Circulating cooling method and system for single-phase immersion liquid cooling server

Abstract

The invention relates to the technical field of immersion liquid cooling data center cooling, and particularly provides a single-phase immersion liquid cooling server circulation cooling method and system, and the method comprises the steps: comparing the real-time temperature of a cooling liquid with a preset temperature threshold value, transmitting a first program instruction by a control system, and carrying out an immersion liquid cooling cabinet internal circulation mode; or a second program instruction is sent, and a heat exchange circulation mode is carried out; after the heat exchange circulation mode is started, a main liquid outlet pipeline is opened; the cooling liquid flows back to the liquid outlet of the immersed liquid cooling cabinet through the backflow branch pipeline, the real-time temperature of the cooling liquid and the preset temperature threshold value are continuously judged, and switching between the internal circulation mode and the heat exchange circulation mode of the immersed liquid cooling cabinet is achieved according to the comparison result. The system comprises an immersed liquid cooling cabinet, a branch pipeline valve, a main pipeline valve, a main liquid outlet pipeline, a pump, a heat exchanger and a branch pipeline. According to the invention, the topology reconstruction capability of the cooling liquid flow is realized, and local circulation and global circulation are dynamically switched according to the thermal load.

Description

Technical Field

[0001] The present invention relates to the technical field of immersion liquid cooling data center cooling, and in particular to a circulation cooling method and system for a single-phase immersion liquid cooling server. Background Art

[0002] Cloud computing uses virtualization technology to provide scalable computing, storage, and network resources, enabling on-demand allocation and elastic scaling. AI, based on algorithms and massive data-based training models, empowers systems with perception, cognition, and decision-making capabilities. With the widespread adoption and continuous evolution of technologies like AI and cloud computing, the computing power density of chips involved in these technologies has increased exponentially. The power consumption of core components like CPUs and GPUs has jumped from hundreds of watts to kilowatts. Traditional air cooling is no longer sufficient to meet these demands, and single-phase immersion liquid cooling, with its efficient heat exchange capabilities, has become the mainstream solution. However, in high-power scenarios, the energy consumption of liquid cooling systems has become increasingly prominent, especially when the cooling equipment is constantly running, resulting in significant energy waste. Traditional liquid cooling systems operate in a full-time cooling mode. Regardless of chip load, the coolant, after absorbing heat, flows through the heat exchanger for forced cooling. However, server load fluctuates significantly. During low load periods at night, chip heat generation drops dramatically, and the coolant outlet temperature may still be within a safe range. Therefore, the cooling process is a complete waste of energy.

[0003] Prior art 1, Chinese patent, application number 202410928007.3 discloses a liquid-cooled server coolant circulation system and equipment, the system includes: a server cooling side, a circulating heat exchange side and a remote control side, heat exchange is performed between the server cooling side and the circulating heat exchange side through a heat exchanger, and the remote control side obtains the operating parameters of the server cooling side, the circulating heat exchange side and the heat exchanger through communication; the server cooling side includes a cooling booster pump, a liquid distribution unit, an immersion tank, a recovery unit, several server cooling plates and several immersed server positions, and the immersed server positions are located inside the immersion tank; the circulating heat exchange side includes a liquid storage unit, a natural cooler, a first refrigerant pump, a second refrigerant pump and a compressor. Although intelligent control and precise adjustment enable efficient, safe, and reliable operation of the liquid cooling system, effectively reducing server temperatures and extending equipment life, which is of great significance to the green environmental protection and sustainable development of data centers, the indirect heat exchange required through the heat exchanger leads to secondary heat transfer efficiency losses, the complex three-side (server / circulating heat exchange / remote control) system architecture causes control delays, and the reliance on multiple refrigerant pumps and compressors leads to excessive energy consumption.

[0004] Prior art two, Chinese patent, application number 202310707957.9 discloses a single-phase liquid-cooled server and a cooling circulation system. The single-phase liquid-cooled server includes a main casing, a jet structure, a liquid inlet and a liquid outlet. The jet structure is arranged on the main casing, and the jet structure has a built-in cooling medium; the liquid inlet is arranged on the main casing and connected to the jet structure. The liquid inlet is used to drive the cooling medium to be ejected from the jet structure to provide jet liquid cooling to the interior of the main casing; the liquid outlet is arranged on the main casing, and the cooling medium inside the main casing is discharged from the main casing through the liquid outlet. Although the jet structure dissipates heat for the inner cavity as a whole, through the indirect cooling structure, the inner cavity and the outer cavity exchange heat, thereby realizing indirect liquid cooling of the second heating element by the jet structure, providing liquid cooling for the single-phase liquid-cooled server in a simple and efficient way; however, the jet structure increases the flow resistance, the temperature gradient caused by the indirect cooling method is uneven, and the fixed flow mode cannot adapt to dynamic heat loads.

[0005] Prior art three, Chinese patent application number 201210253663.5, discloses a forced cooling circulation structure for a fanless server, comprising a server cabinet housing with a server mounting rack mounted within the server cabinet housing. The structure is characterized in that the server mounting rack divides the space within the server cabinet housing into a hot-end zone and a cold-end zone. A duct is formed at the top of the server cabinet housing by a closed panel, with a fan unit mounted on one side of the duct located in the hot-end zone and a surface cooler unit mounted on the other side of the duct located in the cold-end zone. A fanless server is mounted on the server mounting rack, comprising a server housing with an air inlet slot on one side and an air outlet on the other side, with the air inlet slot facing the cold-end zone and the air outlet facing the hot-end zone. While fanless servers eliminate the need for server exhaust fans for heat dissipation, increasing server capacity within the same cabinet, air-cooled architectures suffer from inherent air heat exchange efficiency bottlenecks, reduced space utilization due to hot and cold-end partitioning, and the risk of condensation from the surface cooler unit.

[0006] Currently, existing technologies 1, 2, and 3 suffer from energy waste in traditional single-mode operation, response lag in fixed threshold control, unbalanced branch / main pipe flow distribution, single-phase immersion direct cooling architecture, and cumulative thermal resistance effects of indirect heat exchange. Therefore, the present invention provides a single-phase immersion liquid cooling server circulating cooling method and system. Summary of the Invention

[0007] In order to achieve the above object, the present invention adopts the following technical solutions: In one aspect of the present invention, a circulating cooling method for a single-phase immersion liquid-cooled server is provided, comprising the following steps: The coolant in the immersion liquid cooling cabinet flows through the chip, and the real-time temperature of the coolant is compared with the preset temperature threshold. When the real-time temperature does not exceed the preset threshold, the control system issues a first program instruction to enter the immersion liquid cooling cabinet circulation mode; when the real-time temperature reaches and exceeds the preset threshold, the control system issues a second program instruction to enter the heat exchange circulation mode; After the heat exchange circulation mode is activated, the main liquid outlet pipe is opened. At the same time, the preset threshold is dynamically adjusted based on the chip temperature trend, load rate, and the return temperature of the immersion liquid cooling cabinet. The opening of the branch pipe valve and the main pipe valve is controlled by PWM signals to achieve a transition state of full branch opening, full main circulation opening, or proportional regulation. The coolant flows back to the liquid outlet of the immersion liquid cooling cabinet through the return branch pipe, and continues to judge the real-time temperature of the coolant and the preset temperature threshold. According to the comparison result, the switching between the internal circulation mode of the immersion liquid cooling cabinet and the heat exchange circulation mode is realized.

