning parameters, ensuring that the system adapts to changing conditions.

[0090] The auto-tuning system can adjust a comprehensive set of tuning parameters, including local compressor parameters (e.g., PI tuning of speed and valve position), physical parameters (e.g., container volume and air network modeling), and a wide range of operating parameters. Physical parameters include characteristics of the equipment, such as pipeline characteristics, volume, delays within the system, and reductions in safety levels. Control parameters include local machine parameters as well as central control parameters. Local machine parameters include PI tuning of speed and valve position, delay times, maximum ramp-up or ramp-down speeds, properties regarding filtering of sensor data, and other control parameters that can be found on the local controller. It can also include model updates of local machines, such as surge limits and choke limits, pressure drops, and flow and power models. Central control parameters are important for operating the system as efficiently as possible. These parameters typically include delay times, parameters regarding the robustness of the system (e.g., safety margins), penalties to prevent undesirable behavior (e.g., shutdowns or pressure drops), and parameters that increase the total cost. In addition, model updates of the global system are possible here.

[0091] The verification of checking whether the new parameters can be applied includes different rules depending on the device. In an embodiment of the present invention, the rules may include:

[0092] New parameters should fall within certain ranges or safe settings.

[0093] The relationship between the new parameters should be acceptable. For example, this could be a ratio that should fall within a certain range, and a sum that should be large enough or small enough.

[0094] • A heuristic algorithm should approve these parameters.

[0095] The new parameters should be close enough to the original parameters.

[0096] • The new parameters should be stable for at least a minimum time (or within a predetermined range for the past minimum time).

[0097] In short, the automatic tuning system for compressed air systems described in this application provides an automated method for commissioning and optimizing the performance of such systems. By utilizing advanced algorithms and historical data, the system ensures that each device operates at its peak efficiency, resulting in significant energy savings and reduced technician input during commissioning. The flexible nature of the system allows it to continuously adapt and improve its tuning parameters, making it a valuable tool for achieving optimal performance in a variety of compressed air applications.

Claims

1. A method for improving control performance of a compressor system (100), the compressor system comprising a control unit and at least one compressor (101-103) configured to provide compressed air or gas, the method comprising the following steps: - collecting initial data by monitoring the compressor system (100), - estimating a new set of parameters by an estimation unit until the estimated parameters are configured differently from the initial parameters of the system, - verifying said new set of parameters derived from said initial data, - repeat all steps until the new set of parameters is verified, - Instructing at least one of the elements in the compressor chamber (113) to apply the new parameters and perform the required actions accordingly.

2. The method for controlling a compressor system (100) according to claim 1, wherein: The control unit is a central controller (112) configured to manage at least one element in the compressor room (113).

3. The method for controlling a compressor system (100) according to claim 1, wherein: The control unit is at least one local controller (104-06) configured to manage at least one element in the compressor room (113).

4. The method for controlling a compressor system (100) according to claim 3, wherein: The local controllers (104-106) are configured to work together in a distributed manner.

5. The method for controlling a compressor system (100) of claim 1, further comprising the step of collecting more data until a sufficient amount of data is achieved in said step of collecting initial data.

6. The method for controlling a compressor system (100) of claim 1, further comprising the step of simulating the new set of parameters derived from the estimated data to compare the results with the initial parameters.

7. The method for controlling a compressor system (100) according to claim 1, further comprising the step of generating the new set of parameters derived from the estimated data according to a set of predefined rules to compare the results with the initial data parameters.

8. The method for controlling a compressor system (100) according to claim 1, further comprising the step of generating the new set of parameters derived from the estimated data according to a supervised AI system to compare the results with the initial data parameters.

9. The method for controlling a compressor system (100) according to claim 1, wherein: The initial data includes static compressor parameters.

10. The method for controlling a compressor system (100) according to claim 1, wherein: The initial data includes data collected by various sensors, which are provided by collecting real-time data to monitor the compressor system (100).

11. The method for controlling a compressor system (100) according to claim 10, wherein: AI algorithms are used to identify patterns that indicate a need for maintenance, and based on the analysis, maintenance technicians are notified of the impending failure.

12. The method for controlling a compressor system (100) according to claim 1, wherein: The estimation process is triggered manually by a user or automatically on a predefined time basis.

13. The method for controlling a compressor system (100) according to claim 1, wherein: The algorithms used to estimate the optimal tuning parameters include neural networks, optimization algorithms and / or system identification techniques.

14. The method for controlling a compressor system (100) according to claim 13, wherein: The neural network is trained using unsupervised learning and / or deep reinforcement learning.

15. The method for controlling a compressor system (100) according to claim 1, wherein: The tuning system adjusts parameters including pressure settings, individual machine settings, central controller settings, and / or compressed air delivery system settings.

16. The method for controlling a compressor system (100) according to claim 15, wherein: The pressure setting is adjusted to maintain the correct pressure required for the particular application, allowing for safety margins and / or implementing automatic backup plans.

17. The method for controlling a compressor system (100) according to claim 15, wherein: The individual machine settings include tuning state machine timing, data filtering settings, local controller parameters; calibration settings for pressure, flow, temperature and / or humidity measurements.

18. The method for controlling a compressor system (100) according to claim 2 and claim 15, wherein: The central controller sets the groups, switching timings and control action response speeds that affect the operating machines within the compressed air system.

19. The method for controlling a compressor system (100) according to claim 15, wherein: The compressed air delivery system settings involve tuning valve positions.

20. A compressor system (100) configured to compress and supply gas, comprising a central controller (112) configured to manage at least one compressor (101-103), each compressor (101-103) being equipped with a local controller (104-106), wherein - the compressor system (100) further comprises a compressor room (113), the compressor room being configured to provide initial data to the central controller (112), - an estimation unit configured to estimate a new data set until the estimated data is configured to be different from the initial data, - the central controller (112) is configured to compile a new set of parameters based on the estimated data of the estimation unit and simulate the new set of parameters derived from the estimated data to compare the results with the initial data parameters, a verification module configured to trigger the repetition of the previous steps until the verification of the new parameters is accepted, - an application module of the central controller (112), the application module being configured to apply the validated tuning parameters to the compressor system (100), - instructing at least one of said elements in the compressor chamber (113) to perform said action according to the verified tuning parameters.

21. The compressor system (100) of claim 20, wherein: The central controller (112) is configured to trigger the estimation process manually or on a predefined time basis.

22. The compressor system (100) of claim 20, wherein: The central controller (112) is configured to trigger the estimation process in a continuous manner.

23. The compressor system (100) of claim 20, wherein: Algorithms used to estimate optimal tuning parameters include neural networks, optimization algorithms, and / or system identification techniques.

24. The compressor system (100) of claim 20, wherein: The tuning parameters adjustable by the tuning system include pressure settings, individual machine settings, central controller settings and / or compressed air delivery system settings.

25. The compressor system (100) of claim 24, wherein: The pressure setting is adjusted to maintain the correct pressure required for the particular application, allowing for a safety margin.

26. The compressor system (100) of claim 24, wherein: The individual machine settings include tuned state machine timings, data filter settings, local controller parameters; calibration settings for pressure, flow, temperature, heat flow and / or humidity measurements.

27. The compressor system (100) of claim 24, wherein: The central controller sets the groups, switching timings and / or control action response speeds that affect the operating machines within the compressor system (100).

28. The compressor system (100) of claim 24, wherein: The compressed air delivery system settings involve tuning valve positions.

Images