Automatic operation and maintenance monitoring method and system for Internet of Things monitoring equipment

Abstract

The invention discloses an automatic operation and maintenance monitoring method and system for Internet of Things monitoring equipment, and belongs to the technical field of operation and maintenance monitoring systems. The method comprises the following steps: S1, building an integrated operation and maintenance platform of the Internet of Things, and accessing a plurality of pieces of equipment which need to be subjected to operation and maintenance monitoring; s2, performing anomaly identification on the reporting frequency and the real-time performance of the equipment, and judging the working condition of the equipment; and S3, carrying out abnormity identification on data newly reported by the equipment. The system part comprises an Internet of Things integrated operation and maintenance platform and a plurality of devices connected with the Internet of Things integrated operation and maintenance platform. According to the method, the integrated operation and maintenance platform of the Internet of Things equipment is established, the data reporting frequency and real-time performance of the equipment are monitored, secondary confirmation is carried out on the working condition of the equipment, meanwhile, a numerical monitoring integrated model is established, abnormal values are identified based on historical data, integrated equipment abnormity alarm information is provided, manual operation and maintenance are replaced by automatic operation and maintenance, and the operation efficiency of the equipment is improved. And the problems of low efficiency and high cost caused by manual operation and maintenance are avoided.

Description

Technical Field

[0001] The present invention belongs to the technical field of operation and maintenance monitoring systems, and in particular relates to an automated operation and maintenance monitoring method and system for Internet of Things monitoring equipment. Background Art

[0002] With the construction of water conservancy informatization, the density and number of Internet of Things monitoring equipment are increasing, and comprehensive, real-time, accurate and reliable data are further constructed, providing support for the construction of a smart water conservancy system with forecasting, early warning, rehearsal and emergency plan (referred to as "four forecasts") functions, effectively improving the early warning foresight and emergency response capabilities.

[0003] As the number of monitoring devices continues to increase, the difficulty of automated monitoring of equipment conditions has also increased. At the same time, the surge in the amount of monitoring data has also posed a challenge to the assurance of data quality, making it more difficult to identify outliers in large amounts of data. These problems not only affect the real-time and accuracy of monitoring data, but may also have a negative impact on early warning systems and emergency response mechanisms. At present, operation and maintenance monitoring mainly relies on manual observation. This practice has not yet formed an efficient operation and maintenance monitoring system, which is not only inefficient but also increases costs. Summary of the invention

[0004] The present invention proposes an automated operation and maintenance monitoring method and system for Internet of Things monitoring equipment. By building an integrated operation and maintenance platform for Internet of Things equipment, the frequency and real-time reporting of equipment data are monitored, and the equipment working condition is reconfirmed. At the same time, an integrated numerical monitoring model is built to identify abnormal values ​​based on historical data, and provide integrated equipment abnormality alarm information. Automated operation and maintenance replaces manual operation and maintenance to solve the problems of low efficiency and high cost caused by manual operation and maintenance.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is:

[0006] An automated operation and maintenance monitoring method for Internet of Things monitoring equipment comprises the following steps:

[0007] S1. Build an integrated IoT operation and maintenance platform and connect multiple devices that require operation and maintenance monitoring;

[0008] S2. Use the IoT integrated operation and maintenance platform to identify abnormalities in the reporting frequency and real-time performance of the equipment and determine the working condition of the equipment;

[0009] S3. The IoT integrated operation and maintenance platform uses historical data as sample data to construct a univariate polynomial regression model and a multivariate linear regression model. It also uses the univariate polynomial regression model and the multivariate linear regression model to identify anomalies in the newly reported data of the device. If an abnormality is found in the data, the IoT integrated operation and maintenance platform will execute an alarm action.

