Non-contact voltage measuring method and system

Abstract

The invention provides a non-contact voltage measuring method and a system thereof. The non-contact voltage measurement method comprises the following steps: measuring a voltage signal source to be measured through the capacitive coupling structure to generate a measurement signal; generating an output signal by a signal processing circuit according to the measurement signal; analyzing, by a sampling unit, the output signal to generate a sampled signal; and outputting the sampling signal to the trained artificial intelligence model, so that the trained artificial intelligence model outputs a restoration signal.

Description

Technical Field

[0001] The present invention relates to voltage measurement technology, and in particular to a non-contact voltage measurement method and system thereof. Background Art

[0002] In the field of motor-related engineering, electrical signals are usually important measurement data in motor systems. However, the general measurement method is to measure the metal traces in the system through electrical contact voltage and / or current sensors, which has a higher measurement risk. In this regard, common situations such as improper use of sensors by the measurer, or high voltage in the measurement object or measurement environment, which can easily cause electric shock accidents. Therefore, how to safely, effectively and accurately measure electrical signals is an important research topic in this field. Summary of the invention

[0003] The object of the present invention is to provide a non-contact voltage measurement method and a non-contact voltage measurement system, which can effectively measure a voltage signal source to be measured.

[0004] Based on the above-mentioned purpose, the present invention proposes a non-contact voltage measurement method, which includes: measuring the voltage signal source to be measured through a capacitive coupling structure to generate a measurement signal; generating an output signal according to the measurement signal through a signal processing circuit; analyzing the output signal through a sampling unit to generate a sampling signal; and outputting the sampling signal to a trained artificial intelligence model so that the trained artificial intelligence model outputs a restored signal.

[0005] In a preferred embodiment, the capacitive coupling structure includes: a flat plate capacitor having a first insulating surface and a second insulating surface, wherein the first insulating surface of the flat plate capacitor is contact-coupled with a first line segment of a signal line of a voltage signal source to be measured, and the second insulating surface of the flat plate capacitor is contact-coupled with a second line segment of the signal line of the voltage signal source to be measured.

[0006] In a preferred embodiment, the step of generating the output signal includes: performing at least one of the following processing on the output signal by the signal processing circuit: analog signal processing, signal filtering and signal amplification.

[0007] In a preferred embodiment, the step of generating the sampling signal includes: performing analog-to-digital conversion on the output signal to generate the sampling signal.

[0008] In a preferred embodiment, the trained artificial intelligence model includes a signal restoration model, which includes multiple adjustable parameters, and the adjustable parameters include weight parameters, offset parameters, and at least one of nonlinear functions, wherein the signal restoration model is used to generate the restored signal based on the sampled signal.

[0009] In a preferred embodiment, the method further includes: comparing the restored signal with a corresponding target signal to generate a comparison result.

[0010] In a preferred embodiment, the trained artificial intelligence model also includes a data generation model, wherein the data generation model is used to generate an analog voltage source and to calculate an analog sampling signal based on the capacitive coupling structure and the transfer function of the signal processing circuit, wherein the analog voltage source and the analog sampling signal are used to train the signal restoration model.

[0011] In a preferred embodiment, the step of outputting the restored signal includes: generating amplitude parameters, phase parameters and frequency parameters according to the sampled signal through the trained artificial intelligence model; and generating the restored signal according to the amplitude parameters, the phase parameters and the frequency parameters through the trained artificial intelligence model.

[0012] Based on the above purpose, the present invention also proposes a non-contact voltage measurement system, which includes: a capacitive coupling structure for measuring a voltage signal source to be measured to generate a measurement signal; a signal processing circuit electrically connected to the capacitive coupling structure to generate an output signal according to the measurement signal; and an operation circuit electrically connected to the signal processing circuit, and the operation circuit includes: a sampling unit for analyzing the output signal to generate a sampling signal; and a trained artificial intelligence model for receiving the sampling signal and outputting a restored signal.

