Control method of power supply system, computer program product and power supply switching system

Abstract

The invention provides a control method of a power supply system, a computer program product and a power supply switching system. The method comprises the steps of obtaining operation parameters of a current power supply of a power supply system; determining whether the current power supply is abnormal according to the operation parameters; under the condition that the current power supply is the main power supply and the current power supply is abnormal, activating the standby power supply, and under the condition that the standby power supply is activated, controlling the main power supply to stop supplying power and adopting the standby power supply to supply power; and when the current power supply is the standby power supply and the current power supply is abnormal, activating the main power supply, and when the main power supply is activated, controlling the standby power supply to stop supplying power and adopting the main power supply to supply power at the same time. The method solves the problem that in the prior art, when a power system breaks down, effective countermeasures can not be taken quickly, and consequently the stability and reliability of the power system are poor.

Description

Technical Field

[0001] The present application relates to the technical field of power system power supply, and in particular, to a control method for a power supply system, a control device for a power supply system, a computer program product, and a power switching system. Background Art

[0002] In the current power system, the stability and reliability of the power supply system are crucial for ensuring power supply. However, the current power supply system may not be able to quickly take effective countermeasures when a fault occurs, resulting in poor stability and reliability of the power supply system. Summary of the Invention

[0003] The main object of the present application is to provide a control method for a power supply system, a control device for a power supply system, a computer program product, and a power switching system, so as to at least solve the problem that the existing power supply system may not be able to quickly take effective countermeasures when a fault occurs, resulting in poor stability and reliability of the power supply system.

[0004] To achieve the above object, according to one aspect of the present application, there is provided a control method for a power supply system, including: obtaining operation parameters of a current power supply of the power supply system, where the power supply system includes a main power supply and a standby power supply, the current power supply is the main power supply or the standby power supply, and the operation parameters include one or more of voltage, current, and frequency; determining whether the current power supply is abnormal according to the operation parameters; in the case where the current power supply is the main power supply and the current power supply is abnormal, activating the standby power supply, and in the case where the standby power supply has been activated, controlling the main power supply to stop power supply while using the standby power supply for power supply, where activating the standby power supply is starting a generator of the standby power supply to wake up the standby power supply from a dormant state; in the case where the current power supply is the standby power supply and the current power supply is abnormal, activating the main power supply, and in the case where the main power supply has been activated, controlling the standby power supply to stop power supply while using the main power supply for power supply, where activating the main power supply is starting a generator of the main power supply to wake up the main power supply from a dormant state.

[0005] Optionally, determining whether the current power supply is abnormal according to the operation parameters includes: determining that the current power supply is normal in the case where the operation parameters are within a normal range, where the normal range is a numerical range of the operation parameters when the current power supply is operating normally; determining that the current power supply is abnormal in the case where the operation parameters are not within the normal range.

[0006] Optionally, determining whether the current power supply is abnormal according to the operating parameters includes: constructing a fault identification model, where the fault identification model is trained using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical operating parameters obtained within a historical time period and historical identification results corresponding to the historical operating parameters, where the historical identification results are whether the current power supply is abnormal within the historical time period; inputting the operating parameters into the fault identification model to obtain an identification result corresponding to the operating parameters.

[0007] Optionally, determining whether the current power supply is abnormal according to the operating parameters includes: obtaining parameter fluctuation data, where the parameter fluctuation data is the absolute value of the difference between the operating parameters at a first moment and the operating parameters at a second moment, the first moment being any moment during the operation of the power supply system, and the second moment being any moment other than the first moment during the operation of the power supply system; determining that the current power supply is normal when the parameter fluctuation data is within a normal fluctuation range, where the normal fluctuation range is the allowable fluctuation range of the operating parameters when the current power supply is operating normally; and determining that the current power supply is abnormal when the parameter fluctuation data is not within the normal fluctuation range.

[0008] Optionally, after determining whether the current power supply is abnormal according to the operating parameters, the method further includes: obtaining an identification result, where the identification result is the result of whether the current power supply is abnormal; constructing a type identification model, where the type identification model is trained using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical operating parameters obtained within a historical time period, historical identification results, and historical type identification results corresponding to the historical operating parameters and the historical identification results, where the historical type identification results are the types of abnormalities of the current power supply within the historical time period; and inputting the operating parameters and the identification result into the type identification model to obtain a type identification result corresponding to the operating parameters and the identification result.

[0009] Optionally, after obtaining the operating parameters of the current power supply of the power supply system, the method further includes: encrypting the operating parameters N times to obtain encrypted operating parameters, where N≥1; and sending the encrypted operating parameters to a target terminal so that the target terminal decrypts the encrypted operating parameters and displays the operating parameters.

[0010] Optionally, after obtaining the operating parameters of the current power supply of the power supply system, the method further includes: storing the operating parameters in a storage terminal; obtaining identity information, where the identity information is one or more of a fingerprint, a password, and a face pre-entered by a target object when logging in to the storage terminal; matching the identity information with preset identity information in a database to obtain a matching result; in the case where the matching result indicates successful matching, allowing the target object to log in to the storage terminal and view the operating parameters, where different preset identity information corresponds to different viewing permissions, and the data that can be viewed with different viewing permissions is different; in the case where the matching result indicates failed matching, not allowing the target object to log in to the storage terminal and not allowing the target object to view the operating parameters.

[0011] According to another aspect of the present application, there is provided a control device for a power supply system, including: a first obtaining unit configured to obtain the operating parameters of the current power supply of the power supply system, where the power supply system includes a main power supply and a standby power supply, the current power supply is the main power supply or the standby power supply, and the operating parameters include one or more of voltage, current, and frequency; a determining unit configured to determine whether the current power supply is abnormal according to the operating parameters; a first processing unit configured to activate the standby power supply when the current power supply is the main power supply and the current power supply is abnormal, and when the standby power supply has been activated, control the main power supply to stop power supply while using the standby power supply for power supply, where activating the standby power supply is to start the generator of the standby power supply so that the standby power supply wakes up from the sleep state; a second execution unit configured to activate the main power supply when the current power supply is the standby power supply and the current power supply is abnormal, and when the main power supply has been activated, control the standby power supply to stop power supply while using the main power supply for power supply, where activating the main power supply is to start the generator of the main power supply so that the main power supply wakes up from the sleep state.

[0012] According to still another aspect of the present application, there is provided a computer program product including a computer program, where the computer program, when executed by a processor, implements the steps of any one of the control methods of the power supply system.

[0013] According to yet another aspect of the present application, there is provided a power supply switching system, including: one or more processors, a memory, and one or more programs, where the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include those for executing any one of the control methods of the power supply system.

[0014] Applying the technical solution of the present application, once an abnormality occurs in the current power source used for power supply, it can respond in a timely manner and quickly switch the power source. If the current power supply is the main power source, when the main power source is abnormal, the backup power source is first activated, that is, the backup power source is pre-started, and then the power supply is switched to the backup power source. In this way, it can be ensured that the backup power source has reached a stable state before the switch, thus ensuring the continuity of power supply when the backup power source is switched, and avoiding the situation that the backup power source cannot meet the supply demand when suddenly powered on. If the current power supply is the backup power source, when the backup power source is abnormal, the main power source is first activated, that is, the main power source is pre-started, and then the power supply is switched to the main power source. In this way, it can be ensured that the main power source has reached a stable state before the switch, thus ensuring the continuity of power supply when the main power source is switched, and avoiding the situation that the main power source cannot meet the supply demand when suddenly powered on. In this way, power interruption can be avoided, thereby improving the stability and reliability of the power supply system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings forming a part of this application are used to provide a further understanding of the present application. The schematic embodiments and descriptions thereof of the present application are used to explain the present application and do not constitute an improper limitation to the present application. In the drawings:

[0016] Figure 1 The hardware structure block diagram of a mobile terminal showing a control method for an execution power supply system provided in an embodiment of the present application is shown;

[0017] Figure 2 The schematic flow chart of a control method for a power supply system provided in an embodiment of the present application is shown;

[0018] Figure 3 The schematic diagram showing the control steps of the present solution is shown;

[0019] Figure 4 The structure block diagram of a control device for a power supply system provided in an embodiment of the present application is shown.

