Capacitive voltage transformer metering performance online monitoring system and method

Abstract

The invention discloses a capacitive voltage transformer metering performance online monitoring system and method. The system comprises a capacitive voltage transformer metering performance monitoring device, an acquisition terminal and a metering online monitoring platform. The capacitor voltage transformer metering performance monitoring device is used for collecting data information of a secondary side of a capacitor voltage transformer and carrying out data processing and calculation, wherein error evaluation is realized by constructing an EMD-LSTM neural network. The acquisition terminal actively uploads sampling data, evaluation data and abnormal event data to the metering online monitoring platform; and the metering online monitoring platform is used for realizing remote online monitoring, data display and data storage. According to the invention, online monitoring and state evaluation of the capacitor voltage transformer can be realized, real-time operation errors of the capacitor can be monitored on the premise that power failure is not needed and detection personnel do not need to be present, and directional power failure verification and operation and maintenance of the transformer can be guided according to a state evaluation result.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent electric energy metering, and in particular to an online monitoring system and method for metering performance of a capacitive voltage transformer. Background Art

[0002] The electric energy metering device is a measuring instrument that records the amount of electric energy used by users. As a component of the electric energy metering device, the accurate and reliable output signal of the voltage transformer is the basis for ensuring the fairness and justice of the electric energy trade settlement. Capacitor voltage transformers have great advantages in insulation performance, low cost, and simple operation and maintenance. Therefore, they are widely used in substations and power plants with voltage levels of 110kV and above. However, the variability of capacitor and reactor parameters leads to poor stability of capacitor voltage transformers compared to electromagnetic voltage transformers, and preventive testing of capacitor voltage transformers may cause damage to the electromagnetic unit. At the same time, the vibration generated by operation will cause the gap of the compensating reactor core to shift, thereby causing the transformer to exceed the tolerance.

[0003] In response to the above-mentioned problems of capacitor voltage transformers, the commonly used calibration methods are power-off calibration method and live calibration method. Due to the difficulty of power outage in substations and other reasons, the traditional power-off calibration method often cannot calibrate capacitor voltage transformers on schedule, resulting in the difficulty in ensuring the accuracy of long-term operation; the live calibration method is to directly connect the standard device to the primary side with power, which can only be connected for a short time, and there are great safety hazards, and it is impossible to achieve long-term dynamic tracking of the substation. Therefore, how to solve the problem of online monitoring and evaluation of the metering status of capacitor voltage transformers without power outages and physical standards will help the long-term safe and stable operation of the power grid, and can ensure the fairness and reliability of electric energy trade. Summary of the invention

[0004] In view of the technical problems pointed out in the above-mentioned prior art, the purpose of the present invention is to provide a system and method for online monitoring of the metering performance of a capacitive voltage transformer.

[0005] To achieve the purpose of the present invention, the technical solution provided by the present invention is as follows:

[0006] First aspect

[0007] The present invention provides a capacitive voltage transformer metering performance online monitoring system, comprising a capacitive voltage transformer metering performance monitoring device, a collection terminal and a metering online monitoring platform;

[0008] Wherein, the capacitor voltage transformer metering performance monitoring device is used to collect data information on the secondary side of the capacitor voltage transformer and perform data processing and calculation;

[0009] The acquisition terminal actively uploads the sampling data, evaluation data and abnormal event data to the measurement online monitoring platform;

[0010] The metering online monitoring platform is used to realize remote online monitoring, data display and data storage.

[0011] Wherein, the capacitive voltage transformer metering performance monitoring device includes a signal conversion unit, a data sampling unit and an edge computing unit;

[0012] Wherein, the signal conversion unit and the data sampling unit complete the data information sampling of the secondary side of the capacitor voltage transformer group;

[0013] The edge computing unit completes the screening, cleaning and sampling of the sampled data, and then completes the error state evaluation through the constructed EMD-LSTM neural network method.

