Switching power supply power management system and method based on artificial intelligence

Abstract

This invention discloses an artificial intelligence-based switching power supply management system and method, belonging to the field of power supply management technology. The invention includes: S10: adjusting the real-time transformation ratio of the multi-stage transformers inside the switching power supply; S20: analyzing the on / off state of the switching power supply's switching transistors at the next moment; S30: acquiring the real-time operating voltage of each load connected to the output terminal of the switching power supply, and predicting the operating delay time of the switching power supply's switching transistors based on the acquired information; S40: determining the power supply status of the switching power supply. This invention predicts the operating delay time of the switching power supply's switching transistors based on the real-time operating voltage of each load connected to the output terminal of the switching power supply, and adjusts the real-time duty cycle of the switching transistors based on the prediction results. This avoids discrepancies between the power supply method of the switching power supply and the actual needs of the loads, further improving the system's power supply management effect.

Description

Technical Field

[0001] This invention relates to the field of power supply management technology, specifically to an artificial intelligence-based switching power supply management system and method. Background Technology

[0002] A switching power supply is a type of power supply that uses modern power electronics technology to control the on and off time ratio of switching transistors to maintain a stable output voltage. With the development and innovation of power electronics technology, switching power supply technology is also constantly evolving. Currently, switching power supplies are widely used in almost all electronic devices due to their small size, lightweight design, and high efficiency, making them an indispensable power supply solution for the rapidly developing electronics and information industry.

[0003] Existing switching power supply management systems typically stabilize the output voltage of electronic devices by comparing the difference between the output voltage and the reference voltage. However, in actual applications, the stability of the output voltage is often affected by factors such as the duty cycle of the switching transistors, as well as the delay during the switching process, resulting in poor management performance of the power supply management system. Summary of the Invention

[0004] The purpose of this invention is to provide an artificial intelligence-based switching power supply management system and method to solve the problems mentioned in the background art.

[0005] To address the aforementioned technical problems, the present invention provides the following technical solution: a power supply management method for switching power supplies based on artificial intelligence, the method comprising:

[0006] S10: Obtain the real-time input voltage of the switching power supply and the real-time load connection status of the output terminal of the switching power supply, and adjust the real-time transformation ratio of the multi-stage transformer set inside the switching power supply.

[0007] S20: Analyze the on / off state of the switching transistor of the switching power supply at the next moment;

[0008] S30: Based on the real-time operating voltage of each load connected to the output terminal of the switching power supply, the operating delay time of the switching power supply switching transistor is predicted.

[0009] S40: Determine the power supply status of the switching power supply.

[0010] Furthermore, S10 includes:

[0011] S101: Based on the real-time load connection status of the switching power supply output terminal, determine the total output voltage of the switching power supply output terminal. The total output voltage = the sum of the rated voltages of each load connected to the switching power supply output terminal. The feedback control circuit in the switching power supply selects whether to adjust the transformation ratio of the multi-stage transformer set inside the switching power supply based on the ratio A between the actual output voltage of the switching power supply output terminal and the total output voltage.

[0012] S102: When 0 < A < 1 or A > 1, the feedback control circuit in the switching power supply adjusts the real-time transformation ratio of the multi-stage transformer inside the switching power supply based on the real-time input voltage of the switching power supply. Based on the voltage loss of the switching transistors during operation, it adjusts the theoretical output voltage of the switching power supply. Perform calculations. Where e represents the power dissipation value when the switch is in the on state, f represents the power dissipation value when the switch is in the off state, h represents the relationship coefficient, R represents the resistance value of the switch, F represents the saturation voltage value of the switch in the on state, and I represents the on current value of the switch.

[0013] The relationship coefficients are obtained through the model h = d * s, where d represents the intercept of the model and s represents the switching frequency of the power supply.

[0014] according to The real-time transformation ratio of a multi-stage transformer is determined, where V t K represents the input voltage value of the switching power supply at time t. t This represents the transformation ratio of a multi-stage transformer at time t;

[0015] S103: When A=1, there is no need to adjust the real-time transformation ratio of the multi-stage transformers inside the switching power supply.

