Remote state monitoring method and system in AC / DC power supply management

Abstract

The invention relates to the technical field of power supply management, and discloses a remote state monitoring method and system in AC / DC power supply management, and the method comprises the steps: analyzing a fault-prone position of an AC / DC power supply through historical fault data, determining a field monitoring point of the AC / DC power supply through the fault-prone position, and determining a field monitoring device of the field monitoring point; collecting field monitoring data on the field monitoring point through the field monitoring equipment, and remotely transmitting the field monitoring data to a preset data analysis system; performing data analysis on the field monitoring data, collecting a normal power supply signal and an abnormal power supply signal of an AC / DC power supply, and establishing an abnormality analysis model for analyzing the monitoring data; outputting and analyzing a power supply monitoring result corresponding to the monitoring data through an anomaly analysis model; and when the monitoring data of the power supply monitoring result is abnormal, the power supply monitoring result is notified to a manager of the AC / DC power supply. According to the invention, timeliness and contextual information consideration in AC / DC power supply management can be improved.

Description

Technical Field

[0001] The invention relates to a remote state monitoring method and system in AC and DC power management, belonging to the technical field of power management. Background Art

[0002] In the early days of AC / DC power management, technicians usually needed to inspect and maintain power supply equipment on site. For example, in a large data center, there are many server cabinets, each equipped with AC / DC power supply equipment. The traditional way is for operation and maintenance personnel to regularly go to the computer room and use various test tools to measure the output voltage, current and other parameters of the power supply. This method is not only inefficient, but also fails to detect problems in time when sudden failures occur in the equipment. For some communication base station power supply systems located in remote areas, the long geographical distance makes the cost of on-site maintenance extremely high. In addition, if encountering bad weather and other conditions, on-site maintenance personnel may not be able to arrive in time, which will result in the power supply problem not being solved in time, affecting the normal provision of communication services.

[0003] At present, remote status monitoring has been gradually applied in AC and DC power management to replace the traditional on-site power status monitoring method. However, the existing remote status monitoring is not the most perfect AC and DC power management method. For example, when the AC and DC power generates a large amount of data, if the large amount of data generated by the AC and DC power is not quickly transmitted to the data analysis center, data delays, data congestion, etc. will occur. The AC and DC power affects the operation of a large number of electrical appliances. If the large amount of data generated by the AC and DC power is not analyzed in time to see whether there are any abnormalities, serious consequences will occur. Secondly, when determining whether the AC and DC power data is abnormal, the existing technology often sets a data threshold, compares the AC and DC power data with the data threshold, and determines whether the AC and DC power is abnormal after comparison. However, for some data that considers not only a single data point but also the contextual information of the data point, it is impossible to judge whether the data is abnormal based on the contextual information of the data point.

[0004] Therefore, the existing technologies do not adequately consider the timeliness and contextual information in AC and DC power management. Summary of the invention

[0005] The present invention provides a remote status monitoring method and system in AC and DC power management, the main purpose of which is to improve the timeliness and context information consideration in AC and DC power management.

[0006] To achieve the above object, the present invention provides a remote status monitoring method in AC / DC power management, comprising:

[0007] Querying historical fault data of the AC and DC power supplies, analyzing the fault-prone locations of the AC and DC power supplies using the historical fault data, determining the on-site monitoring points of the AC and DC power supplies according to the fault-prone locations, and determining the on-site monitoring equipment of the on-site monitoring points based on the historical fault data;

[0008] The field monitoring data at the field monitoring point is collected by the field monitoring equipment, and the field monitoring data is remotely transmitted to a preset data analysis system, wherein the field monitoring data includes voltage monitoring data, current monitoring data, frequency monitoring data and temperature monitoring data;

[0009] In the data analysis system, the field monitoring data is analyzed to obtain analyzed monitoring data, normal power signals and abnormal power signals of the AC and DC power supplies are collected, and an abnormal analysis model of the analyzed monitoring data is established based on the normal power signals and the abnormal power signals;

[0010] Inputting the analyzed monitoring data into the abnormal analysis model, so as to output the power monitoring result corresponding to the analyzed monitoring data through the abnormal analysis model, and determining whether the power monitoring result shows abnormal monitoring data;

[0011] When the monitoring data of the power supply monitoring result is abnormal, the power supply monitoring result is notified to the manager of the AC / DC power supply, so that the manager can confirm the status of the power supply monitoring result and obtain the remote status monitoring result.