[0014] Among them, the EMD-LSTM neural network construction method is as follows:

[0015] First, construct a specific LSTM neural network model, as follows:

[0016] The forget gate can control the impact of historical learning on the current memory module state value:

[0017] f t =σ(W f x t +R f y t-1 +b f )

[0018] The state value of the memory unit at the current moment is as follows:

[0019]

[0020] The value of the memory cell at time t is as follows:

[0021] u t =σ(W u x t +R u y t-1 +b u )

[0022] The input gate can control the impact of the current data input on the state of the storage module, as shown in the following formula:

[0023]

[0024] The output gate can control the output of the state value of the storage module as shown below:

[0025] ot =σ(W o x t +R o y t-1 +b o )

[0026] The output of the LSTM network unit is shown below:

[0027] y t =o t ⊙g2(h t )

[0028] Second, construct EMD as follows:

[0029] First, the upper envelope U is determined by the local maximum and minimum values ​​of the time series data x(t). s (t) and the lower envelope V s (t), and then find the mean envelope m1:

[0030]

[0031] Then, subtracting m1 from x(t) yields c1, the first intrinsic mode function (IMF) component:

[0032] c1=x(t)-m1(t)

[0033] Among them, the residual r1(t) is the difference between x(t) and m1:

[0034] r1(t)=x(t)-c1(t)

[0035]

[0036] Afterwards, the neural network is trained based on a large amount of voltage data obtained from real measurements;

[0037] Furthermore, the short-term voltage condition time series data can be input into the EMD-LSTM neural network for voltage error evaluation.

[0038] Among them, the capacitive voltage transformer metering performance monitoring device and the acquisition terminal are configured at the site where the capacitive voltage transformer is located.

[0039] Among them, the edge computing unit realizes data screening, data cleaning, data sampling and data calculation functions by developing the Raspberry Pi Compute Module 4 module.

[0040] Second aspect

[0041] The present invention provides a method for online monitoring of the metrological performance of a capacitor voltage transformer, which is applied to the above-mentioned online monitoring system for the metrological performance of a capacitor voltage transformer, and comprises the following steps:

[0042] Step S1: The capacitor voltage transformer metering performance monitoring device completes data information sampling on the secondary side of the capacitor voltage transformer group through the signal conversion unit and the data sampling unit;

[0043] Step S2: The capacitive voltage transformer metering performance monitoring device completes the screening, cleaning, and sampling of the sampled data through the edge computing unit, and then completes the error state evaluation through the constructed EMD-LSTM neural network method;

[0044] Step S3: the acquisition terminal obtains sampling data, evaluation data and abnormal event data from the capacitor voltage transformer metering performance monitoring device, and actively uploads them to the metering online monitoring platform;

[0045] Step S4: The metering online monitoring platform implements remote online monitoring and displays data based on the uploaded data, and backs up the data into the database.

[0046] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention can realize online monitoring and status evaluation of capacitor voltage transformers. Compared with the existing power outage verification method and live verification method, the present invention can monitor and evaluate the real-time operation error of capacitor voltage transformers without power outage, physical standard instruments, or on-site inspection personnel, and guide the transformer directional power outage verification and operation and maintenance according to the error evaluation results. The system and method of the present invention can save a lot of manpower and material resources, can promptly detect transformers with out-of-tolerance, and thus promptly handle them, reduce power losses, and improve the digital and intelligent management level of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a structural schematic diagram of an online monitoring system for capacitive voltage transformer metering performance provided by an embodiment of the present invention;

[0048] Figure 2 It is a structural schematic diagram of a capacitive voltage transformer metering performance monitoring device provided by the present invention;

[0049] Figure 3 It is a schematic diagram of the EMD-LSTM neural network provided by the present invention;

[0050] Figure 4 The present invention provides a flowchart of an on-line monitoring method for the metering performance of a capacitive voltage transformer. DETAILED DESCRIPTION

[0051] The following is a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the drawings 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.

[0052] like Figure 1 As shown, this embodiment provides a capacitive voltage transformer metering performance online monitoring system, including a capacitive voltage transformer metering performance monitoring device, a collection terminal and a metering online monitoring platform;

[0053] Wherein, the capacitor voltage transformer metering performance monitoring device is used to collect data information on the secondary side of the capacitor voltage transformer and perform data processing and calculation;

[0054] The acquisition terminal actively uploads the sampling data, evaluation data and abnormal event data to the measurement online monitoring platform;

[0055] The metering online monitoring platform is used to realize remote online monitoring, data display and data storage.

