Electric power monitoring pre-alarm system based on cloud computing

Abstract

The invention discloses an electric power monitoring pre-alarm system based on cloud computing, and the system obtains the real-time operation data of an electric power system through a data collection module, outputs a state evaluation value at a current monitoring moment through a constructed state evaluation model, and carries out the triggering of a pre-alarm according to the state evaluation value. Real-time processing and analysis of operation data of the power system are achieved, monitoring efficiency is improved, a big data analysis technology is adopted, deep mining is conducted on the operation data of the power system, fine management and pre-alarm are achieved, meanwhile, real-time monitoring and pre-alarm of the operation state of the power system are achieved through combination of an intelligent sensor and a data processing center, and the real-time monitoring and pre-alarm of the operation state of the power system are achieved. And the safety and the reliability of the power system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power monitoring and alarm, and in particular to a power monitoring and early warning system based on cloud computing. Background Art

[0002] The power system is the infrastructure and key component of modern society, and its safe and stable operation is crucial to the national economy and people's lives. With the expansion of the scale of the power grid and the improvement of the level of intelligence, the early warning and alarm functions of the power monitoring system are becoming more and more important.

[0003] Existing power monitoring systems often rely on locally deployed early warning devices, which often have the following deficiencies:

[0004] 1. Insufficient data processing capabilities, making it difficult to process large amounts of monitoring data in real time;

[0005] 2. Lack of intelligent analysis capabilities makes it difficult to predict and warn of potential safety hazards in advance. Summary of the invention

[0006] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0007] In view of the above problems of the existing power monitoring system, the present invention is proposed.

[0008] Therefore, the technical problem solved by the present invention is to solve the problem that the existing power monitoring system has insufficient data processing capacity and is difficult to process a large amount of monitoring data in real time, and lacks intelligent analysis capabilities and is difficult to predict and warn potential safety hazards in advance.

[0009] To solve the above technical problems, the present invention provides the following technical solutions: a power monitoring and early warning system based on cloud computing, comprising the following components: cloud computing infrastructure: including cloud servers, cloud storage and cloud networks, providing cloud computing, cloud storage and cloud transmission services for the power monitoring and early warning system; data acquisition module: wirelessly connected to the cloud computing infrastructure, deployed at each monitoring point, to obtain real-time operation data of the corresponding power system, and transmit it to the cloud computing infrastructure for data calculation; early warning module: wirelessly connected to the data acquisition module, specifically including the following functions: a. early warning judgment: judging whether to trigger an alarm based on the intelligent analysis results and early warning model of the data acquisition module; b. alarm generation: generating alarm information when the alarm is triggered; c. alarm notification: notifying relevant personnel of the alarm information in real time through SMS, email and application; user interface module: providing users with an interface for accessing and managing the power monitoring and early warning system, specifically including the following functions: a. data display: displaying real-time monitoring data and early warning information; b. alarm management: users configure early warning rules and alarm methods; c. system management: users manage system settings and parameters.

[0010] As a preferred solution of the cloud computing-based power monitoring and early warning system described in the present invention, the real-time operation data obtained by the data acquisition module specifically includes: real-time monitoring of the current change curve of the power system operation within the rated time by the current sensor deployed at the total output end; real-time monitoring of the voltage at the total output end and the total input end of the power system at the current moment by the voltage sensors deployed at the total output end and the total input end; real-time monitoring of the temperature change curve of the power system within the rated time by the deployed temperature sensor; real-time monitoring of the vibration state of the power system within the rated time by the deployed vibration sensor.

[0011] As a preferred solution of the cloud computing-based power monitoring and early alarm system described in the present invention, after the data acquisition module obtains each real-time operation data, it also includes data preprocessing of each real-time operation data; wherein the data preprocessing step specifically includes: data cleaning, data conversion, data integration and data smoothing.

[0012] As a preferred solution of the cloud computing-based power monitoring and early alarm system described in the present invention, wherein: the data acquisition module performs data calculation on each real-time operation data, specifically including the following steps: S1: after obtaining each real-time operation data, the corresponding basic characteristic value is obtained; S2: constructing a state assessment model, inputting each basic characteristic value, and outputting the state assessment value at the current monitoring moment; wherein, obtaining each basic characteristic value specifically includes: A1: obtaining the current change basic characteristic value according to the current change curve, specifically including: obtaining the maximum value, minimum value, derivative maximum value, derivative minimum value, coordinate value corresponding to the derivative maximum value and coordinate value corresponding to the derivative minimum value of the current change curve; A2: obtaining the current pressure difference as the voltage basic characteristic value according to the voltage of the total output end and the total input end; A3: obtaining the temperature change basic characteristic value according to the temperature change curve, specifically including: obtaining the maximum value, minimum value, derivative maximum value and derivative minimum value of the temperature change curve; A4: obtaining the vibration basic characteristic value within the rated time according to the vibration state, specifically including: the maximum vibration amplitude and the number of vibrations.