[0016] Furthermore, the specific method for S20 to analyze the on / off state of the switching power supply transistor at the next moment is as follows:

[0017] According to D t =W*f / (V t The real-time duty cycle of the switching transistor is calculated using +W*f), where W represents the total output voltage, f represents the influence coefficient, and D... t This represents the duty cycle of the switching transistor at time t;

[0018] The influence coefficient is obtained through the mathematical model f = b * c * s, where b represents the proportionality coefficient and c represents the capacitance value of the switching transistor.

[0019] Within the period R, the energizing time r of the switching power supply at time t. tPerform data collection if (r t / R)<D t Then the switching transistor of the switching power supply will be in the on state at the next moment. If (r t / R)=D t Then the switching transistor of the switching power supply will be in the off state at the next moment. If (r t / R)>D t If so, the switching transistor of the switching power supply is not in operation.

[0020] Furthermore, the specific method for predicting the operation delay time of the switching power supply transistor in S30 is as follows:

[0021] The real-time operating voltages of each load connected to the output terminal of the switching power supply are accumulated and the accumulated result is denoted as Q. The difference between Q and W is calculated. If Q-W≠0, it indicates that there is an operation delay in the switching power supply transistor. If Q-W=0, it indicates that there is no operation delay in the switching power supply transistor.

[0022] according to The operation delay time of the switching transistor in the switching power supply is predicted, where H represents the predicted operation delay time of the switching transistor in the switching power supply.

[0023] When Q-W>0, the duty cycle of the switching transistor in the switching power supply is adjusted to: (D t *R―H) / R;

[0024] When Q-W < 0, the duty cycle of the switching transistor in the switching power supply is adjusted to: (D t *R+H) / R.

[0025] Furthermore, S40 determines the power supply status of the switching power supply based on the adjusted duty cycle of the switching power supply transistor and the transformation ratio of the multi-stage transformer at time t.

[0026] An artificial intelligence-based switching power supply management system, the system comprising a transformer ratio adjustment module, a switching transistor on / off state analysis module, an operation delay time prediction module, and a switching power supply management module;

[0027] The transformer ratio adjustment module is used to adjust the real-time transformer ratio of the multi-stage transformers installed inside the switching power supply.

[0028] The switching transistor on / off state analysis module is used to analyze the on / off state of the switching power supply transistor at the next moment.

[0029] The operation delay time prediction module is used to obtain the real-time operating voltage of each load connected to the output terminal of the switching power supply, and to predict the operation delay time of the switching power supply switching transistor based on the obtained information.

[0030] The power supply management module for the switching power supply is used to determine the power supply status of the switching power supply.

[0031] Furthermore, the transformer ratio adjustment module includes an adjustment judgment unit, an output voltage calculation unit, and a transformer ratio adjustment unit;

[0032] The transformer ratio adjustment unit selects whether to adjust the transformer ratio of the multi-stage transformers installed inside the switching power supply based on the ratio between the actual output voltage and the total output voltage of the switching power supply according to the feedback control circuit in the switching power supply. When it is necessary to adjust the transformer ratio of the multi-stage transformers, the selection result is transmitted to the output voltage calculation unit.

[0033] The output voltage calculation unit receives the selection result transmitted by the transformer ratio adjustment unit, and calculates the theoretical output voltage of the switching power supply based on the received information and the voltage loss of the switching power supply switching transistor during operation.

[0034] The transformer ratio adjustment unit determines the real-time transformer ratio of the multi-stage transformer based on the constructed model.

[0035] Furthermore, the switching transistor on / off state analysis module includes a switching transistor duty cycle calculation unit and a switching transistor on / off state analysis unit;

[0036] The switching transistor duty cycle calculation unit calculates the real-time duty cycle of the switching transistor based on the constructed mathematical model;

[0037] The switching transistor on / off state analysis unit collects the on-time of the switching power supply at time t within a period R, and calculates the on-time based on (r). t / R) and D t By comparing the relationships between them, we can analyze the on / off state of the switching transistor in the switching power supply at the next moment.

[0038] Furthermore, the operation delay prediction module includes an operation delay judgment unit, an operation delay prediction unit, and a switching transistor duty cycle adjustment unit;

[0039] The operation delay judgment unit accumulates the real-time operating voltage of each load connected to the output terminal of the switching power supply, compares the accumulation result with the total output voltage of the switching power supply, and judges whether there is an operation delay in the switching power supply switching transistor based on the comparison result.

