Enhancing energy efficiency with real-time control in radial inflow turbine systems

Abstract

The present invention relates to a Radial Inflow Turbine system (9) in an Organic Rankine System (102) includes a stator (7) in a ring configuration and a rotor assembly (2) with aerodynamic blades to reduce drag and enhance energy transfer. It features a tachometer (3) for real-time shaft (5) speed feedback and a gearbox (6) driven by a stepper motor (4) for precise angle adjustments. The gearbox (6) connects with stator (7) for uniform vane angle adjustments. A hermetically sealed housing (8) maintains the working medium in a gaseous state and prevents leakage. The system integrates pressure sensors (10), temperature sensors (11), and gas flow meters (12) to monitor parameters, alongside control valves (13) and gear adjustments to regulate fluid velocity and vane angles. The present invention discloses a method (200) for real-time operational optimization of system (9) integrated within an ORC (102) comprising a plurality of steps.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS AND PRIORITY

[0002] The present application does not claim priority from any application.

[0003] FIELD OF THE INVENTION

[0004] The present invention relates to optimizing energy efficiency in various applications, from power generation to industrial processes. More particularly, it relates to a system and method for optimizing energy efficiency in radial inflow turbine systems through real-time synchronized control and adaptive regulation.

[0005] BACKGROUND

[0006] The background information herein below relates to the present disclosure but is not necessarily prior art.

[0007] The rapid growth in global energy demand, primarily driven by fossil fuel consumption, has led to significant environmental and economic concerns, chiefly contributing to global warming. The accumulation of greenhouse gases, such as carbon dioxide and methane, has intensified climate change, resulting in rising sea levels, increased flooding, and severe weather events like typhoons and hurricanes. Prolonged droughts are straining water resources and disrupting agriculture, while biodiversity loss accelerates as ecosystems struggle to adapt. These escalating challenges underscore the urgent need for sustainable energy technologies that reduce carbon emissions and enhance energy efficiency

[0008] Climate change is primarily driven by the emission of carbon dioxide (CQ) into the atmosphere, resulting from extensive fossil fuel consumption. Addressing said global challenge necessitates innovative energy solutions, such as Organic Rankine Cycles (ORC), which mitigate environmental impact by harnessing industrial waste heat and renewable energy sources. ORC are specifically designed to convert medium- and low-temperature heat into usable power, offering a sustainable alternative to traditional energy generation methods.

[0009] Reshaping the global energy mix requires the integration of novel, environmental friendly technologies. Prominent solutions include wind turbines, photovoltaic systems, concentrating solar power technologies, tidal and wave energy systems, bio-energy systems, hydropower plants, and ORC systems. Among these, radial inflow turbine systems stand out for their adaptability and efficiency in energy conversion processes.

[0010] Traditionally, the regulation of radial inflow turbines relied on fixed operational parameters and predefined set points. While effective under stable conditions, said approach often faced challenges, such as instability at high rotational speeds (RPM), inefficiency with low-grade heat sources, and suboptimal performance during dynamic operating conditions or fluctuations in external factors like resource availability or demand variations.

[0011] To address these limitations, the present invention introduces real-time synchronized control and adaptive regulation methodologies. These approaches leverage advanced sensing technologies, data analytics, and intelligent control systems to dynamically monitor and optimize turbine operations.

[0012] Real-Time Synchronized Control involves the real-time coordination of turbines within a system or network to maximize energy efficiency and performance. By synchronizing operations, turbines can work collectively to achieve heightened output and reduce energy losses.

[0013] Complementing synchronized control, adaptive regulation incorporates machine learning algorithms and modular design principles. These systems continuously analyze operational data and external conditions, adjusting turbine control strategies autonomously. This capability enables turbines to adapt to varying conditions, such as changes in load demand, ambient temperature fluctuations, or shifts in resource availability, ensuring consistent and efficient performance.

[0014] In essence, real-time synchronized control and adaptive regulation marks a significant shift in how radial inflow turbine systems are managed and operated, unlocking new levels of energy efficiency and performance across diverse applications. With ongoing advancements in sensor technology, data analytics, and controls, the potential for further optimization and innovation in turbine control HE001 strategies remains promising.

[0015] Thus, the key features of the present invention comprise the following:

[0016] • real-time monitoring and ML-based optimization system;

[0017] • integrated generator;

[0018] • ML-based fluid flow control with modular design;

[0019] • efficiency at low temperature and pressure;

[0020] • gear based angular adjustment; and

[0021] • autonomous and adaptive control with droop system.

[0022] Thus, the instant invention represents a paradigm shift in turbine system operations, unlocking unprecedented levels of energy efficiency and performance. By leveraging cutting-edge advancements in sensor technology, data analytics, and control systems, said turbine system addresses contemporary energy challenges while paving the way for future innovations in sustainable energy technologies.

