Method and device for atom detection of partial discharge signal

Abstract

The invention discloses a method and device for atom detection of partial discharge signals, and belongs to the technical field of partial discharge signal detection. Carrying out signal interaction and coupling; according to the method, the atomic optical signals are subjected to photoelectric detection, signal extraction and partial discharge characteristic analysis and identification, so that the high stability and repeatability of the atomic optical signals are ensured by constructing a closed-loop frequency stabilization and digital pre-distortion modulation system. Efficient coupling of an electronic optical signal and a to-be-detected electric signal is realized through a coplanar waveguide structure, and a partial discharge event is effectively identified in combination with a dual-channel differential detection and feature extraction algorithm. The method has the advantages of high sensitivity, strong anti-interference performance, non-contact detection and the like, and is suitable for practical application scenes such as state monitoring of high-voltage equipment and on-line detection of a power system. According to the invention, the interaction between the atomic optical signal and the signal to be detected is utilized, and the optical signal change caused by the interaction is detected, so that the high-sensitivity and high-anti-interference detection of the partial discharge signal is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of detecting partial discharge signals, and particularly relates to a method and device for detecting partial discharge signals by atoms. Background Art

[0002] Currently, most partial discharge detections adopt the capacitive coupling method as disclosed in the patent publication number "CN110045241B". These methods are vulnerable to on-site electromagnetic interference, resulting in a decrease in detection sensitivity or even misjudgment. To overcome the above problems, some studies have attempted to introduce optical detection means, but their response characteristics to partial discharge signals are still limited by the coupling method between the optical system and the object under test. In the prior art, there is no detection mechanism that utilizes the physical interaction between atomic optical signals and signals to be measured to reflect the characteristics of partial discharge. Summary of the Invention

[0003] To solve the defects in the prior art, the present invention proposes a method and device for detecting partial discharge signals by atoms. By using the interaction between atomic optical signals and signals to be measured, and detecting the change in optical signals caused by this interaction, high-sensitivity and high anti-interference detection of partial discharge signals can be achieved.

[0004] The present invention adopts the following technical solutions.

[0005] A method for detecting partial discharge signals by atoms includes: Step 1: Generate and modulate atomic optical signals; Step 2: Perform signal interaction and coupling; Step 3: Photoelectric detection and signal extraction; Step 4: Analyze and identify partial discharge characteristics.

[0006] Further, in Step 1, a narrow-linewidth laser is used to excite a specific atomic medium to generate an atomic resonance optical signal; an external electro-optic modulator is arranged on the optical path of the atomic resonance optical signal, and the atomic resonance optical signal is modulated by the external electro-optic modulator. The modulated atomic optical signal is used as a probe signal for physical interaction with the signal to be measured.

[0007] Further, in Step 2, the modulated atomic optical signal and the signal to be measured are coupled in a set space, that is, the atomic optical signal and the signal to be measured achieve physical interaction at the electromagnetic field level through the set space.

[0008] Further, in Step 2, an open resonator structure is adopted in the set space to enhance the interaction efficiency between the atomic optical signal and the signal to be measured, and an electromagnetic shielding structure is introduced into the set space.

[0009] Further, in step 3, a balanced photodetector is used to receive the atomic optical signal after interaction, and at the same time, the original electrical signal to be measured is introduced as a reference channel to form a differential detection structure; the photodetector converts the atomic optical signal into an electrical signal, and performs digital sampling through an analog-to-digital converter and transmits the data of the digital sampling to the FPGA controller. The FPGA controller demodulates the data of the digital sampling by using a lock-in amplification or digital quadrature demodulation method to extract its amplitude, phase or frequency offset.

[0010] Further, in step 3, the balanced photodetector is composed of two symmetric PIN photodiodes, and the two symmetric PIN photodiodes form two optical paths; the output voltage signal of the balanced photodetector is proportional to the difference in light intensity between the two optical paths and satisfies the following expression:

[0011] where is the responsivity of the balanced photodetector, and are the incident light intensities of the atomic optical signal on the two optical paths respectively.

[0012] Further, in step 4, the FPGA controller synchronizes the sampled data of the received electro-optical signal and the sampled data of the electrical signal to be measured, and extracts the following partial discharge characteristics as key features: Transient amplitude change of the electro-optical signal 、Phase offset of the electro-optical signal and the cross-correlation coefficient between the electro-optical signal and the electrical signal to be measured .