[0013] As a preferred solution of the cloud computing-based power monitoring and early warning system described in the present invention, the state assessment model constructed is specifically:

[0014]

[0015] Wherein, δ is the state evaluation value at the current monitoring moment; K min is the minimum value of the derivative of the current variation curve; K max is the maximum value of the derivative of the current variation curve; Y max is the maximum value of the current variation curve, A; Y min is the minimum value of the current variation curve, A; Y kmin is the coordinate value corresponding to the minimum value of the derivative of the current variation curve, A; Y kmax is the coordinate value corresponding to the maximum value of the derivative of the current variation curve, A; U 差 is the current pressure difference, V; K min ' is the minimum value of the derivative of the temperature variation curve; K max ' is the maximum value of the derivative of the temperature variation curve; Y max ' is the maximum value of the temperature variation curve, ℃; Y min ' is the minimum value of the temperature variation curve, ℃; Y kmin ' is the coordinate value corresponding to the minimum value of the derivative of the temperature variation curve, °C; Y kmax' is the coordinate value corresponding to the maximum value of the derivative of the temperature variation curve, °C; α is the maximum vibration amplitude, mm; β is the number of vibrations, times; 1.307, -1.62, 1 / 2, 0.59, -1.01 and 1.530 are all adjustment constants; dx is the integral operation.

[0016] As a preferred solution of the cloud computing-based power monitoring and early warning system described in the present invention, when the early warning module issues an early warning, when the state evaluation value obtained by the data acquisition module is higher than a threshold value, the current power system is defined as abnormal and the early warning module is triggered.

[0017] As a preferred solution of the cloud computing-based power monitoring and early warning system described in the present invention, the threshold is defined as 2.94 or 2.942.

[0018] Beneficial effects of the present invention: The present invention provides an electric power monitoring and early warning system based on cloud computing, which obtains real-time operating data of the electric power system through a data acquisition module, outputs a state evaluation value at the current monitoring moment by a constructed state evaluation model, and triggers a early warning based on the state evaluation value. The present invention adopts cloud computing technology to realize real-time processing and analysis of the electric power system operating data, improves monitoring efficiency, adopts big data analysis technology to conduct in-depth mining of the electric power system operating data, realizes refined management and early warning, and at the same time, the combination of intelligent sensors and data processing centers realizes real-time monitoring and early warning of the operating status of the electric power system, thereby improving the safety and reliability of the electric power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0020] Figure 1 A system module diagram of the cloud computing-based power monitoring and early warning system provided by the present invention.

[0021] Figure 2 A flow chart of a method for the data acquisition module provided by the present invention to perform data calculation on various real-time operating data. DETAILED DESCRIPTION

[0022] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0023] Existing power monitoring systems often rely on locally deployed early warning devices, which often have the following deficiencies:

[0024] 1. Insufficient data processing capabilities, making it difficult to process large amounts of monitoring data in real time;

[0025] 2. Lack of intelligent analysis capabilities makes it difficult to predict and warn of potential safety hazards in advance.

[0026] Therefore, please refer to Figure 1 The present invention provides a power monitoring and early warning system based on cloud computing, comprising the following components:

[0027] Cloud computing infrastructure: including cloud servers, cloud storage and cloud networks, providing cloud computing, cloud storage and cloud transmission services for the power monitoring and early warning system;

[0028] Data acquisition module: wirelessly connected to the cloud computing infrastructure, deployed at each monitoring point, obtains the real-time operation data of the corresponding power system, and transmits it to the cloud computing infrastructure for data calculation;

[0029] Pre-alarm module: wireless data connection with the data acquisition module, including the following functions:

[0030] a. Early warning judgment: Determine whether to trigger an alarm based on the intelligent analysis results and early warning model of the data acquisition module;

[0031] b. Alarm generation: When an early warning is triggered, an alarm message is generated;

[0032] c. Alarm notification: Alarm information will be notified to relevant personnel in real time via SMS, email and application;

[0033] User interface module: provides users with an interface for accessing and managing the power monitoring and early warning system, including the following functions:

[0034] a. Data display: display real-time monitoring data and warning information;

[0035] b. Alarm management: users configure warning rules and alarm methods;

[0036] c. System Management: User management system settings and parameters.