[0023] SUMMARY OF THE INVENTION

[0024] Before the present system and method, and its components are described, it is to be understood that this disclosure is not limited to the system and its arrangement as described, as there can be multiple possible embodiments which are not expressly illustrated in the present disclosure. It is also to be understood that the terminology used in the description is for the purpose of describing the versions or embodiments only and is not intended to limit the scope of the present application. The summary is not intended to identify all the essential features of the claimed subject matter nor is it intended for use in detecting or limiting the scope of the claimed subject matter.

[0025] The present invention discloses the radial inflow turbine system (9) integrated into an ORC (102) that incorporates advanced components to enhance performance and efficiency. It comprises a stator (7) in a ring configuration and a rotor assembly (2) equipped with aerodynamic blades designed to minimize flow drag and optimize energy transfer. Further, a tachometer (3) provides real-time feedback on the HE001 rotational speed of the shaft (5), while a gearbox (6), driven by a stepper motor (4), enables precise angle adjustments. The gearbox (6) is further connected to the stator (7) assembly within the casing, facilitating uniform adjustments of the stator vane angles. A hermetically sealed housing (8) ensures the working medium remains in a gaseous state while preventing leakage. The system is equipped with pressure sensors (10), temperature sensors (11), and gas flow meters (12) to monitor critical parameters, alongside control valves (13) and gear-based angular adjustments to regulate fluid velocity and vane angles effectively. Also, the said integrated features enable the radial inflow turbine system (9) to operate efficiently within the ORC (102), maximizing energy conversion and maintaining operational stability.

[0026] Further, the present invention discloses a method (200) for real-time operational optimization of a radial inflow turbine system (9) integrated within an ORC (102) comprising a plurality of steps designed to enhance energy conversion efficiency. It comprises monitoring real-time data for temperature, pressure, flow rate, and rotational speed using distributed sensors (201). Further, the thermal load (PL) is computed using the relation PL=m *Cpx(ThTc)PL = \dot{m} \times C_p \times (T_h - T_c)PL=m *Cpx(Th-Tc), where m'\dot{m}m' represents the mass flow rate of the working fluid, CpC_pCp is its specific heat capacity, and ThT_hTh and TcT_cTc are the high and low fluid temperatures (202), respectively. Further, the data is transmitted to a programmable logic controller (PLC) interfaced with a machine learning-based control / computing unit (105) (203). The computing unit generates optimized control signals to dynamically adjust the opening position of the bypass control valve (13) and the angle of the inlet guide vanes (7) (204).

[0027] Further, the turbine operation is regulated to maintain rotational speed within the range of 15,000-30,000 RPM and output torque between 8-55 Nm (205). Additionally, the method comprises adjusting the mass flow rate of the working fluid and the condenser cooling water flow by controlling the speeds of the refrigerant and water pumps based on multi-variable state predictions (206). The synchronized and adaptive control of thermal and mechanical parameters ensures efficient operation, enabling the system to dynamically respond to changing HE001 conditions and optimize energy conversion.

[0028] BRIEF DESCRIPTION OF DRAWINGS

[0029] The present disclosure is described with reference to the accompanying figures. In the Figures, the left-most digit(s) of a reference number identifies the Figure in which the reference number first appears. The same numbers are used throughout the drawings to refer like features and components.

[0030] Figure 1 illustrates a schematic block diagram of the integrated ORC control system architecture, showing the industrial input (101), Organic Rankine Cycle (ORC) system (102), Programmable Logic Controller (PLC) (100), machine learning computing unit (105), data log server (104), and user interface access point (106) in accordance with the present disclosure;

[0031] Figure 2 illustrates the process and instrumentation diagram (P&ID) of the closed- loop ORC system (102), depicting the primary heat exchanger (29), evaporator (30), radial inflow turbine (9), condenser (31), sensors, pumps, valves, and control elements in accordance with the present disclosure;

[0032] Figure 3 illustrates a detailed schematic block diagram of the ORC system (102) highlighting the subcomponents of the radial inflow turbine system (9). The radial inflow turbine unit (9) includes a Volute (1), a Rotor (2), a Tachometer (3), a Stepper Motor (4), a Shaft (5), a Gearbox (6), a Stator or Inlet Guide Vane (7), and a Generator enclosed in hermetic housing (8). The system further comprises an ORC Subcomponents Unit, a Power Electronics Unit (107), a Load Unit (108), and a Programmable Logic Controller (PLC) (100) configured to interface with the ORC system (102) in accordance with the present disclosure;