[0020] Among them, the above-mentioned accompanying drawings include the following reference numerals:

[0021] 102, processor; 104, memory; 106, transmission device; 108, input / output device. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0023] To enable those skilled in the art to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances for the embodiments of this application described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0025] As introduced in the background art, in the prior art, the power supply system may not be able to quickly take effective countermeasures when a failure occurs, resulting in poor stability and reliability of the power supply system. To solve the above problems, the embodiments of this application provide a control method for a power supply system, a control device for a power supply system, a computer program product, and a power supply switching system.

[0026] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0027] The method embodiments provided in the embodiments of this application can be executed on a mobile terminal, a computer terminal, or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 is a hardware structure block diagram of a mobile terminal of a control method for a power supply system according to an embodiment of the present invention. As Figure 1 shown, the mobile terminal may include one or more ( Figure 1 only one is shown in Figure 1 a processor 102 (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Among them, the above-mentioned mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those of ordinary skill in the art can understand that Figure 1 the structure shown is only schematic and does not limit the structure of the above-mentioned mobile terminal. For example, the mobile terminal may further include more or fewer components thanFigure 1 The different configurations shown.

[0028] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the display method of device information in the embodiments of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implements the above-mentioned method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 104 may further include a memory remotely disposed relative to the processor 102, and these remote memories may be connected to the mobile terminal through a network. Examples of the above-mentioned network include but are not limited to the Internet, enterprise intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wireless network provided by a communication provider of the mobile terminal. In one instance, the transmission device 106 includes a network adapter (Network Interface Controller, abbreviated as NIC), which can be connected to other network devices through a base station and thus can communicate with the Internet. In one instance, the transmission device 106 may be a radio frequency (Radio Frequency, abbreviated as RF) module, which is used to communicate with the Internet wirelessly.

[0029] In this embodiment, a control method for a power supply system operating on a mobile terminal, a computer terminal, or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0030] Figure 2 It is a flowchart showing a control method for a power supply system according to an embodiment of the present application. As Figure 2 shown, the method includes the following steps:

[0031] Step S201, obtain the operating parameters of the current power supply of the power supply system, where the power supply system includes a main power supply and a backup power supply, the current power supply is the main power supply or the backup power supply, and the operating parameters include one or more of voltage, current, and frequency;

[0032] Specifically, the operating states of the main power supply and the backup power supply are monitored in real time, and key operating parameters are collected, including but not limited to voltage, current, and frequency. For example, the voltage threshold is set to 220V ± 5%, that is, between 209V and 231V; the current threshold is set to 100A ± 20%, that is, between 80A and 120A; the frequency threshold is set to 50Hz ± 0.5Hz, that is, between 49.5Hz and 50.5Hz.

[0033] Through real-time monitoring and precise parameter setting, abnormal conditions in the power supply system can be detected immediately, improving the sensitivity and accuracy of fault detection. By setting a reasonable threshold range and combining with the high-precision sensors in the data acquisition step, small changes in power supply parameters can be captured in a timely manner. Once the preset threshold is exceeded, the logic judgment step is triggered for fault identification, avoiding false alarms or missed alarms caused by improper threshold setting and ensuring a rapid response of the system to abnormal conditions.

[0034] Step S202: Determine whether the current power supply is abnormal according to the above operating parameters;

[0035] Specifically, based on the real-time comparison and analysis of the collected operating parameters with the preset normal operating range, for example, if the voltage is lower than 209V or higher than 231V, the current is lower than 80A or higher than 120A, or the frequency is lower than 49.5Hz or higher than 50.5Hz, it is determined that the power supply is abnormal. At the same time, according to the historical data trend, potential abnormal behaviors are predicted through machine learning algorithms to make a response in advance.

[0036] Intelligent analysis and judgment of the operating state of the power supply system are realized, which can early warning potential faults, improving the preventive and self-adaptive capabilities of the system. By analyzing historical operating data through deep learning algorithms, abnormal patterns and trends can be identified. When parameter changes matching known abnormal patterns are detected, the redundant detection and fault isolation steps are immediately started, avoiding the system from falling into a shutdown state due to sudden faults, reducing the impact of faults on system operation, and improving the overall stability and reliability.

[0037] Step S203: When the current power supply is the main power supply and the current power supply is abnormal, activate the backup power supply. When the backup power supply has been activated, control the main power supply to stop power supply while using the backup power supply for power supply. Among them, activating the backup power supply is to start the generator of the backup power supply to wake up the backup power supply from the dormant state;

[0038] Specifically, for example, when the data acquisition step reports that the main power supply voltage drops to 200V and the logical judgment step confirms it as abnormal, the redundant detection and fault isolation step immediately starts the generator of the backup power supply, making it enter the hot standby state from the dormant state and ready to take over the power supply task. Once the backup power supply is activated and stable, the control terminal issues an instruction to stop the main power supply, and the system smoothly switches to the backup power supply to ensure continuous power supply.

[0039] When the main power supply fails, it can quickly activate the backup power supply, achieve seamless switching, maintain the continuity and stability of the system power supply, and reduce production interruptions and economic losses. By establishing a fast switching mechanism, the backup power supply can be immediately started when the main power supply fails, ensuring that the power supply switching is completed in the shortest time. At the same time, through the dynamic threshold adjustment step, key parameters are monitored and adjusted in real time to prevent secondary failures during the switching process, ensuring the efficiency and safety of the switching process and avoiding the risks of equipment damage and data loss caused by power failures.

[0040] Step S204, in the case where the current power supply is the backup power supply and the current power supply is abnormal, activate the main power supply. When the main power supply has been activated, while controlling the backup power supply to stop power supply, use the main power supply for power supply. Here, activating the main power supply means starting the generator of the main power supply to wake up the main power supply from the dormant state.

[0041] Specifically, for example, when the logical judgment step confirms that the backup power supply is abnormal due to overload (current exceeding 120A), the system immediately starts the generator of the main power supply to restore its normal operation from the dormant state. After the main power supply is stable, the control terminal controls the backup power supply to stop power supply, and the system switches back to the main power supply for power supply. The whole process ensures the continuity of power supply and the smooth transfer of the load.

[0042] It realizes the two-way intelligent switching between the main power supply and the backup power supply, improves the system redundancy and the ability to cope with sudden failures, and reduces the impact of single-point failures on the overall operation of the system. The two-way redundant design ensures that no matter whether the main power supply or the backup power supply fails, the system can immediately activate the other power supply for power supply. Through the intelligent analysis of the adaptive control strategy generation step, it can automatically select the optimal switching path according to the health status and operating parameters of the current power supply, avoiding the delay and misjudgment of manual intervention, ensuring the high automation and efficiency of power management, reducing the fault switching time, and improving user satisfaction and system availability.