[0010] Furthermore, in step S2, the method for identifying abnormal reporting frequency includes the following steps:

[0011] S201. The operation and maintenance personnel configure frequency anomaly identification rules, including reporting frequency and time threshold;

[0012] S202, the device is connected to the IoT integrated operation and maintenance platform through a long connection;

[0013] S203, the IoT integrated operation and maintenance platform detects the list of devices that have exceeded the time threshold and have not reported data through a scheduled task;

[0014] S204, respectively determining whether the long connection status of each device in the device list is alive;

[0015] S205. If the device is no longer in the long connection state, prompt that the device is offline abnormal. If the device is still in the long connection state, continue to execute;

[0016] S206. The IoT integrated operation and maintenance platform actively sends a data query request to the device that survived the long connection state in the previous step, and retries up to three times;

[0017] S207. If the IoT integrated operation and maintenance platform does not receive a data response from the device for three times, it is determined to be a device failure and an abnormal prompt is given; if a data response from the device is received, it is not considered an abnormality and a prompt is given for network fluctuation.

[0018] Furthermore, in step S2, the method for real-time anomaly identification includes the following steps:

[0019] S211, Operation and maintenance personnel configure equipment reporting frequency rules;

[0020] S212, the device is connected to the IoT integrated operation and maintenance platform through a long connection;

[0021] S213, the IoT integrated operation and maintenance platform detects the list of devices that have exceeded the time threshold and have not reported data through scheduled tasks;

[0022] S214, respectively determining whether the long connection status of each device in the device list is alive;

[0023] S215. If the device is no longer in the long connection state, a prompt is given that the device is offline abnormal; if the device is still in the long connection state, the execution continues;

[0024] S216, the IoT integrated operation and maintenance platform actively sends a device local clock query request to the device that survives the long connection state in the previous step;

[0025] S217, after receiving the device response, the IoT integrated operation and maintenance platform determines whether the device clock matches the server clock;

[0026] S218. If the clocks match, it means that the device has not submitted data on time, indicating a real-time failure of the device; if the clocks do not match, the IoT integrated operation and maintenance platform will proactively send instructions to modify the local clock of the device and prompt that the device clock is wrong.

[0027] Furthermore, in step S3, the method for identifying data anomalies includes the following steps:

[0028] S31. The IoT integrated operation and maintenance platform stores historical monitoring data of devices through a time series library;

[0029] S32. Perform training based on historical monitoring data to construct a univariate polynomial regression model and a multivariate linear regression model;

[0030] S33, after receiving the newly reported data from the equipment, the IoT integrated operation and maintenance platform substitutes the data into the two models for calculation;

[0031] S34. If the newly reported data from the device is greater than the upper limit of one of the regression models, the data is determined to be abnormal and marked as abnormal data; otherwise, the data is normal and no processing is performed.

[0032] Furthermore, in step S32, the method for constructing a univariate polynomial regression model includes the following steps:

[0033] (1) Let the sample set T = [(x1,y1),(x2,y2),(x3,y3)...(x n ,y n )],f(x i ,w)=w0+w1x1+w2x2+w3x3+···+w im x im =∑w j +x ji , where x is a single variable input, w0,w1,w2,...,w M There are M+1 parameters;

[0034] (2) Use the least squares method to calculate the loss function, substitute the model and training data, and we get:

[0035]

[0036] (3) For w j Taking the partial derivative and setting it to 0, we get:

[0037]

[0038] (4) Solve the following linear equations and fit the polynomial coefficients w0, w1, w2, ..., w M :

[0039]

[0040] (5) The univariate polynomial regression model is calculated as:

[0041] and

[0042] Furthermore, in step S32, the method for constructing the multivariate linear regression model includes the following steps:

[0043] (1) Let the sample set: T = [(x 11 ,x 21 ,...,x n1 ,y1),(x 21 ,x 22 ,...,x n2 ,y2),(x 31 ,x 32 ,...,x n3 ,y3),...(x n1 ,x n2 ,...,x nn ,y n )]; where y i =a1×x 1i +a2×x 2i +...+a n × ni +ε; expressed as a matrix expression:

[0044]

[0045] (2) The least squares method is used to fit and solve the multivariate linear regression model:

[0046] y=xa+ε。

[0047] An automated operation and maintenance monitoring system for Internet of Things monitoring equipment comprises an integrated Internet of Things operation and maintenance platform and multiple devices. The integrated Internet of Things operation and maintenance platform is connected to the multiple devices, and the automated operation and maintenance monitoring method for the Internet of Things monitoring equipment is used to perform operation and maintenance monitoring on the multiple devices.