[0033] Figure 4 illustrates a cross-sectional view of the radial inflow turbine unit (9) showing detailed internal components including a Volute (1), a Rotor (2), a Tachometer (3), a Stepper Motor (4), a Shaft (5), a Gearbox (6), a Stator or Inlet Guide Vane (7), and a Generator enclosed in hermetic housing (8). The view highlights the physical arrangement of these components within the turbine assembly in accordance with the present disclosure; HE001

[0034] Figure 5 illustrates an exploded isometric view of the turbine-generator unit, showing all major components in assembled alignment, including rotor-stator interaction, gearbox linkage, and interface with control mechanisms in accordance with the present disclosure;

[0035] Figure 6 illustrates flow chart that represents the real-time optimization cycle of the ORC system, powered by a Radial Inflow Turbine and regulated through a Reinforcement Learning (RL) optimization loop in accordance with the present disclosure;

[0036] Figure 7 illustrates Heat Source Temperature Vs Power Output mechanisms in accordance with the present disclosure;

[0037] Figure 8 illustrates Low-Temperature Vaporization Operation Comparison in accordance with the present disclosure;

[0038] Figure 9 illustrates Static Vs Adjustable Stator Power Output Comparison in accordance with the present disclosure;

[0039] Figure 10 illustrates System Stability Comparison in accordance with the present disclosure;

[0040] Figure 11 illustrates Offline Model Vs Online RL Model Efficiency Comparison in accordance with the present disclosure.

[0041] DESCRIPTION OF THE INVENTION

[0042] As used in the specification and claims, the singular forms “a”, “an” and “the” include plural references unless the context clearly dictates otherwise. For example, the term “an article” may include a plurality of articles unless the context clearly dictates otherwise. Those with ordinary skill in the art will appreciate that the elements in the figures are illustrated for simplicity and clarity and are not necessarily drawn to scale. For example, the dimensions of some of the elements in the figures may be exaggerated, relative to other elements, in order to improve the understanding of the present invention. There may be additional components described in the foregoing application that are not depicted on one of the described drawings. In the event such a component is described, but not depicted in a drawing HE001 the absence of such a drawing should not be considered as an omission of such design from the specification.

[0043] In the accompanying drawings components have been represented, showing only specific details that are pertinent for an understanding of the present invention so as not to obscure the disclosure with details that will be readily apparent to those with ordinary skill in the art having the benefit of the description herein.

[0044] As required, detailed embodiments of the present invention are disclosed herein; however, it is to be understood that the disclosed embodiments are merely exemplary of the invention, which can be embodied in various forms. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the present invention in virtually any appropriately detailed structure. Further, the terms and phrases used herein are not intended to be limiting but rather to provide an understandable description of the invention.

[0045] In accordance with one aspect of the present invention, there is provided a radial inflow turbine system (9) that includes a rotor assembly (2) specifically designed for volute (1) and nozzle ring configuration. The said rotor assembly (2) is further provided with aerodynamic blades designed / tailored to minimize internal flow drag and enhance impulse energy transfer efficiency. The said aerodynamics blades are configured to ensure efficient energy transfer within the radial inflow turbine system (9).

[0046] The rotor assembly comprises 12 freeform 3D blades with optimized curvature and trailing edge angles preferably ranging from 21.1° to 6.5°, designed to guide isobutane vapor smoothly through the turbine passage. At an inlet meridional velocity of 114.5 m / s and peripheral speed of -250 m / s, the blade geometry achieves a relative flow angle of 82.4°, minimizing incidence losses. The design ensures low shock and wake generation, contributing to a high isentropic efficiency of 85.9% and efficient impulse energy transfer under a pressure ratio of 2.4 and 1.0 kg / s mass flow rate HE001

[0047] Further, in a related embodiment, the radial inflow turbine system (9) comprises a stator (7) assembly connected to adjustable studs within the casing / housing regulated by a gear box (6) and driven by a stepper motor (4). It comprise of convergent-divergent nozzles configured to create desired flow and generate reaction forces contributing to the overall efficiency and performance of the said radial inflow turbine system (9). The radial inflow turbine system (9), comprise the stator (7) assembly further comprising a gearbox (6)-based adjustments for controlling inlet guide vane angles to optimize gas velocity and turbine performance.

[0048] The stator assembly (7) comprises 13 inlet guide vanes shaped with a NACA 2414 airfoil profile and mounted to a planetary gear-box (6) based mechanism, enabling synchronized angular movement. The vane angle is actively adjusted in real time within ±5° using feedback from turbine speed, pressure, and flow sensors. Said dynamic control improves aerodynamic alignment at the rotor inlet, enhancing torque generation and RPM stability (Fig. 4-5).