[0040] The operation delay prediction unit predicts the operation delay time of the switching power supply transistor based on the constructed model.

[0041] The duty cycle adjustment unit adjusts the duty cycle of the switching transistor in the switching power supply based on the prediction results of the operation delay time prediction unit.

[0042] Furthermore, the power supply management module determines the power supply status of the switching power supply based on the adjusted duty cycle of the switching power supply transistors and the real-time transformation ratio of the multi-stage transformers.

[0043] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0044] 1. This invention calculates the theoretical output voltage of the switching power supply based on the voltage loss of the switching transistor during operation, and determines the real-time transformation ratio of the multi-stage transformer based on the calculation results, which helps to ensure the stability of the output voltage of the switching power supply.

[0045] 2. This invention calculates the real-time duty cycle of the switching transistors of the switching power supply based on the total output voltage at the output terminal of the switching power supply. Furthermore, in the process of calculating the duty cycle, the influence of the switching transistor capacitance value on the output voltage stability is eliminated, thereby further improving the stability of the output voltage of the switching power supply.

[0046] 3. This invention predicts the operating delay time of the switching transistors of the switching power supply based on the real-time operating voltage of each load connected to the output terminal of the switching power supply. Based on the prediction results, the real-time duty cycle of the switching transistors is adjusted to avoid discrepancies between the power supply method of the switching power supply and the actual needs of the load, thereby further improving the system's power supply management effect. Attached Figure Description

[0047] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0048] Figure 1 This is a schematic diagram illustrating the workflow of an artificial intelligence-based switching power supply management system and method according to the present invention.

[0049] Figure 2 This is a schematic diagram illustrating the working principle of an artificial intelligence-based switching power supply management system and method according to the present invention. Detailed Implementation

[0050] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0051] Please see Figure 1 and Figure 2This invention provides a technical solution: a power supply management method for switching power supplies based on artificial intelligence, the method comprising:

[0052] S10: Obtain the real-time input voltage of the switching power supply and the real-time load connection status of the output terminal of the switching power supply, and adjust the real-time transformation ratio of the multi-stage transformer set inside the switching power supply.

[0053] S10 includes:

[0054] S101: Based on the real-time load connection status of the switching power supply output terminal, determine the total output voltage of the switching power supply output terminal. The total output voltage = the sum of the rated voltages of each load connected to the switching power supply output terminal. The feedback control circuit in the switching power supply selects whether to adjust the transformation ratio of the multi-stage transformer set inside the switching power supply based on the ratio A between the actual output voltage of the switching power supply output terminal and the total output voltage.

[0055] S102: When 0 < A < 1 or A > 1, the feedback control circuit in the switching power supply adjusts the real-time transformation ratio of the multi-stage transformer inside the switching power supply based on the real-time input voltage of the switching power supply. Based on the voltage loss of the switching transistors during operation, it adjusts the theoretical output voltage of the switching power supply. The theoretical output voltage of a switching power supply, calculated as such, refers to the output voltage value at the output terminal of the switching power supply without considering the voltage loss of the switching transistor.

[0056] Where e represents the power dissipation value when the switch is in the on state, f represents the power dissipation value when the switch is in the off state, h represents the relationship coefficient, R represents the resistance value of the switch, F represents the saturation voltage value of the switch in the on state, and I represents the on current value of the switch.

[0057] The relationship coefficients are obtained through the model h = d * s, where d represents the weight of the model, s represents the switching frequency of the power supply, s is equivalent to the independent variable of the linear equation, and h is equivalent to the dependent variable of the linear equation.

[0058] according to The real-time transformation ratio of a multi-stage transformer is determined, where V t K represents the input voltage value of the switching power supply at time t. t This represents the transformation ratio of a multi-stage transformer at time t;

[0059] S103: When A=1, there is no need to adjust the real-time transformation ratio of the multi-stage transformers inside the switching power supply;

[0060] S20: Analyze the on / off state of the switching transistor in the switching power supply at the next moment. The specific method is as follows:

[0061] According to D t =W*f / (V t The real-time duty cycle of the switching transistor is calculated using +W*f), where W represents the total output voltage, f represents the influence coefficient, and D... t This represents the duty cycle of the switching transistor at time t;

[0062] The influence coefficient is obtained through the mathematical model f = b * c * s, where b represents the proportionality coefficient, equivalent to the weight in the linear equation, c represents the capacitance value of the switching transistor, c * s is equivalent to the independent variable of the linear equation, and f is equivalent to the dependent variable of the linear equation; this process eliminates the influence of the switching transistor capacitance value on the stability of the switching power supply output voltage.