[0043] Through this embodiment, once an abnormality occurs in the current power source used for power supply, it can respond in a timely manner and quickly switch the power source. If the current power supply is the main power source, when the main power source is abnormal, the standby power source is first activated, that is, the standby power source is pre-started, and then the power supply is switched to the standby power source. In this way, it can be ensured that the standby power source has reached a stable state before the switch, so as to ensure the continuity of power supply when the standby power source is switched, and avoid the situation that the standby power source cannot meet the supply demand when suddenly powered on. If the current power supply is the standby power source, when the standby power source is abnormal, the main power source is first activated, that is, the main power source is pre-started, and then the power supply is switched to the main power source. In this way, it can be ensured that the main power source has reached a stable state before the switch, so as to ensure the continuity of power supply when the main power source is switched, and avoid the situation that the main power source cannot meet the supply demand when suddenly powered on. This can avoid power interruption, thereby improving the stability and reliability of the power supply system.

[0044] Specifically, in the above solution, the control method can be applied to a control terminal, or a controller, or a server, or any other feasible device. For example, the main power source and the standby power source are connected in parallel, the main power source and the standby power source are respectively electrically connected to a fast-switching device, and the fast-switching device is electrically connected to the control terminal. The fast-switching device is any existing feasible power-switching device. The specific power source is not limited in this solution and can be any available power source.

[0045] Specifically, as Figure 3 shown, this solution includes a data acquisition step and a logic determination step.

[0046] Data acquisition step: used to collect the operating parameters such as voltage, current, and frequency of the power supply system in real time; and has the functions of data uploading and calibration self-check; used to ensure the accuracy of parameter collection and the timeliness of data uploading; use a high-precision reference source (such as a standard voltage source, current source), collect its data and compare it with the known standard value. Measure at different voltage, current, or frequency points to ensure the accuracy of the measurement results under different conditions. Calculate the deviation between each measurement result and the standard value, so as to quantify the accuracy of the acquisition step. If an error is found, automatically adjust the sensitivity of the sensor, the gain or offset of the AD converter, and other adjustable parameters to reduce or eliminate the error.

[0047] Logic judgment step: According to the parameters obtained in the data acquisition step, judge whether the power supply system is in an abnormal state and determine whether a fast-switching operation needs to be started.

[0048] Specifically, the above solution further includes redundancy detection and fault isolation steps: used to connect the backup power supply and the main power supply, while ensuring that the backup power supply and the main power supply are in a parallel mode, which can detect both the backup power supply and the main power supply simultaneously to understand the operating conditions of the backup power supply and the main power supply. When there are numerical deviations in the current power system, a switch between the backup power supply and the main power supply is performed; the backup power supply and the main power supply are set identically, and they are backup power supplies for each other. At the same time, after any power supply is switched, it is in a disconnected state for easy maintenance.

[0049] Specifically, the above solution further includes remote monitoring and intelligent diagnosis steps: providing a cloud remote monitoring interface, supporting remote configuration, status query, fault diagnosis, and automatic report generation;

[0050] The parameters collected in the system and the corresponding feedback data information are all synchronously uploaded to the remote monitoring and intelligent diagnosis steps. The data information is all stored, and it is convenient for staff to query through operation components and display components, etc., and corresponding alarm components can quickly alarm and generate a fault report when a fault occurs.

[0051] In the specific implementation process, according to the above operating parameters, it is determined whether the current power supply is abnormal, which can be achieved through the following steps: when the above operating parameters are within the normal range, it is determined that the current power supply is normal, where the above normal range is the numerical range of the above operating parameters when the current power supply is working normally; when the above operating parameters are not within the above normal range, it is determined that the current power supply is abnormal.

[0052] In this solution, the set threshold is used as the benchmark for power supply status detection, which can quickly identify parameter abnormalities and distinguish between normal operation and abnormal states, so that it can be simply and quickly determined whether the current power supply is abnormal.

[0053] For example, the normal range can be set to 220V ± 5% for voltage, that is, between 209V and 231V; for current, it is set to 100A ± 20%, that is, between 80A and 120A; for frequency, it is set to 50Hz ± 0.5Hz, that is, between 49.5Hz and 50.5Hz. Of course, the threshold values of these ranges are predefined, and those skilled in the art can determine the normal range according to the actual situation.

[0054] Once the operating parameters exceed the above-set normal range, for example, the voltage drops to 200V, the current soars to 130A, or the frequency deviates to 52Hz, it will be immediately determined that the current power supply is in an abnormal state, and further analyze the type of abnormality and decide whether to initiate a quick switching operation.

[0055] In a specific application, in the power system of a hospital, a main power supply and a standby diesel generator are configured as redundant power supplies. Specifically, when it is detected that the voltage of the main power supply suddenly drops to 200V, which is lower than the preset normal range of 220V±5%, an immediate response is made to determine that the main power supply is abnormal. At this time, the standby diesel generator is quickly started and awakened from the dormant state to the standby state. After the standby power supply stably outputs, the control terminal performs a power switching operation, smoothly switching from the main power supply to the standby diesel generator, ensuring the stable power supply of the hospital's power system and avoiding the interruption of medical equipment services due to power problems. After the switching is completed, the status of the standby power supply is continuously monitored, and at the same time, a maintenance program is started to check the cause of the main power supply failure, preparing for fault recovery and preventing future faults.

[0056] Specifically, the above solution includes a dynamic threshold adjustment step: clarify the voltage threshold, current threshold, and working limit data required by the working environment during the operation of the power system; at the same time, compare the data such as the real-time operation of the power system, ambient temperature, and load factors obtained in real time with the working limit data of the power system; according to the obtained comparison results, quickly make corresponding adjustments to achieve the purpose of dynamically adjusting the thresholds of voltage, current, and frequency, so that the power system is always within a reasonable working value range. Of course, the above solution adjusts the threshold according to environmental parameters, which is not contrary to determining whether the current power supply is abnormal in the above solution. The threshold is adjusted before determining whether the current power supply is abnormal, and the normal range is determined through the adjusted threshold to determine whether the current power supply is abnormal.

[0057] Specifically, the above solution also includes an adaptive control strategy generation step: through the comprehensive collection of the operation parameters of the power system, combined with the clarification of the power system's own parameters, and at the same time combined with the data situation of switching the power system in the redundant detection and fault isolation step, preset the power system switching plan, and add various single variable situations to the plan to respond to emergencies in a timely manner. The adaptive control strategy generation step automatically generates one or more sets of fast-switching control strategies based on the data analysis results, combined with factors such as the topology structure of the power system, power quality, and load level. These strategies will take into account sudden situations of various single variables, such as a sudden increase in load or a sharp change in ambient temperature.

[0058] For example, in the data acquisition step, the real-time voltage of the main power supply is recorded as 223V, the current is 105A, and the frequency is 50.01Hz. At the same time, the ambient temperature is recorded as 22°C and the humidity is 55%. According to the system design document, the rated voltage of the main power supply is 220V, and the maximum allowable fluctuation range is ±5%, that is, the normal range is from 209V to 231V; the rated current is 100A, and the maximum allowable increase is 20%, that is, the normal range is from 100A to 120A; the normal range of the frequency is 50Hz ± 0.5Hz. When the data acquisition step monitors that the voltage of the main power supply drops suddenly to 205V, exceeding the normal range, the redundant detection step immediately responds, disconnects the connection of the main power supply, switches the load to the backup power supply, and records the switching time, the type of main power supply failure (voltage drop), the initial response parameters of the backup power supply, etc. According to the above analysis results, the adaptive control strategy generation step generates a preset switching strategy: when it is detected that the voltage drops to 208V, the backup power supply is immediately started to avoid the voltage dropping to a more dangerous level. In addition, this strategy also takes into account the single-variable influence of load changes and ambient temperature, and it is preset that when the ambient temperature rises to 30°C or the load current increases to 110A, the backup power supply is started.