[0049] Further, in a related embodiment, the radial inflow turbine system (9) comprises hermetically sealed casing or housing (8) with gaseous working medium configured to ensure maximum efficiency and prevent working medium loss. The working medium within the casing is maintained in a gaseous state, facilitating efficient energy transfer and eliminating the risk of working medium leakage. Further, it discloses sealed supply openings and close feedback openings configured to guide feedback lines to the power generation system for real-time monitoring and optimization.

[0050] In a related embodiment, the integrated generator enclosed within the said hermetically sealed casing or housing (8) is disclosed. The said integrated generator is directly coupled to the rotor assembly (2) configured for efficient electrical energy generation. Further, the said integrated generator is configured to operate in a highly controlled environment, utilizing the working medium for cooling for optimal generator performance and extended life span. The hermetically sealed casing (8) minimize turbulence, enhance flow dynamics, and integrate feedback HE001 mechanisms to improve performance.

[0051] In a further related embodiment, the turbine and integrated generator are enclosed in a hermetically sealed casing precisely shaped to maintain axial flow alignment and minimize turbulence at stator-rotor interfaces. This design prevents refrigerant leakage, supports safe use of flammable or low-GWP fluids, and houses all sensors and actuators within an isolated, controlled volume. The sealed structure reduces external vibration and particulate ingress, enabling more stable control response, longer component life, and consistent expansion efficiency across operating pressures up to 15 bar.

[0052] The casing geometry is coaxial with the rotor (2) and stator (7) alignment to reduce flow transition losses; internal walls are profiled to minimize boundary layer separation and turbulence; strain-relief zones compensate for thermal expansion between rotor shaft and generator supports and materials selected stainless steel withstand internal pressure up to 15 bar without deformation or vibration resonance.

[0053] In another embodiment, the radial inflow turbine system (9) is modularly designed comprising ML-based fluid control configured to accommodate low-temperature refrigerants (Fig 4-5). Said low temperature refrigerants may be selected from unlimited list comprising isobutane, butane, siloxane etc.

[0054] The radial inflow turbine system (9) is geometrically optimized for a mass flow rate preferably of 1.0 kg / s, inlet pressures preferably in the range of 4-15 bar, and inlet temperatures preferably in the range between 70°C to 150°C. The rotor (2), preferably with a diameter of 117.3 mm and 12 fluid-optimized blades, is designed to maintain aerodynamic performance across a range of organic working fluids with similar specific volumes, molar masses ranging between 58-162 g / mol, and compressibility characteristics (Table 2).

[0055] Further, in an embodiment the said radial inflow turbine system (9) is configured to operate with low temperature refrigerants and pressure, achieving efficiency by reducing operational costs, maximizing the utilization of cost-effective materials and enhancing the energy output. The low-temperature refrigerants are selected HE001 from a unlimited list of isobutane, butane, or siloxanes to improve energy output (Table 2).

[0056] The design leverages consistent relative flow angles (-82°), conservative loading (pressure ratio —2.4), and broad thermodynamic margins to accommodate fluids with small deviations in critical pressure and heat capacity. As such, isobutane, n- butane, R245fa, cyclopentane, MDM siloxane, and toluene — despite differing slightly in boiling point and molecular structure — can be efficiently expanded using the same turbine architecture without loss of flow alignment or mechanical stability (Table 2).

[0057] In a further related embodiment, the radial inflow turbine system (9) further discloses a gear-based angular adjustment comprising pressure sensors (10), temperature sensors (11), and gas flow meter (12) strategically placed throughout the radial inflow turbine system (9). Further, said sensors (10, 11), and gas flow meter (12) are configured for collecting real-time data on working medium conditions including pressure in the range of 0-16 bar, temperature from 0-150°C, and flow rates up to 1.0 kg / s. .

[0058] In a further related embodiment, the radial inflow turbine system (9) discloses a tachometer (3) configured for providing the feedback of rotational speed of shaft (5) so as to inform the autonomous program controlled system for ensuring real-time fluid regulation.

[0059] In a further related embodiment, the said radial inflow turbine system (9) discloses gear-based angular adjustment configured for controlling the stator vane angle or inlet guide vane angle adjusting the inlet gas velocity (Table 1).

[0060] In a further related embodiment, actuators or control valves (13) may be disclosed. Further, the said actuators or control valves (13) are operated by the control unit to regulate flow resistance and flow rate configured in correspondence with pump (20) to optimizing turbine efficiency based on the input data and ML algorithms.

[0061] Further, in an embodiment, the radial inflow turbine system (9) discloses real-time monitoring and ML-based optimization system with gear based angular adjustment. HE001

[0062] Further, an autonomous and adaptive control with droop system that is configured to regulate and synchronize electricity generation is disclosed. Furthermore, said droop system is configured for maintaining fluid velocity at the inlet and regulating the gas turbine RPM in a specific range for stable electricity generation and utilization.

