Power alarm on-line monitoring method and system based on Internet of Things

Abstract

The invention relates to a power alarm on-line monitoring method and system based on the Internet of Things. The method comprises the following steps: the power supply module converts 220V alternating current into 5V direct current and supplies power to the monitoring module and the communication module; the monitoring module collects parameters of the power equipment, and predicts the fault condition of the power equipment through historical data and a machine learning model; parameters collected in real time are compared with preset alarm data, whether power failures occur or not is judged, and the power failures and prediction conditions are uploaded to a central server through a communication module; if the fault occurs or the prediction condition is close to the fault occurrence time, the central server allocates corresponding workers to perform maintenance; historical data of the equipment are processed through a time sequence model such as LSTM, and the system can predict the possibility of equipment failure in advance. When the fault probability exceeds a preset threshold value, the system gives out early warning in advance, and a worker is allowed to carry out preventive maintenance before the fault occurs.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power alarm, and in particular to an online monitoring method and system for electric power alarm based on the Internet of Things. Background Art

[0002] At present, there are two main types of power equipment fault monitoring technology: offline monitoring and online monitoring. Offline monitoring refers to the detection carried out when the power equipment is shut down or powered off. Its advantage is that the detection results are accurate and reliable, but its disadvantage is that the fault cannot be discovered in time, and it will affect the operating efficiency and life of the power equipment. Online monitoring refers to the detection carried out when the power equipment is operating normally or under load. Its advantage is that it can reflect the operating status of the power equipment in real time and discover faults and hidden dangers in time. The current fault alarm system, such as GSM communication, can only alarm after the equipment fails. There is a lack of active prediction of the equipment's operating status, resulting in delayed maintenance and failure to prevent potential problems before the failure. At the same time, there is a lack of intelligence in the scheduling of maintenance personnel after the failure. Usually relying on manual assignment, it may lead to unreasonable staff scheduling and long response time.

[0003] To this end, the present invention proposes an Internet of Things-based power alarm online monitoring method and system. Summary of the invention

[0004] The present invention aims at the technical problems existing in the prior art and provides an Internet of Things-based power alarm online monitoring method and system.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: an online monitoring method and system for power alarm based on the Internet of Things;

[0006] On the one hand, an online monitoring system for power alarm based on the Internet of Things is provided, wherein the online monitoring system comprises a power module, a DC step-down circuit, a lithium battery charging module, a monitoring module, a communication module and a central server;

[0007] The power module is connected to the lithium battery charging module and the monitoring module respectively, and at the same time powers the communication module through the DC step-down circuit;

[0008] The communication module is connected to the central server through the communication network and receives the monitoring information of the monitoring module at the same time;

[0009] The power module and the lithium battery charging module are connected to the communication module respectively. When the power module cannot output voltage, it is converted into the lithium battery charging module to supply power to the communication module.

[0010] Furthermore, in the online monitoring system for electric power alarm based on the Internet of Things, the monitoring system also includes an alarm receiving terminal carried by the staff, the central server transmits the alarm information to the alarm receiving terminal, and designates staff to maintain the alarm information.

[0011] On the other hand, a method for online monitoring of electric power alarm based on the Internet of Things is provided, which is applied to any one of the online monitoring systems for electric power alarm based on the Internet of Things, and the online monitoring method comprises the following steps:

[0012] S1: The power module converts 220V AC power into 5V DC power and supplies power to the monitoring module and communication module;

[0013] S2: The monitoring module collects the parameters of the power equipment and predicts the failure of the power equipment through historical data and machine learning models;

[0014] S3: Compare the parameters collected in real time with the preset alarm data to determine whether a power failure occurs, and upload the predicted situation to the central server through the communication module;

[0015] S4: If a failure occurs or is predicted to occur close to the time of failure, the central server dispatches the corresponding staff for maintenance.

[0016] Furthermore, in the method for online monitoring of power alarm based on the Internet of Things, the monitoring module implements the step of collecting parameters of power equipment, including:

[0017] Collect the voltage, current, temperature and humidity of the power equipment, process the collected data according to the time series, and obtain the data vector according to the time series;

[0018] X(t)=[V(t),I(t),T(t),H(t)] t ;

[0019] Among them, X(t) collects all parameters in time t, including voltage V, current I, temperature T and humidity H;

[0020] Compare the parameters collected in real time with the preset alarm data:

[0021]

[0022] status is the alarm information, V max and V min They are the preset maximum voltage and minimum voltage respectively.