[0012] Optionally, the analyzing the fault-prone location of the AC / DC power supply by using the historical fault data includes:

[0013] Query the historical fault data for recurring fault data after the fault has been repaired;

[0014] Identify a recurring fault location of the recurring fault data in the AC / DC power supply;

[0015] The recurring fault location is regarded as a prone-to-failure location.

[0016] Optionally, determining the on-site monitoring point of the AC / DC power supply through the fault-prone position includes:

[0017] Querying the prone-to-failure category at the prone-to-failure location and the number of fault categories corresponding to the prone-to-failure category;

[0018] Determining whether the number of fault categories exceeds an upper limit of the number of categories of the AC and DC power supplies;

[0019] When the number of fault categories does not exceed the upper limit of the number of categories of the AC and DC power supplies, using the fault-prone location as an on-site monitoring point of the AC and DC power supplies;

[0020] When the number of fault categories exceeds the upper limit of the number of categories of the AC and DC power supplies, determining whether the faulty values ​​corresponding to the faulty categories at the faulty positions are consistent;

[0021] When the faulty values ​​corresponding to the faulty categories at the faulty positions are consistent, retaining the random faulty positions and the inconsistent positions in the faulty positions;

[0022] The random fault position and the inconsistent position are used as on-site monitoring points of the AC / DC power supply.

[0023] Optionally, the determining the field monitoring equipment of the field monitoring point based on the historical fault data includes:

[0024] Obtaining a target fault category belonging to the on-site monitoring point in the historical fault data;

[0025] Based on the target fault category, selecting the monitoring equipment category of the on-site monitoring point;

[0026] Based on the monitoring equipment category, the on-site monitoring equipment of the on-site monitoring point is determined.

[0027] Optionally, collecting the field monitoring data at the field monitoring point by the field monitoring equipment includes:

[0028] The sampling frequency of the field monitoring equipment at the field monitoring point is calculated using the following formula:

[0029] Ω=2pd

[0030] Ω′≥2Ω

[0031] Among them, Ω′ represents the sampling frequency, Ω represents the historical simulation frequency at the on-site monitoring point, p represents the number of angle changes per rotation, and d represents the number of rotations;

[0032] Based on the sampling frequency, the field monitoring data at the field monitoring point is collected using the field monitoring equipment.

[0033] Optionally, the remotely transmitting the on-site monitoring data to a preset data analysis system includes:

[0034] The error check code of the field monitoring data is calculated using the following formula:

[0035]

[0036] Where F represents the error checking code, x i represents the ith value in the field monitoring data, n represents the number of values ​​that need to calculate the error check code once, and m max Indicates the upper limit of the value in the field monitoring data, and % indicates the remainder operation;

[0037] The field monitoring data and the error check code are spliced ​​using the following formula to obtain spliced ​​monitoring data:

[0038] X={x 1 ,x 2 ,...,x n}

[0039] X′=X+F

[0040] Among them, X′ represents the spliced ​​monitoring data, and X represents n x i A numerical sequence of , F represents an error-checking code;

[0041] Using a preset 5G communication technology and a preset 5G communication protocol to establish a data communication link between the field monitoring equipment corresponding to the field monitoring data and the data analysis system;

[0042] The splicing monitoring data is transmitted to a preset data analysis system via the data communication link.

[0043] Optionally, performing data parsing on the on-site monitoring data to obtain parsed monitoring data includes:

[0044] Distinguishing the number of data and the number of verification codes in the field monitoring data;

[0045] Based on the data number, extracting the data to be analyzed from the field monitoring data;

[0046] Performing error detection on the data to be parsed to obtain an error detection result;

[0047] extracting error check codes from the field monitoring data based on the number of check codes;

[0048] Determining whether the error detection result is consistent with the error check code;

[0049] When the error detection result is consistent with the error check code, the data to be analyzed is filtered using the following formula to obtain filtered data:

[0050]

[0051] Among them, X″′ represents the filtered data, X″ jrepresents the jth value in a certain period of time in the data to be parsed, and M represents the number of values ​​in a certain period of time in the data to be parsed;

[0052] The filtered data is normalized to obtain analytical monitoring data.