[0063] The radial inflow turbine system (9) further comprises the programmable logic controller (PLC)(100) that executes ML algorithms for optimizing turbine performance in real time.

[0064] Further, in an embodiment the radial inflow turbine system (9) discloses data analytics and ML-based control unit (105) such that the collected data is processed for implementing predictive modeling and dynamically adjusting the said radial inflow turbine system (9) parameters for optimal performance using predictive optimization algorithms.

[0065] The radial inflow turbine system (9), operating within an ORC framework, incorporates a machine Learning (ML) computing unit (105) executing a Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm to dynamically optimize both the bypass control valve (13) and rotor- stator configuration in real time. The ML unit continuously processes real-time sensor data from the PLC (100) to adjust the control valve (13) opening (0-100%) for pressure and mass flow regulation during startup, transient load variation, and stability tuning; modify stator vane angles within a ±5° range using stepper-motor-driven planetary gear actuation (6), aligning incoming vapor flow to the rotor (2) and enhancing torque delivery; and maintain rotor RPM within the desired operating band of 18,000 to 32,000 RPM, avoiding over speed or under load conditions.

[0066] Said ML optimizes control valves (13) and rotor- stator configurations, maintain fluid velocity and turbine RPM within specified ranges for enhanced efficiency (Fig 1-5). The Functional Integration comprises of PLC (100) to collect real-time data from temperature, pressure, and flow sensors; communicates control signals; ML Unit (105) to run TD3 algorithm and compute optimal control actions based on reward-based feedback loop; sensors (10, 11, 12, etc.) to provide inputs to PLC: pressure (0-16 bar), temperature (0-150°C), mass flow (up to 1.0 kg / s) and control HE001 actuators to include stator vane angle motor (Aa: ±1° to ±5°) and control valve (13), and refrigerant pump(20) (Table 3).

[0067] The control system is built around the TD3 algorithm, enabling predictive regulation of mass flow rate at the turbine inlet by adjusting control valve (13) positions, flow resistance across bypass and expansion paths during transient heat load scenarios, and stator vane angles (Aa ±5°) to maintain optimal flow alignment into the rotor under changing inlet conditions (Table 5). The predictive tuning improves efficiency under fluctuating thermal input conditions; the Adaptive policy updates ensure faster stabilization during start-stop cycles and load transients and the Real-time coordination between sensors and actuators ensures minimal overshoot, reduced cycle losses, and longer component life.

[0068] The said radial inflow turbine system (9) parameters comprise of but not limited to flow rate, flow resistance, and stator vane angles. Further, the flow rate adjustment is carried out by a control valve actuation (13) preferably in the range of 0.6 to 1.2 kgs / sec. the flow resistance adjustments is carried out by valve modulation and pump(20) feedback preferably in the variable range. Also, vane angle adjustment mechanism is carried out by gear box driven stator vane rotation preferably in the range of ±1° to ±5° (Table 4 and 5).

[0069] In an embodiment, the ML-based optimization system is configured to utilize the historical data and past operational scenarios to enhance turbine efficiency under various conditions.

[0070] In a related embodiment, the ML-based optimization system is configured to autonomously adjust fluid flow rates and flow resistance in response to changes in heat source temperature, pressure, and working medium conditions without human intervention.

[0071] In a further related embodiment, the data collected from the sensors (10, 11) and gas flow meter (12) are processed and encoded within the PLC module. Serving as the central control unit, the said controller efficiently manages and coordinates various tasks within the system. Acting as the neural hub of operations, it seamlessly HE001 executes machine learning (ML) while meticulously overseeing the operation of the machinery according to predefined code parameters. The integration of sensors (10, 11) and gas flow meter (12) with the control unit or controller not only facilitates real-time monitoring of system performance but also enables the display of readings in numerical form.

[0072] This feature provides operators with comprehensive insights into the system's operational status. Furthermore, the control unit or controller seamlessly executes predefined tasks related to hardware operation, including the control valves (13), stepper motor (4), various accompanying sensors (10, 11) and flow meter (12). Moreover, the incorporation of diverse electronic components, facilitated by different encoding cards, ensures efficient data processing across a spectrum of sensor outputs.

[0073] In another embodiment, the radial inflow turbine system (9) design is configured to be operated with an ORC (102), utilizing waste heat for energy recovery and efficiency enhancement. The overall energy conversion efficiency is increased making the system suitable for waste heat recovery application.