[0023] Furthermore, in the method for online monitoring of power alarm based on the Internet of Things, the step of predicting the fault condition of power equipment through historical data and machine learning model includes: using LSTM model to process time series data:

[0024] h t =LSTM(X t ,h t-1 ,c t-1 );

[0025] Among them, h t is the hidden state of the current data, h t-1 is the hidden state of the data at the previous moment, c t-1 is the memory unit of the previous moment;

[0026] The fault prediction formula is:

[0027] P(t)=f LSTM X(t);

[0028] Where X(t) is the input parameter at the current time t.

[0029] Furthermore, the method for online monitoring of power alarm based on the Internet of Things is to calculate the specific fault occurrence time t j , through the failure probability curve P f Perform interpolation or fitting to find the time point when the fault threshold P(j) is reached;

[0030] Assuming that the probability of failure increases approximately linearly with time, the formula for predicting the time of failure is:

[0031]

[0032] Among them, P(t) is the failure probability at the current time t, It is the rate of change of failure probability over time, that is, the failure growth rate, which is calculated through the failure probability curve formed by historical data.

[0033] Furthermore, in the method for online monitoring of power alarm based on the Internet of Things, in the step S4, the staff are reasonably allocated to maintain the faulty equipment through a scheduling algorithm, and the specific steps are as follows:

[0034] Obtaining task information: The central server obtains new fault information, including fault location and urgency;

[0035] Calculate worker priority: Calculate the worker's priority score by taking into account the worker's location, current workload, and the urgency of the fault;

[0036] Select the best staff: select the staff with the highest priority according to the priority score and assign tasks;

[0037] Update Worker Capacity: Increases the capacity of the worker assigned to the task.

[0038] Furthermore, in the method for online monitoring of electric power alarm based on the Internet of Things, the current workload is calculated using a workload model:

[0039] For each worker, maintain its current number of tasks A i , and set the maximum daily task volume A max ;

[0040] When A i ≥A max , the staff is considered to be fully loaded and unable to receive new assignments;

[0041] Current workload of staff:

[0042]

[0043] K i is the load index of worker i, ranging from [0-1].

[0044] Furthermore, in the method for online monitoring of power alarm based on the Internet of Things, the distance and time estimation between the position of the staff and the fault location includes: based on the current position P of the staff i and the fault location P, estimate the time required for the staff to reach the fault location, and the distance is calculated as:

[0045]

[0046] Where (x i ,y i ) is the coordinate of worker i, (x, y) is the coordinate of the fault location, d i is the distance from worker i to the fault location;

[0047] The calculation of the arrival time is:

[0048]

[0049] Where v is the average velocity.

[0050] Furthermore, in the method for online monitoring of power alarms based on the Internet of Things, the location of the staff, the current workload and the urgency of the fault are comprehensively considered to calculate the priority score of the staff, including:

[0051]

[0052] Among them, w1, w2 and w3 are weight coefficients, which control the impact of workload, distance and fault urgency in scheduling respectively, and E is the urgency of the fault; as the faults and maintenance tasks change, the load and priority of the staff will be updated in real time.

[0053] The beneficial effects of the present invention are:

[0054] 1. By processing the historical data of the equipment through time series models such as LSTM, the system can predict the possibility of equipment failure in advance. When the probability of failure exceeds the preset threshold, the system will issue an early warning, allowing staff to perform preventive maintenance before the failure occurs; the calculation of the failure probability growth rate is introduced, combined with the historical operation data of the equipment, to predict the specific time of future failures, further improving the efficiency and accuracy of maintenance;

[0055] 2. When the main power supply is cut off, the system automatically switches to lithium battery power supply to ensure that the communication module and monitoring module continue to operate and that the device status information can be uploaded to the central server in real time; when the power is restored, the system can automatically switch back to the main power supply and charge the backup battery at the same time. This design ensures the system's ability to continue operating in the event of a power outage, greatly improving the reliability of the monitoring system;

[0056] 3. Based on the staff's current workload, geographical location and the urgency of the fault, the system can automatically calculate the priority of each staff member and assign tasks reasonably. Through this intelligent scheduling algorithm, the system ensures that the most suitable person can handle the fault in the shortest time. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a flow chart of the method for online monitoring of electric power alarm based on the Internet of Things of the present invention;

[0058] Figure 2 It is a system schematic diagram of the electric power alarm online monitoring system based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0060] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0061] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0062] Example 1

[0063] Provided is an Internet of Things-based power alarm online monitoring system, the online monitoring system comprising a power module, a DC step-down circuit, a lithium battery charging module, a monitoring module, a communication module and a central server;

[0064] The power module is connected to the lithium battery charging module and the monitoring module respectively, and at the same time powers the communication module through the DC step-down circuit;

[0065] The communication module is connected to the central server through the communication network and receives the monitoring information of the monitoring module at the same time;

[0066] The power module and the lithium battery charging module are connected to the communication module respectively. When the power module cannot output voltage, it is converted into the lithium battery charging module to supply power to the communication module.