[0013] Further, in step 4, two channels of the high-speed analog-to-digital converter perform parallel data sampling on the electro-optical signal and the electrical signal to be measured by using a high-precision clock synchronization unit; Based on the analysis of variance method, the transient amplitude change amount of the electro-optical signal in a set time period is extracted , specifically including: (1) Perform baseline calibration: Obtain the optical signal baseline in advance during a set time period without partial discharge , The calculation formula of 𝐼 where is the number of data of the digital sampling of the electro-optical signal during a set time period without partial discharge, is the amplitude value of the th data of the digital sampling of the electro-optical signal during a set time period without partial discharge; (2) Perform transient detection: Use the analysis of variance method, that is, first obtain the variance of the amplitude values of the digitized sampling data of the electro-optical signal during a set period without partial discharge. , when the amplitude value of the digitized sampling of the electro-optical signal during the set period is outside , then this is determined as the transient amplitude value and defined as ; 𝜎 (3) Calculate the transient amplitude change , and its calculation formula is:

[0014] where is to obtain the maximum value; Through the digital quadrature demodulation method, convert the modulated electro-optical signal into in-phase and quadrature components, and use the four-quadrant arctangent algorithm to calculate the phase offset of the electro-optical signal , which specifically includes: (1) Perform quadrature demodulation: Perform quadrature demodulation on the digitized sampling data of the modulated electro-optical signal at time , where is the frequency of the electro-optical signal, is the phase of the electro-optical signal at time , is the amplitude of the electro-optical signal. After quadrature demodulation, obtain the in-phase component and the quadrature component at time ; (2) Perform phase extraction: Use the four-quadrant arctangent algorithm to calculate the instantaneous phase at time ; (3) Calculate the phase offset of the electro-optical signal , where is the average value of the instantaneous phases of all sampling times of the electro-optical signal during the set period, is the average value of the instantaneous phases of all sampling times of the electro-optical signal during the set period without partial discharge; Construct the cross-correlation function of the electro-optical signal to obtain the cross-correlation coefficient between the electro-optical signal and the measured electrical signal, which specifically includes: (1) Construct the cross-correlation function of the electro-optical signal, where is the a data is the th data of the digital sampling of the electrical signal to be measured during the set time period is the average value of the data of the digital sampling of the electro-optical signal during the set time period is the average value of the data of the digital sampling of the electrical signal to be measured during the set time period; (2) The cross-correlation coefficient between the electro-optical signal and the electrical signal to be measured The calculation formula is where is to obtain the maximum value of

[0015] Further, in step 4, the transient amplitude change of the electro-optical signal the phase shift of the electro-optical signal and the cross-correlation coefficient between the electro-optical signal and the electrical signal to be measured are normalized and then input into the multi-layer perceptron classifier; the multi-layer perceptron classifier adopts a three-layer structure: 3 nodes in the input layer, 10 nodes in the hidden layer, 1 node in the output layer, the activation function is ReLU, and the output layer uses the Sigmoid function to generate the partial discharge probability value , if the partial discharge probability value is higher than the set threshold , it is determined that there is partial discharge, otherwise it is determined that there is no partial discharge

[0016] An apparatus for detecting partial discharge signals by atoms, comprising: A photodetector, an analog-to-digital converter and an FPGA controller are sequentially connected in sequence, and the analog-to-digital converter is also connected to the analog-to-digital converter; The apparatus for detecting partial discharge signals by atoms further includes: A generating module, which is used to generate and modulate the atomic optical signal; A coupling module, which is used to perform signal interaction and coupling; An extraction module, which is used for photoelectric detection and signal extraction; An identification module, which is used for partial discharge feature analysis and identification