[0063] Within the period R, the energizing time r of the switching power supply at time t. t Perform data collection if (r t / R)<D t Then the switching transistor of the switching power supply will be in the on state at the next moment. If (r t / R)=D t Then the switching transistor of the switching power supply will be in the off state at the next moment. If (r t / R)>D t If so, the switching transistor of the switching power supply is not in operation.

[0064] S30: Based on the real-time operating voltage of each load connected to the output terminal of the switching power supply, the operating delay time of the switching power supply's switching transistor is predicted using the acquired information. The specific method is as follows:

[0065] The real-time operating voltages of each load connected to the output terminal of the switching power supply are accumulated and the accumulated result is denoted as Q. The difference between Q and W is calculated. If Q-W≠0, it indicates that there is an operation delay in the switching power supply transistor. If Q-W=0, it indicates that there is no operation delay in the switching power supply transistor.

[0066] according to The operation delay time of the switching transistor in the switching power supply is predicted, where H represents the predicted operation delay time of the switching transistor in the switching power supply.

[0067] When Q-W>0, the duty cycle of the switching transistor in the switching power supply is adjusted to: (D t *R―H) / R;

[0068] When Q-W < 0, the duty cycle of the switching transistor in the switching power supply is adjusted to: (D t *R+H) / R;

[0069] S40: Determine the power supply status of the switching power supply;

[0070] S40 determines the power supply status of the switching power supply based on the adjusted duty cycle of the switching power supply transistor and the transformation ratio of the multi-stage transformer at time t.

[0071] An artificial intelligence-based switching power supply management system includes a transformer ratio adjustment module, a switching transistor on / off state analysis module, an operation delay time prediction module, and a switching power supply management module.

[0072] The transformer ratio adjustment module is used to adjust the real-time transformer ratio of the multi-stage transformers installed inside the switching power supply;

[0073] The transformer ratio adjustment module includes an adjustment judgment unit, an output voltage calculation unit, and a transformer ratio adjustment unit;

[0074] The transformer ratio adjustment unit selects whether to adjust the transformer ratio of the multi-stage transformers inside the switching power supply based on the ratio between the actual output voltage and the total output voltage of the switching power supply according to the feedback control circuit in the switching power supply. When it is necessary to adjust the transformer ratio of the multi-stage transformers, the selection result is transmitted to the output voltage calculation unit.

[0075] The output voltage calculation unit receives the selection results transmitted by the transformer ratio adjustment unit, and calculates the theoretical output voltage of the switching power supply based on the received information and the voltage loss of the switching power supply switching transistor during operation.

[0076] The transformer ratio adjustment unit determines the real-time transformer ratio of the multi-stage transformer based on the constructed model;

[0077] The switching transistor on / off state analysis module is used to analyze the on / off state of the switching transistor in the switching power supply at the next moment.

[0078] The switching transistor on / off state analysis module includes a switching transistor duty cycle calculation unit and a switching transistor on / off state analysis unit;

[0079] The switching transistor duty cycle calculation unit calculates the real-time duty cycle of the switching transistor based on the constructed mathematical model;

[0080] The switching transistor on / off state analysis unit collects the on-time of the switching power supply at time t within a period R, and calculates the on-time based on (r). t / R) and D t By comparing the relationships between them, we can analyze the on / off state of the switching transistor in the switching power supply at the next moment.

[0081] The operation delay time prediction module is used to obtain the real-time operating voltage of each load connected to the output terminal of the switching power supply, and predict the operation delay time of the switching power supply switching transistor based on the obtained information.

[0082] The operation delay prediction module includes an operation delay judgment unit, an operation delay prediction unit, and a switching transistor duty cycle adjustment unit;

[0083] The operation delay judgment unit accumulates the real-time operating voltage of each load connected to the output terminal of the switching power supply, compares the accumulation result with the total output voltage of the switching power supply, and judges whether there is an operation delay in the switching power supply switching transistor based on the comparison result.