[0048] Furthermore, the IoT integrated operation and maintenance platform is provided with an equipment operating condition determination module and an abnormal data identification module;

[0049] The equipment working condition determination module is used to identify abnormalities in reporting frequency and real-time abnormalities of the equipment;

[0050] The abnormal data identification module is used to identify data anomalies of the device.

[0051] Furthermore, the abnormal data identification module identifies abnormalities in the data newly reported by the device by constructing a univariate polynomial regression model and a multivariate linear regression model.

[0052] Due to the adoption of the above technical solution, the present invention has the following beneficial effects:

[0053] 1. The present invention provides an integrated automatic operation and maintenance monitoring solution, covering equipment operating conditions and data anomaly monitoring, avoiding abnormal omissions and manual monitoring, improving operation and maintenance efficiency, and saving labor costs.

[0054] 2. The present invention can customize equipment operating condition determination rules for different equipment, thereby improving flexibility and scalability.

[0055] 3. The present invention trains a regression model based on historical monitoring data, performs mathematical statistical analysis through data change patterns, and then determines outliers with higher accuracy.

[0056] 4. The present invention provides an integrated operation and maintenance monitoring platform, which facilitates the centralized presentation of various abnormal problems and helps administrators and operation and maintenance personnel to quickly discover and solve problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a flow chart of abnormal reporting frequency identification in the automated operation and maintenance monitoring method of the Internet of Things monitoring equipment proposed by the present invention;

[0058] Figure 2 It is a flow chart of real-time anomaly identification in the automated operation and maintenance monitoring method of Internet of Things monitoring equipment proposed by the present invention;

[0059] Figure 3 It is a flow chart of data anomaly identification in the automated operation and maintenance monitoring method of the Internet of Things monitoring equipment proposed by the present invention; DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] Example 1

[0062] The present invention proposes an automated operation and maintenance monitoring method for Internet of Things monitoring equipment, which includes steps S1, S2 and S3.

[0063] S1. Build an integrated IoT operation and maintenance platform and connect multiple devices that require operation and maintenance monitoring.

[0064] S2. Use the IoT integrated operation and maintenance platform to identify abnormalities in the equipment’s reporting frequency and real-time performance, and determine the equipment’s operating condition.

[0065] The method for identifying abnormal reporting frequency includes steps S201-S207.

[0066] S201. The operation and maintenance personnel configure frequency anomaly identification rules, including reporting frequency and time threshold. The reporting frequency may be, for example, once an hour or once every five minutes.

[0067] S202. The device is connected to the IoT integrated operation and maintenance platform through a long connection.

[0068] S203. The IoT integrated operation and maintenance platform detects a list of devices that have exceeded a time threshold and have not reported data through a scheduled task.

[0069] S204, respectively determine whether the long connection status of each device in the device list is alive.

[0070] S205. If the device is no longer in the long connection state, a prompt is given that the device is offline abnormal. If the device is still in the long connection state, the execution continues.

[0071] S206. The IoT integrated operation and maintenance platform proactively sends a data query request to the device that survived the long connection state in the previous step, and retries up to three times.

[0072] S207. If the IoT integrated operation and maintenance platform does not receive a data response from the device for three times, it is determined to be a device failure and an abnormal prompt is given; if a data response from the device is received, it is not considered an abnormality and a prompt is given for network fluctuation.

[0073] In other words, the IoT integrated operation and maintenance platform is responsible for storing the data reporting records of each device. When the required reporting frequency and time threshold are exceeded, the platform will actively send a data query request to the device and retry three times. If a data response is received from the device, it means that the missing data report may be caused by network fluctuations and it will not be judged as an abnormality. If no response is received for three times, it will be judged as a device abnormality.

[0074] The method for real-time anomaly identification includes steps S211-S218.

[0075] S211. Operation and maintenance personnel configure device reporting frequency rules.

[0076] S212. The device is connected to the IoT integrated operation and maintenance platform through a long connection.