[0053] Optionally, the establishing of the abnormality analysis model for analyzing the monitoring data based on the normal power signal and the abnormal power signal includes:

[0054] Counting the number of normal types of the normal power supply signal and the number of abnormal types of the abnormal power supply signal;

[0055] Performing a data size comparison between the number of normal categories and the number of abnormal categories to obtain a size comparison result;

[0056] Using the size comparison result, the smallest number of categories is selected from the normal number of categories and the abnormal number of categories;

[0057] Acquire a target power signal corresponding to the minimum number of types in the normal power signal and the abnormal power signal;

[0058] Based on the target power signal, establishing an abnormal analysis model for analyzing the monitoring data;

[0059] Wherein, the initial anomaly analysis model includes a data processing layer, an LSTM layer and a fully connected layer;

[0060] Wherein, the data processing layer includes:

[0061] ω(Y k )=(Y k-(w-1) ,,...,Y k-1 ,Y k )

[0062] f=ω(Y 1 ,Y 2 ,...,Y k ,...Y K )

[0063] Among them, f represents the output result of the data processing layer, Y 1 ,Y 2 ,...,Y k ,...Y K represents the target power signal with a length of K, and ω() represents the selection of Y k With Y k The function of the previous w-1 target power signals.

[0064] Optionally, notifying the management personnel of the AC and DC power supplies of the power monitoring result includes:

[0065] Using a preset 5G communication technology and a preset 5G communication protocol to establish a data transmission link between a data analysis system corresponding to the power supply monitoring result and an interface display terminal of the manager;

[0066] The power monitoring result is notified to the manager of the AC and DC power supply via the data transmission link.

[0067] In order to solve the above problems, the present invention also provides a remote status monitoring system in AC / DC power management, the system comprising:

[0068] an equipment determination module, configured to query historical fault data of an AC / DC power supply, analyze a fault-prone location of the AC / DC power supply using the historical fault data, determine a field monitoring point of the AC / DC power supply through the fault-prone location, and determine a field monitoring device of the field monitoring point based on the historical fault data;

[0069] A data transmission module, used to collect the field monitoring data at the field monitoring point through the field monitoring equipment, and remotely transmit the field monitoring data to a preset data analysis system, wherein the field monitoring data includes voltage monitoring data, current monitoring data, frequency monitoring data and temperature monitoring data;

[0070] A model building module is used to perform data analysis on the field monitoring data in the data analysis system to obtain analyzed monitoring data, collect normal power supply signals and abnormal power supply signals of the AC and DC power supplies, and establish an abnormal analysis model for the analyzed monitoring data based on the normal power supply signals and the abnormal power supply signals;

[0071] A power supply monitoring module, used for inputting the analyzed monitoring data into the abnormal analysis model, so as to output the power supply monitoring result corresponding to the analyzed monitoring data through the abnormal analysis model, and determining whether the power supply monitoring result has monitoring data abnormality;

[0072] The remote monitoring module is used to notify the administrator of the AC / DC power supply of the power monitoring result when the monitoring data of the power monitoring result is abnormal, so that the administrator can confirm the status of the power monitoring result and obtain the remote status monitoring result.

[0073] Compared with the problems described in the background technology, this method uses the signal with a small sample size between the number of abnormal signals and the number of normal signals to establish an abnormal analysis model, which can reduce the amount of data analysis. If the number of samples of normal signals is too numerous, an abnormal analysis model can be established based on the number of abnormal signals, so that when the collected signal is received, it is only necessary to analyze whether the data belongs to the abnormal category. In addition, a data segmentation part is added to the abnormal analysis model, that is, each data and the first M-1 data of the data are sampled, so that each data and the context of this data can be analyzed using LSTM. Secondly, data is quickly transmitted through 5G communication technology to reduce the problem of insufficient timeliness of data transmission and data transmission congestion. Therefore, the present invention can improve the timeliness and context information considerations in AC and DC power management. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 A schematic flow chart of a remote status monitoring method in AC / DC power management provided by an embodiment of the present invention;

[0075] Figure 2 A schematic diagram of a module for implementing the remote status monitoring method in AC / DC power management provided by an embodiment of the present invention.

