Main cable monitoring method and system of flexible photovoltaic power station and related device

Abstract

The invention discloses a main cable monitoring method and system of a flexible photovoltaic power station and a related device, and relates to the field of photovoltaic power generation, a sensing optical fiber is fixed along a main cable, and the method comprises the following steps: collecting a scattering echo signal of the sensing optical fiber in a period of time, a scattered and returned optical signal is generated in the sensing optical fiber; according to the frequency change of the Rayleigh scattering light signal in the scattering echo signal, obtaining the vibration frequency data of the main cable; acquiring strain data and temperature data of the main cable according to the frequency shift of the Brillouin scattering light signal in the scattering echo signal; and inputting the vibration frequency data, the strain force data, the temperature data, the inherent parameters of the main cable and the environmental parameters at the same moment into a preset classification model for classification, and obtaining an event category result of the main cable output by the preset classification model. The sensing optical fiber is used for monitoring the main cable, environmental parameters are introduced to cope with environmental interference, and the monitoring effect of the main cable is effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of photovoltaic power generation, and in particular to a main cable monitoring method and system for a flexible photovoltaic power station and related devices. BACKGROUND

[0002] In a flexible photovoltaic power station, the main cable is a core load-bearing structure for supporting photovoltaic panels. Due to long-term exposure to outdoor environments, the main cable is susceptible to wind load (a pressure or suction force generated on the surface of a building or engineering structure when wind encounters it), temperature changes, mechanical fatigue, and other factors, which can cause damage or breakage of the main cable, thereby affecting the safety of the flexible photovoltaic power station.

[0003] Therefore, staff need to monitor the main cable to detect potential problems in advance and reduce risks. However, the current main cable monitoring method mainly uses point sensors. Since point sensors can only monitor local points, they cannot cover the entire length of the main cable, resulting in poor monitoring effect. SUMMARY

[0004] In view of the above problems, the present application provides a main cable monitoring method and system for a flexible photovoltaic power station to improve the monitoring effect of the main cable in complex environments. The specific solutions are as follows:

[0005] The first aspect of the present application provides a main cable monitoring method for a flexible photovoltaic power station, a sensing optical fiber is fixed along the main cable, and the main cable monitoring method for the photovoltaic power station comprises:

[0006] Collecting scattered echo signals of the sensing optical fiber within a period of time, the scattered echo signals being signals returned by the sensing optical fiber after emitting light pulse signals from the sensing optical fiber;

[0007] Obtaining vibration frequency data of the main cable according to frequency changes of Rayleigh scattered light signals in the scattered echo signals;

[0008] Obtaining strain force data and temperature data of the main cable according to frequency shifts of Brillouin scattered light signals in the scattered echo signals, the frequency shift of Brillouin scattering of the scattered echo signals being linearly related to the temperature of the main cable and the strain force of the main cable;

[0009] Inputting the vibration frequency data, the strain force data, the temperature data, inherent parameters and environmental parameters of the main cable at the same time into a preset classification model for classification to obtain an event category result of the main cable output by the preset classification model.

[0010] In one possible implementation, a plurality of measuring points are provided on the main cable, and the collecting of the scattered echo signals of the sensing optical fiber within a period of time comprises:

[0011] For each measuring point on the main cable, a scattered echo signal of the sensing fiber is collected within a period of time.

[0012] In a possible implementation, the vibration frequency data of the main cable is obtained according to a frequency change of Rayleigh scattered light signals in the scattered echo signal.

[0013] The vibration frequency data of the main cable is obtained by demodulating a polarization vibration energy difference of Rayleigh scattered light signals in the scattered echo signal.

[0014] In a possible implementation, the obtaining process of the preset classification model includes:

[0015] The three-dimensional data of the main cable, the inherent parameters of the main cable and the environmental parameters are collected, and the three-dimensional data of the main cable includes the vibration frequency data, the strain force data and the temperature data of the main cable.

[0016] A plurality of groups of training data under different working conditions are obtained, and each group of training data under a working condition is composed of the three-dimensional data of the main cable, the inherent parameters of the main cable and the environmental parameters with different values.

[0017] The labeled training data obtained after event labeling of the training data are obtained, and the labeled training data are used to train the convolutional neural network classification model, to obtain the preset classification model, and the labeled types of the labeled training data include various normal events and various abnormal events.

[0018] The second aspect of the application provides a main cable monitoring system of a flexible photovoltaic power station, a sensing fiber is fixed along a main cable, and the main cable monitoring system of the photovoltaic power station includes:

[0019] A collection unit is configured to collect a scattered echo signal of the sensing fiber within a period of time, and the scattered echo signal is a signal returned by the sensing fiber after the sensing fiber transmits a light pulse signal.