[0059] In some embodiments, according to the above operating parameters, it is determined whether the above current power supply is abnormal. Specifically, it can be implemented through the following steps: construct a fault identification model, where the above fault identification model is trained using multiple sets of training data, and each set of training data in the above multiple sets of training data includes historical operating parameters obtained within a historical time period, and the historical identification results corresponding to the above historical operating parameters, where the above historical identification results are whether the above current power supply is abnormal within the above historical time period; input the above operating parameters into the above fault identification model to obtain the identification result corresponding to the above operating parameters.

[0060] In this solution, training the model with historical data can capture the complex relationship between abnormal power supply parameters and faults. This enables the model to make accurate judgments even in the face of weak parameter fluctuations or complex fault modes during actual operation. By inputting real-time operating parameters into the trained intelligent model, the model quickly analyzes and identifies changes in the power supply state, and further can accurately determine whether the current power supply is abnormal.

[0061] For example, the fault identification model is trained through machine learning based on a large amount of historical operating data, which includes historical voltage, current, and frequency parameters, as well as the historical identification results of whether the corresponding power supply is abnormal. For example, the historical voltage values are distributed between 190V and 240V, the current values are between 75A and 125A, and the frequency values are between 49Hz and 51Hz. By learning the correlation between these parameters and historical faults, the model can accurately judge the power supply state, thereby improving the accuracy and response speed of fault identification.

[0062] When the data acquisition step obtains the operating parameters of the current power supply in real time, such as voltage 215V, current 110A, and frequency 50.2Hz, these parameters will be sent to the fault identification model for analysis. By comparing these parameters with the normal and abnormal patterns in the historical data, the model outputs a judgment result indicating whether the current power supply is abnormal.

[0063] In a specific application, in the power system management of a large data center, since the servers have extremely high requirements for power stability, any power supply abnormality may cause data loss or system crashes. Specifically, the control terminal of the data center uses the above - constructed fault identification model to analyze the power supply operating parameters in real time. Assume the normal voltage range is 220V ± 5%, that is, from 209V to 231V; the current range is 100A ± 20%, that is, from 80A to 120A; the frequency range is 50Hz ± 0.5Hz, that is, from 49.5Hz to 50.5Hz. When the data acquisition step detects that the voltage drops to 205V, the model immediately analyzes that this belongs to an abnormal state, and then starts the backup power supply to achieve seamless switching, avoiding business interruption in the data center due to voltage abnormality and protecting the continuity of the data center operation and the security of the data.

[0064] In the data center, when the voltage of the current power supply (main power supply) drops to 205V as analyzed by the fault identification model, which is within the abnormal range, the model immediately outputs an abnormal identification result. At this time, the system quickly starts the standby diesel generator, waking it up from the dormant state to the standby state. After the standby power supply stably outputs, the control terminal performs a fast switch, smoothly switching from the main power supply to the standby power supply, ensuring the continuity of the power supply in the data center, avoiding the interruption of data center operation caused by power supply failures, protecting the stable operation of the servers and storage devices in the data center, preventing data loss and system crashes, and enhancing the business continuity and data security of the data center.

[0065] Specifically, of course, if only relying on fixed thresholds and preset control strategies for fault detection and switching operations, however, this method often fails to achieve the best switching effect and response speed when facing complex and changeable power system environments and load demands. In addition, traditional control terminals lack intelligent data analysis and prediction capabilities and cannot pre - warn potential power supply failures. Therefore, in another feasible solution of this scheme, the above - mentioned scheme includes a data analysis step: using machine learning algorithms to perform in - depth learning on the historical operation data (i.e., historical operation parameters) of the power system, predicting potential power supply failures and adjusting the parameter settings of the fast - switch device in advance to achieve preventive switching before a fault occurs.

[0066] Specifically, the data analysis step includes:

[0067] b1. Feature extraction step: Extract key features from the historical data of the power supply system, including but not limited to voltage fluctuation patterns and current peak frequencies;

[0068] b2. Model training and optimization step: Train a machine learning model based on the extracted features and continuously optimize the model to improve the accuracy and timeliness of fault prediction;

[0069] Process the extracted features, including data cleaning, data transformation, feature selection, and feature extraction, in order to provide accurate features for the subsequent learning model and enhance the training effect of the learning model;

[0070] After feature extraction, select a suitable learning algorithm as needed, including classification: logistic regression, support vector machine, random forest, neural network; regression: linear regression, ridge regression, and XGBoost, to enhance the training effect of the learning model;

[0071] b3. Prediction result verification step: Verify the accuracy of the prediction result by comparing it with the actual operation data and feedback it to the model training and optimization step for iterative improvement.

[0072] Specifically, the traditional power control terminal lacks intelligent data analysis and prediction capabilities and cannot give early warnings of potential power supply faults, resulting in the problem that effective response measures may not be taken quickly when a fault occurs. Through the data analysis step, this application uses machine learning algorithms to perform in-depth learning on the historical operation data of the power supply system, can accurately predict potential power supply faults, and provide a reliable basis for preventive switching. The dynamic threshold adjustment step can automatically adjust the thresholds of voltage, current, and frequency according to the real-time operation status of the power supply system, ambient temperature, and load change factors, so that the fast transfer device can maintain the best response speed and switching effect under different operating conditions.

[0073] In the specific implementation process, to determine whether the current power supply is abnormal according to the above operating parameters, it can be achieved through the following steps: Obtain parameter fluctuation data, where the parameter fluctuation data is the absolute value of the difference between the operating parameters at the first moment and the operating parameters at the second moment. The first moment is any moment during the operation of the power supply system, and the second moment is any moment other than the first moment during the operation of the power supply system; When the parameter fluctuation data is within the normal fluctuation range, determine that the current power supply is normal, where the normal fluctuation range is the allowable fluctuation range of the operating parameters when the current power supply is working normally; When the parameter fluctuation data is not within the normal fluctuation range, determine that the current power supply is abnormal.

[0074] In this solution, by comparing the parameter values at different time points, the amplitude and trend of parameter fluctuations can be identified. The setting of the normal fluctuation range is based on the normal operating parameters of the power supply system and engineering experience. By comparing the current fluctuation data with this range, abnormal fluctuations and normal fluctuations can be effectively distinguished. By setting a reasonable parameter fluctuation range, misjudgment of slight power fluctuations is avoided, and thus it can be further accurately determined whether the current power supply is abnormal.

[0075] Specifically, for example, the instantaneous values of voltage, current, and frequency are captured regularly (e.g., every 1 second). Then, the absolute value of the parameter change between two adjacent measurements is calculated. For example, if the voltage is 218V at the first moment (t1) and 210V at the second moment (t2), the fluctuation data of the voltage is |218V - 210V| = 8V.

[0076] The normal fluctuation range can be set, for example, as follows: the voltage fluctuation does not exceed ±5V, the current fluctuation does not exceed ±10A, and the frequency fluctuation does not exceed ±0.2Hz. If the parameter fluctuation data are all within these ranges, the logical judgment step will determine that the current power supply operation state is normal. Of course, the specific values are not limited, and those skilled in the art can set appropriate value ranges according to the actual situation.

[0077] In a certain measurement, the voltage suddenly drops from 218V to 200V, that is, the fluctuation data is |218V - 200V| = 18V, exceeding the set normal range (±5V). The logical judgment step then determines that the current power supply is abnormal, and there may be a voltage drop fault.