[0008] In an optional embodiment, the process of achieving the transition state of branch full opening, main cycle full opening or proportional regulation includes the following steps: Receive feedback on the temperature contact point coordinates, real-time chip load rate, and return port temperature. Generate a time axis extension vector based on the temperature contact point coordinates. Convert the real-time chip load rate into an intensity modulation coefficient. Build a spatial compensation scalar based on the return port temperature and output a dynamic deformation threshold boundary. Phase lag compensation is performed on the dynamic deformation threshold boundary. When the boundary contraction rate exceeds the critical value, a full-open trigger pulse is generated. When the boundary fluctuation frequency is in the transition zone, a proportional adjustment waveform is output to form a PWM fundamental wave sequence. The historical flow ratio of the total liquid outlet pipeline is extracted from the PWM fundamental wave sequence as the inertia weight. The transient compensation amount is calculated based on the temperature difference between the current deformation threshold boundary and the return liquid port to synthesize the valve opening combination weight. Combined with the valve opening combination weight, the full-open trigger pulse drives the branch valve to form a zero-resistance channel, and the proportional adjustment waveform matches the main pipeline valve to generate a gradual throttling surface, realizing the three-state output of branch full opening, main cycle full opening or proportional transition.

[0009] In an optional embodiment, the process of synthesizing the valve opening combination weights includes the following steps: Extract the periodic energy consumption envelope from the historical flow data of the total liquid outlet pipeline, generate the inertia strong and weak oscillation sequence through the flow difference calculation of adjacent time periods, input the inertia strong and weak oscillation sequence into the attenuation memory filter, and output the inertia weight basis; The real-time temperature difference between the dynamic deformation threshold boundary and the return liquid port is received and processed by a spatial thermal pressure converter. The curvature of the deformation threshold boundary is used as the field intensity gradient reference, and the absolute value of the temperature difference is used as the action intensity scalar to generate a transient compensation vector field. Inertia weight basis and transient compensation vector field: project the inertia weight basis along the pipeline axis to form a steady-state skeleton, and inject the transient compensation vector field component at the steady-state skeleton node to form a weighted grid with compensation nodes; The weighted grid with compensation nodes is reconstructed by the valve response adapter to extract the free flow domain of the section corresponding to the fully open trigger pulse. The grid density distribution is adjusted according to the proportional adjustment waveform slope, and finally the valve opening combination weight is output.

[0010] In an optional embodiment, the process of forming a weight grid with compensation nodes includes the following steps: Taking the center line of the total liquid outlet pipe as the reference axis, the inertia weight base is axially stretched and transformed according to the direction of fluid movement to form a tubular weight frame. Skeleton control nodes are evenly distributed on the surface of the tubular weight frame. The three-dimensional transient compensation vector field is compressed along the pipeline radial direction, the projection intensity spectrum of the vector field in the axial direction is extracted, the vortex component modulus of the vector field in the circumferential direction is captured, and a two-dimensional compensation action surface is generated; The two-dimensional compensation surface is spatially phase-matched with the skeleton control nodes. The compensation strength base of each node is determined based on the projected intensity spectrum. The coupling action between adjacent nodes is distributed according to the vortex component modulus to form an enhanced node set with energy labeling. The enhanced node set with energy label is input into the field constraint generator. The tubular weighted frame is used as the initial mesh topology. The mesh density expansion is generated at the nodes according to the compensation strength cardinality. Non-uniform connection tendons are generated between the nodes according to the coupling action. Finally, a weighted mesh with compensation nodes is constructed.

[0011] In an optional implementation, the process of forming an energy-labeled enhanced node set includes the following steps: Bind the amplitude distribution of the projected intensity spectrum to the axial position of the skeleton control node in spatial coordinates, use the reference axis zero point as the origin of spectrum-axis alignment, divide the pipeline length into equal parts according to the intensity spectrum wavelength, and generate a spectrum node mapping table; The spectrum node mapping table is input into the intensity converter, which takes the logarithmic attenuation of the spectrum amplitude corresponding to each node as the base body, superimposes the curvature change rate of the deformation threshold boundary at the node, and outputs the dynamic compensation base matrix; The captured vortex component modulus is processed by the circulation decomposer, and the phase difference angle between the modulus peaks is extracted to generate the adjacent node action coefficient, and the filling ratio of the modulus envelope area to the pipe cross section is obtained to form the energy potential transfer factor set; The dynamic compensation basis matrix and the energy potential transfer factor set are input into the field fusion core. The compensation basis matrix elements are used as node energy cores. The energy cores are extended to adjacent nodes according to the action coefficient to form radiation energy bands. The width of the radiation energy bands is adjusted according to the filling ratio, and finally an enhanced node set with energy labels is generated.

[0012] In an optional embodiment, the process of obtaining the filling ratio of the module envelope area to the pipe cross section includes the following steps: The captured vortex component modulus waveform is input into the extreme value topology analyzer to identify the effective peak group set whose modulus exceeds the critical amplitude, record the azimuth coordinates of each peak in the pipeline circumferential coordinate system, and generate a peak group azimuth distribution map; The peak group azimuth distribution diagram is processed by the relative motion solver to calculate the tangential offset of adjacent peak azimuths, convert the offset into a vector angle with the pipeline center as the origin, and output the node action angle matrix; The module envelope area is input into the geometric constraint converter. The cross-sectional area of ​​the pipe is used as the reference constraint frame. The dynamic overlap ratio between the envelope area and the reference constraint frame is calculated to generate the vortex core occupancy factor. The node action angle matrix and vortex core occupancy factor are input into the fluid interference synthesizer, the vector angle tangent is used as the action intensity coefficient, and the vortex core occupancy factor is used to modulate the effective action radius of the action intensity coefficient, ultimately forming an energy potential transfer factor set.

[0013] In an optional embodiment, the process of switching between the immersion liquid cooling cabinet internal circulation mode and the heat exchange circulation mode according to the comparison result includes the following steps: The coolant temperature data obtained in the return branch pipe is processed by noise suppression and time domain alignment to form a pure return waveform. The pure return waveform is input into the phase analyzer to output the return phase mark. The return phase mark and the currently running cooling mode state are input into the migration criterion synthesizer to form a dual-mode migration trigger field; When in heat exchange mode: the reflux waveform amplitude continues to be lower than the dynamic deformation threshold boundary to generate the internal circulation enabling factor; when in internal circulation mode: the reflux waveform peak contacts the deformation threshold boundary to trigger the heat exchange activation factor; The dual-mode migration trigger field is input into the physical field mapping module. The internal circulation enabling factor drives the closure of the total liquid outlet pipeline valve to form a closed circulation topology. The heat exchange activation factor triggers the branch valve zero resistance channel to establish an open flow channel configuration, completing the cooling mode switching.

[0014] In an optional embodiment, the process of completing the cooling mode switching includes the following steps: The inner loop enabling factor is input into the constraint field generator, the factor strength value is extracted as the closure strength coefficient, the free flow domain closing sequence of the associated weight grid is used to generate the main pipeline valve closing instruction set; The main pipeline valve locking instruction set is acted upon by the fluid path constraint field, with the immersion cavity wall as the fixed boundary and the return branch pipe as the unidirectional conducting axis, forming a closed loop topology; The heat exchange activation factor triggers the zero-resistance channel builder, activates the space-time coordinates of the full-open trigger pulse, calls the compensation node energy distribution of the weighted grid, and generates the branch valve expansion wave front; The closed loop topology and open flow channel configuration are output to the thermal inertia balance monitor to detect the consistency between the temperature gradient in the cavity and the heat flow trend vector, verify that the reflux pure waveform conforms to the phase characteristic spectrum of the target mode, and confirm that the cooling mode switching is completed.

[0015] Another aspect of the present invention provides a single-phase immersion liquid cooling server circulating cooling system for implementing the single-phase immersion liquid cooling server circulating cooling method, comprising: an immersion liquid cooling cabinet, a branch pipeline valve, a main pipeline valve, a main liquid outlet pipeline, a pump, a heat exchanger and a branch pipeline.