[0056] It should be noted that the capacitor voltage transformer metering performance monitoring device and the acquisition terminal are configured at the station network site where the capacitor voltage transformer is located; the capacitor voltage transformer metering performance monitoring device is designed as an integrated device, which is used to collect data information on the secondary side of the capacitor voltage transformer and perform data processing and calculation; the acquisition terminal is used to actively upload sampling data, evaluation data and abnormal event data to the metering online monitoring platform; the metering online monitoring platform is used to realize remote online monitoring, data display and data storage.

[0057] Figure 2 This is a structural diagram of a capacitive voltage transformer metering performance monitoring device, which includes a signal conversion unit, a data sampling unit and an edge computing unit. The edge computing unit can realize data screening, data cleaning, data sampling and data computing functions by developing a RaspberryPi Compute Module 4 module.

[0058] It should be noted that the signal conversion unit and the data sampling unit complete the data information sampling of the secondary side of the capacitor voltage transformer group;

[0059] The edge computing unit completes the screening, cleaning and sampling of the sampled data, and then completes the error state evaluation through the constructed EMD-LSTM neural network method.

[0060] Figure 3This is a schematic diagram of the EMD-LSTM neural network solution in an online monitoring method for the metering performance of a capacitive voltage transformer of the present invention. The design starting point is to use the mode decomposition (EMD) method to decompose the characteristic vector of the voltage transformer monitoring data and the information containing different time scales, and then use the long short-term memory (LSTM) network to predict each component, and finally obtain the error prediction result.

[0061] The EMD-LSTM neural network construction method is as follows:

[0062] First, construct a specific LSTM neural network model, as follows:

[0063] The forget gate can control the impact of historical learning on the current memory module state value:

[0064] f t =σ(W f x t +R f y t-1 +b f )

[0065] The state value of the memory unit at the current moment is as follows:

[0066]

[0067] The value of the memory cell at time t is as follows:

[0068] u t =σ(W u x t +R u y t-1 +b u )

[0069] The input gate can control the impact of the current data input on the state of the storage module, as shown in the following formula:

[0070]

[0071] The output gate can control the output of the state value of the storage module as shown below:

[0072] o t =σ(W o x t +R o y t-1 +b o )

[0073] The output of the LSTM network unit is shown below:

[0074] y t =o t ⊙g2(ht )

[0075] Second, construct EMD as follows:

[0076] First, the upper envelope U is determined by the local maximum and minimum values ​​of the time series data x(t). s (t) and the lower envelope V s (t), and then find the mean envelope m1:

[0077]

[0078] Then, subtracting m1 from x(t) yields c1, the first intrinsic mode function (IMF) component:

[0079] c1=x(t)-m1(t)

[0080] Among them, the residual r1(t) is the difference between x(t) and m1:

[0081] r1(t)=x(t)-c1(t)

[0082]

[0083] Afterwards, the neural network is trained based on a large amount of voltage data obtained from real measurements;

[0084] Furthermore, the short-term voltage condition time series data can be input into the EMD-LSTM neural network for voltage error evaluation.

[0085] Figure 1 The online monitoring system for the measurement performance of a capacitor voltage transformer shown in FIG. adopts the method of the present invention to realize online monitoring and status evaluation of a capacitor voltage transformer. The specific steps are as follows: Figure 4 As shown:

[0086] Step S1: The capacitor voltage transformer metering performance monitoring device completes data information sampling on the secondary side of the capacitor voltage transformer group through the signal conversion unit and the data sampling unit;

[0087] Step S2: The capacitive voltage transformer metering performance monitoring device completes the screening, cleaning, and sampling of the sampled data through the edge computing unit, and then completes the error state evaluation through the constructed EMD-LSTM neural network method;

[0088] Step S3: the acquisition terminal obtains sampling data, evaluation data and abnormal event data from the capacitor voltage transformer metering performance monitoring device, and actively uploads them to the metering online monitoring platform;

[0089] Step S4: The metering online monitoring platform implements remote online monitoring and displays data based on the uploaded data, and backs up the data into the database.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate and explain the present invention, and are not intended to limit the present invention to the scope of the described embodiments. In addition, those skilled in the art can understand that the present invention is not limited to the above embodiments, and more variations and modifications can be made according to the teachings of the present invention, and these variations and modifications all fall within the scope of the protection claimed by the present invention.