[0013] In a preferred embodiment, the capacitive coupling structure includes: a flat plate capacitor having a first insulating surface and a second insulating surface, wherein the first insulating surface of the flat plate capacitor contacts a first line segment of a signal line of the voltage signal source to be measured, and the second insulating surface of the flat plate capacitor contacts a second line segment of the signal line of the voltage signal source to be measured.

[0014] In a preferred embodiment, the signal processing circuit performs at least one of the following processing on the output signal: analog signal processing, signal filtering and signal amplification.

[0015] In a preferred embodiment, the sampling unit performs analog-to-digital conversion on the output signal to generate the sampling signal.

[0016] In a preferred embodiment, the trained artificial intelligence model includes a signal restoration model, which includes multiple adjustable parameters, and the adjustable parameters include a weight parameter, an offset parameter, and at least one of a nonlinear function, wherein the signal restoration model is used to generate the restored signal based on the sampled signal.

[0017] In a preferred embodiment, the operation circuit compares the restored signal with a corresponding target signal to generate a comparison result.

[0018] In a preferred embodiment, the trained artificial intelligence model also includes a data generation model, wherein the data generation model is used to generate an analog voltage source and to calculate an analog sampling signal based on the capacitive coupling structure and the transfer function of the signal processing circuit, wherein the analog voltage source and the analog sampling signal are used to train the signal restoration model.

[0019] In a preferred embodiment, the trained artificial intelligence model generates an amplitude parameter, a phase parameter, and a frequency parameter based on the sampled signal, and the trained artificial intelligence model generates the restored signal based on the amplitude parameter, the phase parameter, and the frequency parameter.

[0020] Based on the above scheme, the non-contact voltage measurement method and the non-contact voltage measurement system of the present invention can measure the non-contact voltage in a non-contact manner through a capacitive coupling structure, and use a trained artificial intelligence model to generate accurate measurement results. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 FIG. 4 is a schematic diagram of a non-contact voltage measurement system according to an embodiment of the present invention.

[0022] Figure 2 FIG. 4 is a measurement schematic diagram of non-contact voltage measurement according to an embodiment of the present invention.

[0023] Figure 3 is a flow chart of a non-contact voltage measurement method according to an embodiment of the present invention.

[0024] Figure 4 is a schematic diagram of a measurement signal according to an embodiment of the present invention.

[0025] Figure 5 is a schematic diagram of an output signal according to an embodiment of the present invention.

[0026] Figure 6 is a schematic diagram of a restored signal according to an embodiment of the present invention.

[0027] Figure 7 is a schematic diagram of a target signal according to an embodiment of the present invention.

[0028] Figure 8 is a flow chart of generating a restoration signal according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to further understand the purpose, structure, features, and functions of the present invention, the following detailed description is provided in conjunction with the embodiments. In addition, wherever possible, elements / components / steps with the same reference numerals in the drawings and embodiments represent the same or similar components.

[0030] Figure 1 FIG. 1 is a schematic diagram of a non-contact voltage measurement system according to an embodiment of the present invention. Figure 1 The non-contact voltage measurement system 100 includes a capacitive coupling structure 110, a signal processing circuit 120, and an operation circuit 130. The capacitive coupling structure 110 is electrically connected to the signal processing circuit 120. The signal processing circuit 120 is electrically connected to the operation circuit 130. In the present embodiment, the capacitive coupling structure 110 may be a flat plate capacitor and may be used to measure a voltage signal source 10 to be measured. The voltage signal source 10 to be measured may, for example, include a signal source and a signal line. The capacitive coupling structure 110 may measure a voltage signal transmitted by the signal source through the signal line in a manner that does not directly contact the metal traces in the signal line.

[0031] In this embodiment, the signal processing circuit 120 may include an analog to digital converter (ADC) circuit, a filter circuit, a signal amplifier circuit, and related analog and / or digital circuits, but the present invention is not limited thereto. In this embodiment, the operation circuit 130 may include a sampling unit 131, an artificial intelligence model 132, and an output unit 133.