[0016] Among them, the immersion liquid cooling cabinet is provided with at least one liquid outlet and two liquid inlets, the liquid outlets are respectively installed at the upper end of one side of the immersion liquid cooling cabinet, and the two liquid inlets are arranged at the middle position and the lower end of one side of the immersion liquid cooling cabinet; the liquid inlet at the middle position is connected to the main liquid outlet pipe through a branch pipe and a branch pipe valve; a main pipe valve is installed on the main liquid outlet pipe, the outlet end of the main liquid outlet pipe is connected to the inlet end of the pump, the outlet end of the pump is connected to the inlet end of the heat exchanger, and the outlet end of the heat exchanger is connected to the liquid inlet at the lower end through a reflux branch pipe.

[0017] The present invention achieves efficient thermal management of immersion liquid cooling systems through a multimodal control strategy. The dual-mode adaptive switching mechanism constructs a basic control framework based on binary judgment logic of temperature thresholds. The first program instruction maintains microcirculation within the cabinet to reduce pump power loss. When the second program instruction is triggered, forced heat exchange is achieved to ensure heat dissipation capacity under transient thermal shock. The dynamic parameter correction system establishes a multivariate feedback model of chip temperature change rate, load rate, and return liquid temperature. An online threshold adjustment algorithm is used to avoid control lag. PWM modulation is used to achieve stepless adjustment of valve opening and balance the flow distribution between the branch and the main pipeline. The closed-loop control architecture sets a secondary temperature detection node for the return branch to form a hysteresis comparison circuit for mode switching, and constructs a dual feedback control loop for the coolant temperature field. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 This is a flow chart of the circulating cooling method for a single-phase immersion liquid-cooled server provided in Example 1 of the present invention; Figure 2 This is a schematic diagram of the circulating cooling method for a single-phase immersion liquid-cooled server provided in Example 1 of the present invention; Figure 3This is a process diagram of comparing the real-time temperature of the coolant with a preset temperature threshold provided in Example 2 of the present invention; Figure 4 This is a process diagram for achieving a transition state of fully opening branches, fully opening the main loop, or proportional regulation, as provided in Example 5 of the present invention; Figure 5 This is a process diagram for switching between an immersion liquid cooling cabinet internal circulation mode and a heat exchange circulation mode according to a comparison result provided in Example 10 of the present invention; Figure 6 This is a block diagram of a circulating cooling system for a single-phase immersion liquid-cooled server provided in Example 13 of the present invention; Figure 7 A block diagram of the electronic device provided by the present invention; Figure 8 A block diagram of a computer-readable storage medium provided by the present invention; Figure numerals: 1. Immersed liquid cooling cabinet; 2. Branch pipe valve; 3. Main pipe valve; 4. Main liquid outlet pipe; 5. Pump; 6. Heat exchanger; 7. Branch pipe; 8. Central processing unit / microprocessor / main control chip; 9. Storage medium; 10. Data bus 1; 11. Input / output bus / external bus / device bus; 12. Display; 13. Input / output device; 14. Computer-readable instructions; 15. Non-temporary computer-readable storage medium. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present invention will be described below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0020] In the following, the terms "first," "second," etc., are used for descriptive convenience only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature identified with "first," "second," etc., may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0021] In the present invention, unless otherwise clearly specified and limited, the term "connection" should be understood in a broad sense. For example, "connection" can be a fixed mechanical connection, a detachable mechanical connection, or an integrated one; or, "connection" can be a direct connection or an indirect connection through an intermediate medium. In addition, unless otherwise clearly specified and limited, the term "coupling" should be understood in a broad sense. For example, "coupling" can be a direct electrical connection, such as physical contact and electrical conduction between two components, or it can be understood as the electrical connection between different components in a circuit structure through a physical line that can transmit electrical signals, such as printed circuit board (PCB) copper foil or wire, so as to transmit electrical signals; or, "coupling" can be an indirect electrical connection between two components through an intermediate medium; or, "coupling" can be an electrical connection between two components in an airless / non-contact manner, such as electrical connection between two components using capacitive coupling to transmit electrical signals.

[0022] In an embodiment of the present invention, directional terms such as "up", "down", "left" and "right" may be defined including but not limited to the orientation relative to the schematic placement of the components in the drawings. It should be understood that these directional terms may be relative concepts, which are used for relative description and clarification, and may change accordingly according to changes in the orientation of the components in the drawings.

[0023] The inventive concept of the present invention:

[0024] Example 1: Figure 1 As shown, an embodiment of the present invention provides a single-phase immersion liquid cooling server circulation cooling method, comprising the following steps: Step S100: Coolant in the immersion liquid cooling cabinet flows through the chip, and the real-time temperature of the coolant is compared with a preset temperature threshold. When the real-time temperature does not exceed the preset threshold, the control system issues a first program instruction to enter the immersion liquid cooling cabinet circulation mode; when the real-time temperature reaches and exceeds the preset threshold, the control system issues a second program instruction to enter the heat exchange circulation mode; Step S200: After the heat exchange cycle mode is activated, the main liquid outlet pipe is opened; at the same time, the preset threshold is dynamically adjusted based on the chip temperature trend, load factor, and the return temperature of the immersion liquid cooling cabinet; the opening of the branch pipe valve and the main pipe valve is controlled by PWM signals to achieve a transition state of full branch opening, full main circulation opening, or proportional regulation; Step S300: The coolant flows back to the liquid outlet of the immersion liquid cooling cabinet through the return branch pipe, and the real-time temperature of the coolant and the preset temperature threshold are continuously judged. The switching between the internal circulation mode of the immersion liquid cooling cabinet and the heat exchange circulation mode is realized according to the comparison result.

[0025] In the above embodiment, the specific principle is as follows Figure 2 As shown, this embodiment achieves efficient thermal management of an immersion liquid cooling system through a multimodal control strategy. The dual-mode adaptive switching mechanism (step S100) establishes a basic control framework based on binary judgment logic based on temperature thresholds. A first program instruction maintains microcirculation within the cabinet to reduce pump power loss. A second program instruction triggers forced heat exchange, ensuring heat dissipation under transient thermal shock. The dynamic parameter correction system (step S200) establishes a multivariate feedback model based on chip temperature change rate, load factor, and return liquid temperature. An online threshold adjustment algorithm is used to avoid control lag. PWM modulation achieves stepless adjustment of valve opening to balance flow distribution between the branch and main pipeline. The closed-loop control architecture (step S300) establishes a secondary temperature detection node in the return branch, forming a hysteresis comparison circuit for mode switching and establishing a dual feedback control loop for the coolant temperature field.

[0026] In summary, this embodiment achieves the topological reconstruction capability of the coolant flow, dynamically switches between local and global circulation according to the thermal load, eliminates system hydraulic oscillations through continuous adjustment of valve opening, improves the response speed to sudden loads through dynamic thresholds, and ensures the timing accuracy of mode switching through return temperature monitoring; ultimately achieving the Pareto optimality of minimizing pumping power consumption and maximizing heat dissipation efficiency.

[0027] Example 2: Figure 3 As shown, based on Example 1, the process of comparing the real-time temperature of the coolant with the preset temperature threshold in step S100 provided by the embodiment of the present invention includes the following steps: Step S101: Obtain the original coolant temperature sequence, and generate a pure temperature waveform through noise suppression and time alignment. Input the preset temperature threshold into the load-temperature coupling program, receive the chip load rate and historical temperature rise curve, and output the deformation threshold boundary. The upper boundary value is elastically adjusted with load fluctuations. Step S102: The clean temperature waveform and the deformation threshold boundary are synchronously input into the phase analyzer. When the amplitude of the clean temperature waveform is continuously lower than the boundary, a steady-state feature vector is generated. When the peak of the clean temperature waveform touches the boundary, a transition feature flag is triggered. Step S103: The steady-state characteristic vector activates the circulation instruction encoder and outputs the first program instruction; the transition characteristic mark triggers the heat exchange enabler, which outputs the second program instruction and feeds back the current temperature contact point coordinates to the preset threshold for dynamic correction; in the reflow temperature detection, the phase analyzer performs boundary penetration detection on the corrected deformation threshold boundary, and triggers the instruction switching condition when the reflow temperature waveform separates from the boundary.