[0076] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0077] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0078] The embodiment of the present application provides a remote status monitoring method in AC / DC power management. The execution subject of the remote status monitoring method in AC / DC power management includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the remote status monitoring method in AC / DC power management can be executed by software or hardware installed in a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0079] Embodiment 1:

[0080] Reference Figure 1 FIG. 1 is a flow chart of a remote state monitoring method in AC / DC power management provided by an embodiment of the present invention. In this embodiment, the remote state monitoring method in AC / DC power management includes:

[0081] S1. Query historical fault data of an AC / DC power supply, analyze a fault-prone location of the AC / DC power supply using the historical fault data, determine a field monitoring point of the AC / DC power supply according to the fault-prone location, and determine a field monitoring device of the field monitoring point based on the historical fault data.

[0082] The historical fault data refers to the location and signal type of the AC / DC power supply failure recorded by the management personnel when the AC / DC power supply fails within a historical period, wherein the signal type includes voltage type, current type, temperature type, frequency type, etc.

[0083] In one embodiment of the present invention, the use of the historical fault data to analyze the prone-fault location of the AC / DC power supply includes: querying the historical fault data for recurrent fault data after fault repair; identifying the recurrent fault location of the recurrent fault data in the AC / DC power supply; and using the recurrent fault location as the prone-fault location.

[0084] The recurring fault data refers to fault data of the same location and the same signal type that occurs again after the fault is repaired.

[0085] In one embodiment of the present invention, determining the on-site monitoring point of the AC / DC power supply through the prone-to-failure position includes: querying the prone-to-failure category at the prone-to-failure position and the number of fault categories corresponding to the prone-to-failure category; judging whether the number of fault categories exceeds the upper limit of the number of categories of the AC / DC power supply; when the number of fault categories does not exceed the upper limit of the number of categories of the AC / DC power supply, using the prone-to-failure position as the on-site monitoring point of the AC / DC power supply; when the number of fault categories exceeds the upper limit of the number of categories of the AC / DC power supply, judging whether the prone-to-failure values ​​corresponding to the prone-to-failure category at the prone-to-failure position are consistent; when the prone-to-failure values ​​corresponding to the prone-to-failure category at the prone-to-failure position are consistent, retaining the random fault position and the inconsistent position in the prone-to-failure position; using the random fault position and the inconsistent position as the on-site monitoring point of the AC / DC power supply.

[0086] Among them, the number of fault categories refers to the number of fault-prone locations corresponding to a certain fault-prone category, and the fault-prone category refers to the signal type, the upper limit of the number of categories refers to the upper limit of the number of purchased equipment set in advance based on the actual budget, and the inconsistent position refers to the fault-prone location when the fault-prone value corresponding to the fault-prone category at the fault-prone location is inconsistent.

[0087] Optionally, the process of determining whether the fault-prone values ​​corresponding to the fault-prone categories at the fault-prone locations are consistent refers to determining whether the signal values ​​flowing through multiple locations with the same fault category are consistent. If they are consistent, only one of the locations can be randomly retained, because the result measured at this location is consistent with the results measured at other locations, which can also reduce the number of devices.

[0088] In one embodiment of the present invention, determining the on-site monitoring equipment of the on-site monitoring point based on the historical fault data includes: obtaining a target fault category belonging to the on-site monitoring point in the historical fault data; selecting a monitoring equipment category of the on-site monitoring point based on the target fault category; and determining the on-site monitoring equipment of the on-site monitoring point based on the monitoring equipment category.

[0089] The field monitoring equipment corresponds to a voltage type, a current type, a temperature type, a frequency type, etc., such as a current sensor.

[0090] S2. Collect the field monitoring data at the field monitoring point through the field monitoring equipment, and remotely transmit the field monitoring data to a preset data analysis system, wherein the field monitoring data includes voltage monitoring data, current monitoring data, frequency monitoring data and temperature monitoring data.

[0091] In one embodiment of the present invention, the collecting of the field monitoring data at the field monitoring point by the field monitoring device includes: calculating the sampling frequency of the field monitoring device collecting the field monitoring point by using the following formula:

[0092] Ω=2pd

[0093] Ω′≥2Ω

[0094] Among them, Ω′ represents the sampling frequency, Ω represents the historical simulation frequency at the on-site monitoring point, p represents the number of angle changes per rotation, and d represents the number of rotations;

[0095] Based on the sampling frequency, the field monitoring data at the field monitoring point is collected using the field monitoring equipment.