[0037] It should be noted that cloud computing infrastructure is the foundation for cloud computing services, which includes key components such as cloud servers, cloud storage and cloud networks. The following is a detailed analysis of these components and how they provide support for the power monitoring and early warning system:

[0038] Cloud Server

[0039] Technical details:

[0040] 1. Virtualization technology: Cloud servers use virtualization technology to abstract physical hardware resources, allowing multiple virtual machines (VMs) to share the same physical server resources.

[0041] 2. Elastic computing: Cloud servers can dynamically allocate and expand resources, such as CPU and memory, according to demand to meet computing needs under different load conditions.

[0042] 3. High availability: Through redundant deployment and multi-node architecture, the continuous availability of services is ensured, and rapid recovery can be achieved even when a node fails.

[0043] Application in power monitoring and early warning system:

[0044] 1. Data processing: Cloud servers can process massive amounts of data from smart sensors and conduct real-time analysis and early warning.

[0045] 2. Application hosting: The application of the power monitoring system can be hosted on a cloud server for rapid deployment and easy maintenance.

[0046] Cloud Storage

[0047] Technical details:

[0048] 1. Distributed storage: Cloud storage usually adopts a distributed storage system to store data on multiple physical storage devices to improve data reliability and access speed.

[0049] 2. Data backup and recovery: Through data redundancy and backup mechanisms, the security and integrity of data are guaranteed, and data can be quickly restored when it is lost or damaged.

[0050] 3. Data encryption: Cloud storage services usually provide data encryption functions to ensure the security of data during storage and transmission.

[0051] Application in power monitoring and early warning system:

[0052] 1. Data persistence: Cloud storage is used to persist historical data and configuration information of the power monitoring system.

[0053] 2. Data sharing: Multiple users and applications can access data in cloud storage at the same time, realizing data sharing and collaboration.

[0054] Cloud Network

[0055] Technical details:

[0056] 1. Virtual network: Cloud network provides virtual network through virtualization technology, allowing users to build complex network topology.

[0057] 2. Load balancing: The cloud network has a load balancing function that can automatically allocate resources according to network traffic and load conditions to improve network performance and reliability.

[0058] 3. Network security: Cloud networks provide security measures such as firewalls and intrusion detection systems to protect the security of data transmission in the network.

[0059] Application in power monitoring and early warning system:

[0060] 1. Data transmission: The cloud network is responsible for transmitting real-time data from smart sensors to the data processing center, as well as pre-alarm information from the data processing center to the user interface.

[0061] 2. Remote access: Through the cloud network, users can remotely access the power monitoring system, monitor the system status in real time and receive pre-alarm notifications.

[0062] Comprehensive Application

[0063] In the power monitoring and early warning system, various components of the cloud computing infrastructure work together to provide the following services:

[0064] 1. Real-time data processing: The cloud server processes the real-time data collected by the smart sensors for rapid analysis and early warning.

[0065] 2. Data storage and management: Cloud storage is used to store large amounts of historical data and system configurations, while providing data backup and recovery capabilities.

[0066] 3. Data transmission and sharing: The cloud network ensures real-time transmission and remote access of data, so that early warning information can be quickly delivered to relevant decision makers.

[0067] In this way, cloud computing infrastructure provides strong support for the power monitoring and early warning system, improving the system's monitoring efficiency and early warning accuracy.

[0068] Specifically: The real-time operation data acquired by the data acquisition module specifically includes:

[0069] The current variation curve of the power system operation within the rated time is obtained by real-time monitoring through the current sensor deployed at the total output end;

[0070] The voltage sensors deployed at the total output end and the total input end are used to monitor and obtain the voltage of the total output end and the total input end of the power system at the current moment in real time;

[0071] The temperature variation curve of the power system within the rated time is obtained through real-time monitoring of the deployed temperature sensors;

[0072] The vibration status of the power system within the rated time is obtained through real-time monitoring by the deployed vibration sensors.