[0078] In a specific application, in the power supply control system of an industrial production line, a main power supply and a redundant power supply are configured on the production line to ensure the continuity of power supply. Specifically, when implemented, by analyzing the current fluctuation data in real time, for example, if the current is 90A at the first moment and 115A at the second moment, the fluctuation data is |90A - 115A| = 25A, exceeding the set normal fluctuation range (±10A). It is then determined that the current power supply is abnormal, and there may be an overload or power instability situation. At this time, the status of the standby power supply is checked and switching preparation is carried out. When the standby power supply is activated and stable, the system performs a quick switch from the main power supply to the standby power supply to ensure the continuity of power supply for the production line, avoid production interruption caused by power supply abnormalities, reduce economic losses, and ensure the stability and safety of industrial production.

[0079] Through the above-described embodiments, in an industrial production environment, by adopting the method described above, possible overload situations can be detected immediately. For example, if the set current fluctuation range is ±10A, when a current change from 90A to 115A is detected, that is, the fluctuation data is 25A, which exceeds the normal fluctuation range, a rapid response is made to start the redundant power supply inspection and switching program, avoiding power interruption of the production line due to overload, protecting the normal operation of key equipment in the production line, preventing production stagnation and product loss, enhancing the continuity and economic benefits of industrial production, and at the same time reducing the production safety risks caused by power failures.

[0080] In some embodiments, after determining whether the current power supply is abnormal according to the above operating parameters, the method further includes the following steps: obtaining an identification result, where the identification result is the result of whether the current power supply is abnormal; constructing a type identification model, where the type identification model is trained using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical operating parameters obtained within a historical time period, historical identification results, and historical type identification results corresponding to the historical operating parameters and the historical identification results, where the historical type identification result is the type of abnormality of the current power supply within the historical time period; inputting the operating parameters and the identification result into the type identification model to obtain the type identification result corresponding to the operating parameters and the identification result.

[0081] In this solution, by analyzing the operating parameters, the generated identification result directly reflects whether the power supply system is in a normal operating state. By constructing and training a type identification model, the model can learn and understand the complex relationship between historical operating parameters and fault types. Even when the current parameter change pattern is not exactly the same as the previous pattern, the model can predict the most likely fault type based on the learned rules. After confirming that the power supply is abnormal, the type identification model can identify the most likely fault type causing the abnormality based on the details of the current operating parameters and historical learning experience, thereby improving the accuracy of fault diagnosis.

[0082] Specifically, algorithms such as the SVM algorithm, decision tree algorithm, random forest algorithm, MLP algorithm, CNN algorithm, etc. can be used to construct the type identification model.

[0083] Specifically, the logical judgment step includes:

[0084] a1. Threshold comparison step: used to compare the collected voltage, current, and frequency parameters with a preset normal range;

[0085] a2. Fault type identification step: identifying the fault type that occurs in the power supply system according to the comparison result, including voltage dip, frequency offset, and power interruption;

[0086] Compare the fluctuations of the voltage and current outputs with the output of the power supply during stable operation to determine whether the voltage and current outputs are stable. When data deviation occurs, determine whether it is within the acceptable fluctuation range. When any fluctuation exceeds the acceptable range, initiate the corresponding operation.

[0087] a3. Fast switching decision step: Based on the fault type, power supply system configuration, and preset switching strategies, decide whether to initiate the fast switching operation and determine the optimal switching path.

[0088] During the scheme setting, fully classify the fault types and conduct comprehensive combinations to quickly determine the fault types it satisfies, and then select the corresponding path switching scheme according to the satisfied fault types.

[0089] Specifically, the power supply system configuration parameters include the topology of the power supply system (series, parallel, or other complex configurations), the types of each power supply (such as mains power, UPS, diesel generator), the location distribution, the current operating status (such as online, offline, faulty), as well as the capacity and load level.

[0090] First, confirm the fault type. For example, whether it is a voltage dip. If so, determine whether the dip amplitude and duration exceed the preset dynamic threshold. Evaluate all available backup power supplies, check whether they are online, whether they have sufficient capacity to support the current load, and whether their geographical locations are favorable for fast switching. For each switchable power supply, the fast switching decision step evaluates the cost and risk of switching, including the time required for switching, the possible impact of the switching process on system stability, the load balancing situation after switching, and the startup and operating costs of the backup power supply. The decision step applies various optimization algorithms, such as Dijkstra algorithm, A* search algorithm, or genetic algorithm, to find the path with the minimum switching cost. The algorithm will consider all the above parameters, as well as the feedback from the fault isolation step, and calculate the switching scheme with the shortest switching time and the least system interference.

[0091] After the decision step confirms the optimal switching path, it will generate and send control instructions to the fast switching device, and at the same time monitor the entire switching process to ensure a smooth switching. Once the switching is completed, it will continue to monitor the status of the power supply system until it is confirmed that the backup power supply is operating stably.

[0092] For example, consider the power system of a data center with three power supplies: main power supply M (mains power), secondary power supply S (UPS), and redundant power supply R (diesel generator). The system is configured in parallel mode. When the main power supply fails, the secondary power supply S can take over instantaneously, while the redundant power supply R needs several minutes to start up and be put into use.

[0093] The data acquisition step detected that the voltage of the main power supply M dropped to 190V, far below the normal threshold of 220V ± 10%, and the duration exceeded the set warning time. The quick-switching decision step confirmed that the fault type was a severe voltage drop and determined that the fault exceeded the tolerance range. The decision step evaluated the status of the secondary power supply S and the redundant power supply R. The secondary power supply S was online and had sufficient capacity, suitable for immediate takeover; the redundant power supply R needed several minutes to start and was not suitable for emergencies.

[0094] The decision step used a path optimization algorithm to evaluate the cost of switching to the secondary power supply S. Since S was physically paralleled with M and S had sufficient instantaneous response ability, the switching cost was the lowest. The quick-switching decision step determined that switching to the secondary power supply S was the optimal path, generated a control instruction, and sent it to the fast-switching device to execute the switching.

[0095] After receiving the instruction, the fast-switching device instantly switched the load of the data center from the main power supply M to the secondary power supply S. After the switching was completed, the decision step continued to monitor the system status until it confirmed that the secondary power supply S was operating stably.

[0096] The decision step simultaneously notified the maintenance team to check the reason of the main power supply M and prepared the redundant power supply R as a possible long-term alternative in case the secondary power supply S also failed.

[0097] The adaptive control strategy generation step can combine the topology of the power supply system, power quality, and load importance level to automatically generate an optimized fast-switching control strategy and automatically adjust the strategy when necessary to adapt to system changes, ensuring the stability and reliability of the power supply system. The remote monitoring and intelligent diagnosis step provides a cloud remote monitoring interface, supporting remote configuration, status query, fault diagnosis, and automatic report generation functions, which can greatly reduce the operation and maintenance costs and improve the operation and maintenance efficiency.

[0098] In the specific implementation process, after obtaining the operation parameters of the current power supply of the power supply system, the above method further includes the following steps: encrypting the above operation parameters N times to obtain encrypted operation parameters, where N ≥ 1; sending the above encrypted operation parameters to the target terminal so that the above target terminal decrypts the above encrypted operation parameters and displays the above operation parameters.

[0099] In this solution, by adopting a multi-encryption strategy, even a high-level attacker is difficult to crack the data easily because each encryption increases the difficulty of cracking. The attacker needs to master the keys and algorithm logics of multiple encryption algorithms, preventing the risk of data being intercepted or tampered with midway. The encrypted data is difficult to restore without the correct key and algorithm, which effectively prevents unauthorized third parties from obtaining real data information, thus greatly enhancing the security of the data.

[0100] Specifically, multiple encryption algorithms can be used for data encryption, such as the AES encryption standard. Assume N = 3, that is, the operating parameters are encrypted three times. The first time, the operating parameters are converted into ciphertext using AES encryption. The second time, RSA asymmetric encryption is used for secondary encryption. The third time, the SHA-256 hashing algorithm may be used to further enhance the encryption effect and ensure the security of data during transmission.