[0028] In the above embodiment, this embodiment realizes the nonlinear deformation of the preset threshold value through the load-temperature coupling program, so that the temperature boundary has the elastic and scalable characteristics of adapting to the chip load rate and the historical temperature rise curve, solving the problem of the hysteresis of the fixed threshold response to the transient thermal load. Based on the phase analysis of the pure temperature waveform after noise suppression and the deformation threshold, a steady-state / transition dual-mode feature detection system is established. The continuous amplitude detection ensures the stability of the mode switching, and the peak contact detection provides the critical state response capability. The steady-state feature vector and the transition feature mark respectively drive the circulation instruction encoder and the heat exchange enabler to form a feedback loop of the instruction output and the threshold correction. The boundary penetration detection mechanism realizes the precise triggering of the mode switching condition by separating and judging the reflow temperature waveform and the correction boundary. The time alignment processing ensures the temporal consistency of the temperature sequence and the load data, and the synchronous input of the phase analyzer ensures the real-time nature of the threshold comparison; the temperature contact point coordinate feedback enables the dynamic correction of the preset threshold to have spatial positioning capability, thereby improving the control accuracy of the transition process.

[0029] In summary, this embodiment constructs an adaptive liquid cooling control system with load following characteristics, and achieves smooth transition and energy consumption optimization during the cooling mode switching process through the synergistic effect of noise suppression, elastic boundary, dual-mode detection and closed-loop correction.

[0030] Example 3: Based on Example 2, the process of forming a pure temperature waveform through noise suppression and time alignment in step S101 provided by the embodiment of the present invention includes the following steps: Step S1011: a sensor array distributed in the three-dimensional coordinate system of the immersion cavity of the immersion liquid cooling cabinet generates an original temperature field intensity distribution, and a heat flow tendency vector is extracted by differential operation of temperature differences between adjacent nodes; Step S1012: Input the heat flux tendency vector into the transient response screen, divide the time axis according to the chip power pulse frequency: adopt field intensity mean convergence during the power stable period, enable gradient change rate capture during the power jump period, and output a time-scale aligned field intensity sequence; Step S1013: The time-scale aligned field intensity sequence enters the eddy current interference eliminator, identifies the periodic disturbance ripples formed by the vortex of the coolant flow, reverses the phase of the periodic disturbance ripples and superimposes them on the original coolant temperature sequence to generate a decoherent field intensity matrix; Step S1014: The decorrelation field strength matrix is ​​reconstructed under boundary constraints, the cavity wall temperature is used as a static anchor point, and the heat flow tendency vector is used as a dynamic correction reference, and finally a pure temperature waveform is output.

[0031] In the above embodiment, this embodiment replaces the traditional point temperature acquisition with three-dimensional field intensity gradient analysis, and combines power pulse time domain segmentation and eddy current coherence elimination technology, so that the output pure temperature waveform completely retains the true thermal state of the coolant, and provides the subsequent phase analyzer with a basic waveform with physical field time and space characteristics.

[0032] Example 4: Based on Example 3, the process of extracting the heat flow tendency vector by performing temperature differential calculation of adjacent nodes in step S1011 provided by the embodiment of the present invention includes the following steps: Step S10111: The three-dimensional coordinates of the sensor array form a node space topology, and a bidirectional differential scan is performed on the real-time temperatures of adjacent nodes. A transverse thermal potential difference set is generated for the X-axis node pairs, a longitudinal thermal potential difference set is generated for the Y-axis node pairs, and a vertical thermal potential difference set is generated for the Z-axis node pairs. The three sets of thermal potential difference sets are combined into a spatial thermal potential gradient map. Step S10112: Analyze the spatial thermal potential gradient map, identify the effective transition path whose absolute value of the gradient exceeds the critical value, integrate the thermal potential difference along the effective transition path to generate the motion potential energy distribution, and output the quantized potential energy field; Step S10113: The quantized potential energy field is subjected to vortex core focusing processing, with the local potential energy extreme point as the convergence core, and the dominant trend component is synthesized according to the weighted motion potential energy intensity to finally form a heat flow trend vector.

[0033] In the above embodiment, this embodiment establishes spatial heat transfer correlation through bidirectional differential scanning, uses motion potential energy path integral to replace traditional vector calculation, and combines the vortex core focusing aggregation mechanism to enable the heat flow tendency vector to accurately characterize the dynamic heat transfer characteristics of the coolant in three-dimensional space, providing a physical field kinematic basis for subsequent time domain compression and waveform reconstruction.

[0034] Example 5: Figure 4 As shown, based on Example 1, the process of achieving the transition state of branch full opening, main cycle full opening or proportional regulation in step S200 provided by the embodiment of the present invention includes the following steps: Step S201: Receive feedback on the temperature contact point coordinates, the real-time chip load rate, and the liquid return port temperature, generate a time axis extension vector based on the temperature contact point coordinates, convert the real-time chip load rate into an intensity modulation coefficient, construct a spatial compensation scalar based on the liquid return port temperature, and output a dynamic deformation threshold boundary; Step S202: Phase lag compensation is performed on the dynamic deformation threshold boundary. When the boundary contraction rate exceeds a critical value, a full-open trigger pulse is generated. When the boundary fluctuation frequency is in the transition zone, a proportional adjustment waveform is output to form a PWM fundamental wave sequence. The historical flow ratio of the total liquid outlet pipeline is extracted from the PWM fundamental wave sequence as an inertia weight. The transient compensation amount is calculated based on the temperature difference between the current deformation threshold boundary and the return liquid port to synthesize the valve opening combination weight. Step S203: Combined with the valve opening combination weight, the full-open trigger pulse drives the branch valve to form a zero-resistance channel, and the proportional adjustment waveform matches the main pipeline valve to generate a gradual throttling surface to achieve three-state output of branch full opening, main cycle full opening or proportional transition.

[0035] In the above embodiments, this embodiment integrates multi-dimensional correction factors through three-dimensional deformation, uses a phase lag compensator to convert boundary dynamic characteristics into PWM waveforms, and combines a flow field equilibrium solver to achieve accurate mapping of valve state and thermodynamic deformation, forming a closed-loop adaptive control system.

[0036] Example 6: Based on Example 5, the process of synthesizing the valve opening combination weight in step S202 provided in this embodiment of the present invention includes the following steps: Step S2021: extracting the periodic energy consumption envelope from the historical flow data of the total liquid outlet pipeline, generating an inertia strong and weak oscillation sequence by performing flow difference calculations in adjacent time periods, inputting the inertia strong and weak oscillation sequence into an attenuated memory filter, and outputting an inertia weight basis; Step S2022: receiving the real-time temperature difference between the dynamic deformation threshold boundary and the liquid return port, processing it through a spatial thermal pressure converter, using the deformation threshold boundary curvature as the field intensity gradient reference and the absolute value of the temperature difference as the action intensity scalar to generate a transient compensation vector field; Step S2023: The inertia weight basis and the transient compensation vector field are projected along the pipeline axis to form a steady-state skeleton, and the transient compensation vector field components are injected into the nodes of the steady-state skeleton to form a weighted grid with compensation nodes. Step S2024: The weighted grid with compensation nodes is reconstructed through the valve response adapter, the free flow domain of the section corresponding to the fully open trigger pulse is extracted, the grid density distribution is adjusted according to the proportional adjustment waveform slope, and finally the valve opening combination weight is output.