[0074] The radial inflow turbine system (9) is engineered as a core component of an ORC system (102) optimized for low-grade industrial waste heat recovery. Designed to handle heat inputs from 70°C to 150°C and working pressures from 4 to 15 bar, the turbine converts thermal energy into mechanical power at rotational speeds up to 30,000 RPM. The system integrates (FIG 2) a primary heat exchanger to transfer waste heat to the thermic oil loop; an evaporator for phase change of organic working fluid (e.g., isobutane); a radial inflow turbine rotor capable of operating at mass flow rates of ~1.0 kg / s; and condenser coupled to the outlet, recovering heat while completing the ORC cycle.

[0075] The said design is supported by performance studies (and validated through rotor efficiency metrics preferably in the Isentropic efficiency of 85.9%; Pressure ratio of ~2.4; working fluids comprising Isobutane, R245fa, siloxanes that are suitable for closed-loop cycles recovering low-temperature waste heat. Further, the turbine’s flow path and volute geometry are matched to the thermal profile of ORC fluids, HE001 ensuring optimal energy recovery even under fluctuating industrial heat sources.

[0076] In another non-limiting embodiment, a method (200) of real-time synchronized control and adaptive regulation of radial inflow turbine system (9) for enhanced energy efficiency is disclosed. Further, the method (200) comprises plurality of steps such as monitoring the temperature of hot flue gases (T_h), mass flow rate (rh), and RPM (co) using the respective sensors (10, 11) (201).

[0077] Further, in a related embodiment, the Programmable Logic Controller (PLC) calculate the input load (PL) based on the equation: PIm=* Cp * (T h - T_c) wherein the Cp may be the specific heat constant of the flue gas, and T_c is a constant reference temperature (202).

[0078] Further, said PLC calculate the electrical power output (P_elec) of the turbine using a predefined function or equation that relates P_elec to PL and RPM (203). Said function or equation likely considers the turbine's efficiency (q), but the q value itself is not be directly measured in instant system. Further, said PLC compares the estimated efficiency from the reinforcement learning model with the target efficiency (204).

[0079] In a further related embodiment, based on the comparison, said PLC adjust the control valve (13) position and blade angle to achieve the desired efficiency improvement while maintaining the RPM and torque within the specified range (15000-30000 RPM, 8-55 Nm) (205). Said adjustment likely involves moving the control valve (13) and rotating the IGVs (Inlet Guide Vanes) using the stepper motor (4).

[0080] Further, in an embodiment, optionally adjusting the mass flow rate of the working fluid and condenser cooling water flow by controlling the refrigerant and water pump speeds, based on multi-variable state prediction (206) is disclosed which enhances the energy conversion efficiency through synchronized, adaptive control of thermal and mechanical parameters.

[0081] Further, in an another embodiment, the control valve (13) is feedback driven with position detector to control its position by means 4-20mA output signals and the HE001 stepper motor (4) also take the feedback where as for every 1 rotation it may change the blade position to 1 degree storing the previous blade angle position in order to regulate it in 0-30 degree span for stator inlet guide vane.

[0082] Thus, the presently disclosed invention represents a significant advancement in turbine system management by integrating several innovative features. It employs a reinforcement learning model trained on historical data to calculate current efficiency and predict optimal operational parameters, such as valve position and blade angle. A stepper motor-driven inlet guide vane mechanism dynamically adjusts the blade angle based on real-time efficiency calculations, ensuring optimal torque and RPM.

[0083] The system further features a real-time monitoring and machine learning-based optimization, continuously tracking critical parameters like hot flue gas temperature, mass flow rate, and RPM to improve operational efficiency. Its integrated generator with a modular, scalable design enhances adaptability across diverse applications. Furthermore, the system operates efficiently under low-temperature and low- pressure conditions, making it suitable for a broader range of industrial settings. An autonomous and adaptive control mechanism with an integrated droop system ensures stability and responsiveness to fluctuating loads and external conditions, further solidifying its role as a cutting-edge solution in turbine management. Said dynamic control ensures that the turbine operates within the desired RPM and torque range while continuously striving to improve efficiency over time.

[0084] Technical Advancement and Economic Significance

[0085] The method of the present invention maximizes energy output while minimizing losses;

[0086] The integral design of the present invention:

[0087] Enhances overall performance and operational efficiency;

[0088] Reduces fuel consumption and operational costs;

[0089] Has improved system reliability and stability, reducing the risk of equipment failures and downtime; and HE001

[0090] Has broad applications across various industries, including but not limited to power generation (e.g., hydroelectric power plants, gas turbines); industrial processes (e.g., chemical manufacturing, oil refining); renewable energy systems (e.g., wind turbines).