[0101] The encrypted operating parameters are sent to the target terminal where the remote monitoring and intelligent diagnosis steps are located through a secure transmission channel. When the data arrives, the target terminal uses a pre-agreed decryption algorithm (such as the private key of AES and RSA and the inverse operation of SHA-256) to gradually restore the data, and finally presents the original operating parameter values on the display and operation interface, such as voltage 220V, current 100A, and frequency 50Hz.

[0102] In some embodiments, after obtaining the operating parameters of the current power supply of the power supply system, the above method further includes the following steps: storing the above operating parameters in a storage terminal; obtaining identity information, where the above identity information is one or more of fingerprints, passwords, and faces pre-entered by a target object when logging in to the above storage terminal; matching the above identity information with preset identity information in a database to obtain a matching result; in the case where the above matching result indicates a successful match, allowing the above target object to log in to the above storage terminal and view the above operating parameters, where different viewing permissions correspond to different preset identity information, and the data that can be viewed with different viewing permissions is different; in the case where the above matching result indicates a failed match, not allowing the above target object to log in to the above storage terminal and not allowing the above target object to view the above operating parameters.

[0103] In this solution, database comparison is a key link in identity verification. It ensures that the identity information provided by the user is consistent with the pre-registered information. Combined with multi-factor verification, it can effectively resist identity forgery and password guessing attacks, safeguard the privacy of the operating parameters of the power system and the controllability of data access. By setting different levels of access permissions, it is possible to control the range of data that can be accessed and operated according to the user's role and scope of responsibilities, avoiding unauthorized personnel from accessing sensitive information and performing unauthorized operations, enhancing the security management and compliance operations of the operating data of the power system, reducing the risks of data leakage and operation errors. The immediate response mechanism for login failure ensures the immediate prevention of unauthorized access. This strategy reduces the possibility of illegal users using data for malicious operations or information theft, and maintains the security of the operating data of the power system and the effectiveness of access control.

[0104] For example, after the operating parameters such as voltage of 220V, current of 100A, and frequency of 50Hz are collected in real time by the data acquisition step, the encrypted communication and authentication step encrypts and stores these data in a secure storage terminal in the cloud or locally, ensuring the security and integrity of the data for subsequent analysis and traceability.

[0105] The control terminal has the functions of encrypted communication and authentication. When a user attempts to log in to the terminal storing the operating parameters, the system will require the user to provide authentication information, including fingerprint, password, or facial recognition. For example, when User A needs to view the operating parameters, the system first prompts User A to verify through fingerprint recognition. If the fingerprint match fails, the system will require the input of a pre-set password, with a length of at least 8 digits, including uppercase and lowercase letters, numbers, and special characters, to ensure the complexity of the password. If the password verification passes, User A will be granted permission to access the operating parameters.

[0106] After the user provides the authentication information, the system compares the data with a preset database that stores the biometric information (such as fingerprints, facial images) and passwords of all authorized users. For example, for User A, the system compares the obtained fingerprint data with the fingerprint sample of User A reserved in the database. If the match is successful, it then verifies whether the password is correct to further confirm the user's identity.

[0107] Based on the user's identity information, the system will assign different levels of access permissions. For example, as an ordinary operation and maintenance personnel, User A can only view the voltage, current, and frequency parameters of the current power system, but cannot modify the system settings or view the historical fault records. As a senior administrator, User B can not only view all operating parameters, but also access the system settings and historical fault reports, and even perform remote control operations.

[0108] If the identity information provided by the user does not match the preset information in the database, the system will reject the user's login request and not allow them to view or operate the operating parameters. For example, if User C attempts to log in to the storage terminal but fails the fingerprint or password verification, the system will immediately terminate the login process to prevent unauthorized access.

[0109] Specifically, the above solution further includes encryption communication and authentication steps: Select any one of the algorithms of symmetric, asymmetric, and linear hashing to encrypt the transmitted data as needed, and set the corresponding decryption program at the receiving end to perform decryption quickly; In actual operation, different encryption processes can be performed on the same data simultaneously and transmitted to the same receiving end at the same time. By comparing multiple sets of data, the accuracy of data transmission can be ensured; Moreover, classify the logged-in personnel, set corresponding permissions, and set a recording function at the same time. Each login and operation are recorded and cannot be deleted, which helps with querying; Multiple verification mechanisms such as fingerprints, passwords, and face recognition can be set during login; Ensure the communication security between the control terminal and the fast-switching device.

[0110] Specifically, the above encryption communication and authentication steps support multiple communication protocols, including but not limited to Modbus, IEC60870-5-104, DNP3, and Ethernet / IP, to adapt to the communication requirements of different fast-switching devices and monitoring systems; Select the corresponding communication protocol according to the available equipment and equipment environment conditions to ensure the accuracy and timeliness of information data transmission, and at the same time, the durability of the equipment needs to be ensured.

[0111] Specifically, the above solution further includes a display and operation interface: Provide a user interaction interface for displaying the power system status, fast-switching device status, and historical operation records, and allowing users to perform parameter settings and manual control operations.

[0112] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the control method of the power system of the present application will be described in detail below in conjunction with specific embodiments.

[0113] This embodiment relates to a specific control method for a power system, including the following steps:

[0114] Step A: Real-time collect the voltage, current, and frequency operation parameters of the power system;

[0115] Step B: Determine whether the power system is in an abnormal state according to the collected parameters, and determine whether a fast switching operation needs to be started;

[0116] Step C: When it is determined that a fast switching operation needs to be started, generate the corresponding control instruction;

[0117] Step D: Send the control instruction to the fast-switching device of the power system for execution, and receive the status feedback of the fast-switching device;

[0118] Step E: Display the power system status, fast-switching device status, and historical operation records on the display and operation interface, and provide an interface for users to perform parameter settings and manual control operations;

[0119] Step F: Perform security verification on the data in the control process to ensure the legality and security of the control instructions.

[0120] It further includes the following steps:

[0121] Step S1: Use machine learning algorithms to perform in-depth learning on the historical operation data of the power supply system to predict potential power failures;

[0122] Step S2: Dynamically adjust the thresholds of voltage, current, and frequency according to the real-time operation status, ambient temperature, and load change factors of the power supply system;

[0123] Step S3: Combine the topological structure, power quality, and load level of the power supply system to automatically generate a fast transfer control strategy;

[0124] Step S4: When a potential failure is predicted, automatically adjust the parameter settings of the fast transfer device and perform preventive switching operations;

[0125] Step S5: Identify and isolate the fault source, and at the same time start the standby power supply to ensure the continuity and reliability of the power supply system.

[0126] The embodiment of the present application also provides a control device for a power supply system. It should be noted that the control device for the power supply system in the embodiment of the present application can be used to execute the control method for the power supply system provided in the embodiment of the present application. This device is used to implement the above-mentioned embodiments and preferred implementation manners, and those that have been described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0127] The following introduces the control device for the power supply system provided in the embodiment of the present application.