[0073] It should be noted that the current sensor, voltage sensor, temperature sensor and vibration sensor are all existing conventional electronic components and will not be described in detail here.

[0074] It should be noted that in order to optimize the calculation and ensure the accuracy and effectiveness of the computing power, the rated time may preferably be 6 to 12 hours.

[0075] Furthermore, after the data acquisition module acquires each real-time operation data, it also includes data preprocessing for each real-time operation data;

[0076] Among them, the data preprocessing steps specifically include: data cleaning, data conversion, data integration and data smoothing.

[0077] It should be noted that:

[0078] 1. Data cleaning:

[0079] De-duplicate: Identify and remove duplicate observations.

[0080] Handling missing values: Fill in or delete missing data. You can use the mean, median, mode, or use a model to predict missing values.

[0081] Removing outliers: Identifying and handling outliers can be done through various methods such as IQR (interquartile range), Z-score, etc.

[0082] 2. Data conversion:

[0083] Data normalization: Convert the data to a format with zero mean and unit variance, such as using Z-score normalization.

[0084] Data normalization: Scale the data to a fixed range, such as between 0 and 1, such as using Min-Max normalization.

[0085] Encode categorical data: Convert categorical variables to numerical form, for example using one-hot encoding or label encoding.

[0086] 3. Data Integration:

[0087] Merge sets: Combine data sets from different sources for unified analysis.

[0088] Data alignment: Align data from different datasets to the same time point or spatial location.

[0089] 4. Data smoothing:

[0090] Denoising: Applying filters or smoothing techniques to reduce random noise in the data.

[0091] Data interpolation: Filling in missing points in a data series to smooth the data.

[0092] For further information, see Figure 2 The data acquisition module performs data calculation on each real-time operation data, specifically including the following steps:

[0093] S1: After obtaining each real-time operation data, obtain the corresponding basic characteristic value;

[0094] S2: construct a state assessment model, input each of the basic characteristic values, and output the state assessment value at the current monitoring time;

[0095] Among them, obtaining each basic characteristic value specifically includes:

[0096] A1: Obtaining the basic characteristic value of current change according to the current change curve, specifically including: obtaining the maximum value, minimum value, maximum value of derivative, minimum value of derivative, coordinate value corresponding to the maximum value of derivative and coordinate value corresponding to the minimum value of derivative of the current change curve;

[0097] A2: Obtain the current voltage difference as the voltage basic characteristic value based on the voltage of the total output end and the total input end;

[0098] A3: Obtain the basic characteristic value of temperature change according to the temperature change curve, specifically including: obtaining the maximum value, minimum value, derivative maximum value and derivative minimum value of the temperature change curve;

[0099] A4: Obtain the basic characteristic values ​​of vibration within the rated time according to the vibration state, including: maximum vibration amplitude and vibration frequency.

[0100] Furthermore, the constructed state assessment model is as follows:

[0101]

[0102] Among them, δ is the state evaluation value at the current monitoring time; K min is the minimum value of the derivative of the current change curve; K max is the maximum value of the derivative of the current change curve; Y max is the maximum value of the current variation curve, A; Y minis the minimum value of the current variation curve, A; Y kmin A is the coordinate value corresponding to the minimum value of the derivative of the current change curve; Y kmax is the coordinate value corresponding to the maximum value of the derivative of the current change curve, A; U 差 is the current pressure difference, V; K min ' is the minimum value of the derivative of the temperature change curve; K max ' is the maximum value of the derivative of the temperature change curve; Y max ' is the maximum value of the temperature change curve, ℃; Y min ' is the minimum value of the temperature change curve, ℃; Y kmin ' is the coordinate value corresponding to the minimum value of the derivative of the temperature change curve, ℃; Y kmax ' is the coordinate value corresponding to the maximum value of the derivative of the temperature variation curve, ℃; α is the maximum vibration amplitude, mm; β is the number of vibrations, times; 1.307, -1.62, 1 / 2, 0.59, -1.01 and 1.530 are all adjustment constants; dx is the integral operation.