[0017] The beneficial effects of the present invention are that, compared with the prior art, the technical effects of the present invention include: The present invention generates and modulates atomic optical signals; performs signal interaction and coupling; conducts photoelectric detection and signal extraction, as well as partial discharge feature analysis and recognition. Thus, by constructing a closed-loop frequency stabilization and digital predistortion modulation system, the high stability and repeatability of atomic optical signals are ensured. The efficient coupling of electro-optical signals and the electrical signals to be measured is achieved through a coplanar waveguide structure. Combining with a dual-channel differential detection and feature extraction algorithm, partial discharge events are effectively identified. This method has the advantages of high sensitivity, strong anti-interference ability, and non-contact detection, and is applicable to practical application scenarios such as the condition monitoring of high-voltage equipment and the on-line detection of power systems. Description of the Drawings

[0018] Figure 1 is a flowchart of the method for detecting partial discharge signals by atoms described in the present invention; Figure 2 is a module structure diagram of the device for detecting partial discharge signals by atoms described in the present invention. Detailed Embodiments

[0019] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions of the present invention in conjunction with the drawings in the embodiments of the present invention. The embodiments described herein are only some of the embodiments of the present invention, rather than all of them. Based on the spirit of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0020] As Figure 1 shown, a method for detecting partial discharge signals by atoms described in the present invention includes: Step 1: Generate and modulate atomic optical signals; The purpose of Step 1 is to generate atomic optical signals with specific frequencies.

[0021] In a preferred but non-limiting embodiment of the present invention, in Step 1, a narrow-linewidth laser is used to excite a specific atomic medium (such as rubidium atomic vapor) to generate an atomic resonance optical signal with stable frequency and polarization characteristics; when the atomic resonance optical signal passes through the atomic medium, an electromagnetically induced transparency (EIT) effect or a coherent population transfer (CPT) effect occurs to form an optical probe with high stability and tunable characteristics. An external electro-optic modulator is arranged on the optical path of the atomic resonance optical signal, and the atomic resonance optical signal is modulated by the external electro-optic modulator to make it have specific frequency modulation or phase encoding characteristics, so as to enhance the signal-to-noise ratio and anti-interference ability in subsequent detection. The modulated atomic optical signal formed is used as a probe signal to physically interact with the electrical signal to be measured. This process ensures that the atomic optical signal has a high-sensitivity response to the electromagnetic disturbance caused by partial discharge in subsequent interactions.

[0022] In an embodiment of the present invention, a narrow linewidth laser with a central wavelength of 780 nm (linewidth < 10 kHz) is used to excite a rubidium atomic vapor cell. The laser frequency is precisely locked to the hyperfine transition resonance frequency of the D2 line of rubidium atoms (85Rb F = 2 → F' = 3) to excite the electromagnetically induced transparency (EIT) effect. Specifically, the laser frequency is synchronized with the atomic transition frequency in the reference saturation absorption cell through the Pound - Drever - Hall (PDH) frequency locking technique, and the frequency stability reaches within ±10 kHz.

[0023] Subsequently, the laser signal enters an electro - optic modulator (EOM) and is phase - modulated under the drive of an external radio - frequency signal (10.7 MHz). The modulation depth is dynamically adjusted by an FPGA controller to compensate for the non - linear response of the modulator and ensure that the modulated optical signal has a stable modulation depth (within ±1%). The modulated optical signal carries the characteristics of periodic phase perturbations, forming a probe signal that is highly sensitive to the electromagnetic perturbations caused by partial discharges.

[0024] Step 2: Perform signal interaction and coupling; The purpose of step 2 is to physically interact the atomic optical signal and the electrical signal to be measured in a set space.

[0025] In a preferred but non - restrictive embodiment of the present invention, in step 2, the atomic optical signal formed after modulation and the electrical signal to be measured are coupled in a set space, that is, the atomic optical signal and the electrical signal to be measured achieve physical interaction at the electromagnetic field level through this set space (the set space is a free space or a waveguide structure). The local discharge pulses that may exist in the electrical signal to be measured will change the electromagnetic environment in this region, and then modulate the propagation characteristics of the atomic optical signal, such as phase, polarization state, or absorption intensity.

[0026] In a preferred but non - restrictive embodiment of the present invention, in step 2, a high - bandwidth waveguide or an open resonator structure is used in the set space to enhance the interaction efficiency between the atomic optical signal and the electrical signal to be measured, and an electromagnetic shielding structure is introduced in the set space to suppress the influence of external interference signals. This coupling process ensures that the response of the atomic optical signal to the partial discharge signal has high selectivity and repeatability. The atomic optical signal after interaction carries the perturbation information related to partial discharges in the signal to be measured and enters the subsequent detection and analysis process.