[0037] In the above embodiments, this embodiment quantifies the historical flow inertia through periodic energy consumption envelope analysis, converts the temperature difference into a physical field using spatial thermal pressure conversion, and combines fluid-solid interference grid synthesis technology to realize the spatiotemporal coupling of valve control elements, providing the execution terminal with precise control parameters with fluid dynamics adaptability.

[0038] Example 7: Based on Example 6, the process of forming a weight grid with compensation nodes in step S2023 provided in this embodiment of the present invention includes the following steps: Step S20231: Using the centerline of the total liquid outlet pipe as the reference axis, the inertia weight base is axially stretched and transformed according to the direction of fluid movement to form a tubular weight frame, and equidistantly distributed skeleton control nodes are set on the surface of the tubular weight frame; Step S20232: compressing the three-dimensional transient compensation vector field along the pipeline radial direction, extracting the projection intensity spectrum of the vector field in the axial direction, capturing the vortex component modulus of the vector field in the circumferential direction, and generating a two-dimensional compensation action surface; Step S20233: performing spatial phase matching on the two-dimensional compensation action surface and the skeleton control node, determining the compensation strength base of each node based on the projected intensity spectrum, distributing the coupling action between adjacent nodes according to the vortex component modulus, and forming an enhanced node set with energy labeling; Step S20234: The enhanced node set with energy label is input into the field constraint generator, and the tubular weight frame is used as the initial grid topology. The grid density expansion is generated at the nodes according to the compensation strength cardinality, and non-uniform connection tendons are generated between the nodes according to the coupling action, and finally a weighted grid with compensation nodes is constructed.

[0039] In the above embodiments, this embodiment solidifies the historical flow characteristics into a spatial framework through axial stretching transformation, uses field intensity dimensionality reduction mapping to achieve three-dimensional to two-dimensional transformation of transient compensation, and combines node energy injection and topological adaptive growth mechanism to enable the weight grid to have dual control properties of historical inertial characteristics and real-time thermodynamic response.

[0040] Example 8: Based on Example 7, the process of forming an enhanced node set with energy label in step S20233 provided in this embodiment of the present invention includes the following steps: Step S202331: Bind the amplitude distribution of the projected intensity spectrum to the axial position of the skeleton control node by spatial coordinates, use the reference axis zero point as the origin of spectrum-axis alignment, divide the pipeline length into equal parts according to the intensity spectrum wavelength, and generate a spectrum node mapping table; Step S202332: The spectrum node mapping table is input into the intensity converter, the logarithmic attenuation of the spectrum amplitude corresponding to each node is taken as the cardinality, the curvature change rate of the deformation threshold boundary at the node is superimposed, and the dynamic compensation cardinality matrix is ​​output; Step S202333: The captured vortex component modulus is processed by the circulation decomposer, and the phase difference angle between the modulus peaks is extracted to generate the adjacent node action coefficient, and the filling ratio of the modulus envelope area to the pipe cross section is obtained to form an energy potential transfer factor set; Step S202334: The dynamic compensation basis matrix and the energy potential transfer factor set are input into the field fusion core, and the compensation basis matrix elements are used as the node energy core. The energy core is extended to the adjacent nodes according to the action coefficient to form a radiation energy band, and the width of the radiation energy band is adjusted according to the filling ratio, and finally an enhanced node set with energy label is generated.

[0041] In the above embodiments, this embodiment realizes precise axial positioning of energy distribution through spectrum-axis space binding, utilizes dual dynamic calibration compensation base of logarithmic attenuation and curvature differential, and combines the joint action modeling of vortex phase difference and cross-section filling to integrate the enhanced nodes into a comprehensive energy carrier that carries historical inertia, real-time thermal pressure and fluid motion characteristics.

[0042] Example 9: Based on Example 8, the process of obtaining the filling ratio of the module envelope area to the pipe cross section in step S202333 provided in the embodiment of the present invention includes the following steps: Step S2023331: input the captured vortex component modulus waveform into the extreme value topology analyzer, identify the valid peak group set whose modulus exceeds the critical amplitude, record the azimuth coordinates of each peak in the pipeline circumferential coordinate system, and generate a peak group azimuth distribution map; Step S2023332: The peak group azimuth distribution diagram is processed by the relative motion solver to calculate the tangential offset of adjacent peak azimuth angles, convert the offset into a vector angle with the pipeline center as the origin, and output the node action angle matrix; Step S2023333: The module envelope area is input into the geometric constraint converter, and the cross-sectional area of ​​the pipe is used as the reference constraint frame. The dynamic overlap ratio between the envelope area and the reference constraint frame is calculated to generate the vortex core occupancy factor. Step S2023334: The node action angle matrix and the vortex core occupancy factor are input into the fluid interference synthesizer, the vector angle tangent value is used as the action intensity coefficient, and the vortex core occupancy factor is used to modulate the effective action radius of the action intensity coefficient, and finally form an energy potential transfer factor set.

[0043] In the above embodiments, this embodiment locks the vortex energy core through extreme topological analysis, establishes a circumferential kinematic model using tangential offset-vector angle conversion, and combines the envelope-section dynamic coupling mechanism to enable the energy potential transfer factor set to accurately characterize the energy transfer characteristics of the vortex field in the pipeline space.

[0044] Example 10: Figure 5 As shown, based on Example 1, the process of switching between the immersion liquid cooling cabinet internal circulation mode and the heat exchange circulation mode according to the comparison result in step S300 provided by the embodiment of the present invention includes the following steps: Step S301: Coolant temperature data acquired in the return branch pipe is subjected to noise suppression and time domain alignment processing to form a return pure waveform, which is then input into a phase analyzer to output a return phase mark. Step S302: The return phase mark and the current cooling mode state are input into the migration criterion synthesizer to form a dual-mode migration trigger field; When in heat exchange mode: the reflux waveform amplitude continues to be lower than the dynamic deformation threshold boundary to generate the internal circulation enabling factor; when in internal circulation mode: the reflux waveform peak contacts the deformation threshold boundary to trigger the heat exchange activation factor; Step S303: The dual-mode migration trigger field is input into the physical field mapping module, the internal circulation enabling factor drives the closure of the total liquid outlet pipe valve to form a closed circulation topology, and the heat exchange activation factor triggers the branch valve zero resistance channel to establish an open flow channel configuration, completing the cooling mode switching.

[0045] In the above embodiment, this embodiment regenerates the multiplexed core analysis module through the reflux phase feature, utilizes the dual-mode migration trigger field to integrate boundary penetration events and operating status, and combines the physical field mapping inversion to achieve disturbance-free switching of cooling modes, forming a closed-loop migration system from temperature detection to fluid path control.

[0046] Example 11: Based on Example 10, the process of completing the cooling mode switching in step S303 provided in this embodiment of the present invention includes the following steps: Step S3031: Input the inner loop enabling factor into the constraint field generator, extract the factor strength value as the closure strength coefficient, associate it with the free flow domain closing sequence of the weighted grid, and generate the main pipeline valve closing instruction set; Step S3032: The main pipeline valve locking instruction set is acted upon by the fluid path constraint field, with the immersion chamber wall as the fixed boundary and the return branch pipeline as the unidirectional conducting axis, to form a closed loop topology; Step S3033: The heat exchange activation factor triggers the zero-resistance channel builder, activates the full-open trigger pulse time-space coordinates, calls the compensation node energy distribution of the weighted grid, and generates the branch valve expansion wavefront; Step S3034: The closed loop topology and the open channel configuration are output to the thermal inertia balance monitor to detect the consistency between the temperature gradient in the cavity and the heat flow trend vector, verify that the pure reflux waveform conforms to the phase characteristic spectrum of the target mode, and confirm that the cooling mode switching is completed.