[0091] Modifications to embodiments of the present disclosure described in the foregoing are possible without departing from the scope of the present disclosure as defined by the accompanying claims. Expressions such as “including”, “comprising”, “incorporating”, “consisting of’, “have”, “is” used to describe and claim the present disclosure are intended to be construed in a non-exclusive manner, namely allowing for items, components or elements not explicitly described also to be present. Reference to the singular is also to be construed to relate to the plural.

[0092] Although specific features of various embodiments of the disclosure may be shown in some drawings and not in others, this is for convenience only. In accordance with the principles of the disclosure, any feature of a drawing may be referenced and / or claimed in combination with any feature of any other drawing.

[0093] Examples:

[0094] The following examples have been included to provide illustrations of the presently disclosed subject matter. In light of the present disclosure and the general level of skill in the art, those of skill will appreciate that the following Examples are intended to be exemplary only and that numerous changes, modifications and alterations can be employed without departing from the spirit and scope of the presently disclosed subject matter.

[0095] Examples include data within the designed capacity limits of the currently developed system. However, the scope and claims of the invention are not restricted to these specific operational ranges or conditions. These examples are intended as a concise consolidation of experimental validation supporting the broader claims of enhanced efficiency, stability, and adaptability over conventional ORC systems.

[0096] • Heat Source Temperature Vs Power Output

[0097] A study on the comparative analysis showed that the Radial Inflow Turbine system HE001 delivers higher and stable power output across varying heat source temperatures as compared to traditional fixed control systems (Figure 7).

[0098] • Low- Temperature Refrigerant Vaporization Efficiency

[0099] Further studies carried out showed that the Radial Inflow Turbine system (9) maintains superior efficiency at low evaporation temperatures, thereby enhancing ORC system viability under low-grade heat conditions (Figure 8).

[0100] Static Stator Vs Adjustable Stator Power Output Comparison: Further, as depicted in Graph 2 the power output is consistently higher in the Radial Inflow turbine system with adjustable guide vanes over the traditional static stator system (Figure 9).

[0101] • System Stability Comparison under Varying Conditions

[0102] As illustrated in graph 4 the RL-based control (Radial inflow turbine systemjarchitecture ensures reduced power fluctuation and improved stability under partial load and transient load conditions (Figure 10)..

[0103] • Offline Model Vs Online RL Model Efficiency

[0104] As illustrated in graph 5, it was observed that the online Radial Inflow Turbine system control achieves higher system efficiency and adaptability compared to conventional offline predictive models (Figure 12).

[0105] Further, the flow chart (Figure 6) represents the real-time optimization cycle of the ORC system, powered by a Radial Inflow Turbine and regulated through a Reinforcement Learning (RL) optimization loop comprising the following steps.

[0106] System Start:

[0107] • ORC system initiates its cycle, beginning with standard startup procedures.

[0108] Monitor ORC System:

[0109] • Sensors and flow meters measure critical parameters such as temperature, pressure, RPM, and mass flow rates.

[0110] This data is fed to the Programmable Logic Controller (PLC) for initial HE001 processing.

[0111] Basic Control Logic:

[0112] • The PLC executes primary control logic for maintaining baseline turbine operation and stability.

[0113] • Basic adjustments to valve positions, vane angles, and pump speeds are handled to meet initial performance criteria.

[0114] Execute RL Optimization? (Decision Block):

[0115] • The system evaluates if the current operational state meets predefined optimization thresholds.

[0116] • If the conditions are not optimal, the process flows to Record Operational Data for analysis.

[0117] • If optimization is required, the system proceeds to Apply RL Policy.

[0118] Apply RL Policy:

[0119] • The Machine Learning (ML) Computing Unit fetches the most recent RL policy.

[0120] • Control signals are sent to the control valve (13), guide vanes (7), refrigerant pump, and water pump to optimize mass flow rates, RPM, and fluid velocity.

[0121] ML Computing Unit & Policy Update:

[0122] • The RL model executes policy adjustments and sends real-time updates to the Data Log Server for future learning iterations.

[0123] • Simultaneously, the policy is updated to reflect the latest environmental changes and operational feedback.

[0124] Update Policy:

[0125] • The learning model refines its policies based on new performance data, improving future optimization decisions.

[0126] • This step ensures continuous learning and adaptation to fluctuating industrial heat loads and ORC dynamics. HE001

[0127] Data Log Server:

[0128] • All operational and optimization data is logged for historical analysis and traceability.

[0129] • This server acts as a reference for anomaly detection and predictive maintenance.

