Alternating current adapter intelligent ordered control algorithm and device with real-time state sensing function

Abstract

The invention discloses an alternating-current adapter intelligent ordered control algorithm and device with real-time state sensing, and belongs to the technical field of adapter control, and the algorithm comprises the steps: synchronously collecting multi-source heterogeneous data during the operation of an alternating-current adapter through an electrical sensor, a mechanical vibration sensor and an environment sensor; adopting a sparrow algorithm to optimize hyper-parameters of the Gaussian process regression model, constructing a real-time state evaluation model, inputting multi-source heterogeneous data, and outputting adapter health scores; identifying the type of an access load based on an equipment fingerprint database, and generating a dynamic power supply priority sequence in combination with the health score, the real-time electricity price signal and the load battery state; and distributing output power according to a priority sequence, and sending a scheduling instruction to an execution unit through a 60GHz millimeter wave link. Through synchronous acquisition of electrical, mechanical and environmental sensors and a sparrow algorithm optimization model, in combination with equipment fingerprint dynamic scheduling and millimeter wave instructions, the problem of single-dimension misjudgment is solved, and the overload risk is reduced.

Description

Technical Field

[0001] The present invention relates to the field of adapter control technology, and in particular to an intelligent and orderly control algorithm and device for an AC adapter with real-time state perception. Background Art

[0002] A search revealed that the invention patent with publication number CN117807487A discloses a method and device for intelligently sensing cable joint status. The method includes: collecting multi-source heterogeneous data on the operating status of cable joints through multiple types of sensors; performing preliminary screening on the multi-source heterogeneous data, processing missing data and noise data, and then storing the multi-source heterogeneous data in a data warehouse; performing standardization and whitening on the multi-source heterogeneous data in the data warehouse and converting it into feature vector data; constructing a Gaussian process regression cable joint status assessment model, and inputting the feature vector data into the Gaussian process regression cable joint status assessment model to obtain the target state of the cable joint. The present invention uses the Gaussian process regression cable joint status assessment model to fuse and collaboratively sense the multi-source heterogeneous data on the cable joint status, accurately predicting the operating status of the cable joint and avoiding misjudgment of single data information.

[0003] In the above-mentioned disclosed technology, the operating status of the cable connector is judged only by monitoring the temperature and humidity, without associating the mechanical conditions with the electrical parameters. As a result, it is impossible to distinguish whether the "temperature rise" is due to electrical problems, such as overload, or mechanical problems, such as wear caused by plugging and unplugging; and there is a lack of dynamic scheduling capabilities for multiple devices, and it is impossible to respond to peak and valley electricity price signals. Summary of the Invention

[0004] In order to overcome the above-mentioned shortcomings of the prior art, the present invention provides an intelligent and orderly control algorithm and device for an AC adapter with real-time status perception, aiming to solve the technical problem in the prior art of judging the operating status of the cable connector only by monitoring temperature and humidity without associating mechanical conditions with electrical parameters, resulting in the inability to distinguish whether the temperature rise is caused by electrical problems or mechanical problems.

[0005] The technical solution adopted by the present invention to solve the technical problem is: an intelligent and orderly control algorithm for AC adapters with real-time state perception, including: Synchronously collect multi-source heterogeneous data during the operation of the AC adapter through electrical sensors, mechanical vibration sensors, and environmental sensors; The Sparrow algorithm is used to optimize the hyperparameters of the Gaussian process regression model, build a real-time status assessment model, input multi-source heterogeneous data, and output the adapter health score; Identify the type of connected load based on the device fingerprint library, and generate a dynamic power supply priority sequence based on health scores, real-time electricity price signals, and load battery status. Allocate output power according to the priority sequence and send scheduling instructions to the execution units.

[0006] As a further improvement of the present invention, allocating output power according to a priority sequence and sending a scheduling instruction to the execution unit includes: Output power is allocated in a priority sequence, and scheduling instructions are sent to the execution unit via a 60GHz millimeter wave link.

[0007] As a further improvement of the present invention: the 60GHz millimeter wave link uses the HMC6300 transmitter and HMC6301 receiver chipset, and the transmission delay is less than 200 microseconds.

[0008] As a further improvement of the present invention, the electrical sensor includes a Hall current sensor and an impedance spectrum analysis circuit. The impedance spectrum analysis circuit detects 0.1 μm oxidation.