[0027] In an embodiment of the present invention, the modulated atomic optical signal is guided along the waveguide propagation path to the detection area and forms an electromagnetic coupling with the conductor structure (such as a high - voltage cable) where the electrical signal to be measured in the monitoring area is located through an electromagnetic coupling device. The electrical signal to be measured is the magnetic field signal of a 10 kV - class AC transmission line, and the potential frequency range of its local discharge signal is 100 MHz - 1 GHz.

[0028] A coplanar waveguide structure is adopted as the electromagnetic coupling device. The atomic optical signal propagates along the waveguide propagation path and interacts with the electromagnetic field on the conductor. When there is a partial discharge event in the circuit, the transient electromagnetic pulse generated by it (typical duration < 1 ns, amplitude up to several V / m) will disturb the energy level structure of the atomic medium, and then modulate the phase or polarization characteristics of the passing optical signal.

[0029] An electromagnetic shielding layer (made of μ-metal material, shielding efficiency > 60 dB@1 GHz) is introduced into the electromagnetic coupling device structure to suppress the influence of environmental electromagnetic interference and improve the signal-to-noise ratio of the system. Measured results show that this structure can increase the response sensitivity of the electro-optical signal to the partial discharge signal by about 3 times.

[0030] Step 3: Photoelectric detection and signal extraction; The purpose of Step 3 is to receive the electro-optical signal after interaction and the original electrical signal to be measured through a photodetector, and output the corresponding electrical signal.

[0031] In a preferred but non-limiting embodiment of the present invention, in Step 3, a balanced photodetector with a high response speed is used to receive the atomic optical signal after interaction, and at the same time, the original electrical signal to be measured is introduced as a reference channel to form a differential detection structure; the photodetector converts the atomic optical signal into an electrical signal, and performs digital sampling through a high-speed analog-to-digital converter (ADC) and transmits the digital sampling data to the FPGA controller, with a sampling rate not less than 10 GS / s to capture the transient disturbance characteristics caused by partial discharge. The FPGA controller demodulates the digital sampling data of the electro-optical signal formed after modulation by using the lock-in amplification or digital quadrature demodulation method, and extracts key parameters such as its amplitude, phase or frequency offset. This step realizes high-sensitivity detection of the weak electromagnetic disturbance caused by partial discharge and converts the signal characteristics into analyzable digital data.

[0032] In a preferred but non-limiting embodiment of the present invention, in Step 3, the atomic optical signal after interaction enters a balanced photodetector, which is composed of two symmetric PIN photodiodes. The two symmetric PIN photodiodes form two optical paths, which can effectively suppress the common-mode noise; the output voltage signal of the balanced photodetector is proportional to the difference in light intensity of the two optical paths and satisfies the following expression:

[0033] where is the responsivity of the balanced photodetector (unit: V / W), and They are the incident light intensities of the atomic optical signals on the two optical paths respectively.

[0034] This voltage signal then enters a channel of a high-speed analog-to-digital converter (ADC, sampling rate 10 GS / s, resolution 10 bit) to complete digital sampling. At the same time, the electrical signal to be measured also enters another channel of the high-speed analog-to-digital converter through a coupler for synchronous sampling, and the data of the synchronous sampling of the electrical signal to be measured forms a dual-channel differential structure. By comparing the time-aligned data of the electronic optical signal and the electrical signal to be measured, the perturbation characteristics in the response of the electronic optical signal are extracted.

[0035] Step 4: Partial discharge feature analysis and identification.

[0036] The purpose of Step 4 is to process the electrical signal output by the photodetector, extract the characteristic parameters related to partial discharge, and determine whether there is a partial discharge signal.

[0037] In a preferred but non-limiting embodiment of the present invention, in Step 4, the FPGA controller synchronously processes the sampled data of the received electronic optical signal and the sampled data of the electrical signal to be measured, and extracts the following partial discharge characteristics as key features: Transient amplitude change of the electronic optical signal and phase shift of the electronic optical signal and the cross-correlation coefficient between the electronic optical signal and the electrical signal to be measured .