Claims

1. A capacitive voltage transformer metering performance online monitoring system, characterized in that: It includes a capacitive voltage transformer metering performance monitoring device, a collection terminal and a metering online monitoring platform; Wherein, the capacitor voltage transformer metering performance monitoring device is used to collect data information on the secondary side of the capacitor voltage transformer and perform data processing and calculation; The acquisition terminal actively uploads the sampling data, evaluation data and abnormal event data to the measurement online monitoring platform; The metering online monitoring platform is used to realize remote online monitoring, data display and data storage.

2. The online monitoring system for the measurement performance of a capacitor voltage transformer according to claim 1 is characterized in that: The capacitive voltage transformer metering performance monitoring device comprises a signal conversion unit, a data sampling unit and an edge computing unit; Wherein, the signal conversion unit and the data sampling unit complete the data information sampling of the secondary side of the capacitor voltage transformer group; The edge computing unit completes the screening, cleaning and sampling of the sampled data, and then completes the error state evaluation through the constructed EMD-LSTM neural network method.

3. The online monitoring system for the measurement performance of a capacitor voltage transformer according to claim 2 is characterized in that: The EMD-LSTM neural network construction method is as follows: First, construct a specific LSTM neural network model, as follows: The forget gate can control the impact of historical learning on the current memory module state value: f t =σ(W f x t +R f y t-1 +b f ) The state value of the memory unit at the current moment is as follows: The value of the memory cell at time t is as follows: u t =σ(W u x t +R u y t-1 +b u ) The input gate can control the impact of the current data input on the state of the storage module, as shown in the following formula: The output gate can control the output of the state value of the storage module as shown below: the t =σ(W o x t +R o y t-1 +b o ) The output of the LSTM network unit is shown below: y t =o t ⊙g2(h t ) Second, construct EMD as follows: First, the upper envelope U is determined by the local maximum and minimum values ​​of the time series data x(t). s (t) and the lower envelope V s (t), and then find the mean envelope m1: Then, subtracting m1 from x(t) yields c1, the first intrinsic mode function (IMF) component: c1=x(t)-m1(t) Among them, the residual r1(t) is the difference between x(t) and m1: r1(t)=x(t)-c1(t) Afterwards, the neural network is trained based on a large amount of voltage data obtained from real measurements; Furthermore, the short-term voltage condition time series data can be input into the EMD-LSTM neural network for voltage error evaluation.

4. The online monitoring system for the measurement performance of a capacitor voltage transformer according to claim 1 is characterized in that: The capacitive voltage transformer metering performance monitoring device and the acquisition terminal are configured at the site where the capacitive voltage transformer is located.

5. The online monitoring system for the measurement performance of a capacitor voltage transformer according to claim 1 is characterized in that: The edge computing unit realizes data screening, data cleaning, data sampling and data computing functions by developing the Raspberry Pi Compute Module 4 module.

6. A method for online monitoring of the metrological performance of a capacitive voltage transformer, characterized in that: The method is applied to an online monitoring system for the measurement performance of a capacitive voltage transformer according to any one of claims 1 to 5, comprising the following steps: Step S1: The capacitor voltage transformer metering performance monitoring device completes data information sampling on the secondary side of the capacitor voltage transformer group through the signal conversion unit and the data sampling unit; Step S2: The capacitive voltage transformer metering performance monitoring device completes the screening, cleaning, and sampling of the sampled data through the edge computing unit, and then completes the error state evaluation through the constructed EMD-LSTM neural network method; Step S3: the acquisition terminal obtains sampling data, evaluation data and abnormal event data from the capacitor voltage transformer metering performance monitoring device, and actively uploads them to the metering online monitoring platform; Step S4: The metering online monitoring platform implements remote online monitoring and displays data based on the uploaded data, and backs up the data into the database.

Images