[0128] Figure 4 It is a structural block diagram of a control device for a power supply system according to an embodiment of the present application. As Figure 4 shown, the device includes:

[0129] The first acquisition unit 10 is used to acquire the operation parameters of the current power supply of the power supply system, where the power supply system includes a main power supply and a standby power supply, the current power supply is the main power supply or the standby power supply, and the operation parameters include one or more of voltage, current, and frequency;

[0130] The determination unit 20 is used to determine whether the current power supply is abnormal according to the operation parameters;

[0131] The first processing unit 30 is configured to activate the backup power supply when the current power supply is the main power supply and the current power supply is abnormal. When the backup power supply has been activated, it controls the main power supply to stop power supply while supplying power using the backup power supply. Here, activating the backup power supply means starting the generator of the backup power supply to wake up the backup power supply from the dormant state;

[0132] The second processing unit 40 is configured to activate the main power supply when the current power supply is the backup power supply and the current power supply is abnormal. When the main power supply has been activated, it controls the backup power supply to stop power supply while supplying power using the main power supply. Here, activating the main power supply means starting the generator of the main power supply to wake up the main power supply from the dormant state.

[0133] Through this embodiment, once the current power supply used for power supply has an abnormality, it can respond in a timely manner and quickly switch the power supply. If the current power supply is the main power supply, when the main power supply is abnormal, the backup power supply is first activated, that is, the backup power supply is pre-started, and then the power supply is switched to the backup power supply. In this way, it can be ensured that the backup power supply has reached a stable state before the switch, so as to ensure the continuity of power supply during the switch of the backup power supply and avoid the situation that the backup power supply suddenly powers on and cannot meet the supply demand. If the current power supply is the backup power supply, when the backup power supply is abnormal, the main power supply is first activated, that is, the main power supply is pre-started, and then the power supply is switched to the main power supply. In this way, it can be ensured that the main power supply has reached a stable state before the switch, so as to ensure the continuity of power supply during the switch of the main power supply and avoid the situation that the main power supply suddenly powers on and cannot meet the supply demand. In this way, power interruption can be avoided, thereby improving the stability and reliability of the power supply system.

[0134] In the specific implementation process, the determination unit includes a first determination module and a second determination module. The first determination module is configured to determine that the current power supply is normal when the operating parameters are within the normal range, where the normal range is the numerical range of the operating parameters when the current power supply is working normally; the second determination module is configured to determine that the current power supply is abnormal when the operating parameters are not within the normal range.

[0135] In this solution, the set threshold is used as the benchmark for power supply state detection, which can quickly identify parameter abnormalities and distinguish between normal operation and abnormal states, so that it can simply and quickly determine whether the current power supply is abnormal.

[0136] In some embodiments, the determination unit includes a construction module and a processing module. The construction module is configured to construct a fault identification model, where the fault identification model is trained using multiple sets of training data. Each set of the multiple sets of training data includes historical operation parameters obtained within a historical time period and historical identification results corresponding to the historical operation parameters, where the historical identification results indicate whether the current power supply was abnormal within the historical time period. The processing module is configured to input the operation parameters into the fault identification model to obtain an identification result corresponding to the operation parameters.

[0137] In this solution, training the model with historical data can capture the complex relationship between abnormal power supply parameters and faults. This enables the model to make accurate judgments even in the face of weak parameter fluctuations or complex fault patterns during actual operation. By inputting real-time operation parameters into the trained intelligent model, the model quickly analyzes and identifies changes in the power supply status, and can further accurately determine whether the current power supply is abnormal.

[0138] In a specific implementation process, the determination unit includes an acquisition module, a third determination module, and a fourth determination module. The acquisition module is configured to acquire parameter fluctuation data, where the parameter fluctuation data is the absolute value of the difference between the operation parameters at a first moment and the operation parameters at a second moment. The first moment is any moment during the operation of the power supply system, and the second moment is any moment other than the first moment during the operation of the power supply system. The third determination module is configured to determine that the current power supply is normal when the parameter fluctuation data is within the normal fluctuation range, where the normal fluctuation range is the allowable fluctuation range of the operation parameters when the current power supply is operating normally. The fourth determination module is configured to determine that the current power supply is abnormal when the parameter fluctuation data is not within the normal fluctuation range.

[0139] In this solution, by comparing parameter values at different time points, the amplitude and trend of parameter fluctuations can be identified. The normal fluctuation range is set based on the normal operation parameters of the power supply system and engineering experience. By comparing the current fluctuation data with this range, abnormal fluctuations and normal fluctuations can be effectively distinguished. By setting a reasonable parameter fluctuation range, misjudgments of minor power supply fluctuations are avoided, and further, whether the current power supply is abnormal can be accurately determined.

[0140] In some embodiments, the above-mentioned device further includes a second acquisition unit, a construction unit, and a third processing unit. The second acquisition unit is configured to acquire an identification result after determining whether the current power supply is abnormal according to the above-mentioned operating parameters, where the identification result is the result of whether the current power supply is abnormal; the construction unit is configured to construct a type identification model, where the type identification model is trained using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical operating parameters acquired within a historical time period, historical identification results, and historical type identification results corresponding to the historical operating parameters and the historical identification results, where the historical type identification result is the type of abnormality of the current power supply within the historical time period; the third processing unit is configured to input the operating parameters and the identification result into the type identification model to obtain a type identification result corresponding to the operating parameters and the identification result.

[0141] In this solution, by analyzing the operating parameters, the generated identification result directly reflects whether the power supply system is in a normal operating state. By constructing and training a type identification model, the model can learn and understand the complex relationship between historical operating parameters and fault types. Even when the current parameter change pattern is not exactly the same as the previous pattern, the model can predict the most likely fault type based on the learned rules. After confirming that the power supply is abnormal, the type identification model can identify the most likely fault type causing the abnormality based on the details of the current operating parameters and historical learning experience, thereby improving the accuracy of fault diagnosis.

[0142] In a specific implementation process, the above-mentioned device further includes an encryption unit and a sending unit. The encryption unit is configured to encrypt the above-mentioned operating parameters N times after acquiring the operating parameters of the current power supply of the power supply system to obtain encrypted operating parameters, where N≥1; the sending unit is configured to send the encrypted operating parameters to a target terminal so that the target terminal decrypts the encrypted operating parameters and displays the operating parameters.

[0143] In this solution, by adopting a multiple encryption strategy, even a high-level attacker is difficult to crack the data easily because each encryption increases the difficulty of cracking. The attacker needs to master the keys and algorithm logics of multiple encryption algorithms, preventing the risk of data being intercepted or tampered with midway. The encrypted data is difficult to restore without the correct key and algorithm, which effectively prevents unauthorized third parties from obtaining real data information, thereby greatly enhancing the security of the data.

[0144] In some embodiments, the above-mentioned device further includes a storage unit, a third acquisition unit, a matching unit, a fourth processing unit, and a fifth processing unit. The storage unit is configured to store the above-mentioned operating parameters in a storage terminal after acquiring the operating parameters of the current power supply of the power supply system; the third acquisition unit is configured to acquire identity information, where the above-mentioned identity information is one or more of a fingerprint, a password, and a face pre-entered by a target object to log in to the storage terminal; the matching unit is configured to match the above-mentioned identity information with preset identity information in a database to obtain a matching result; the fourth processing unit is configured to, when the above-mentioned matching result indicates a successful match, allow the above-mentioned target object to log in to the storage terminal and view the above-mentioned operating parameters, where different above-mentioned preset identity information corresponds to different viewing permissions, and different data can be viewed with different viewing permissions; the fifth processing unit is configured to, when the above-mentioned matching result indicates a failed match, not allow the above-mentioned target object to log in to the storage terminal and not allow the above-mentioned target object to view the above-mentioned operating parameters.

[0145] In this solution, database comparison is a key link in identity authentication. It ensures that the identity information provided by the user is consistent with the pre-registered information. Combined with multi-factor authentication, it can effectively resist identity forgery and password guessing attacks, safeguard the privacy of the operating parameters of the power system and the controllability of data access. By setting different levels of access permissions, it is possible to control the scope of data that can be accessed and operated according to the user's role and responsibility scope, avoiding unauthorized personnel from accessing sensitive information and performing unauthorized operations, enhancing the security management and compliance operations of the operating data of the power system, reducing the risks of data leakage and operation errors. The instant response mechanism for login failure ensures the instant prevention of unauthorized access. This strategy reduces the possibility of illegal users using data for malicious operations or information theft, and maintains the security of the operating data of the power system and the effectiveness of access control.