[0009] As a further improvement of the present invention, the mechanical vibration sensor is a three-dimensional micro-electromechanical vibration sensor that captures 200 Hz loosening signals.

[0010] As a further improvement of the present invention, the environmental sensor includes a nano zinc oxide temperature sensor array and a humidity sensor. The nano zinc oxide temperature sensor array achieves a resolution of 0.1°C, achieving micron-level fault warning.

[0011] As a further improvement of the present invention: the covariance function of the Gaussian process regression model is defined as a time-varying form: ; in, is the equipment aging factor, ranging from 0.01 to 0.05; is the signal variance, is the length scale, 、 Represents two different moments. Equipment aging factor The value increases with the cumulative number of plug-in and unplugging of the adapter, and the equipment aging factor The lifetime prediction error is greatly reduced by increasing the number of plugging and unplugging times (0.01 to 0.05) and introducing a time-varying term.

[0012] As a further improvement of the present invention: the generation formula of the dynamic power supply priority sequence is: ; in, Dynamic power supply priority, Identifies the device type. The battery level of the device. Time period identifier, is the battery state weight coefficient, is the equipment type weight coefficient, is the electricity price period weight coefficient, medical equipment , industrial equipment , consumer electronics Peak power period , off-peak hours .

[0013] As a further improvement of the present invention: the calculation method of the equipment aging factor is: ; in The cumulative number of plug-in and unplugging times for the adapter, , The unit plug-in coefficient realizes the linear quantification of the equipment aging factor, and accurately triggers the replacement alarm after 10,000 plug-ins.

[0014] The present invention also provides a device for an intelligent and orderly control algorithm for an AC adapter with real-time state perception, comprising a stacked hardware module and a self-energy extraction circuit; The stacked hardware module is integrated into the adapter housing and includes a sensor array, an edge computing unit, and a millimeter wave communication module; The self-energy circuit obtains energy from the AC magnetic field through the CT coil induction and is connected to the solid-state lithium capacitor backup power supply.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. In the present invention, three types of data, namely electrical parameters, mechanical vibration parameters and environmental parameters, are collected synchronously. The sparrow algorithm is used to optimize the hyperparameters of the Gaussian process regression model, and a comprehensive state assessment model is constructed to output the health score of the adapter. The Hall current sensor monitors overload current, and the impedance spectrum analysis circuit detects contact surface oxidation. The three-dimensional micro-electromechanical vibration sensor collects the vibration spectrum from 0 to 5 kHz to identify plug-in wear and mechanical looseness. The nano-zinc oxide temperature sensor array and humidity sensor assess the environmental corrosion risk. The sparrow algorithm dynamically adjusts the hyperparameters of the Gaussian process regression model to improve model accuracy.

[0016] 2. In the present invention, the load type is automatically identified based on the device fingerprint library, and a dynamic power supply priority sequence is generated by combining the adapter health score, load battery power, and real-time peak and valley electricity price signals.

[0017] 3. In the present invention, a 60-gigahertz millimeter wave communication link is used to transmit control instructions, and a model HMC6300 transmitter and HMC6301 receiver chipset are used. The transmission delay is less than 200 microseconds, and signal attenuation caused by mechanical wear is avoided through non-contact transmission. It also has anti-deflection capability and supports stable transmission under plus or minus 15 degrees of mechanical deviation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flowchart of implementation case 1 of the present invention.

[0019] Figure 2 This is a flowchart of step 1 of implementation example 1 of the present invention.

[0020] Figure 3 This is a flowchart of step 2 of implementation example 1 of the present invention.

[0021] Figure 4 This is a flowchart of step three of implementation example 1 of the present invention.

[0022] Figure 5 This is a flowchart of step 4 of implementation example 1 of the present invention.

[0023] Figure 6 This is a structural block diagram of implementation case 2 in the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] See also Figures 1-6 , an intelligent and orderly control algorithm for AC adapters with real-time state perception, including: Synchronously collect multi-source heterogeneous data during the operation of the AC adapter through electrical sensors, mechanical vibration sensors, and environmental sensors; The Sparrow algorithm is used to optimize the hyperparameters of the Gaussian process regression model, build a real-time status assessment model, input multi-source heterogeneous data, and output the adapter health score; Identify the type of connected load based on the device fingerprint library, and generate a dynamic power supply priority sequence based on health scores, real-time electricity price signals, and load battery status. Output power is allocated in a priority sequence, and scheduling instructions are sent to the execution unit via a 60GHz millimeter wave link.