[0067] The monitoring system also includes an alarm receiving terminal carried by a staff member. The central server transmits the alarm information to the alarm receiving terminal and designates a staff member to maintain the alarm information.

[0068] In this embodiment, the system consists of:

[0069] Power module: converts 220V AC power into 5V DC power to supply power to each module of the system.

[0070] DC step-down circuit: regulates and stabilizes 5V DC power to power the system's communication module.

[0071] Lithium battery charging module: charges the backup battery. When the main power fails, it automatically switches to the backup battery to ensure continuous operation of the system.

[0072] Monitoring module: real-time monitoring of the power parameters of the equipment, such as voltage, current, etc. It determines whether the power supply is normal by collecting the 5V voltage status and transmits the information to the communication module.

[0073] Communication module: Maintains connection with the central server through the IoT network (LTE4G), receives feedback from the monitoring module, and uploads it to the central server.

[0074] Central server: Receives device status information and notifies the corresponding staff to handle when a failure occurs. The server will save all device records for users to view at any time.

[0075] Operation process:

[0076] Power management: When the 220V power supply is normal, the power module converts the power into 5V and powers the device. At this time, the lithium battery charging module charges the backup battery.

[0077] Data collection: The monitoring module continuously collects the voltage status of the equipment (such as 5V). If the voltage disappears, it means that the power supply is interrupted, and the monitoring module immediately feeds back the information to the communication module.

[0078] Alarm processing: The communication module transmits the fault information to the central server through the Internet of Things network, and the server further transmits the alarm information to the designated staff’s mobile phone.

[0079] Backup power switching: If the power module cannot provide 5V voltage, the system will automatically switch to lithium battery power supply to ensure that the communication module continues to work and the device can continue to monitor.

[0080] Maintenance notification: The central server regularly monitors the status of the device (sending status requests to the device every 3 seconds). If the device fails to respond, the server regards this as an abnormal device status and notifies the staff to check.

[0081] Example: Assume that in an industrial park, there are multiple distributed power equipment (such as transformers and distribution cabinets) whose power supply status needs to be monitored in real time. In order to effectively monitor the operating status of these devices and avoid manual inspections that consume a lot of manpower and material resources, the management decides to install an online power alarm monitoring system based on the Internet of Things.

[0082] Power module: Each power device is equipped with a power module to convert the 220V AC power input into 5V DC power to supply the monitoring module and communication module. When the device is in normal power supply state, the power module charges the built-in lithium battery of the device.

[0083] Monitoring module: The monitoring module collects the voltage status of the power equipment in real time through sensors to determine whether the equipment is in a normal power supply state. For example, when the power supply is normal, the monitoring module feedbacks 5V voltage; when the power is interrupted, the monitoring module detects that the voltage disappears and sends the information to the communication module.

[0084] Communication module: The communication module is connected to the central server via the LTE4G network and receives power supply information from the monitoring module. When a power outage is detected, the communication module will automatically upload the information to the central server. Even if there is a problem with the power module and the device is powered off, the lithium battery power supply will ensure that the communication module continues to work and monitoring will not be interrupted.

[0085] Central server: The central server receives all real-time power supply information from the power equipment in the park and stores the information in the server. When a device has a power supply problem, the server will immediately send the fault information to the designated staff's mobile phone. At this time, the staff can rush to the site to perform equipment maintenance as soon as possible, avoiding serious accidents.

[0086] Practical application: One day, the power supply of a power distribution cabinet in the park failed. The monitoring module detected that the 5V voltage disappeared, and the communication module immediately uploaded this information to the central server through the LTE network. After receiving the information, the server immediately sent an alarm notification to the maintenance personnel responsible for the area. The maintenance personnel received the alarm through their mobile phones and went to the site to deal with the fault, avoiding further damage to the power equipment.