[0032] The operation circuit 130 may include, for example, a processor and a storage device. The processor may be implemented by, for example, a central processing unit (CPU), a microprocessor (MCU) or a field programmable gate array (FPGA) or the like, or a chip having a data operation function, but the present invention is not limited thereto. The storage device may be, for example, a memory, wherein the memory may be, for example, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a random access memory (RAM), a semiconductor memory or other volatile memory or non-volatile memory, and may be used to store the algorithms or programs related to the sampling unit 131, the artificial intelligence model 132 and the output unit 133, and may also store or temporarily store the various parameters, data, signals and models mentioned in the present invention. In one embodiment, the sampling unit 131, the artificial intelligence model 132 and the output unit 133 may also be implemented by a digital circuit.

[0033] Figure 2 FIG. 4 is a measurement schematic diagram of non-contact voltage measurement according to an embodiment of the present invention. Figure 1 The non-contact voltage measurement system 100 can be specifically implemented as follows: Figure 2 The architecture of the capacitor coupling structure 110 can be realized as follows Figure 2 The plate capacitor 210. Figure 2 , Figure 2 2 is a schematic side view of a flat plate capacitor 210. In the present embodiment, the voltage signal source 30 to be measured may be an alternating current signal (e.g., a mains signal), and the alternating current signal may be transmitted through a signal line 20. In the present embodiment, the flat plate capacitor 210 may be formed by stacking an upper electrode plate 211, a dielectric layer 213, and a lower electrode plate 212, and the entire outer layer is coated with an insulating material (not shown) to form a first insulating surface S1 and a second insulating surface S2. The signal line 20 includes a first line segment 21, a second line segment 22, a metal trace (conductor) 23, and an insulating layer 24, wherein the insulating layer 24 covers the metal trace 23. The upper electrode plate 211 and the lower electrode plate 212 of the flat plate capacitor 210 are electrically connected to a signal processing circuit 220 to provide a measurement signal to the signal processing circuit 220. The signal processing circuit 220 is electrically connected to an operation circuit 230.

[0034] In this embodiment, the first insulating surface S1 of the flat capacitor 210 can contact the first line segment 21 of the signal line 20, and the second insulating surface S2 of the flat capacitor 210 can contact the second line segment 22 of the signal line 20. For example, the user can bend the signal line 20 so that the two line segments of the signal line 20 contact the first insulating surface S1 and the second insulating surface S2 of the flat capacitor 210 respectively, and form effective overlapping areas respectively. In this way, the two metal traces 23 respectively form stray capacitance C1 and stray capacitance C2 between the upper electrode plate 211 and the lower electrode plate 212 of the flat capacitor 210 due to the presence of insulating materials and / or medium such as air. In this regard, the stray capacitance C1, the stray capacitance C2, the capacitance Cin of the flat capacitor 210 itself, and the equivalent input impedance (Rin) of the signal processing circuit 220 can form a circuit loop, so that the AC signal of the voltage signal source 30 to be measured can transfer energy to the signal processing circuit 220 by capacitive coupling. In other words, the plate capacitor 210 of this embodiment does not need to be electrically connected to the ground terminal or the system reference point to measure the voltage signal source 30 to be measured.

[0035] In this embodiment, the transfer function G between the voltage signal source 30 to be measured and the input voltage (Vin) of the signal processing circuit 220 is v-v (s), transfer function G v-i (s), gain relationship G v-v (ω), gain relationship G v-i (ω), phase relationship θ v-v (ω), phase relationship θ v-i (ω) can be described by the following formulas (1) to (6), for example. In each formula, s represents the frequency parameter of Laplace transformation, w represents the frequency parameter of conventional spectrum analysis, v represents the voltage variable, and i represents the current variable. Taking spectrum analysis as an example, the gain relationship G v-v (ω) is the gain change from the voltage to be measured to the input voltage Vin, and the phase relationship θ v-v (ω) is the phase change from the voltage to be measured to the input voltage Vin, and the gain relationship G v-i (ω) is the gain change from the voltage to be measured to the input voltage Vin, and the phase relationship θ v-i (ω) is the phase change from the voltage to be measured to the input voltage Vin.