[0047] Among the above embodiments, this embodiment converts logical factors into physical constraints through a constraint field generator, uses the fluid path constraint field to realize geometric space reconstruction, and combines the wavefront propagation mechanism of the zero-resistance channel builder to enable mode switching to have both instantaneous responsiveness and thermodynamic stability, completing the precise mapping from control instructions to fluid space topology.

[0048] Example 12: Based on Example 11, the process of verifying that the pure reflux waveform conforms to the phase characteristic spectrum of the target mode in step S3034 provided in the embodiment of the present invention includes the following steps: Step S30341: Call the historical phase signature library according to the switching instruction type, the inner loop mode corresponds to the steady-state feature vector set, the hot exchange mode is associated with the transition feature signature sequence, and the target mode reference spectrum is synthesized; Step S30342: The reflow pure waveform uses the heat flow tropism vector as the projection axis, and the waveform amplitude is decomposed along the projection axis to generate a spatial projection characteristic line. The spatial projection characteristic line and the target mode reference spectrum are input into the curvature fit analyzer to obtain the geometric similarity ratio between the characteristic line curvature radius and the reference spectrum wavelength. The spatiotemporal alignment of the characteristic line inflection point and the reference spectrum phase jump is detected, and a dynamic fit coefficient matrix is ​​output. Step S30343: The dynamic matching coefficient matrix is ​​judged by the threshold penetration detector. When the geometric similarity ratio is continuously greater than the critical value and the spatiotemporal alignment reaches 90%, the mode steady-state authentication signal is triggered to complete the verification.

[0049] In the above embodiments, this embodiment establishes a mode authentication benchmark through historical phase mark reconstruction, uses heat flow vector space projection to convert waveforms into quantifiable geometric features, and combines curvature-phase dual matching analysis to achieve accurate judgment of the cooling mode steady state, forming a complete verification chain from fluid thermodynamic characteristics to control logic authentication.

[0050] Example 13: Figure 6 As shown, based on Examples 1 to 12, the single-phase immersion liquid cooling server circulating cooling system provided by the embodiments of the present invention includes: an immersion liquid cooling cabinet 1, a branch pipe valve 2, a main pipe valve 3, a main liquid outlet pipe 4, a pump 5, a heat exchanger 6 and a branch pipe 7.

[0051] Among them, the immersion liquid cooling cabinet 1 is provided with at least one liquid outlet and two liquid inlets, the liquid outlets are respectively installed at the upper end of one side of the immersion liquid cooling cabinet 1, and the two liquid inlets are arranged at the middle position and the lower end of one side of the immersion liquid cooling cabinet 1; the liquid inlet at the middle position is connected to the total liquid outlet pipe 4 through a branch pipe 7 and a branch pipe valve 2; the total liquid outlet pipe 4 is installed with a main pipe valve 3, the outlet end of the total liquid outlet pipe 4 is connected to the inlet end of the pump 5, the outlet end of the pump 5 is connected to the inlet end of the heat exchanger 6, and the outlet end of the heat exchanger 6 is connected to the liquid inlet at the lower end through a reflux branch pipe.

[0052] In the above embodiment, in this embodiment, the temperature sensor is directly attached to the surface of the chip to monitor the core temperature of the chip in real time; the outlet temperature sensor is installed at the outlet of the total outlet pipe 4 of the immersion liquid cooling cabinet 1 to monitor the coolant temperature after absorbing the heat generated by the chip during operation; the chip temperature and the coolant temperature at the outlet are monitored in real time; when the chip temperature is lower than the set threshold, the branch pipe valve 2 is automatically opened by the control system to allow the coolant to flow directly back to the immersion liquid cooling cabinet 1; when the chip temperature rises, the branch pipe valve 2 is closed to allow the coolant to enter the heat exchanger 6 for cooling; a reflux branch pipe is added to the liquid inlet at the lower end of the immersion liquid cooling cabinet 1, and the circulation path of the coolant is dynamically adjusted to achieve on-demand distribution.

[0053] In actual implementation, it also includes components such as an electronically controlled valve consisting of a branch pipe valve 2 and a main pipe valve 3, a flow control device, etc.; high-precision thermocouples or infrared temperature sensors are attached to the surface of core chips such as CPUs or GPUs to collect chip temperature in real time, reflecting the most direct indicator of heat dissipation requirements. A platinum resistance temperature sensor is embedded in the main liquid outlet pipe 4 to collect the temperature of the coolant after absorbing heat; at the same time, auxiliary sensors are deployed at the liquid inlet in the middle position and at the lower end to monitor the actual temperature of the return coolant to verify the cooling effect. At the same time, a flow control device is installed to accurately control the flow of the return coolant according to the heat generation of the chip and the temperature of the coolant, to ensure that the chip can be effectively cooled without affecting the cooling effect and system stability due to excessive or insufficient flow.

[0054] When the single-phase immersion liquid cooling server circulation cooling system of this embodiment is running, the chips in the AI ​​and cloud computing servers are the source of heat generation, and the coolant in the immersion liquid cooling cabinet 1 flows through the chips. When the coolant absorbs a small amount of heat from the chips in the immersion liquid cooling cabinet 1, the temperature rises from the initial value but does not exceed the threshold value; the control system determines that the coolant is still in the effective cooling temperature range and does not need to be cooled, and the control system issues a command to close the main pipeline valve 3 and open the branch pipeline valve 2; the path switching conditions are defined by preset thresholds (chip temperature, coolant temperature and temperature fluctuation rate). When the chip temperature and the outlet coolant temperature are both lower than the set low value and there is an effective temperature difference, it is determined that the reflux branch pipeline can be started, and when the chip temperature and the outlet coolant temperature exceed the set low value When the setpoint is high or the temperature fluctuates rapidly, the main cooling loop in the main outlet pipe 4 is activated. Simultaneously, dynamic corrections are made based on multi-dimensional data such as chip temperature trends, load factor, and return port temperature. For example, these adjustments involve switching paths in anticipation of temperature increases and tightening thresholds under high loads. At the execution level, a rapid-action electromagnetic three-way valve is used to control the opening of branch pipe valve 2 and main pipe valve 3 via PWM signals, achieving transitional states between full branch opening, full main loop opening, or proportional regulation. Electric throttle valves and differential pressure sensors ensure flow balance. Furthermore, a status check is performed every 500ms, comparing the actual temperature at the return port (the lower inlet) with the expected value to correct the action. In the event of a sensor failure or valve anomaly, a safety mode is immediately triggered and an alarm is issued, ensuring stable system operation. Coolant flows directly back through the return branch pipe: from the outlet of immersion liquid cooling cabinet 1, through branch pipe 7, to the return port, and then back into immersion liquid cooling cabinet 1, where it contacts the chips again. There is a temperature difference between the returning coolant and the chip, so it continues to absorb heat (the chip is still slowly generating heat at this time), completing secondary cooling and avoiding heat waste caused by the coolant being idle. When the coolant absorbs a large amount of heat, the temperature rises from the initial value to exceed the threshold, and the temperature sensor transmits the signal of the chip and the outlet temperature to the control unit. The control system determines that the coolant temperature is too high and direct return will cause insufficient heat dissipation of the chip (the temperature difference is too small and the heat absorption efficiency decreases). The control system issues an instruction: close the branch pipe valve 2 and open the main pipe valve 3. The coolant enters the traditional cooling process: from the outlet, heat exchanger, return liquid port, immersion liquid cooling cabinet 1, reabsorbs the heat of the chip to ensure the cooling effect.