[0130] Table 1: The influence of vane angle on turbine inlet conditions at a mass flow rate of 1.0 kg / s, inlet pressure of 12 bar, and temperature of 110°C:

[0131] Table 2: Validation of radial inflow turbine system for the following refrigerants with comparable thermophysical properties: HE001

[0132] Table 3: Defined Operating Ranges Controlled via TD3 Algorithm:

[0133] Table 4: Optimized Parameters Under ML Control: Table 5: Key Control Parameters Under Predictive ML Adjustment: HE001

[0134] Table 6: Operational ranges regulated through this method (200):

[0135] Dated this 9thday of May 2025

[0136] Mamatha R

[0137] IN / PA 4746

[0138] Agent for Applicant

Claims

We claim:

1. A Radial Inflow Turbine system (9) used in a organic rankine system (102) comprising:• Stator(7) ring configuration;• a rotor assembly (2) with aerodynamic blades minimizing flow drag and enhancing energy transfer;• a tachometer (3) for providing real time feedback of shaft(5) rotational speed;• a gearbox (6) coupled and driven by stepper motor(4) for precise angle adjustment• a gearbox (6) connected with stator(7) assembly within the casing / housing for adjusting the stator (7) vane angles uniformly• a hermetically sealed housing (8) for maintaining the working medium in a gaseous state and preventing leakage;• Radial Inflow turbine (9) operated with an Organic Rankine Cycle (102);• pressure sensors (10), temperature sensors (11), and gas flow meters (12) to monitor system parameters; and• control valves (13) and gear-based angular adjustments regulating fluid velocity and vane angles; such that changes in temperature, pressure, and working medium conditions are autonomously adapted.

2. The radial inflow turbine system (9) as claimed in claim 1, wherein the rotor assembly (2) comprises fluid-optimized blades configured to minimize internal flow resistance and enhance impulse energy transfer efficiency.

3. The radial inflow turbine system (9) as claimed in claiml, wherein the stator (7) assembly comprise gearbox (6)-based adjustments for controlling inlet guide vane angles to optimize gas velocity and turbine performance.

4. The radial inflow turbine system (9) as claimed in claim 1, wherein the radial inflow turbine (9) operates with low-temperature refrigerants.

5. The radial inflow turbine system (9) as claimed in claiml, wherein the low- temperature refrigerants comprise isobutane, butane, or siloxanes to improve energy output.

6. The radial inflow turbine system (9) as claimed in claim 1, wherein the hermetically sealed casing (8) minimize turbulence, enhance flow dynamics, and integrate feedback mechanisms to improve performance.

7. The radial inflow turbine system (9) as claimed in claim 1, wherein the radial inflow turbine (9) operates on an Organic Rankine Cycle (102), utilizing waste heat for energy recovery and efficiency enhancement.

8. The radial inflow turbine system (9) as claimed in claim 1, wherein pressure sensors (10), temperature sensors (11), and gas flow meters (12) are configured to monitor system parameters comprising pressure in the range of 0-16 bar, temperature from 0-150°C, and flow rates up to 1.0 kg / s, wherein the collected data is processed by a Programmable Logic Controller (PLC) for real-time performance adjustments.

9. The radial inflow turbine system (9) as claimed in claim 1, wherein the programmable logic controller (PLC) execute ML algorithms for optimizing turbine performance in real time.

10. The radial inflow turbine system (9) as claimed in claiml, wherein the ML optimize control valves (13) and rotor-stator configurations, maintain fluid velocity and turbine RPM within specified ranges for enhanced efficiency.

11. The radial inflow turbine system (9) as claimed in claim 1, wherein a machine learning-based control unit (105) processes real-time data from pressure sensors (10), temperature sensors (11), and flow meters (12), and dynamically adjusts flow rate, flow resistance, and stator vane angles using predictive optimization algorithms.HE00112. A method (200) for real-time operational optimization of a radial inflow turbine system (9) integrated within an Organic Rankine Cycle (ORC)(102), comprising:• Monitoring real-time temperature, pressure, flow rate, and rotational speed data from distributed sensors (201);• computing the thermal load (PL) using the relation PL = rh x Cp x (Th- Tc), where rh is the working fluid mass flow rate, Cp is the specific heat capacity, and Th and Tc are the respective high and low fluid temperatures ;(202)• transmitting the acquired data to a programmable logic controller (PLC) configured to interface with a machine learning-based computing unit (203);• generating optimized control signals from the ML-based computing unit(105)to dynamically adjust the opening position of a bypass control valve (13) and the angle of inlet guide vanes (7) (204);• regulating the turbine operation to maintain rotational speed within a defined range of 15,000-30,000 RPM and output torque between 8-55 Nm (205); and• optionally adjusting the mass flow rate of the working fluid and condenser cooling water flow by controlling the refrigerant and water pump speeds, based on multi-variable state prediction (206), such that it enhances the energy conversion efficiency through synchronized, adaptive control of thermal and mechanical parameters.Dated this 9thday of May 2025Mamatha RIN / PA 4746Agent for Applicant

Images