[0096] The data analysis system refers to a computer processor used for performing data analysis.

[0097] In one embodiment of the present invention, the remotely transmitting the field monitoring data to a preset data analysis system includes: calculating an error check code of the field monitoring data using the following formula:

[0098]

[0099] Where F represents the error checking code, x irepresents the ith value in the field monitoring data, n represents the number of values ​​that need to calculate the error check code once, and m max Indicates the upper limit of the value in the field monitoring data, and % indicates the remainder operation;

[0100] The field monitoring data and the error check code are spliced ​​using the following formula to obtain spliced ​​monitoring data:

[0101] X={x 1 ,x 2 ,...,x n}

[0102] X′=X+F

[0103] Among them, X′ represents the spliced ​​monitoring data, and X represents n x i A numerical sequence of , F represents an error-checking code;

[0104] A data communication link is established between the field monitoring equipment corresponding to the field monitoring data and the data analysis system using the preset 5G communication technology and the preset 5G communication protocol; and the spliced ​​monitoring data is transmitted to the preset data analysis system through the data communication link.

[0105] S3. In the data analysis system, the field monitoring data is analyzed to obtain analyzed monitoring data, normal power signals and abnormal power signals of the AC and DC power supplies are collected, and an abnormal analysis model for the analyzed monitoring data is established based on the normal power signals and the abnormal power signals.

[0106] In one embodiment of the present invention, the data parsing of the field monitoring data to obtain the parsed monitoring data includes: distinguishing the number of data and the number of check codes in the field monitoring data; extracting the data to be parsed in the field monitoring data based on the number of data; performing error detection on the data to be parsed to obtain an error detection result; extracting the error check code in the field monitoring data based on the number of check codes; judging whether the error detection result is consistent with the error check code; when the error detection result is consistent with the error check code, performing data filtering on the data to be parsed using the following formula to obtain filtered data:

[0107]

[0108] Among them, X″′ represents the filtered data, X″ j represents the jth value in a certain period of time in the data to be parsed, and M represents the number of values ​​in a certain period of time in the data to be parsed;

[0109] The filtered data is normalized to obtain analytical monitoring data.

[0110] The number of data refers to the length of X, the number of check codes refers to the length of F, the data to be parsed refers to X, and the error detection result refers to the error detection result obtained at the receiving end using the formula The error checking code of X is calculated, and the aforementioned process of calculating the error checking code is performed at the sending end.

[0111] Optionally, the process of normalizing the filtered data to obtain analyzed monitoring data is implemented by a normalization algorithm.

[0112] The normal power supply signal refers to a signal that has not been abnormal in a historical period, such as a current signal within a period of time, and the abnormal power supply signal refers to a signal that has been abnormal in a historical period.

[0113] In one embodiment of the present invention, the abnormal analysis model for analyzing the monitoring data is established based on the normal power signal and the abnormal power signal, including: counting the number of normal types of the normal power signal and the number of abnormal types of the abnormal power signal; performing data size comparison on the normal number of types and the abnormal number of types to obtain a size comparison result; using the size comparison result to obtain the minimum number of types from the normal number of types and the abnormal number of types; obtaining a target power signal corresponding to the minimum number of types in the normal power signal and the abnormal power signal; establishing the abnormal analysis model for analyzing the monitoring data based on the target power signal; wherein the initial abnormal analysis model includes a data processing layer, an LSTM layer and a fully connected layer; wherein the data processing layer includes:

[0114] ω(Y k )=(Y k-(w-1) ,,...,Y k-1 ,Y k )

[0115] f=ω(Y 1 ,Y 2 ,...,Y k ,...Y K )

[0116] Among them, f represents the output result of the data processing layer, Y 1 ,Y 2 ,...,Y k ,...Y K represents the target power signal with a length of K, and ω() represents the selection of Y k With Y k The function of the previous w-1 target power signals.

[0117] Optionally, the process of using the size comparison result to select the minimum number of types from the normal number of types and the abnormal number of types refers to selecting the smaller number between the normal number of types and the abnormal number of types.