[0055] In the above embodiment, this embodiment adds a branch to the traditional liquid outlet pipe to directly return the server, perform heat exchange with the chip again, take away the heat generated by the chip, and monitor the chip temperature and the outlet coolant temperature in real time. The branch valve is automatically opened through the control system, which reduces the operation of the heat exchanger and related cooling equipment, reduces energy consumption, improves the energy utilization efficiency of the system, and effectively reduces the operating costs of application scenarios such as data centers; by dynamically judging the coolant temperature and switching the circulation path, the start-up frequency of the heat exchanger can be reduced during low-load periods or even completely shut down. In scenarios where the server load fluctuates greatly, the energy consumption of the heat exchange system can be reduced by 30%-60%, which can save hundreds of thousands to millions of kilowatt-hours of electricity annually for large data centers, significantly reducing the PUE value, and helping data centers achieve energy conservation and carbon reduction goals. The entire circulation system requires three key parts to work together. The first is accurate monitoring. By deploying high-precision temperature sensors on the chip surface and at the liquid outlet, temperature changes are captured in real time to provide data basis for path switching. The second is intelligent control. After receiving the temperature signal from the sensor, it determines whether to open the branch according to the preset logic. PLC or single-chip microcomputer is usually used to achieve millisecond-level valve control response. Finally, reasonable pipeline design is required. The branch needs to form a parallel structure with the main circulation path and achieve seamless switching through a three-way valve. At the same time, the pipeline diameter, length and flow distribution must be calculated to avoid flow field turbulence caused by resistance changes. Ensure that the coolant can evenly cover the chip surface regardless of whether the main circulation or branch is running, without local overheating and wasting cooling capacity. Through the logic of "temperature trigger-path switching-dynamic circulation", the ineffective operation of the heat exchanger is reduced while ensuring the reliability of heat dissipation, thereby reducing system energy consumption.

[0056] The design of the return branch in this embodiment reduces the operating time of the heat exchanger and related pump and valve equipment, reduces the probability of wear of mechanical parts, thereby extending the equipment maintenance cycle and reducing the losses caused by downtime and maintenance. At the same time, the direct return of low-temperature coolant avoids the problem of excessive cooling that may occur in traditional full-time cooling, reduces the thermal stress caused by sudden temperature rise and fall on the chip, and indirectly increases the service life of the server hardware. Flexibility and adaptability: It can adapt to different load fluctuation scenarios. Whether it is full heat dissipation during high loads during the day or energy-saving cycles during low loads at night, the system can automatically switch through intelligent control without manual intervention. The branch design is highly compatible with the modification of existing liquid cooling systems. There is no need to reconstruct the core architecture. Upgrades can be achieved by adding new pipes, sensors and control units, which reduces the threshold and cost of technology implementation. Environmental protection: By reducing energy consumption, it indirectly reduces the dependence of data centers on grid electricity, especially in areas where thermal power is the main source, which can reduce greenhouse gas emissions such as carbon dioxide.

[0057] Figure 7 A block diagram is shown of an exemplary electronic device suitable for implementing embodiments of the present invention.

[0058] The electronic device may include a central processing unit / microprocessor / main control chip, etc. 8; a storage medium 9, coupled to the central processing unit / microprocessor / main control chip, etc. 8, and storing computer executable instructions therein for performing the steps of each method of an embodiment of the present invention when executed by the processor.

[0059] The central processing unit / microprocessor / main control chip 8 may include but is not limited to one or more processors or microprocessors.

[0060] The storage medium 9 may include, but is not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (such as hard disk, floppy disk, solid-state drive, removable disk, CD-ROM, DVD-ROM, Blu-ray disc, etc.).

[0061] In addition, the electronic device may also include (but not limited to) a data bus 10, an input / output bus / external bus / device bus 11, a display 12, and input / output devices 13 (eg, keyboard, mouse, speaker, etc.).

[0062] The central processing unit / microprocessor / main control chip etc. 8 can communicate with external devices ( 12 , 13 etc.) via an I / O bus 11 via a wired or wireless network (not shown).

[0063] The storage medium 9 may also store at least one computer executable instruction for executing the various functions and / or method steps in the embodiments described in this technology when run by the central processing unit / microprocessor / main control chip 8.

[0064] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0065] Figure 8 A schematic diagram of a computer-readable storage medium according to an embodiment of the present invention is shown.

[0066] like Figure 8As shown, the non-transitory computer-readable storage medium 15 stores instructions, such as computer-readable instructions 14. When the computer-readable instructions 14 are executed by the processor, the various methods described above can be executed. Non-transitory computer-readable storage media include, but are not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. Non-transitory non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. For example, the non-transitory computer-readable storage medium 15 can be connected to a computing device such as a computer, and then, when the computing device executes the computer-readable instructions 14 stored on the computer-readable storage medium 15, the various methods described above can be performed.

[0067] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0068] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0069] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0070] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for executing all or part of the steps of the various embodiments of the method of the present invention via a computer device (which can be a personal computer, server, or network device, etc.). The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0071] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A single-phase immersion liquid cooling server circulation cooling method, characterized in that: The following steps are involved: The coolant in the immersion liquid cooling cabinet flows through the chip, and the real-time temperature of the coolant is compared with the preset temperature threshold. When the real-time temperature does not exceed the preset threshold, the control system issues a first program instruction to enter the immersion liquid cooling cabinet circulation mode; when the real-time temperature reaches and exceeds the preset threshold, the control system issues a second program instruction to enter the heat exchange circulation mode; After the heat exchange circulation mode is activated, the main liquid outlet pipe is opened. At the same time, the preset threshold is dynamically adjusted based on the chip temperature trend, load rate, and the return temperature of the immersion liquid cooling cabinet. The opening of the branch pipe valve and the main pipe valve is controlled by PWM signals to achieve a transition state of full branch opening, full main circulation opening, or proportional regulation. The coolant flows back to the liquid outlet of the immersion liquid cooling cabinet through the return branch pipe, and continues to judge the real-time temperature of the coolant and the preset temperature threshold. According to the comparison result, the switching between the internal circulation mode of the immersion liquid cooling cabinet and the heat exchange circulation mode is realized.

2. The single-phase immersion liquid cooling server circulation cooling method according to claim 1, characterized in that: The process of achieving the transition state of branch full open, main loop full open or proportional regulation includes the following steps: Receive feedback on the temperature contact point coordinates, real-time chip load rate, and return port temperature. Generate a time axis extension vector based on the temperature contact point coordinates. Convert the real-time chip load rate into an intensity modulation coefficient. Build a spatial compensation scalar based on the return port temperature and output a dynamic deformation threshold boundary. The dynamic deformation threshold boundary is subjected to phase lag compensation. When the boundary contraction rate exceeds the critical value, a full-open trigger pulse is generated. When the boundary fluctuation frequency is in the transition zone, a proportional adjustment waveform is output to form a PWM fundamental wave sequence. The historical flow ratio of the total liquid outlet pipe is extracted from the PWM fundamental wave sequence as the inertia weight, and the transient compensation amount is calculated according to the temperature difference between the current deformation threshold boundary and the return liquid port to synthesize the valve opening combination weight; Combined with the valve opening combination weight, the full-open trigger pulse drives the branch valve to form a zero-resistance channel, and the proportional adjustment waveform matches the main pipeline valve to generate a gradual throttling surface, realizing the three-state output of branch full opening, main cycle full opening or proportional transition.