[0146] The control device of the above-mentioned power supply system includes a processor and a memory. The above-mentioned first acquisition unit, determination unit, first processing unit, second processing unit, etc. are all stored in the memory as program units, and the corresponding functions are implemented by the processor executing the above-mentioned program units stored in the memory. The above-mentioned modules are all located in the same processor; or, the above-mentioned each module is located in different processors in any combination form.

[0147] The processor contains a kernel, and the kernel retrieves the corresponding program unit from the memory. One or more kernels can be set, and by adjusting the kernel parameters, the problem that the power supply system may not be able to quickly make effective response measures when a fault occurs in the prior art, resulting in poor stability and reliability of the power supply system, can be solved.

[0148] The memory may include non-permanent memory in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0149] Embodiments of the present invention provide a computer-readable storage medium, the computer-readable storage medium including a stored program, wherein when the program runs, it controls the device where the computer-readable storage medium is located to execute the control method of the above power supply system.

[0150] Embodiments of the present invention provide a processor, the processor being used to run a program, wherein when the program runs, it executes the control method of the above power supply system.

[0151] Embodiments of the present invention provide a device, the device including a processor, a memory, and a program stored on the memory and executable on the processor, and when the processor executes the program, it implements at least the steps of the control method of the power supply system. The device herein may be a server, a PC, a PAD, a mobile phone, etc.

[0152] A computer program product includes a non-volatile computer-readable storage medium, the non-volatile computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, it implements the steps of the control method of the power supply system in various embodiments of the present application.

[0153] The present application also provides a power switching system, including one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include those for executing any one of the above control methods of the power supply system.

[0154] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. They can be implemented by program codes executable by the computing device, so that they can be stored in a storage device and executed by the computing device. And in some cases, the steps shown or described herein can be executed in a different order, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0155] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0156] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0157] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0158] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0159] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0160] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0161] A computer-readable medium includes both permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, disk storage or other magnetic storage devices, or any other non-transitory media that can be used to store information accessible by a computing device. As defined herein, a computer-readable medium does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0162] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or apparatus comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or apparatus. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising the element.

[0163] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A control method for a power supply system, characterized in that, Including: Obtain the operating parameters of the current power supply of the power supply system, where the power supply system includes a main power supply and a backup power supply, the current power supply is the main power supply or the backup power supply, and the operating parameters include one or more of voltage, current, and frequency; Determine whether the current power supply is abnormal according to the operating parameters; When the current power supply is the main power supply and the current power supply is abnormal, activate the backup power supply. When the backup power supply has been activated, control the main power supply to stop power supply and supply power using the backup power supply at the same time. Activating the backup power supply is to start the generator of the backup power supply so that the backup power supply wakes up from the dormant state; When the current power supply is the backup power supply and the current power supply is abnormal, activate the main power supply. When the main power supply has been activated, control the backup power supply to stop power supply and supply power using the main power supply at the same time. Activating the main power supply is to start the generator of the main power supply so that the main power supply wakes up from the dormant state.

2. The method according to claim 1, characterized in that, Determining whether the current power supply is abnormal according to the operating parameters includes: When the operating parameters are within the normal range, determine that the current power supply is normal, where the normal range is the numerical range of the operating parameters when the current power supply is operating normally; When the operating parameters are not within the normal range, determine that the current power supply is abnormal.

3. The method according to claim 1, characterized in that, Determining whether the current power supply is abnormal according to the operating parameters includes: Construct a fault identification model, where the fault identification model is trained using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical operating parameters obtained within a historical time period and historical identification results corresponding to the historical operating parameters, where the historical identification result is whether the current power supply was abnormal during the historical time period; Input the operating parameters into the fault identification model to obtain the identification result corresponding to the operating parameters.

4. The method according to claim 1, wherein Determining whether the current power supply is abnormal according to the operating parameters includes: Obtain parameter fluctuation data, where the parameter fluctuation data is the absolute value of the difference between the operating parameters at a first moment and the operating parameters at a second moment, the first moment is any moment during the operation of the power supply system, and the second moment is any moment during the operation of the power supply system other than the first moment; When the parameter fluctuation data is within the normal fluctuation range, determine that the current power supply is normal, where the normal fluctuation range is the allowable fluctuation range of the operating parameters when the current power supply is operating normally; When the parameter fluctuation data is not within the normal fluctuation range, determine that the current power supply is abnormal.

5. The method according to claim 1, wherein After determining whether the current power supply is abnormal according to the operating parameters, the method further includes: Obtain an identification result, where the identification result is the result of whether the current power supply is abnormal; Build a type recognition model, where the type recognition model is trained using multiple sets of training data, and each set of training data in the multiple sets of training data includes historical operating parameters obtained within a historical time period, historical recognition results, and the historical type recognition results corresponding to the historical operating parameters and the historical recognition results, where the historical type recognition results are the types of anomalies of the current power supply within the historical time period; Input the operating parameters and the recognition results into the type recognition model to obtain the type recognition results corresponding to the operating parameters and the recognition results.

6. The method according to any one of claims 1 to 5, characterized in that After obtaining the operating parameters of the current power supply of the power supply system, the method further includes: Encrypt the operating parameters N times to obtain encrypted operating parameters, where N≥1; Send the encrypted operating parameters to a target terminal so that the target terminal decrypts the encrypted operating parameters and displays the operating parameters.

7. The method according to any one of claims 1 to 5, characterized in that, After obtaining the operating parameters of the current power supply of the power supply system, the method further includes: Store the operating parameters in a storage terminal; Obtain identity information, where the identity information is one or more of a fingerprint, a password, and a face pre-entered by a target object when logging in to the storage terminal; Match the identity information with preset identity information in a database to obtain a matching result; In the case where the matching result indicates a successful match, allow the target object to log in to the storage terminal and view the operating parameters, where different preset identity information corresponds to different viewing permissions, and different viewing permissions can view different data; In the case where the matching result indicates a failed match, do not allow the target object to log in to the storage terminal and do not allow the target object to view the operating parameters.

8. A control device for a power supply system, characterized in that, Includes: A first acquisition unit for acquiring the operating parameters of the current power supply of the power supply system, where the power supply system includes a main power supply and a backup power supply, the current power supply is the main power supply or the backup power supply, and the operating parameters include one or more of voltage, current, and frequency; A determination unit for determining whether the current power supply is abnormal according to the operating parameters; A first processing unit for activating the backup power supply in the case where the current power supply is the main power supply and the current power supply is abnormal, and in the case where the backup power supply has been activated, controlling the main power supply to stop power supply while supplying power using the backup power supply, where activating the backup power supply is starting the generator of the backup power supply to wake the backup power supply from the sleep state; A second processing unit for activating the main power supply in the case where the current power supply is the backup power supply and the current power supply is abnormal, and in the case where the main power supply has been activated, controlling the backup power supply to stop power supply while supplying power using the main power supply, where activating the main power supply is starting the generator of the main power supply to wake the main power supply from the sleep state.

9. A computer program product, comprising a computer program, characterized in that, The computer program, when executed by a processor, implements the steps of the control method of the power supply system according to any one of claims 1 to 7.

10. A power supply switching system, characterized in that, Includes: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include a control method for executing the power supply system according to any one of claims 1 to 7.

Images