[0020] A first obtaining unit is configured to obtain vibration frequency data of the main cable according to a frequency change of Rayleigh scattered light signals in the scattered echo signal.

[0021] A second obtaining unit is configured to obtain strain force data and temperature data of the main cable according to a frequency shift of Brillouin scattered light signals in the scattered echo signal, and the frequency shift of the Brillouin scattering of the scattered echo signal is in a linear relationship with the temperature of the main cable and the strain force of the main cable.

[0022] The classification unit is configured to input the vibration frequency data, the strain force data, the temperature data, the inherent parameters and the environmental parameters of the main cable at the same time into a preset classification model to classify and obtain an event category result of the main cable output by the preset classification model.

[0023] In a possible implementation, the main cable is provided with a plurality of measuring points, and the acquisition unit is specifically configured to:

[0024] For each measuring point on the main cable, the scattering echo signal of the sensing optical fiber is acquired within a period of time.

[0025] In a possible implementation, the first acquisition unit is specifically configured to:

[0026] The polarization vibration energy difference of the Rayleigh scattering light signal in the scattering echo signal is demodulated to obtain the vibration frequency data of the main cable.

[0027] In a possible implementation, the main cable monitoring system of the photovoltaic power station further comprises a construction unit of the preset classification model, and the construction unit is specifically configured to:

[0028] The three-dimensional data of the main cable, the inherent parameters and the environmental parameters of the main cable are acquired, and the three-dimensional data of the main cable comprises the vibration frequency data, the strain force data and the temperature data of the main cable;

[0029] A plurality of groups of training data under different working conditions are acquired, and each group of training data under a working condition is composed of the three-dimensional data of the main cable, the inherent parameters and the environmental parameters of the main cable with different values;

[0030] The labeled training data obtained after event labeling of the training data are acquired, and the labeled training data are used to train the convolutional neural network classification model to obtain the preset classification model, and the types of the labeled training data include various normal events and various abnormal events.

[0031] The third aspect of the application provides an electronic device, comprising at least one processor and a memory connected with the processor, wherein:

[0032] The memory is used to store a computer program;

[0033] The processor is used to execute the computer program, so that the electronic device can implement the main cable monitoring method of the flexible photovoltaic power station according to the first aspect or any implementation manner of the first aspect.

[0034] The fourth aspect of the present application provides a computer program product comprising computer readable instructions which, when executed on an electronic device, cause the electronic device to implement the main cable monitoring method of the photovoltaic power station of the first aspect or any implementation manner of the first aspect.

[0035] By the above technical solution, the present application provides a main cable monitoring method, system and related device of a flexible photovoltaic power station. The method uses a sensing optical fiber to monitor the main cable. By collecting the scattered echo signals returned by the sensing optical fiber according to the optical pulse signals, the vibration frequency data, strain force data and temperature data of the main cable can be analyzed and obtained. The vibration frequency data, strain force data, temperature data, inherent parameters and environmental parameters at the same time of the main cable are input into a preset classification model for classification to obtain the event category result of the main cable output by the preset classification model. The method uses a sensing optical fiber to monitor the main cable. The sensing optical fiber can easily cover the full length of the main cable. When analyzing, the method not only adds the internal parameters and inherent parameters of the main cable, but also adds the environmental parameters. Therefore, the preset classification model can cope with the abnormal situation of the main cable parameters under environmental interference, and can identify the environmental interference events that are not abnormal to the main cable itself, which can effectively reduce the interference of the outdoor environment on the main cable monitoring. Therefore, the method can effectively improve the monitoring effect of the main cable. BRIEF DESCRIPTION OF DRAWINGS

[0036] The above and other features, advantages, and aspects of the present disclosure will become more apparent by describing in detail the following specific embodiments thereof with reference made to the accompanying drawings. Throughout the drawings, the same or similar reference numerals are used to represent the same or similar elements. It is to be understood that the drawings are schematic, and the proportions of the elements and features do not necessarily bear the same scale.

[0037] Figure 1 A composition schematic diagram of a distributed optical fiber sensing host provided by an embodiment of the present application;

[0038] Figure 2 A flowchart schematic diagram of a main cable monitoring method of a flexible photovoltaic power station provided by an embodiment of the present application;

[0039] Figure 3 A structure schematic diagram of a main cable monitoring system of a flexible photovoltaic power station provided by an embodiment of the present application;

[0040] Figure 4 A hardware structure block diagram of an electronic device provided by the present application. DETAILED DESCRIPTION

[0041] The embodiments of the present application are described below with reference to the accompanying drawings. The terms used in the implementation part of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0042] The embodiments of the present application are described below with reference to the accompanying drawings. Those skilled in the art can know that, with the development of technology and the emergence of new scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0043] The terms "first", "second", etc. in the specification of the present application and the above drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, and this is only a way of distinguishing the objects with the same attributes in the description of the embodiments of the present application. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, so that the processes, methods, systems, products or equipment containing a series of units do not have to be limited to those units, but can include other units not clearly listed or inherent to these processes, methods, products or equipment.