[0118] Optionally, the process of establishing the abnormality analysis model for analyzing the monitoring data based on the target power signal refers to the process of optimizing the established untrained abnormality analysis model using the target power signal as training data. It should be noted that the result output by the abnormality analysis model is the category of the target power signal and others. For example, when the target power signal is an abnormal power signal, the result output by the abnormality analysis model is the abnormality category and others, and others means no abnormality.

[0119] S4. Input the analyzed monitoring data into the abnormal analysis model, so as to output the power monitoring result corresponding to the analyzed monitoring data through the abnormal analysis model, and determine whether the power monitoring result shows abnormal monitoring data.

[0120] S5. When the power monitoring result shows abnormal monitoring data, the power monitoring result is notified to the manager of the AC / DC power supply, so that the manager can confirm the status of the power monitoring result and obtain a remote status monitoring result.

[0121] In one embodiment of the present invention, notifying the manager of the AC / DC power supply of the power monitoring result includes: using a preset 5G communication technology and a preset 5G communication protocol to establish a data transmission link between a data analysis system corresponding to the power monitoring result and an interface display terminal of the manager; and notifying the manager of the AC / DC power supply of the power monitoring result through the data transmission link.

[0122] Optionally, the process of obtaining a remote status monitoring result by having the management personnel confirm the status of the power supply monitoring result refers to a process of having the management personnel inquire whether the power supply monitoring result is abnormal and whether maintenance is required.

[0123] Compared with the problems described in the background technology, this method uses the signal with a small sample size between the number of abnormal signals and the number of normal signals to establish an abnormal analysis model, which can reduce the amount of data analysis. If the number of samples of normal signals is too numerous, an abnormal analysis model can be established based on the number of abnormal signals, so that when the collected signal is received, it is only necessary to analyze whether the data belongs to the abnormal category. In addition, a data segmentation part is added to the abnormal analysis model, that is, each data and the first M-1 data of the data are sampled, so that each data and the context of this data can be analyzed using LSTM. Secondly, data is quickly transmitted through 5G communication technology to reduce the problem of insufficient timeliness of data transmission and data transmission congestion. Therefore, the present invention can improve the timeliness and context information considerations in AC and DC power management.

[0124] Embodiment 2:

[0125] like Figure 2 The figure shows a functional module diagram of a remote status monitoring system in AC and DC power management of the present invention.

[0126] The remote status monitoring system 200 in AC / DC power management of the present invention can be installed in an electronic device. According to the functions to be implemented, the remote status monitoring system in AC / DC power management can include a device determination module 201, a data transmission module 202, a model building module 203, a power monitoring module 204 and a remote monitoring module 205. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0127] In the embodiment of the present invention, the functions of each module / unit are as follows:

[0128] The device determination module 201 is used to query the historical fault data of the AC and DC power supplies, analyze the fault-prone locations of the AC and DC power supplies using the historical fault data, determine the field monitoring points of the AC and DC power supplies according to the fault-prone locations, and determine the field monitoring devices of the field monitoring points based on the historical fault data;

[0129] The data transmission module 202 is used to collect the field monitoring data at the field monitoring point through the field monitoring equipment, and remotely transmit the field monitoring data to a preset data analysis system, wherein the field monitoring data includes voltage monitoring data, current monitoring data, frequency monitoring data and temperature monitoring data;

[0130] The model building module 203 is used to perform data analysis on the field monitoring data in the data analysis system to obtain analyzed monitoring data, collect normal power signals and abnormal power signals of the AC and DC power supplies, and establish an abnormal analysis model of the analyzed monitoring data based on the normal power signals and the abnormal power signals;

[0131] The power monitoring module 204 is used to input the analyzed monitoring data into the abnormal analysis model, so as to output the power monitoring result corresponding to the analyzed monitoring data through the abnormal analysis model, and determine whether the power monitoring result has monitoring data abnormality;

[0132] The remote monitoring module 205 is used to notify the administrator of the AC / DC power supply of the power monitoring result when the monitoring data of the power monitoring result is abnormal, so that the administrator can confirm the status of the power monitoring result and obtain the remote status monitoring result.

[0133] In detail, each module in the remote status monitoring system 300 in the AC / DC power management of the embodiment of the present invention is used in the same manner as above. Figure 1 The remote status monitoring method in AC / DC power management described in the present invention is the same technical means and can produce the same technical effect, so it will not be repeated here.