[0103] It should be noted that when generating a state assessment model, it is first necessary to determine the basic inclusion factors of the model. The basic inclusion factors in the present invention are creatively selected as the basic characteristic value of current change, the basic characteristic value of voltage, the basic characteristic value of temperature change and the basic characteristic value of vibration. Then, considering that the overall state at a moment is caused by multiple parameters, the basic formula of the model is determined. First, the first and second terms of the model are the degree of influence of the current. The first term specifically represents the total influence of the current, and the second term is an adjustment to the basic formula of the first term, which is reflected in the degree of difference between different reference points of the curve; the third term of the model is analogous to the first term of the model, which reflects the total influence of temperature; the fourth term of the model reflects the degree of influence of vibration. After determining each basic formula, each test data is included in the simulator, and the state assessment value under different experimental data is continuously output. The adjustment constant is continuously optimized by the robustness of each input value until the Robust curve is smooth, and the adjustment constant under the current state can be selected.

[0104] Specifically, when the pre-alarm module issues an early warning, when the state evaluation value obtained by the data acquisition module is higher than the threshold, the current power system is defined as abnormal, and the pre-alarm module is triggered.

[0105] Specifically, the threshold is defined as 2.94 or 2.942.

[0106] It should be noted that the definition of the threshold in this scheme depends on the selection of the adjustment constant in the state assessment model, and it actually has no independent meaning. When the adjustment constant changes accordingly, the corresponding threshold value is automatically adjusted. The adjustment process is verified by the vector simulator. It is only necessary to ensure that the final simulated series of results are sufficiently robust. The verification of the adjustment process is the application of existing conventional simulations, which will not be elaborated here.

[0107] It should be additionally explained that the pre-alarm module generates alarm information and notifies relevant personnel of the alarm information in real time. Relevant personnel conduct information review, warning setting and system management through the user interface module, which are all direct applications of existing conventional technologies and will not be elaborated here.

[0108] In order to verify the technical effect of this scheme, the following simulation experiment is carried out:

[0109] Test verification process:

[0110] Test preparation:

[0111] Build cloud computing infrastructure, including cloud servers, cloud storage and cloud networks.

[0112] Deploy data acquisition modules, including current sensors, voltage sensors, temperature sensors, and vibration sensors.

[0113] Ensure that all sensors can collect data in real time and transmit it wirelessly to the cloud computing infrastructure.

[0114] Data collection:

[0115] During a predetermined period of time, power system operation data from different monitoring points are collected, including current, voltage, temperature and vibration information.

[0116] Data preprocessing:

[0117] Clean, transform, integrate and smooth the collected data.

[0118] Feature extraction:

[0119] Extract basic characteristic values ​​from the processed data, including the maximum value, minimum value, derivative maximum value, etc. of the current variation curve.

[0120] State assessment model training:

[0121] Use historical data to train the state assessment model to ensure that the model can accurately reflect the state of the power system.

[0122] Real-time monitoring and early warning:

[0123] The system starts to monitor the operating status of the power system in real time and uses the status assessment model to perform real-time assessment.

[0124] When the system detects potential safety hazards, the early warning mechanism is triggered.

[0125] Test data verification:

[0126] Test data verification form: part Maximum current (A) Minimum current (A) Voltage drop (V) Maximum temperature (°C) Minimum temperature (°C) Maximum vibration amplitude Vibration times Warning results 1 150 100 5 35 30 0.2 10 No warning 2 200 120 8 40 32 0.5 15 Early Warning 3 180 110 7 38 31 0.3 12 No warning 4 250 150 10 42 34 0.7 20 Early Warning 5 220 130 9 41 33 0.4 14 No warning

[0127] The present invention provides an electric power monitoring and early warning system based on cloud computing, which obtains real-time operation data of the electric power system through a data acquisition module, outputs a state evaluation value at the current monitoring moment by a constructed state evaluation model, and triggers early warning according to the state evaluation value. The present invention adopts cloud computing technology to realize real-time processing and analysis of the operation data of the electric power system, improves monitoring efficiency, adopts big data analysis technology to conduct in-depth mining of the operation data of the electric power system, realizes refined management and early warning, and at the same time, the combination of intelligent sensors and data processing centers realizes real-time monitoring and early warning of the operation status of the electric power system, and improves the safety and reliability of the electric power system.