[0087] Through this system, the power equipment in the park can be monitored in real time around the clock without the need for manual inspections, greatly improving maintenance efficiency and the safety of equipment management.

[0088] Through the Internet of Things and 4GLTE network, the system can monitor power equipment in real time to ensure that faults are discovered as soon as possible; the system can automatically notify maintenance personnel when equipment fails, reducing the cost of manual inspections and improving operation and maintenance efficiency; even if the equipment loses power, the backup battery can ensure the continuous operation of the system and avoid monitoring interruptions.

[0089] Example 2

[0090] Provided is an Internet of Things-based power alarm online monitoring method, which is applied to any of the Internet of Things-based power alarm online monitoring systems, and the online monitoring method comprises the following steps:

[0091] S1: The power module converts 220V AC power into 5V DC power and supplies power to the monitoring module and communication module;

[0092] S2: The monitoring module collects the parameters of the power equipment and predicts the failure of the power equipment through historical data and machine learning models;

[0093] S3: Compare the parameters collected in real time with the preset alarm data to determine whether a power failure occurs, and upload the predicted situation to the central server through the communication module;

[0094] S4: If a failure occurs or is predicted to occur close to the time of failure, the central server dispatches the corresponding staff for maintenance.

[0095] Specifically, the monitoring module implements the step of collecting parameters of the power equipment including:

[0096] Collect the voltage, current, temperature and humidity of the power equipment, process the collected data according to the time series, and obtain the data vector according to the time series;

[0097] X(t)=[V(t),I(t),T(t),H(t)] t ;

[0098] Among them, X(t) collects all parameters in time t, including voltage V, current I, temperature T and humidity H;

[0099] Compare the parameters collected in real time with the preset alarm data:

[0100]

[0101] status is the alarm information, V max and V min They are the preset maximum voltage and minimum voltage respectively.

[0102] Specifically, the step of predicting the fault condition of the power equipment by using historical data and machine learning models includes: using an LSTM model to process time series data:

[0103] h t =LSTM(X t ,h t-1 ,c t-1 );

[0104] Among them, h t is the hidden state of the current data, h t-1 is the hidden state of the data at the previous moment, c t-1 is the memory unit of the previous moment;

[0105] The fault prediction formula is:

[0106] P(t)=f LSTM X(t);

[0107] Where X(t) is the input parameter at the current time t.

[0108] Specifically, in order to calculate the specific fault occurrence time t j , through the failure probability curve P f Perform interpolation or fitting to find the time point when the fault threshold P(j) is reached;

[0109] Assuming that the probability of failure increases approximately linearly with time, the formula for predicting the time of failure is:

[0110]

[0111] Among them, P(t) is the failure probability at the current time t, It is the rate of change of failure probability over time, that is, the failure growth rate, which is calculated through the failure probability curve formed by historical data.

[0112] As an example, in the above industrial park example, the monitoring module of each device will regularly collect key operating parameters such as voltage, current, temperature and humidity; the system collects data every 1 minute; assuming that the current time is t, the data collected by the monitoring module is:

[0113] Voltage V = 220 V, current I = 10 A, temperature T = 45 ° C and humidity H = 60%;

[0114] These parameters form the time series vector collected at time t:

[0115] X(t)=[V(t),I(t),T(t),H(t)] t =[220,10,45,60] t

[0116] The system will store and transmit this data to the central server for further fault prediction.

[0117] The system will compare the parameters collected in real time with the preset thresholds. For example, the preset voltage alarm range is set as:

[0118] V max =240V;

[0119] V min =200V;

[0120] The real-time collected data V = 220V is within the normal range, so no alarm is triggered at this time. If the voltage is lower than 200V or higher than 240V, the system will trigger an alarm and upload the data to the server.

[0121] Assume that the park wants to predict whether the transformer equipment will fail in the future. Historical data shows that when the voltage fluctuates greatly, the probability of equipment failure increases. In order to predict the future operating status of the equipment, the system uses the LSTM model. The LSTM model can process time series data, memorize the changing trends of the historical parameters of power equipment, and predict whether a failure may occur in the future based on these trends:

[0122] h t =LSTM(X t ,h t-1 ,c t-1 );

[0123] Among them, h t is the hidden state of the current data, h t-1 is the hidden state of the data at the previous moment, c t-1 is the memory unit of the previous moment;

[0124] The fault prediction formula is:

[0125] P(t)=f LSTM X(t);

[0126] Where X(t) is the input parameter at the current time t.