[0026] Through the synchronous collection of electrical, mechanical, and environmental sensors and the sparrow algorithm optimization model, combined with dynamic scheduling of device fingerprints and millimeter wave instructions, the problem of single-dimensional misjudgment is solved and the risk of overload is reduced.

[0027] In the present invention, the load type is automatically identified based on the device fingerprint library, and a dynamic power supply priority sequence is generated in combination with the adapter health score, load battery power, and real-time peak and valley electricity price signals. This avoids the problem of disordered power supply and increased line overload risk when multiple devices are connected, which is caused by the lack of multi-device power supply scheduling function in the existing technology (such as the invention patent with publication number CN117807487A).

[0028] In some embodiments, the electrical sensor includes a Hall current sensor and an impedance spectrum analysis circuit, the mechanical vibration sensor is a three-dimensional micro-electromechanical vibration sensor, and the environmental sensor includes a nano-zinc oxide temperature sensor array and a humidity sensor. The impedance spectrum analysis circuit detects 0.1 μm oxidation, the three-dimensional micro-electromechanical vibration sensor captures 200 Hz loosening signals, and the nano-zinc oxide temperature sensor array achieves 0.1°C resolution, achieving micron-level fault warning.

[0029] In some embodiments, the covariance function of a Gaussian process regression model is defined as a time-varying form: ; in The device aging factor has a value range of 0.01–0.05. Its value increases with the cumulative number of plug-in and plug-out times of the adapter. The life prediction error is greatly reduced by increasing the number of plugging and unplugging times (0.01 to 0.05) and introducing a time-varying term; is the signal variance, is the length scale, 、 Represents two different moments.

[0030] In some implementations, the dynamic power supply priority sequence generation formula is: ; in, Dynamic power supply priority, Identifies the device type. The battery level of the device. is the time period identifier, is the battery state weight coefficient, is the equipment type weight coefficient, is the electricity price period weight coefficient, medical equipment , industrial equipment , consumer electronics Peak power period , off-peak hours .

[0031] Medical weight Ensure that the probability of power outage is small and peak power Reduce loads to ensure critical load power supply and grid response.

[0032] In some embodiments, a 60 GHz millimeter wave link uses the HMC6300 transmitter and HMC6301 receiver chipset, with a transmission delay of less than 200 microseconds. The HMC6300 and HMC6301 chipsets support ±15° skew, and a delay of less than 200 microseconds speeds up protection action by 50 times.

[0033] The present invention adopts a 60-gigahertz millimeter-wave communication link to transmit control instructions, using the HMC6300 transmitter and HMC6301 receiver chipset. The transmission delay is less than 200 microseconds, and the signal attenuation caused by mechanical wear is avoided through non-contact transmission. The invention has the ability to resist deflection and supports stable transmission under mechanical deviations of plus or minus 15 degrees. This avoids the problems of existing technologies (such as the invention patent with publication number CN117807487A) that rely on wired slip ring transmission, and once the slip ring is worn, the bit error rate exceeds one millionth, and the control delay is greater than ten milliseconds, resulting in the inability to respond to faults in real time.

[0034] In some embodiments, the device aging factor is calculated as: ; in The cumulative number of plug-in and unplugging times for the adapter, , The unit plug-in coefficient realizes the linear quantification of the equipment aging factor, and accurately triggers the replacement alarm after 10,000 plug-ins.

[0035] In some embodiments, a device for an intelligent and orderly control method of an AC adapter with real-time state perception includes at least a stacked hardware module and a self-energy circuit; the stacked hardware module is integrated inside the adapter housing and includes a sensor array, an edge computing unit, and a millimeter wave communication module; the self-energy circuit obtains energy from the AC magnetic field through CT coil induction and is connected to a solid-state lithium capacitor backup power supply.

[0036] The stacked module diameter is ≤25mm, greatly reducing the volume. The CT coil consumes 3-5W of energy, and the solid-state lithium capacitor maintains 10ms of power-off endurance.