[0128] It should be noted that the above embodiments are only used to illustrate the technical solutions 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 solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. The power monitoring and early warning system based on cloud computing is characterized by: Includes the following components: Cloud computing infrastructure: including cloud servers, cloud storage and cloud networks, providing cloud computing, cloud storage and cloud transmission services for the power monitoring and early warning system; Data acquisition module: wirelessly connected to the cloud computing infrastructure, deployed at each monitoring point, obtains real-time operation data of the corresponding power system, and transmits it to the cloud computing infrastructure for data calculation; Pre-alarm module: wirelessly connected to the data acquisition module, specifically including the following functions: a. Warning judgment: Based on the intelligent analysis results and warning model of the data acquisition module, determine whether to trigger an alarm; b. Alarm generation: When an early warning is triggered, an alarm message is generated; c. Alarm notification: Alarm information will be notified to relevant personnel in real time via SMS, email and application; User interface module: provides users with an interface for accessing and managing the power monitoring and early warning system, including the following functions: a. Data display: displays real-time monitoring data and early warning information; b. Alarm management: users configure warning rules and alarm methods; c. System Management: User management system settings and parameters.

2. The cloud computing-based power monitoring and early warning system according to claim 1 is characterized in that: The real-time operation data acquired by the data acquisition module specifically includes: The current variation curve of the power system operation within the rated time is obtained by real-time monitoring through the current sensor deployed at the total output end; The voltage sensors deployed at the total output end and the total input end are used to monitor and obtain the voltage of the total output end and the total input end of the power system at the current moment in real time; The temperature variation curve of the power system within the rated time is obtained through real-time monitoring of the deployed temperature sensors; The vibration status of the power system within the rated time is obtained through real-time monitoring by the deployed vibration sensors.

3. The cloud computing-based power monitoring and early warning system according to claim 2 is characterized in that: After the data acquisition module acquires each real-time operation data, it also includes data preprocessing for each real-time operation data; Among them, the data preprocessing steps specifically include: data cleaning, data conversion, data integration and data smoothing.

4. The cloud computing-based power monitoring and early warning system according to claim 3 is characterized in that: The data acquisition module performs data calculation on each real-time operation data, specifically comprising the following steps: S1: After obtaining each real-time operation data, obtain the corresponding basic characteristic value; S2: construct a state assessment model, input each of the basic characteristic values, and output the state assessment value at the current monitoring time; Wherein, obtaining each of the basic characteristic values ​​specifically includes: A1: Obtaining a basic characteristic value of current change according to the current change curve, specifically including: obtaining a maximum value, a minimum value, a derivative maximum value, a derivative minimum value, a coordinate value corresponding to the derivative maximum value, and a coordinate value corresponding to the derivative minimum value of the current change curve; A2: Obtain the current voltage difference as the voltage basic characteristic value based on the voltage of the total output end and the total input end; A3: Obtaining a basic characteristic value of temperature change according to the temperature change curve, specifically including: obtaining a maximum value, a minimum value, a derivative maximum value, and a derivative minimum value of the temperature change curve; A4: Obtain the basic characteristic values ​​of vibration within the rated time according to the vibration state, including: maximum vibration amplitude and vibration frequency.

5. The cloud computing-based power monitoring and early warning system according to claim 4 is characterized in that: The state assessment model constructed is specifically: ； Wherein, δ is the state evaluation value at the current monitoring moment; K min is the minimum value of the derivative of the current variation curve; K max is the maximum value of the derivative of the current variation curve; Y max is the maximum value of the current variation curve, A; Y min is the minimum value of the current variation curve, A; Y kmin is the coordinate value corresponding to the minimum value of the derivative of the current variation curve, A; Y kmax is the coordinate value corresponding to the maximum value of the derivative of the current variation curve, A; U 差 is the current pressure difference, V; K min ' is the minimum value of the derivative of the temperature variation curve; K max ' is the maximum value of the derivative of the temperature variation curve; Y max ' is the maximum value of the temperature variation curve, ℃; Y min ' is the minimum value of the temperature variation curve, ℃; Y kmin ' is the coordinate value corresponding to the minimum value of the derivative of the temperature variation curve, °C; Y kmax ' is the coordinate value corresponding to the maximum value of the derivative of the temperature variation curve, °C; α is the maximum vibration amplitude, mm; β is the number of vibrations, times; 1.307, -1.62, 1 / 2, 0.59, -1.01 and 1.530 are all adjustment constants; dx is the integral operation.

6. The cloud computing-based power monitoring and early warning system according to claim 5 is characterized in that: When the pre-alarm module issues an early warning, when the state evaluation value acquired by the data acquisition module is higher than a threshold value, the current power system is defined as abnormal, and the pre-alarm module is triggered.

7. The cloud computing-based power monitoring and early warning system according to claim 6 is characterized in that: The threshold is defined as 2.94 or 2.942.

Images