[0038] In a preferred but non-limiting embodiment of the present invention, in Step 4, two channels of the high-speed analog-to-digital converter use a high-precision clock synchronization unit (time error <10 ps) to perform parallel data sampling on the electronic optical signal and the electrical signal to be measured, ensuring that the sampled data of the two signals are strictly aligned in the time domain; Based on the analysis of variance method, the transient amplitude change amount of the electronic optical signal in the period when partial discharge events may occur is extracted , specifically including: (1) Perform baseline calibration: Obtain the optical signal baseline in advance during the period of no partial discharge set , The calculation formula is: 𝐼 where is the number of digital sampling data of the electronic optical signal formed after modulation during the period of no partial discharge set, is the amplitude value of the th data arranged in the order of sampling time of the digital sampling of the electronic optical signal formed after modulation during the period of no partial discharge set; (2) Conduct transient detection: Use the analysis of variance method, that is, first obtain the variance of the amplitude values of the digitized sampling data of the electro-optical signal during the set period without partial discharge. When the amplitude value of the th data arranged in the order of sampling time of the digitized sampling of the electro-optical signal during the set period when a partial discharge event may occur is outside, then this is determined as the transient amplitude value and defined as ; 𝜎 (3) Calculate the transient amplitude change , and its calculation formula is:

[0039] where is to obtain the maximum value; this method can effectively identify the mutation characteristics of the electro-optical signal caused by partial discharge.

[0040] Through the digital quadrature demodulation method, convert the modulated electro-optical signal into in-phase and quadrature components, and use the four-quadrant arctangent algorithm to calculate the phase offset of the electro-optical signal , which specifically includes: (1) Conduct quadrature demodulation: Perform quadrature demodulation on the digitized sampling data of the modulated electro-optical signal at time , where is the frequency of the electro-optical signal, is the phase of the electro-optical signal at time , is the amplitude of the electro-optical signal. After quadrature demodulation, obtain the in-phase component and the quadrature component at time ; (2) Conduct phase extraction: Use the four-quadrant arctangent algorithm to calculate the instantaneous phase at time ; (3) Calculate the phase offset [[ID=u59]] of the electro-optical signal, where is the average value of the instantaneous phases of all sampling times of the electro-optical signal during the set period when a partial discharge event may occur, is the average value of the instantaneous phases of all sampling times of the electro-optical signal during the set period without partial discharge; Use the four-quadrant arctangent function to achieve high-precision phase calculation and ensure that the phase offset detection error is less than 0.1 rad.

[0041] Construct the cross-correlation function of the electro-optical signal to obtain the cross-correlation coefficient between the electro-optical signal and the electrical signal to be measured , which specifically includes: (1) Construct the cross-correlation function of the electro-optical signal , where is the th data arranged in the order of sampling time of the digital sampling of the electro-optical signal during the set time period when a partial discharge event may occur, is the th data arranged in the order of sampling time of the digital sampling of the electrical signal to be measured during the set time period when a partial discharge event may occur, is the average value of the data arranged in the order of sampling time of the digital sampling of the electro-optical signal during the set time period when a partial discharge event may occur, is the average value of the data arranged in the order of sampling time of the digital sampling of the electrical signal to be measured during the set time period when a partial discharge event may occur; (2) The cross-correlation coefficient between the electro-optical signal and the electrical signal to be measured is calculated as , where is to obtain the maximum value. This parameter reflects the coupling strength between the electro-optical signal and the electrical signal to be measured in the partial discharge event.

[0042] In a preferred but non-limiting embodiment of the present invention, in step 4, the transient amplitude change of the electro-optical signal, the phase shift of the electro-optical signal, and the cross-correlation coefficient between the electro-optical signal and the electrical signal to be measured are normalized and then input into a multi-layer perceptron (MLP) classifier; the multi-layer perceptron (MLP) classifier adopts a three-layer structure: 3 nodes in the input layer, 10 nodes in the hidden layer, 1 node in the output layer, the activation function is ReLU, and the output layer uses the Sigmoid function to generate the partial discharge probability value . If the partial discharge probability value is higher than the set threshold , it is determined that there is a partial discharge, otherwise it is determined that there is no partial discharge. The training data of the embodiment of the present invention sent into the multi-layer perceptron (MLP) classifier contains 100,000 groups of simulation data (including partial discharge models and interference signals), and the verification set accuracy rate > 99%. Finally, the judgment result of the existence or non-existence of partial discharge is output. The set threshold can be set according to specific requirements, just as can be set to 0.75.