3. The single-phase immersion liquid cooling server circulation cooling method according to claim 2, characterized in that: The process of synthesizing the valve opening combination weight includes the following steps: Extract the periodic energy consumption envelope from the historical flow data of the total liquid outlet pipeline, generate the inertia strong and weak oscillation sequence through the flow difference calculation of adjacent time periods, input the inertia strong and weak oscillation sequence into the attenuation memory filter, and output the inertia weight basis; The real-time temperature difference between the dynamic deformation threshold boundary and the return liquid port is received and processed by a spatial thermal pressure converter. The curvature of the deformation threshold boundary is used as the field intensity gradient reference, and the absolute value of the temperature difference is used as the action intensity scalar to generate a transient compensation vector field. Inertia weight basis and transient compensation vector field: project the inertia weight basis along the pipeline axis to form a steady-state skeleton, and inject the transient compensation vector field component at the steady-state skeleton node to form a weighted grid with compensation nodes; The weighted grid with compensation nodes is reconstructed by the valve response adapter to extract the free flow domain of the section corresponding to the fully open trigger pulse. The grid density distribution is adjusted according to the proportional adjustment waveform slope, and finally the valve opening combination weight is output.

4. The single-phase immersion liquid cooling server circulating cooling method according to claim 3, characterized in that: The process of forming a weighted grid with compensation nodes includes the following steps: Taking the center line of the total liquid outlet pipe as the reference axis, the inertia weight base is axially stretched and transformed according to the direction of fluid movement to form a tubular weight frame. Skeleton control nodes are evenly distributed on the surface of the tubular weight frame. The three-dimensional transient compensation vector field is compressed along the pipeline radial direction, the projection intensity spectrum of the vector field in the axial direction is extracted, the vortex component modulus of the vector field in the circumferential direction is captured, and a two-dimensional compensation action surface is generated; The two-dimensional compensation surface is spatially phase-matched with the skeleton control nodes. The compensation strength base of each node is determined based on the projected intensity spectrum. The coupling action between adjacent nodes is distributed according to the vortex component modulus to form an enhanced node set with energy labeling. The enhanced node set with energy label is input into the field constraint generator. The tubular weighted frame is used as the initial mesh topology. The mesh density expansion is generated at the nodes according to the compensation strength cardinality. Non-uniform connection tendons are generated between the nodes according to the coupling action. Finally, a weighted mesh with compensation nodes is constructed.

5. The single-phase immersion liquid cooling server circulating cooling method according to claim 4, characterized in that: The process of forming an energy-labeled enhanced node set includes the following steps: Bind the amplitude distribution of the projected intensity spectrum to the axial position of the skeleton control node in spatial coordinates, use the reference axis zero point as the origin of spectrum-axis alignment, divide the pipeline length into equal parts according to the intensity spectrum wavelength, and generate a spectrum node mapping table; The spectrum node mapping table is input into the intensity converter, which takes the logarithmic attenuation of the spectrum amplitude corresponding to each node as the base body, superimposes the curvature change rate of the deformation threshold boundary at the node, and outputs the dynamic compensation base matrix; The captured vortex component modulus is processed by the circulation decomposer, and the phase difference angle between the modulus peaks is extracted to generate the adjacent node action coefficient, and the filling ratio of the modulus envelope area to the pipe cross section is obtained to form the energy potential transfer factor set; The dynamic compensation basis matrix and the energy potential transfer factor set are input into the field fusion core. The compensation basis matrix elements are used as node energy cores. The energy cores are extended to adjacent nodes according to the action coefficient to form radiation energy bands. The width of the radiation energy bands is adjusted according to the filling ratio, and finally an enhanced node set with energy labels is generated.

6. The single-phase immersion liquid cooling server circulating cooling method according to claim 5, characterized in that: The process of obtaining the fill ratio of the module envelope area to the pipe cross section includes the following steps: The captured vortex component modulus waveform is input into the extreme value topology analyzer to identify the effective peak group set whose modulus exceeds the critical amplitude, record the azimuth coordinates of each peak in the pipeline circumferential coordinate system, and generate a peak group azimuth distribution map; The peak group azimuth distribution diagram is processed by the relative motion solver to calculate the tangential offset of adjacent peak azimuths, convert the offset into a vector angle with the pipeline center as the origin, and output the node action angle matrix; The module envelope area is input into the geometric constraint converter. The cross-sectional area of ​​the pipe is used as the reference constraint frame. The dynamic overlap ratio between the envelope area and the reference constraint frame is calculated to generate the vortex core occupancy factor. The node action angle matrix and vortex core occupancy factor are input into the fluid interference synthesizer, the vector angle tangent is used as the action intensity coefficient, and the vortex core occupancy factor is used to modulate the effective action radius of the action intensity coefficient, ultimately forming an energy potential transfer factor set.

7. The single-phase immersion liquid cooling server circulating cooling method according to claim 1, characterized in that: The process of switching between the immersion liquid cooling cabinet internal circulation mode and the heat exchange circulation mode based on the comparison results includes the following steps: The coolant temperature data obtained in the return branch pipe is processed by noise suppression and time domain alignment to form a pure return waveform. The pure return waveform is input into the phase analyzer to output the return phase mark. The return phase mark and the currently running cooling mode state are input into the migration criterion synthesizer to form a dual-mode migration trigger field; When in heat exchange mode: the reflux waveform amplitude continues to be lower than the dynamic deformation threshold boundary to generate the internal circulation enabling factor; when in internal circulation mode: the reflux waveform peak contacts the deformation threshold boundary to trigger the heat exchange activation factor; The dual-mode migration trigger field is input into the physical field mapping module. The internal circulation enabling factor drives the closure of the total liquid outlet pipeline valve to form a closed circulation topology. The heat exchange activation factor triggers the branch valve zero resistance channel to establish an open flow channel configuration, completing the cooling mode switching.

8. The single-phase immersion liquid cooling server circulating cooling method according to claim 7, characterized in that: The process of switching the cooling mode includes the following steps: The inner loop enabling factor is input into the constraint field generator, the factor strength value is extracted as the closure strength coefficient, the free flow domain closing sequence of the associated weight grid is used to generate the main pipeline valve closing instruction set; The main pipeline valve locking instruction set is acted upon by the fluid path constraint field, with the immersion cavity wall as the fixed boundary and the return branch pipe as the unidirectional conducting axis, forming a closed loop topology; The heat exchange activation factor triggers the zero-resistance channel builder, activates the space-time coordinates of the full-open trigger pulse, calls the compensation node energy distribution of the weighted grid, and generates the branch valve expansion wave front; The closed loop topology and open flow channel configuration are output to the thermal inertia balance monitor to detect the consistency between the temperature gradient in the cavity and the heat flow trend vector, verify that the reflux pure waveform conforms to the phase characteristic spectrum of the target mode, and confirm that the cooling mode switching is completed.

9. A single-phase immersion liquid cooling server circulating cooling system, used to implement the single-phase immersion liquid cooling server circulating cooling method according to any one of claims 1 to 8, characterized in that: Includes: immersion liquid cooling cabinet, branch pipeline valves, main pipeline valves, main liquid outlet pipeline, pump, heat exchanger and branch pipeline; Among them, the immersion liquid cooling cabinet is provided with at least one liquid outlet and two liquid inlets, the liquid outlets are respectively installed at the upper end of one side of the immersion liquid cooling cabinet, and the two liquid inlets are arranged at the middle position and the lower end of one side of the immersion liquid cooling cabinet; the liquid inlet at the middle position is connected to the main liquid outlet pipe through a branch pipe and a branch pipe valve; a main pipe valve is installed on the main liquid outlet pipe, the outlet end of the main liquid outlet pipe is connected to the inlet end of the pump, the outlet end of the pump is connected to the inlet end of the heat exchanger, and the outlet end of the heat exchanger is connected to the liquid inlet at the lower end through a reflux branch pipe.

Images