[0036]

[0037]

[0038]

[0039]

[0040]

[0041]

[0042] Figure 3 FIG. 1 is a flow chart of a non-contact voltage measurement method according to an embodiment of the present invention. Figure 1 as well as Figure 3 The non-contact voltage measurement system 100 performs the following steps S310 to S340. In step S310, the non-contact voltage measurement system can measure the voltage signal source 10 to be measured through the capacitive coupling structure 110 to generate a measurement signal. Figure 4 , Figure 4 is a schematic diagram of a measurement signal according to an embodiment of the present invention. In this embodiment, the capacitive coupling structure 110 can output Figure 4 The measurement signal 410 is shown. In step S320, the signal processing circuit 120 may generate an output signal according to the measurement signal. The signal processing circuit 120 may output the output signal to the sampling unit 131. Figure 5 , Figure 5 is a schematic diagram of an output signal of an embodiment of the present invention. In this embodiment, the signal processing circuit 120 may be, for example, Figure 4 The measurement signal 410 shown in the figure is subjected to analog signal processing, wherein for example, signal conversion (for example, adjusting the voltage range of the signal), signal filtering and / or signal amplification are performed on the measurement signal 410 to generate a signal as shown in FIG. Figure 5 The output signal 510 is shown, but the present invention is not limited thereto. The signal processing circuit 120 is used to enhance the measurement signal 410 and maintain the waveform characteristics of the original signal to facilitate subsequent signal sampling.

[0043] In step S330, the sampling unit 131 may analyze the output signal to generate a sampling signal. Figure 5 The output signal 510 shown is converted from analog to digital to generate a sampled signal (ie, a digital signal). In step S340, the sampling unit 131 may output the sampled signal to the trained artificial intelligence model 132, so that the trained artificial intelligence model 132 outputs a restored signal. Figure 6 , Figure 6 FIG. 1 is a schematic diagram of a restored signal according to an embodiment of the present invention. In this embodiment, the trained artificial intelligence model 132 can generate amplitude parameters, phase parameters, and frequency parameters according to the sampled signal, and the trained artificial intelligence model 132 can generate the following according to the amplitude parameters, phase parameters, and frequency parameters: Figure 6The restored signal 610 is shown. The trained artificial intelligence model 132 can perform functions such as amplitude restoration, phase identification, frequency tracking, and waveform reconstruction.

[0044] In this embodiment, the trained artificial intelligence model 132 may include a signal restoration model. The signal restoration model may be used to generate a restored signal 610 according to the sampled signal. The signal restoration model may also include a plurality of adjustable parameters, and the adjustable parameters include at least one of a weight parameter, an offset parameter, and a nonlinear function. In one embodiment, the reference Figure 7 , Figure 7 is a schematic diagram of a target signal according to an embodiment of the present invention. The operation circuit 130 can compare the restored signal 610 and the Figure 7 The corresponding target signal 710 shown in the figure is used to generate a comparison result, and the adjustable parameters are optimized and trained according to the comparison result and the optimization algorithm. In other words, the artificial intelligence model 132 can achieve accurate signal restoration function by training and optimizing the adjustable parameters during the training process. For example, the gain relationship G v-v (ω), G v-i (ω) can be used to optimize the parameters related to the amplitude restoration function. The aforementioned phase relationship θ v-v (ω), θ v-i (ω) can be used to optimize the relevant parameters of the phase discrimination function, etc., so as to train a more accurate artificial intelligence model 132.

[0045] In this embodiment, the artificial intelligence model 132 can provide a restored signal 610 to the output unit 133. The output unit 133 can select to output the measurement results such as waveform to time axis data or waveform measurement feature values ​​to the user according to the aforementioned adjustable parameters according to the use requirements, and can display the relevant values ​​and waveforms of the measurement results through a display, for example, but the present invention is not limited thereto.

[0046] Figure 8 FIG. 1 is a flow chart of generating a restoration signal according to an embodiment of the present invention. Figure 1 as well as Figure 8 The trained artificial intelligence model 132 may execute the following steps S810 to S830 to generate a restored signal. In this embodiment, the artificial intelligence model 132 may include an input layer, a plurality of hidden layers, and an output layer.