[0134] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0135] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A remote status monitoring method in AC / DC power management, characterized in that: The method comprises: Querying historical fault data of the AC and DC power supplies, analyzing the fault-prone locations of the AC and DC power supplies using the historical fault data, determining the on-site monitoring points of the AC and DC power supplies according to the fault-prone locations, and determining the on-site monitoring equipment of the on-site monitoring points based on the historical fault data; The field monitoring data at the field monitoring point is collected by the field monitoring equipment, and the field monitoring data is remotely transmitted to a preset data analysis system, wherein the field monitoring data includes voltage monitoring data, current monitoring data, frequency monitoring data and temperature monitoring data; In the data analysis system, the field monitoring data is analyzed to obtain analyzed monitoring data, normal power signals and abnormal power signals of the AC and DC power supplies are collected, and an abnormal analysis model of the analyzed monitoring data is established based on the normal power signals and the abnormal power signals; Inputting the analyzed monitoring data into the abnormal analysis model, so as to output the power monitoring result corresponding to the analyzed monitoring data through the abnormal analysis model, and determining whether the power monitoring result shows abnormal monitoring data; When the monitoring data of the power supply monitoring result is abnormal, the power supply monitoring result is notified to the manager of the AC / DC power supply, so that the manager can confirm the status of the power supply monitoring result and obtain the remote status monitoring result.

2. The remote status monitoring method in AC / DC power management according to claim 1, characterized in that: The analyzing the fault-prone location of the AC / DC power supply by using the historical fault data includes: Query the historical fault data for recurring fault data after the fault has been repaired; Identify a recurring fault location of the recurring fault data in the AC / DC power supply; The recurring fault location is regarded as a prone-to-failure location.

3. The remote status monitoring method in AC / DC power management according to claim 1, characterized in that: The determining of the on-site monitoring point of the AC / DC power supply through the prone-to-failure position comprises: Querying the prone-to-failure category at the prone-to-failure location and the number of fault categories corresponding to the prone-to-failure category; Determining whether the number of fault categories exceeds an upper limit of the number of categories of the AC and DC power supplies; When the number of fault categories does not exceed the upper limit of the number of categories of the AC and DC power supplies, using the prone-to-failure location as an on-site monitoring point of the AC and DC power supplies; When the number of fault categories exceeds the upper limit of the number of categories of the AC and DC power supplies, determining whether the faulty values ​​corresponding to the faulty categories at the faulty positions are consistent; When the faulty values ​​corresponding to the faulty categories at the faulty positions are consistent, retaining the random fault positions and the inconsistent positions in the faulty positions; The random fault position and the inconsistent position are used as on-site monitoring points of the AC / DC power supply.

4. The remote status monitoring method in AC / DC power management according to claim 1, characterized in that: The determining of the field monitoring equipment of the field monitoring point based on the historical fault data includes: Obtaining a target fault category belonging to the on-site monitoring point in the historical fault data; Based on the target fault category, selecting the monitoring equipment category of the on-site monitoring point; Based on the monitoring equipment category, the on-site monitoring equipment of the on-site monitoring point is determined.

5. The remote status monitoring method in AC / DC power management according to claim 1, characterized in that: The collecting of the on-site monitoring data at the on-site monitoring point by the on-site monitoring equipment includes: The sampling frequency of the field monitoring equipment at the field monitoring point is calculated using the following formula: Ω=2pd Ω′≥2Ω Among them, Ω′ represents the sampling frequency, Ω represents the historical simulation frequency at the on-site monitoring point, p represents the number of angle changes per rotation, and d represents the number of rotations; Based on the sampling frequency, the field monitoring data at the field monitoring point is collected using the field monitoring equipment.

6. The remote status monitoring method in AC / DC power management according to claim 1, characterized in that: The remote transmission of the on-site monitoring data to a preset data analysis system includes: The error check code of the field monitoring data is calculated using the following formula: Among them, F represents the error detection code, x i represents the ith value in the field monitoring data, n represents the number of values ​​that need to calculate the error check code once, and m max Indicates the upper limit of the value in the field monitoring data, and % indicates the remainder operation; The field monitoring data and the error check code are spliced ​​using the following formula to obtain spliced ​​monitoring data: X={x1,x2,...,x n } X′=X+F Among them, X′ represents the spliced ​​monitoring data, and X represents n x i A numerical sequence of , F represents an error-checking code; Using a preset 5G communication technology and a preset 5G communication protocol to establish a data communication link between the field monitoring equipment corresponding to the field monitoring data and the data analysis system; The splicing monitoring data is transmitted to a preset data analysis system via the data communication link.