[0037] Implementation Case 1: See also Figure 1-Figure 5 This implementation case provides the following technical solutions: an intelligent and orderly control algorithm for AC adapters with real-time state perception, including: Step 1: Synchronously collect multi-source heterogeneous data during the operation of the AC adapter through electrical sensors, mechanical vibration sensors, and environmental sensors; Step 2: Use the Sparrow algorithm to optimize the hyperparameters of the Gaussian process regression model, build a real-time status assessment model, input multi-source heterogeneous data, and output the adapter health score; Step 3: Identify the type of connected load based on the device fingerprint library, and generate a dynamic power supply priority sequence based on the health score, real-time electricity price signals, and load battery status; Step 4: Allocate output power according to the priority sequence and send scheduling instructions to the execution unit via the 60GHz millimeter wave link.

[0038] Through the synchronous collection of electrical, mechanical, and environmental sensors and the sparrow algorithm optimization model, combined with dynamic scheduling of device fingerprints and millimeter wave instructions, the problem of single-dimensional misjudgment is solved and the risk of overload is reduced.

[0039] The electrical sensors include Hall current sensors and impedance spectrum analysis circuits. The mechanical vibration sensor is a three-dimensional micro-electromechanical vibration sensor. The environmental sensors include a nano-zinc oxide temperature sensor array and a humidity sensor. The impedance spectrum analysis circuit detects 0.1μm oxidation, the three-dimensional micro-electromechanical vibration sensor captures 200Hz loosening signals, and the nano-zinc oxide temperature sensor array achieves 0.1°C resolution, achieving micron-level fault warning.

[0040] The covariance function of the Gaussian process regression model is defined as a time-varying form: ; in The device aging factor has a value range of 0.01–0.05. Its value increases with the cumulative number of plug-in and plug-out times of the adapter. The life prediction error is greatly reduced by increasing the number of plugging and unplugging times (0.01 to 0.05) and introducing a time-varying term; is the signal variance, is the length scale, 、 Represents two different moments.

[0041] The formula for generating the dynamic power supply priority sequence is: ; in, Dynamic power supply priority, Identifies the device type. The battery level of the device. is the time period identifier, is the battery state weight coefficient, is the equipment type weight coefficient, is the electricity price period weight coefficient, medical equipment , industrial equipment , consumer electronics Peak power period , off-peak hours .

[0042] Medical weight Ensure that the probability of power outage is small and peak power Reduce loads to ensure critical load power supply and grid response.

[0043] The 60GHz millimeter wave link uses the HMC6300 transmitter and HMC6301 receiver chipset, with transmission delay less than 200 microseconds. The HMC6300 and HMC6301 chipset support ±15° yaw, and a delay of less than 200 microseconds speeds up protection action by 50 times.

[0044] The calculation method of equipment aging factor is: ; in The cumulative number of plug-in and unplugging times for the adapter, , The unit plug-in coefficient realizes the linear quantification of the equipment aging factor, and accurately triggers the replacement alarm after 10,000 plug-ins.

[0045] Implementation Case 2: See also Figure 6 , an intelligent and orderly control device for an AC adapter with real-time status perception, which includes at least a stacked hardware module and a self-energy circuit; the stacked hardware module is integrated inside the adapter shell and includes a sensor array, an edge computing unit and a millimeter wave communication module; the self-energy circuit obtains energy from the AC magnetic field through the CT coil induction and is connected to a solid-state lithium capacitor backup power supply.

[0046] The stacked module diameter is ≤25mm, greatly reducing the volume. The CT coil consumes 3-5W of energy, and the solid-state lithium capacitor maintains 10ms of power-off endurance.

[0047] Implementation Case 3: In this implementation case, using the disclosed method, researchers implemented a PDU-SMART / 48 AC adapter integrated with a stackable hardware module (diameter ≤ 25mm) in an intelligent power distribution system in an A3 cabinet in an IDC computer room in Suzhou. Its Hall effect current sensor (Allegro ACS72981, ±50A range) monitored the current at each port in real time, while an impedance spectrum analysis circuit (AD5933 chip) scanned the contact impedance at a 10kHz frequency. A three-dimensional MEMS vibration sensor (ST LIS2DW12) collected the 0-5kHz spectrum, while a nano-zinc oxide temperature sensor array (accuracy ±0.1°C) and a Sensirion SHT40 humidity sensor operated simultaneously. When port 1 was connected to a medical imaging server (device fingerprint ID: MED_CT_004), the system detected an anomaly: a sudden increase in current to 42A (threshold 40A), a peak in the vibration spectrum at 375Hz (significant of a loose screw), and a temperature sensor array indicating a contact temperature rise of 8.2°C.