[0047] In step S810, the operation circuit 130 may input the sampled signal to the input layer of the artificial intelligence model 132. The artificial intelligence model 132 may, for example, first perform a down-sampling function to reduce the sampling rate of the sampled signal (digital signal) of N-dimensional length to reduce the data size to data of M-dimensional length, where N is greater than M, and N and M are positive integers. In this way, the memory size required for each subsequent hidden layer can be effectively saved and the operation resources can be effectively saved so that it can be executed in an operation circuit with lower operation power.

[0048] In step S820, the operation circuit 130 may perform operations on multiple hidden layers of the artificial intelligence model 132. The multiple hidden layers may, for example, include a phase identification-frequency tracking subnetwork, a coupling structure weight subnetwork, and an amplitude restoration subnetwork. The phase identification-frequency tracking subnetwork may, for example, be used to identify the phase characteristics of the signal to be measured in real time, and to immediately feedback the frequency of the signal to be measured. The coupling structure weight subnetwork may be used to infer the system characteristic parameters of the coupling structure, so that the artificial intelligence model 132 can consider the influence of the coupling structure to improve the accuracy of the restored signal. The amplitude restoration subnetwork may be used to restore the fundamental wave amplitude of the signal to be measured and its harmonic amplitude component waveform and value. In this regard, the subnetworks of different hidden layers may be implemented by different nonlinear functions, and the nonlinear functions may include optimized weight parameters and offset parameters, etc.

[0049] In step S830, the operation circuit 130 may generate a restored signal through the output layer of the artificial intelligence model 132. The artificial intelligence model 132 may, for example, perform an up-sampling function to restore the original downsampled and operated M-dimensional length signal to the original N-dimensional length restored signal. Therefore, the artificial intelligence model 132 of this embodiment can achieve an effective signal restoration function.

[0050] In addition, in one embodiment, the artificial intelligence model 132 may further include a data generation model. The data generation model may be used to generate an analog voltage source and to calculate an analog sampled signal based on the transfer function (G(s)) of the capacitive coupling structure 110 and the signal processing circuit 120, and may be used, for example, with Figure 7 The corresponding target signal 710 shown is used to establish a training data set to effectively verify the training results of the artificial intelligence model 132 during the training process. In this regard, during the model training process, the artificial intelligence model 132 can generate a corresponding reference restoration signal according to the analog sampling signal, and the operation circuit 130 can effectively train the artificial intelligence model 132 by comparing the reference restoration signal with the target signal.

[0051] In summary, the non-contact voltage measurement method and the non-contact voltage measurement system of the present invention can measure the original voltage signal of the voltage signal source to be measured in a non-contact manner, and can accurately restore the measured signal through the trained artificial intelligence model. In other words, the restored signal generated by the artificial intelligence model of the present invention restoring the measured signal corresponding to the original voltage signal of the voltage signal source to be measured can have a high degree of restoration, so that the restored signal can be effectively used for subsequent signal processing and / or signal analysis.

[0052] The present invention has been described by the above-mentioned relevant embodiments, however, the above-mentioned embodiments are only examples for implementing the present invention. It must be pointed out that the disclosed embodiments do not limit the scope of the present invention. On the contrary, changes and modifications made without departing from the spirit and scope of the present invention are all within the scope of patent protection of the present invention.

Claims

1. A non-contact voltage measurement method, characterized in that: include: Measuring a voltage signal source to be measured through a capacitive coupling structure to generate a measurement signal; generating an output signal according to the measurement signal through a signal processing circuit; Analyzing the output signal through a sampling unit to generate a sampling signal; as well as The sampling signal is output to the trained artificial intelligence model so that the trained artificial intelligence model outputs a restored signal.

2. The non-contact voltage measurement method according to claim 1, wherein: The capacitive coupling structure includes: A flat plate capacitor having a first insulating surface and a second insulating surface, The first insulating surface of the flat plate capacitor is contact-coupled with a first line segment of a signal line of the voltage signal source to be measured, and the second insulating surface of the flat plate capacitor is contact-coupled with a second line segment of the signal line of the voltage signal source to be measured.