[0077] S213. The IoT integrated operation and maintenance platform uses scheduled tasks to detect a list of devices that have exceeded the time threshold and have not reported data.

[0078] S214, respectively determine whether the long connection status of each device in the device list is alive.

[0079] S215. If the device is no longer in the long connection state, a prompt is given that the device is offline abnormal; if the device is still in the long connection state, the execution continues.

[0080] S216. The IoT integrated operation and maintenance platform proactively sends a device local clock query request to the device that survived the long connection state in the previous step.

[0081] S217. After receiving the device response, the IoT integrated operation and maintenance platform determines whether the device clock matches the server clock.

[0082] S218. If the clocks match, it means that the device has not submitted data on time, indicating a real-time failure of the device; if the clocks do not match, the IoT integrated operation and maintenance platform will proactively send instructions to modify the local clock of the device and prompt that the device clock is wrong.

[0083] That is to say, the IoT integrated operation and maintenance platform determines whether the actual device data reporting time is consistent with the required time based on the reporting frequency configured by the device and the platform server time. If not, the platform will actively send a local clock query request to the device to determine whether the real-time problem is caused by the clock inconsistency. If the clock is inconsistent, the platform will actively send a time calibration request to the device. In addition, the platform records real-time anomalies that are not caused by clock problems.

[0084] The present invention can customize equipment operating condition determination rules for different equipment, thereby improving flexibility and scalability.

[0085] S3. The IoT integrated operation and maintenance platform uses historical data as sample data to construct a univariate polynomial regression model and a multivariate linear regression model. It also uses the univariate polynomial regression model and the multivariate linear regression model to identify anomalies in the newly reported data of the device. If an abnormality is found in the data, the IoT integrated operation and maintenance platform will execute an alarm action.

[0086] The method for identifying data anomalies includes steps S31-S34.

[0087] S31. The IoT integrated operation and maintenance platform stores historical monitoring data of devices through a time series library.

[0088] S32. Train based on historical monitoring data to construct a univariate polynomial regression model and a multivariate linear regression model.

[0089] Specifically, the method for constructing a univariate polynomial regression model includes the following steps.

[0090] (1) Let the sample set T = [(x1,y1),(x2,y2),(x3,y3)...(xn ,y n )],f(x i ,w)=w0+w1x1+w2x2+w3x3+···+w im x im =∑w j +x ji , where x is a single variable input, w0,w1,w2,...,w M There are M+1 parameters.

[0091] (2) Use the least squares method to calculate the loss function, substitute the model and training data, and we get:

[0092]

[0093] (3) For w j Taking the partial derivative and setting it to 0, we get:

[0094]

[0095] (4) Solve the following linear equations and fit the polynomial coefficients w0, w1, w2, ..., w M .

[0096]

[0097] (5) The univariate polynomial regression model is calculated as:

[0098]

[0099] The method for constructing a multiple linear regression model includes the following steps.

[0100] (1) Let the sample set: T = [(x 11 ,x 21 ,...,x n1 ,y1),(x 21 ,x 22 ,...,x n2 ,y2),(x 31 ,x 32 ,...,x n3 ,y3),...(x n1 ,x n2 ,...,x nn ,y n )]; where y i =a1×x 1i +a2×x 2i +...+a n × ni +ε; expressed as a matrix expression:

[0101]

[0102] (2) The least squares method is used to fit and solve the multivariate linear regression model:

[0103] y=xa+ε。

[0104] The present invention trains a regression model based on historical monitoring data, performs mathematical statistical analysis through data change patterns, and then determines outliers with higher accuracy.

[0105] S33. After receiving the new data reported by the equipment, the IoT integrated operation and maintenance platform substitutes it into the two models for calculation.

[0106] S34. If the newly reported data from the device is greater than the upper limit of one of the regression models, the data is determined to be abnormal and marked as abnormal data; otherwise, the data is normal and no processing is performed.