[0048] The Sparrow algorithm (population size 50, 100 iterations) dynamically optimizes the hyperparameters of the Gaussian process regression model. After inputting multi-source data, it outputs a health score: current overload is weighted at 60%, mechanical looseness at 30%, and ambient temperature rise at 10%. The overall score drops to 62 (a threshold of 70 triggers an alarm). At this time, the battery charge of the industrial-grade AI training server on port 3 (fingerprint ID: IND_GPU_12) has dropped to 18%, which is during the off-peak period (23:00-07:00, μ = 1). The dynamic power supply priority is calculated as follows: Medical equipment: Priority = 3 × 3 (equipment type) + 0.8 × 100 (power) + 1 × 1 (off-peak power) = 109.8; Industrial equipment: Priority = 2 × 2 + 0.18 × 100 + 1 × 1 = 23.8; The system sends instructions via a 60GHz millimeter wave link (HMC6300 / HMC6301 chipset, 183μs latency): industrial equipment power is limited to 65%, while medical equipment maintains full power operation.

[0049] The self-powered circuit draws 3.5W of power from the 230V busbar via the CT coil, and the solid-state lithium capacitor maintains power during 10ms grid flickers. The adapter has been plugged and unplugged a cumulative total of 12,387 times, with an aging factor of γ = 0.01 + 2e-5 × 12387 = 0.2577. The time-varying covariance function reduces the lifetime prediction error from ±15% to ±6.2%. Within 3.2 seconds of a fault occurring, the system isolated the overloaded port and sent an alert to the operations and maintenance platform, achieving a speed improvement of 11 times compared to traditional solutions.

[0050] The working principle of the present invention is as follows: multi-source heterogeneous data during the operation of the AC adapter is collected synchronously through electrical sensors, mechanical vibration sensors and environmental sensors, among which the Hall current sensor and impedance spectrum analysis circuit monitor electrical overload and contact surface oxidation, the three-dimensional micro-electromechanical vibration sensor captures mechanical looseness signals in the frequency band of zero to five kilohertz, and the nano-zinc oxide temperature sensor array and humidity sensor evaluate environmental risks; then the sparrow algorithm is used to dynamically optimize the hyperparameters of the Gaussian process regression model to construct a real-time status assessment model, and by introducing the equipment aging factor and the time-varying covariance function that increases with the number of plug-in and unplug times, a high-precision health score is output; medical equipment, industrial equipment and consumer electronics are identified based on the equipment fingerprint library. For the three sub-types of loads, a scheduling sequence is generated according to the dynamic power supply priority formula with a medical weight of three, an industrial weight of two, a consumer weight of one, and a peak power of negative one and a valley power of positive one, in combination with the health score, real-time peak and valley electricity price signals and the load battery status. Finally, the HMC6300 transmitter and HMC6301 receiver chipset are used through a 60-gigahertz millimeter wave link to send instructions to the execution unit within a transmission delay of less than two hundred microseconds. At the same time, the stacked hardware module integrates all components with a diameter of twenty-five millimeters, and the current transformer coil induction draws energy to maintain a three to five watt power supply. The solid-state lithium capacitor provides a ten-millisecond backup power supply, realizing closed-loop control of the entire process from multimodal perception to intelligent scheduling.