[0043] Verified by actual measurement data, the method of the present invention successfully identified 97 partial discharge events in 100 tests, with a false alarm rate lower than 2%, significantly superior to the traditional capacitive coupling detection method.

[0044] As Figure 2 shown, a device for detecting partial discharge signals by atoms according to the present invention includes: A photodetector, an analog-to-digital converter, and an FPGA controller are sequentially connected in series, and the analog-to-digital converter is also connected to the analog-to-digital converter; The device for detecting partial discharge signals by atoms further includes: A generating module for generating and modulating an atomic optical signal; A coupling module for signal interaction and coupling; An extraction module for photoelectric detection and signal extraction; An identification module for partial discharge feature analysis and identification.

[0045] The beneficial effects of the present invention are that, compared with the prior art, the technical effects of the present invention include: The present invention generates and modulates an atomic optical signal; performs signal interaction and coupling; conducts photoelectric detection and signal extraction, as well as partial discharge feature analysis and identification. Thus, by constructing a closed-loop frequency stabilization and digital predistortion modulation system, the high stability and repeatability of the atomic optical signal are ensured. The efficient coupling of the electro-optical signal and the electrical signal to be measured is achieved through a coplanar waveguide structure. Combining a dual-channel differential detection and feature extraction algorithm, partial discharge events are effectively identified. This method has the advantages of high sensitivity, strong anti-interference ability, and non-contact detection, and is suitable for actual application scenarios such as high-voltage equipment condition monitoring and power system on-line detection.

[0046] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that: modifications or equivalent replacements can still be made to the specific embodiments of the present invention, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A method for detecting partial discharge signals by an atom, characterized in that, Including: Step 1: Generate and modulate an atomic optical signal; Step 2: Perform signal interaction and coupling; Step 3: Photoelectric detection and signal extraction; Step 4: Partial discharge feature analysis and identification.

2. The method for detecting partial discharge signals by atoms according to claim 1, characterized in that, In Step 1, a narrow linewidth laser is used to excite a specific atomic medium to generate an atomic resonance optical signal; An external electro-optic modulator is arranged on the optical path of the atomic resonance optical signal, and the atomic resonance optical signal is modulated by the external electro-optic modulator. The formed atomic optical signal after modulation is used as a probe signal for physical interaction with the electrical signal to be measured.

3. The method for detecting partial discharge signals by atoms according to claim 2, characterized in that, In Step 2, the formed atomic optical signal after modulation and the electrical signal to be measured are coupled in a set space, that is, the atomic optical signal and the electrical signal to be measured achieve physical interaction at the electromagnetic field level through the set space.

4. The method for detecting partial discharge signals by atoms according to claim 3, characterized in that In Step 2, an open resonator structure is adopted in the set space to enhance the interaction efficiency between the atomic optical signal and the electrical signal to be measured, and an electromagnetic shielding structure is introduced into the set space.

5. The method for detecting partial discharge signals by atoms according to claim 4, characterized in that In Step 3, a balanced photodetector is used to receive the atomic optical signal after interaction, and at the same time, the original electrical signal to be measured is introduced as a reference channel to form a differential detection structure; the photodetector converts the atomic optical signal into an electrical signal, and performs digital sampling through an analog-to-digital converter and transmits the data of the digital sampling to the FPGA controller. The FPGA controller demodulates the data of the digital sampling by using a lock-in amplification or digital quadrature demodulation method to extract its amplitude, phase or frequency offset.

6. The method for detecting partial discharge signals by atoms according to claim 5, characterized in that In step 3, the balanced photodetector consists of two symmetric PIN photodiodes, and the two symmetric PIN photodiodes form two optical paths; the output voltage signal of the balanced photodetector is proportional to the difference in light intensity between the two optical paths and satisfies the following expression: Among them To balance the responsivity of the photodetector and are respectively the incident light intensities of the atomic optical signal on the two optical paths.