3. The non-contact voltage measurement method according to claim 1, wherein: The steps of generating the output signal include: The output signal is processed by the signal processing circuit at least one of the following: analog signal processing, signal filtering and signal amplification.

4. The non-contact voltage measurement method according to claim 1, wherein: The steps of generating the sampling signal include: The output signal is converted from analog to digital to generate the sampling signal.

5. The non-contact voltage measurement method according to claim 1, wherein: The trained artificial intelligence model includes a signal restoration model, which includes multiple adjustable parameters, and the adjustable parameters include weight parameters, offset parameters and at least one of nonlinear functions, wherein the signal restoration model is used to generate the restored signal based on the sampled signal.

6. The non-contact voltage measurement method according to claim 5, wherein: Also includes: The restored signal and the corresponding target signal are compared to generate a comparison result.

7. The non-contact voltage measurement method according to claim 5, wherein: The trained artificial intelligence model also includes a data generation model, wherein the data generation model is used to generate an analog voltage source and to calculate an analog sampling signal based on the capacitive coupling structure and the transfer function of the signal processing circuit, wherein the analog voltage source and the analog sampling signal are used to train the signal restoration model.

8. The non-contact voltage measurement method according to claim 1, wherein: The steps of outputting the restoration signal include: Generating amplitude parameters, phase parameters and frequency parameters according to the sampled signal by the trained artificial intelligence model; and The restored signal is generated by the trained artificial intelligence model according to the amplitude parameter, the phase parameter and the frequency parameter.

9. A non-contact voltage measurement system, characterized in that: include: The capacitive coupling structure is used to measure the voltage signal source to be measured to generate a measurement signal; A signal processing circuit electrically connected to the capacitive coupling structure to generate an output signal according to the measurement signal; as well as An operation circuit is electrically connected to the signal processing circuit, and the operation circuit includes: A sampling unit, used for analyzing the output signal to generate a sampling signal; as well as The trained artificial intelligence model is used to receive the sampled signal and output a restored signal.

10. The non-contact voltage measurement system as claimed in claim 9, wherein: The capacitive coupling structure includes: A flat plate capacitor having a first insulating surface and a second insulating surface, The first insulating surface of the flat plate capacitor contacts a first line segment of a signal line of the voltage signal source to be measured, and the second insulating surface of the flat plate capacitor contacts a second line segment of the signal line of the voltage signal source to be measured.

11. The non-contact voltage measurement system as claimed in claim 9, wherein: The signal processing circuit performs at least one of the following processing on the output signal: analog signal processing, signal filtering and signal amplification.

12. The non-contact voltage measurement system as claimed in claim 9, wherein: The sampling unit performs analog-to-digital conversion on the output signal to generate the sampling signal.

13. The non-contact voltage measurement system as claimed in claim 9, wherein: The trained artificial intelligence model includes a signal restoration model, which includes multiple adjustable parameters, and the adjustable parameters include a weight parameter, an offset parameter, and at least one of a nonlinear function, wherein the signal restoration model is used to generate the restored signal based on the sampled signal.

14. The non-contact voltage measurement system as claimed in claim 13, wherein: The operation circuit compares the restored signal with the corresponding target signal to generate a comparison result.

15. The non-contact voltage measurement system as claimed in claim 13, wherein: The trained artificial intelligence model also includes a data generation model, wherein the data generation model is used to generate an analog voltage source and to calculate an analog sampling signal based on the capacitive coupling structure and the transfer function of the signal processing circuit, wherein the analog voltage source and the analog sampling signal are used to train the signal restoration model.

16. The non-contact voltage measurement system as claimed in claim 9, wherein: The trained artificial intelligence model generates an amplitude parameter, a phase parameter and a frequency parameter according to the sampled signal, and the trained artificial intelligence model generates the restored signal according to the amplitude parameter, the phase parameter and the frequency parameter.

Images