7. The remote status monitoring method in AC / DC power management according to claim 1, characterized in that: The performing data analysis on the on-site monitoring data to obtain analyzed monitoring data includes: Distinguishing the number of data and the number of verification codes in the field monitoring data; Based on the data number, extracting the data to be analyzed from the field monitoring data; Performing error detection on the data to be parsed to obtain an error detection result; extracting error check codes from the field monitoring data based on the number of check codes; Determining whether the error detection result is consistent with the error check code; When the error detection result is consistent with the error check code, the data to be analyzed is filtered using the following formula to obtain filtered data: Among them, X″′ represents the filtered data, X″ j represents the jth value in a certain period of time in the data to be parsed, and M represents the number of values ​​in a certain period of time in the data to be parsed; The filtered data is normalized to obtain analytical monitoring data.

8. The remote status monitoring method in AC / DC power management according to claim 1, characterized in that: The establishing of the abnormality analysis model for analyzing the monitoring data based on the normal power signal and the abnormal power signal includes: Counting the number of normal types of the normal power supply signal and the number of abnormal types of the abnormal power supply signal; Performing a data size comparison between the number of normal categories and the number of abnormal categories to obtain a size comparison result; Using the size comparison result, the smallest number of categories is selected from the normal number of categories and the abnormal number of categories; Acquire a target power signal corresponding to the minimum number of types in the normal power signal and the abnormal power signal; Based on the target power signal, establishing an abnormal analysis model for analyzing the monitoring data; Wherein, the initial anomaly analysis model includes a data processing layer, an LSTM layer and a fully connected layer; Wherein, the data processing layer includes: ω(Y k )=(And k-(w-1) ,,...,AND k-1 ,AND k ) f=ω(Y1,Y2,...,Y k ,...Y K ) Among them, f represents the output result of the data processing layer, Y1,Y2,...,Y k ,...Y K represents the target power signal with a length of K, and ω() represents the selection of Y k With Y k The function of the previous w-1 target power signals.

9. The remote status monitoring method in AC / DC power management according to claim 1, characterized in that: The step of notifying the AC / DC power supply management personnel of the power supply monitoring result includes: Using a preset 5G communication technology and a preset 5G communication protocol to establish a data transmission link between a data analysis system corresponding to the power supply monitoring result and an interface display terminal of the manager; The power monitoring result is notified to the manager of the AC and DC power supply via the data transmission link.

10. A remote status monitoring system in AC / DC power management, characterized in that: The system comprises: an equipment determination module, configured to query historical fault data of an AC / DC power supply, analyze a fault-prone location of the AC / DC power supply using the historical fault data, determine a field monitoring point of the AC / DC power supply through the fault-prone location, and determine a field monitoring device of the field monitoring point based on the historical fault data; A data transmission module, used to collect the field monitoring data at the field monitoring point through the field monitoring equipment, and remotely transmit the field monitoring data to a preset data analysis system, wherein the field monitoring data includes voltage monitoring data, current monitoring data, frequency monitoring data and temperature monitoring data; A model building module is used to perform data analysis on the field monitoring data in the data analysis system to obtain analyzed monitoring data, collect normal power supply signals and abnormal power supply signals of the AC and DC power supplies, and establish an abnormal analysis model for the analyzed monitoring data based on the normal power supply signals and the abnormal power supply signals; A power supply monitoring module, used for inputting the analyzed monitoring data into the abnormal analysis model, so as to output the power supply monitoring result corresponding to the analyzed monitoring data through the abnormal analysis model, and determining whether the power supply monitoring result has monitoring data abnormality; The remote monitoring module is used to notify the administrator of the AC / DC power supply of the power monitoring result when the monitoring data of the power monitoring result is abnormal, so that the administrator can confirm the status of the power monitoring result and obtain the remote status monitoring result.

Images