[0051] The main functions of the present invention are: In the present invention, three types of data, electrical parameters, mechanical vibration parameters, and environmental parameters, are collected simultaneously. The Sparrow algorithm is used to optimize the hyperparameters of the Gaussian process regression model, construct a comprehensive state assessment model, and output the adapter health score. A Hall current sensor monitors overload current, an impedance spectrum analysis circuit detects contact surface oxidation, and a three-dimensional micro-electromechanical vibration sensor collects vibration spectra from 0 to 5 kHz to identify plug-in wear and mechanical looseness. A nano-zinc oxide temperature sensor array and humidity sensor assess environmental corrosion risks. The Sparrow algorithm dynamically adjusts the hyperparameters of the Gaussian process regression model to improve model accuracy. Load type is automatically identified based on the device fingerprint library. A dynamic power supply priority sequence is generated by combining the adapter health score, load battery level, and real-time peak and valley electricity price signals. By adopting a 60 GHz millimeter wave communication link to transmit control instructions, using the HMC6300 transmitter and HMC6301 receiver chipset, the transmission delay is less than 200 microseconds. Signal attenuation caused by mechanical wear is avoided through non-contact transmission, and the device has anti-sway capability, supporting stable transmission under mechanical deviations of plus or minus 15 degrees.

[0052] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and implementations are within the scope and spirit of the present invention and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwiring, or a combination of any of these. Furthermore, each functional unit 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.

[0053] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be 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. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0054] The units described as separate components may or may not be physically separate, and the components of the control device may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0055] If the integrated unit is implemented in the form of 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 part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0056] 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 or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and description of the present invention.

Claims

1. An intelligent and orderly control algorithm for AC adapters with real-time state perception, characterized by: include: Synchronously collect multi-source heterogeneous data during the operation of the AC adapter through electrical sensors, mechanical vibration sensors, and environmental sensors; The Sparrow algorithm is used to optimize the hyperparameters of the Gaussian process regression model, build a real-time status assessment model, input multi-source heterogeneous data, and output the adapter health score; Identify the type of connected load based on the device fingerprint library, and generate a dynamic power supply priority sequence based on health scores, real-time electricity price signals, and load battery status. Allocate output power according to the priority sequence and send scheduling instructions to the execution units.

2. The intelligent and orderly control algorithm for AC adapters with real-time state perception according to claim 1 is characterized by: The allocating output power according to the priority sequence and sending a scheduling instruction to the execution unit includes: Output power is allocated in a priority sequence, and scheduling instructions are sent to the execution unit via a 60GHz millimeter wave link.

3. The intelligent and orderly control algorithm for AC adapters with real-time state perception according to claim 2 is characterized by: The 60GHz millimeter wave link uses the HMC6300 transmitter and HMC6301 receiver chipset.

4. The intelligent and orderly control algorithm for AC adapters with real-time state perception according to claim 1 is characterized by: The electrical sensor includes a Hall current sensor and an impedance spectrum analysis circuit.

5. The intelligent and orderly control algorithm for AC adapters with real-time state perception according to claim 4 is characterized by: The mechanical vibration sensor is a three-dimensional micro-electromechanical vibration sensor.

6. The intelligent and orderly control algorithm for AC adapters with real-time state perception according to claim 5 is characterized by: The environmental sensor comprises a nano zinc oxide temperature sensor array and a humidity sensor.

7. The intelligent and orderly control algorithm for AC adapters with real-time state perception according to claim 1 is characterized by: The covariance function of the Gaussian process regression model is defined as a time-varying form: ； in, is the equipment aging factor, ranging from 0.01 to 0.05; is the signal variance, is the length scale, 、 Represents two different moments.

8. The intelligent and orderly control algorithm for AC adapters with real-time state perception according to claim 1 is characterized by: The generation formula of the dynamic power supply priority sequence is: ； in, Dynamic power supply priority, Identifies the device type. The battery level of the device. is the time period identifier, is the battery state weight coefficient, is the equipment type weight coefficient, is the electricity price period weight coefficient, medical equipment , industrial equipment , consumer electronics Peak power period , off-peak hours .

9. The intelligent and orderly control algorithm for AC adapters with real-time state perception according to claim 7 is characterized by: The calculation method of the equipment aging factor is: ； in The cumulative number of plug-in and unplugging times for the adapter, , .

10. A device for implementing an intelligent and orderly control algorithm for an AC adapter with real-time state perception according to any one of claims 1 to 9, characterized in that: Including stackable hardware modules and self-energy circuits; The stacked hardware module is integrated into the adapter housing and includes a sensor array, an edge computing unit, and a millimeter wave communication module; The self-energy circuit obtains energy from the AC magnetic field through the CT coil induction and is connected to the solid-state lithium capacitor backup power supply.

Images