[0107] The present invention builds an integrated operation and maintenance platform for IoT devices, monitors the frequency and real-time reporting of device data, performs secondary confirmation of the device operating conditions, and builds an integrated numerical monitoring model at the same time, identifies abnormal values ​​based on historical data, and provides integrated device abnormality alarm information. The present invention covers equipment operating conditions and data abnormality monitoring, avoids abnormal omissions and manual monitoring, improves operation and maintenance efficiency, and saves labor costs. The present invention provides an integrated operation and maintenance monitoring platform, which facilitates the centralized presentation of various abnormal problems, helping administrators and operation and maintenance personnel to quickly discover and solve problems.

[0108] Example 2

[0109] The present invention also proposes an automated operation and maintenance monitoring system for Internet of Things monitoring equipment, which includes an Internet of Things integrated operation and maintenance platform and multiple devices. The Internet of Things integrated operation and maintenance platform is connected to the multiple devices, and the multiple devices are operated and monitored through the automated operation and maintenance monitoring method of the Internet of Things monitoring equipment.

[0110] The IoT integrated operation and maintenance platform is provided with an equipment working condition determination module and an abnormal data identification module. The equipment working condition determination module is used to identify abnormal reporting frequency and real-time abnormality of the equipment. The abnormal data identification module is used to identify data abnormalities of the equipment. The abnormal data identification module identifies abnormalities of the newly reported data of the equipment by constructing a univariate polynomial regression model and a multivariate linear regression model.

[0111] The present invention uses the historical monitoring data of the equipment to train the univariate polynomial regression model and the multivariate linear regression model, and judges the outliers of the equipment reported data to improve the accuracy. At the same time, the reporting frequency and real-time performance of the equipment are monitored, and flexible monitoring customization is achieved through configuration, and the secondary verification actively triggered by the platform is added to improve the robustness of abnormal monitoring. Overall, the integrated automatic operation and maintenance monitoring of the water conservancy Internet of Things monitoring equipment is realized, the operation and maintenance efficiency is improved, and the labor cost is reduced.

[0112] The above description is a detailed description of the preferred feasible embodiments of the present invention, but the embodiments are not intended to limit the scope of the patent application of the present invention. All equivalent changes or modified changes completed under the technical spirit suggested by the present invention should fall within the patent scope covered by the present invention.

Claims

1. A method for automated operation and maintenance monitoring of Internet of Things monitoring equipment, characterized in that: The following steps are involved: S1. Build an integrated IoT operation and maintenance platform and connect multiple devices that require operation and maintenance monitoring; S2. Use the IoT integrated operation and maintenance platform to identify abnormalities in the reporting frequency and real-time performance of the equipment and determine the working condition of the equipment; S3. The IoT integrated operation and maintenance platform uses historical data as sample data to construct a univariate polynomial regression model and a multivariate linear regression model. It also uses the univariate polynomial regression model and the multivariate linear regression model to identify anomalies in the newly reported data of the device. If an abnormality is found in the data, the IoT integrated operation and maintenance platform will execute an alarm action.

2. The method for automated operation and maintenance monitoring of an Internet of Things monitoring device according to claim 1, characterized in that: In step S2, the method for identifying abnormal reporting frequency includes the following steps: S201. The operation and maintenance personnel configure frequency anomaly identification rules, including reporting frequency and time threshold; S202, the device is connected to the IoT integrated operation and maintenance platform through a long connection; S203, the IoT integrated operation and maintenance platform detects the list of devices that have exceeded the time threshold and have not reported data through a scheduled task; S204, respectively determining whether the long connection status of each device in the device list is alive; S205. If the device is no longer in the long connection state, prompt that the device is offline abnormal. If the device is still in the long connection state, continue to execute; S206. The IoT integrated operation and maintenance platform actively sends a data query request to the device that survived the long connection state in the previous step, and retries up to three times; S207. If the IoT integrated operation and maintenance platform does not receive a data response from the device for three times, it is determined to be a device failure and an abnormal prompt is given; if a data response from the device is received, it is not considered an abnormality and a prompt is given for network fluctuation.