7. The method for detecting partial discharge signals by atoms according to claim 6, wherein In Step 4, the FPGA controller synchronizes the sampled data of the received electro-optical signal and the sampled data of the electrical signal to be measured, and extracts the following partial discharge features as key features: Transient amplitude change of electro-optical signal , phase shift of electro-optical signal and cross-correlation coefficient between electro-optical signal and electrical signal to be measured .

8. The method for detecting partial discharge signals by atoms according to claim 7, characterized in that In Step 4, two channels of a high-speed analog-to-digital converter perform parallel data sampling on the electro-optical signal and the electrical signal to be measured by using a high-precision clock synchronization unit; Based on the analysis of variance method, extract the transient amplitude change of the electro-optical signal during the set time period , specifically including: (1) Perform baseline calibration: Obtain the optical signal baseline in advance during a preset time period without partial discharge. , The calculation formula of I wherein is the number of data of the digital sampling of the electro-optical signal during a set time period without partial discharge, is the amplitude value of the th data of the digital sampling of the electro-optical signal during a set time period without partial discharge; (2) Perform transient detection: Use the analysis of variance method, that is, first obtain the variance of the amplitude values of the digitized samples of the electro-optical signal during a set period without partial discharge. , when the amplitude value of the th data of the digitized sample of the electro-optical signal during the set period is outside , then this is determined as the transient amplitude value and defined as ; 𝜎 (3) Calculate the transient amplitude change amount The calculation formula is as follows: Among them to obtain the maximum value; By means of digital quadrature demodulation method, the electro-optical signal formed after modulation is converted into in-phase and quadrature components, and the phase offset of the electro-optical signal is calculated by using the four-quadrant arctangent algorithm , which specifically includes: (1) Perform quadrature demodulation: For the electro-optical signal formed after modulation at time digitally sampled data perform quadrature demodulation, where is the frequency of the electro-optical signal, is the phase of the electro-optical signal at time , is the amplitude of the electro-optical signal. After quadrature demodulation, obtain the in-phase component and the quadrature component at time ; (2) Perform phase extraction: Use the four-quadrant arctangent algorithm to calculate the instantaneous phase at time ; ; (3) Calculate the phase offset of the electro-optical signal , where is the average of the instantaneous phases at all sampling moments of the electro-optical signal during the set time period, is the average of the instantaneous phases at all sampling moments of the electro-optical signal during the set time period without partial discharge; Construct the cross-correlation function of the electro-optical signal to obtain the cross-correlation coefficient between the electro-optical signal and the electrical signal to be measured , which specifically includes: (1) Construct the cross-correlation function of the electro-optical signal , where is the -th data of the digital sampling of the electro-optical signal during the set time period, is the -th data of the digital sampling of the electrical signal to be measured during the set time period, is the average value of the data of the digital sampling of the electro-optical signal during the set time period, is the average value of the data of the digital sampling of the electrical signal to be measured during the set time period; (2)Cross-correlation coefficient between the electro-optical signal and the electrical signal to be measured The calculation formula is , where is to obtain the maximum value.

9. The method for detecting partial discharge signals by atoms according to claim 8, wherein In step 4, the transient amplitude change of the electro-optical signal , the phase shift of the electro-optical signal and the cross-correlation coefficient between the electro-optical signal and the electrical signal to be measured are normalized and then input into a multi-layer perceptron classifier; the multi-layer perceptron classifier adopts a three-layer structure: 3 nodes in the input layer, 10 nodes in the hidden layer, 1 node in the output layer, the activation function is ReLU, and the output layer uses the Sigmoid function to generate the partial discharge probability value . If the partial discharge probability value is higher than the set threshold , it is determined that there is partial discharge, otherwise it is determined that there is no partial discharge.

10. An apparatus for detecting partial discharge signals by an atom, characterized in that, Including: The photodetector, the analog-to-digital converter and the FPGA controller are sequentially connected in series, and the analog-to-digital converter is also connected to the analog-to-digital converter; The device for detecting partial discharge signals by atoms further includes: A generation module, which is used to generate and modulate an atomic optical signal; A coupling module, which is used to perform signal interaction and coupling; An extraction module, which is used for photoelectric detection and signal extraction; An identification module, which is used for partial discharge feature analysis and identification.

Images