[0127] Specifically, in order to calculate the specific fault occurrence time t j , through the failure probability curve P f Perform interpolation or fitting to find the time point when the fault threshold P(j) is reached;

[0128] Assuming that the probability of failure increases approximately linearly with time, the formula for predicting the time of failure is:

[0129]

[0130] Among them, P(t) is the failure probability at the current time t, It is the rate of change of failure probability over time, that is, the failure growth rate, which is calculated through the failure probability curve formed by historical data.

[0131] For example, assuming that the failure probability predicted by tLSTM at the current moment is 0.6, the growth rate of the failure probability is The time when the fault occurred That is to say, the system predicts that the equipment may fail in 4 hours, and the system will notify the maintenance personnel in advance to conduct inspection and maintenance; this monitoring method collects equipment operating parameters in real time and combines the LSTM machine learning model to predict future failures, which can help discover potential problems in advance and avoid losses caused by sudden failures; the system can not only determine whether an alarm is triggered at present, but also predict the time of future failures based on historical data and trends, so as to arrange maintenance in time.

[0132] Specifically, in step S4, the staff is reasonably allocated to maintain the faulty equipment through the scheduling algorithm. The specific steps are as follows:

[0133] Obtaining task information: The central server obtains new fault information, including fault location and urgency;

[0134] Calculate worker priority: Calculate the worker's priority score by taking into account the worker's location, current workload, and the urgency of the fault;

[0135] Select the best staff: select the staff with the highest priority according to the priority score and assign tasks;

[0136] Update Worker Capacity: Increases the capacity of the worker assigned to the task.

[0137] The current workload is calculated using the workload model:

[0138] For each worker, maintain its current number of tasks A i , and set the maximum daily task volume A max ;

[0139] When A i ≥A max , the staff is considered to be fully loaded and unable to receive new assignments;

[0140] Current workload of staff:

[0141]

[0142] K i is the load index of worker i, ranging from [0-1].

[0143] The distance and time estimation between the position of the worker and the fault location includes: based on the current position P of the worker i and the fault location P, estimate the time required for the staff to reach the fault location, and the distance is calculated as:

[0144]

[0145] Where (x i ,y i ) is the coordinate of worker i, (x, y) is the coordinate of the fault location, d i is the distance from worker i to the fault location;

[0146] The calculation of the arrival time is:

[0147]

[0148] Where v is the average velocity.

[0149] The worker's location, current workload, and urgency of the fault are comprehensively considered to calculate the worker's priority score, including:

[0150]

[0151] Among them, w1, w2 and w3 are weight coefficients, which control the impact of workload, distance and fault urgency in scheduling respectively, and E is the urgency of the fault; as the faults and maintenance tasks change, the load and priority of the staff will be updated in real time.

[0152] As an example, in the above industrial park example, the central server receives fault warning information of a device located in the industrial park; the fault information includes: device location, fault type (high priority, involving important power supply equipment), fault urgency (E=0.9, indicating that it is very urgent and needs to be handled immediately);

[0153] Calculate the priority of the workers. Assume that the company has three maintenance workers. Their locations, current workloads, and distances to the fault locations are as follows:

[0154]

[0155] The calculation of a worker's priority score includes:

[0156]

[0157] Among them, the weight coefficients are w1=0.4, w2=0.3 and w3=0.3 respectively; calculate the priority score:

[0158] For Worker 1:

[0159]

[0160] For Worker 2:

[0161]

[0162] For Worker 3:

[0163]

[0164] According to the calculation results, worker 3 has the highest priority score, so the system assigns the fault task to worker 3 for processing. Through this scheduling algorithm, the power company can quickly dispatch the most suitable worker when a fault occurs, avoiding the randomness of manual arrangements and ensuring maximum work efficiency. For example, if a worker's load is close to full load, the scheduling algorithm will automatically assign the task to other workers with lower loads. This algorithm also takes into account the distance between the personnel and the fault location, thereby minimizing the response time.

[0165] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0166] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An online monitoring system for power alarm based on the Internet of Things, characterized in that: The online monitoring system includes a power module, a DC step-down circuit, a lithium battery charging module, a monitoring module, a communication module and a central server; The power module is connected to the lithium battery charging module and the monitoring module respectively, and at the same time powers the communication module through the DC step-down circuit; The communication module is connected to the central server through the communication network and receives the monitoring information of the monitoring module at the same time; The power module and the lithium battery charging module are connected to the communication module respectively. When the power module cannot output voltage, it is converted into the lithium battery charging module to supply power to the communication module.