3. The method for automated operation and maintenance monitoring of an Internet of Things monitoring device according to claim 2, characterized in that: In step S2, the method for real-time anomaly identification includes the following steps: S211, Operation and maintenance personnel configure equipment reporting frequency rules; S212, the device is connected to the IoT integrated operation and maintenance platform through a long connection; S213, the IoT integrated operation and maintenance platform detects the list of devices that have exceeded the time threshold and have not reported data through scheduled tasks; S214, respectively determining whether the long connection status of each device in the device list is alive; S215. If the device is no longer in the long connection state, a prompt is given that the device is offline abnormal; if the device is still in the long connection state, the execution continues; S216, the IoT integrated operation and maintenance platform actively sends a device local clock query request to the device that survives the long connection state in the previous step; S217, after receiving the device response, the IoT integrated operation and maintenance platform determines whether the device clock matches the server clock; S218. If the clocks match, it means that the device has not submitted data on time, indicating a real-time failure of the device; if the clocks do not match, the IoT integrated operation and maintenance platform will proactively send instructions to modify the local clock of the device and prompt that the device clock is wrong.

4. The method for automated operation and maintenance monitoring of Internet of Things monitoring equipment according to claim 3 is characterized in that: In step S3, the method for identifying data anomalies includes the following steps: S31. The IoT integrated operation and maintenance platform stores historical monitoring data of devices through a time series library; S32. Perform training based on historical monitoring data to construct a univariate polynomial regression model and a multivariate linear regression model; S33, after receiving the newly reported data from the equipment, the IoT integrated operation and maintenance platform substitutes the data into the two models for calculation; S34. If the newly reported data from the device is greater than the upper limit of one of the regression models, the data is determined to be abnormal and marked as abnormal data; otherwise, the data is normal and no processing is performed.

5. The method for automated operation and maintenance monitoring of Internet of Things monitoring equipment according to claim 4, characterized in that: In step S32, the method for constructing a univariate polynomial regression model includes the following steps: (1) Let the sample set T = [(x1,y1),(x2,y2),(x3,y3)...(x n ,y n )],f(x i ,w)=w0+w1x1+w2x2+w3x3+···+w im x im =∑w j +x ji , where x is a single variable input, w0,w1,w2,...,w M There are M+1 parameters; (2) Use the least squares method to calculate the loss function, substitute the model and training data, and we get: (3) For w j Taking the partial derivative and setting it to 0, we get: (4) Solve the following linear equations and fit the polynomial coefficients w0, w1, w2, ..., w M : (5) The univariate polynomial regression model is calculated as: and 6. The method for automated operation and maintenance monitoring of Internet of Things monitoring equipment according to claim 5, characterized in that: In step S32, the method for constructing a multiple linear regression model includes the following steps: (1) Let the sample set: T = [(x 11 ,x 21 ,...,x n1 ,y1),(x 21 ,x 22 ,...,x n2 ,y2),(x 31 ,x 32 ,...,x n3 ,y3),...(x n1 ,x n2 ,...,x nn ,y n )]; where y i =a1×x 1i +a2×x 2i +...+a n × ni +ε; expressed as a matrix expression: (2) The least squares method is used to fit and solve the multivariate linear regression model: y=xa+ε。 7. An automated operation and maintenance monitoring system for Internet of Things monitoring equipment, characterized in that: It comprises an integrated operation and maintenance platform of the Internet of Things and a plurality of devices, wherein the integrated operation and maintenance platform of the Internet of Things is connected to the plurality of devices, and the operation and maintenance of the plurality of devices is monitored by the automated operation and maintenance monitoring method of the Internet of Things monitoring device described in any one of claims 1 to 6.

8. The automated operation and maintenance monitoring system for Internet of Things monitoring equipment according to claim 7, characterized in that: The IoT integrated operation and maintenance platform is provided with an equipment operating condition determination module and an abnormal data identification module; The equipment working condition determination module is used to identify abnormalities in reporting frequency and real-time abnormalities of the equipment; The abnormal data identification module is used to identify data anomalies of the device.

9. The automated operation and maintenance monitoring system for Internet of Things monitoring equipment according to claim 8, characterized in that: The abnormal data identification module identifies abnormalities in the data newly reported by the device by constructing a univariate polynomial regression model and a multivariate linear regression model.

Images