[0084] The operation delay prediction unit predicts the operation delay time of the switching transistor in the switching power supply based on the constructed model.

[0085] The duty cycle adjustment unit adjusts the duty cycle of the switching transistor in the switching power supply based on the prediction results of the operation delay time prediction unit.

[0086] The power supply management module determines the power supply status of the switching power supply based on the adjusted duty cycle of the switching transistors and the real-time transformation ratio of the multi-stage transformers.

[0087] Implementation Example 1: Assume the total output voltage W = 220V, the influence coefficient f = 0.1, and the input voltage V of the switching power supply at 12:01. t =400V, then the duty cycle of the switching transistor at 12:01 is:

[0088] D t =W*f / (V t +W*f)=220*0.1 / (400+220*0.1)=0.05;

[0089] Let the period R = 1 minute, and the start time of the period be 12:00. The energizing time r of the switching power supply at 12:01 is... t =6 seconds, then r t / R = 0.1, because D t =0.05<r t / R = 0.1, therefore, the switching transistor of the switching power supply will be in the conducting state in the next second.

[0090] Example 2: Given Q = 210V and total output voltage W = 220V, then Q - W = 210 - 220 = -10V. Therefore, the operating delay time of the switching power supply's switching transistor is:

[0091]

[0092] — 0.12 seconds means that the switching transistor of the switching power supply switches its on / off state 0.12 seconds in advance; if H = 0.12 seconds, it means that the switching transistor of the switching power supply switches its on / off state 0.12 seconds late.

[0093] When Q-W = -10 < 0, the duty cycle of the switching transistor in the switching power supply is adjusted as follows:

[0094] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0095] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A power supply management method for switching power supplies based on artificial intelligence, characterized in that: The method includes: S10: Obtain the real-time input voltage of the switching power supply and the real-time load connection status of the output terminal of the switching power supply, and adjust the real-time transformation ratio of the multi-stage transformer set inside the switching power supply. S20: Analyze the on / off state of the switching transistor in the switching power supply at the next moment. The specific method is as follows: According to D t =W*f / (V t The real-time duty cycle of the switching transistor is calculated using +W*f), where W represents the total output voltage, f represents the influence coefficient, and D... t V represents the duty cycle of the switching transistor at time t. t This represents the input voltage value of the switching power supply at time t. Within the period R, the energizing time r of the switching power supply at time t. t Perform data collection if (r t / R)<D t Then the switching transistor of the switching power supply will be in the on state at the next moment. If (r t / R)=D t Then the switching transistor of the switching power supply will be in the off state at the next moment. If (r t / R)>D t If so, the switching transistor of the switching power supply is not in operation. S30: Based on the real-time operating voltage of each load connected to the output terminal of the switching power supply, the operating delay time of the switching power supply switching transistor is predicted. S40: Determine the power supply status of the switching power supply.

2. The power supply management method for a switching power supply based on artificial intelligence according to claim 1, characterized in that: S10 includes: S101: Based on the real-time load connection status of the switching power supply output terminal, determine the total output voltage of the switching power supply output terminal. The total output voltage = the sum of the rated voltages of each load connected to the switching power supply output terminal. The feedback control circuit in the switching power supply selects whether to adjust the transformation ratio of the multi-stage transformer set inside the switching power supply based on the ratio A between the actual output voltage of the switching power supply output terminal and the total output voltage. S102: When 0 < A < 1 or A > 1, the feedback control circuit in the switching power supply adjusts the real-time transformation ratio of the multi-stage transformer inside the switching power supply based on the real-time input voltage of the switching power supply. Based on the voltage loss of the switching transistors during operation, it adjusts the theoretical output voltage of the switching power supply. Perform calculations. Where e represents the power dissipation value when the switch is in the on state, f represents the power dissipation value when the switch is in the off state, h represents the relationship coefficient, R represents the resistance value of the switch, F represents the saturation voltage value of the switch in the on state, and I represents the on current value of the switch. according to The real-time transformation ratio of a multi-stage transformer is determined, where V t K represents the input voltage value of the switching power supply at time t. t This represents the transformation ratio of a multi-stage transformer at time t; S103: When A=1, there is no need to adjust the real-time transformation ratio of the multi-stage transformers inside the switching power supply.