2. According to the Internet of Things-based power alarm online monitoring system according to claim 1, it is characterized in that: The monitoring system also includes an alarm receiving terminal carried by a staff member. The central server transmits the alarm information to the alarm receiving terminal and designates a staff member to maintain the alarm information.

3. A method for online monitoring of power alarm based on the Internet of Things, characterized in that: Applied to the Internet of Things-based power alarm online monitoring system as described in any one of claims 1-2, the online monitoring method comprises the following steps: S1: The power module converts 220V AC power into 5V DC power and supplies power to the monitoring module and communication module; S2: The monitoring module collects the parameters of the power equipment and predicts the failure of the power equipment through historical data and machine learning models; S3: Compare the parameters collected in real time with the preset alarm data to determine whether a power failure occurs, and upload the predicted situation to the central server through the communication module; S4: If a failure occurs or is predicted to occur close to the time of failure, the central server dispatches the corresponding staff for maintenance.

4. The method for online monitoring of power alarm based on the Internet of Things according to claim 3 is characterized in that: The monitoring module implements the step of collecting parameters of the power equipment including: Collect the voltage, current, temperature and humidity of the power equipment, process the collected data according to the time series, and obtain the data vector according to the time series; X(t)=[V(t),I(t),T(t),H(t)] t ; Among them, X(t) collects all parameters in time t, including voltage V, current I, temperature T and humidity H; Compare the parameters collected in real time with the preset alarm data: status is the alarm information, V max and V min They are the preset maximum voltage and minimum voltage respectively.

5. The method for online monitoring of electric power alarm based on the Internet of Things according to claim 3 is characterized in that: The step of predicting the fault condition of the power equipment by using historical data and machine learning model includes: LSTM model to process time series data: h t =LSTM(X t ,h t-1 ,c t-1 ); Among them, h t is the hidden state of the current data, h t-1 is the hidden state of the data at the previous moment, c t-1 is the memory unit of the previous moment; The fault prediction formula is: P(t)=f LSTM X(t); Where X(t) is the input parameter at the current time t.

6. The method for online monitoring of power alarm based on the Internet of Things according to claim 5 is characterized in that: In order to calculate the specific failure occurrence time t j , through the failure probability curve P f Perform interpolation or fitting to find the time point when the fault threshold P(j) is reached; Assuming that the probability of failure increases approximately linearly with time, the formula for predicting the time of failure is: Among them, P(t) is the failure probability at the current time t, It is the rate of change of failure probability over time, that is, the failure growth rate, which is calculated through the failure probability curve formed by historical data.

7. The method for online monitoring of electric power alarm based on the Internet of Things according to claim 3 is characterized in that: In the step S4, the staff is reasonably allocated to maintain the faulty equipment through the scheduling algorithm. The specific steps are as follows: Obtaining task information: The central server obtains new fault information, including fault location and urgency; Calculate worker priority: Calculate the worker's priority score by taking into account the worker's location, current workload, and the urgency of the fault; Select the best staff: select the staff with the highest priority according to the priority score and assign tasks; Update Worker Capacity: Increases the capacity of the worker assigned to the task.

8. The method for online monitoring of electric power alarm based on Internet of Things according to claim 7 is characterized in that: The current workload is calculated using the workload model: For each worker, maintain its current number of tasks A i , and set the maximum daily task volume A max ; When A i ≥A max , the staff is considered to be at capacity and unable to receive new assignments; Current workload of staff: K i is the load index of worker i, ranging from [0-1].

9. The method for online monitoring of electric power alarm based on Internet of Things according to claim 8 is characterized in that: The distance and time estimation between the position of the worker and the fault location includes: based on the current position P of the worker i and the fault location P, estimate the time required for the staff to reach the fault location, and the distance is calculated as: Where (x i ,y i ) is the coordinate of worker i, (x, y) is the coordinate of the fault location, d i is the distance from worker i to the fault location; The calculation of the arrival time is: Where v is the average velocity.

10. The method for online monitoring of electric power alarm based on Internet of Things according to claim 9, characterized in that: The worker's location, current workload, and urgency of the fault are comprehensively considered to calculate the worker's priority score, including: Among them, w1, w2 and w3 are weight coefficients, which control the impact of workload, distance and fault urgency in scheduling respectively, and E is the urgency of the fault; as the faults and maintenance tasks change, the load and priority of the staff will be updated in real time.

Images