3. The power supply management method for a switching power supply based on artificial intelligence according to claim 2, characterized in that: The specific method for S30 to predict the operation delay time of the switching power supply transistor is as follows: The real-time operating voltages of each load connected to the output terminal of the switching power supply are accumulated and the accumulated result is denoted as Q. The difference between Q and W is calculated. If QW≠0, it indicates that there is an operation delay in the switching power supply transistor. If QW=0, it indicates that there is no operation delay in the switching power supply transistor. according to The operation delay time of the switching transistor in the switching power supply is predicted, where H represents the predicted operation delay time of the switching transistor in the switching power supply. When QW > 0, the duty cycle of the switching transistor in the switching power supply is adjusted to: (D t *RH) / R; When QW < 0, the duty cycle of the switching transistor in the switching power supply is adjusted to: (D t *R+H) / R.

4. The power supply management method for a switching power supply based on artificial intelligence according to claim 3, characterized in that: S40 determines the power supply status of the switching power supply based on the adjusted duty cycle of the switching power supply transistor and the transformation ratio of the multi-stage transformer at time t.

5. An AI-based switching power supply management system applied to the AI-based switching power supply management method according to any one of claims 1-4, characterized in that: The system includes a transformer ratio adjustment module, a switching transistor on / off state analysis module, an operation delay time prediction module, and a switching power supply management module. The transformer ratio adjustment module is used to adjust the real-time transformer ratio of the multi-stage transformers installed inside the switching power supply. The switching transistor on / off state analysis module is used to analyze the on / off state of the switching power supply transistor at the next moment. The operation delay time prediction module is used to obtain the real-time operating voltage of each load connected to the output terminal of the switching power supply, and to predict the operation delay time of the switching power supply switching transistor based on the obtained information. The power supply management module for the switching power supply is used to determine the power supply status of the switching power supply.

6. The switching power supply management system based on artificial intelligence according to claim 5, characterized in that: The transformer ratio adjustment module includes an adjustment judgment unit, an output voltage calculation unit, and a transformer ratio adjustment unit; The transformer ratio adjustment unit selects whether to adjust the transformer ratio of the multi-stage transformers installed inside the switching power supply based on the ratio between the actual output voltage and the total output voltage of the switching power supply according to the feedback control circuit in the switching power supply. When it is necessary to adjust the transformer ratio of the multi-stage transformers, the selection result is transmitted to the output voltage calculation unit. The output voltage calculation unit receives the selection result transmitted by the transformer ratio adjustment unit, and calculates the theoretical output voltage of the switching power supply based on the received information and the voltage loss of the switching power supply switching transistor during operation. The transformer ratio adjustment unit determines the real-time transformer ratio of the multi-stage transformer based on the constructed model.

7. The switching power supply management system based on artificial intelligence according to claim 6, characterized in that: The switching transistor on / off state analysis module includes a switching transistor duty cycle calculation unit and a switching transistor on / off state analysis unit. The switching transistor duty cycle calculation unit calculates the real-time duty cycle of the switching transistor based on the constructed mathematical model; The switching transistor on / off state analysis unit collects the on-time of the switching power supply at time t within a period R, and calculates the on-time based on (r). t / R) and D t By comparing the relationships between them, we can analyze the on / off state of the switching transistor in the switching power supply at the next moment.

8. The switching power supply management system based on artificial intelligence according to claim 7, characterized in that: The operation delay time prediction module includes an operation delay judgment unit, an operation delay time prediction unit, and a switching transistor duty cycle adjustment unit; The operation delay judgment unit accumulates the real-time operating voltage of each load connected to the output terminal of the switching power supply, compares the accumulation result with the total output voltage of the switching power supply, and judges whether there is an operation delay in the switching power supply switching transistor based on the comparison result. The operation delay prediction unit predicts the operation delay time of the switching power supply transistor based on the constructed model. The duty cycle adjustment unit adjusts the duty cycle of the switching transistor in the switching power supply based on the prediction results of the operation delay time prediction unit.

9. The switching power supply management system based on artificial intelligence according to claim 8, characterized in that: The power supply management module determines the power supply status of the switching power supply based on the adjusted duty cycle of the switching transistors and the real-time transformation ratio of the multi-stage transformers.

Images