[0044] With the large-scale construction of flexible photovoltaic power stations, the main cable as the core load-bearing structure supporting the photovoltaic panel is exposed to the outdoor environment for a long time, and is easily affected by factors such as wind load, temperature change, and mechanical fatigue, resulting in abnormal stress, local damage, or fracture of the main cable. Therefore, the main cable needs to be healthily detected in a long distance, real time, and high precision to prevent fracture accidents and reduce operation and maintenance costs.

[0045] Traditional main cable monitoring mainly uses point sensors. Since the monitoring range of the point sensor is limited, a large number of point sensors are needed to cover the full length of the main cable, resulting in high monitoring costs. In addition, when the point sensor is monitored, polling collection and protocol conversion are needed before the data flows into the platform for diagnosis and analysis, resulting in poor real-time performance of the point sensor. Further, the point sensor is arranged together with the main cable in the outdoor environment, and the outdoor environment is complex, which affects the monitoring effect of the point sensor, such as causing false positives of the point sensor.

[0046] To solve the above problems, the embodiments of the present application provide a main cable monitoring method of a flexible photovoltaic power station. One sensing optical fiber can easily cover the full length of the main cable, and the method can realize main cable diagnosis by directly analyzing the optical signal returned by the sensing optical fiber. The preset classification model of the method also considers environmental factors, which can effectively reduce the influence of environmental factors on main cable diagnosis. The main cable monitoring method of the photovoltaic power station according to the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0047] In the embodiment, the sensing optical fiber fixed along the main cable can be a sensing technology carrier for sensing and transmitting external signals by using physical characteristics of the optical fiber. When light propagates in the optical fiber, the physical quantity (such as temperature, pressure, etc.) in the external environment can change the parameters of the light through various optical reactions (such as thermo-optic reaction, elasto-optic reaction) due to the interaction between the light and the external environment, so that the measurement of the physical quantity such as temperature, pressure, etc. can be realized by detecting the parameter change of the light in the sensing optical fiber. In the embodiment, the sensing optical fiber can use a product with a long service life (such as more than 25 years), which can ensure that the service life of the sensing optical fiber is consistent with the service life of the flexible photovoltaic power station, and the sensing optical fiber is generally longer than the main cable. A distributed optical fiber sensing host can access more than 50 kilometers of sensing optical fiber, so that one sensing optical fiber can cover multiple main cables. For the setting of the sensing optical fiber, the sensing optical fiber can be fixed closely with the main cable (such as fixed at an interval of 1-3 meters by using a wide sheet hoop or fixed by rolling), realizing the deployment of the sensing optical fiber along the full length of the main cable, ensuring that the sensing optical fiber is parallel to the main cable, and the sensing optical fiber and the main cable deform synchronously (the deformation of the main cable and the sensing optical fiber remains consistent or follows a certain law), and the relative displacement is consistent when the main cable swings, etc. Of course, in another alternative embodiment, the sensing optical fiber can be wound on the main cable and ensured not to loosen relative to the main cable. Wherein, winding can mean that the sensing optical fiber is spirally, annularly or in a specific track around the main cable.

[0048] Specifically, to realize the optical fiber monitoring of the main cable, the embodiment mainly uses a distributed optical fiber sensor, which can include a distributed optical fiber sensing host and a sensing optical fiber. The embodiment can realize real-time collection and monitoring of signals such as temperature and vibration around the optical fiber by using various light scattering principles through the distributed optical fiber sensing host and the sensing optical fiber.

[0049] The distributed optical fiber sensing host can be integrated with optical devices such as ultra-narrow linewidth light source, pulse EDFA (Erbium-Doped Fiber Amplifier), Raman amplifier, modulator, WDM (Wavelength Division Multiplexing), isolator, DWDM (Dense Wavelength Division Multiplexing), Raman amplifier, polarization analyzer, and optical detector. Specifically, as shown in FIG. 2, the distributed optical fiber sensing host can include an ultra-narrow linewidth light source 201, a pulse EDFA 202, a modulator 203, a WDM 204, an isolator 205, a DWDM 206, a Raman amplifier 207, a polarization analyzer 208, and an optical detector 209. Figure 1The composition of the distributed optical fiber sensing host shown in the schematic diagram, an ultra-narrow light source (laser light source) can be used to output continuous light signals; a driver can be used for light pulse signal generation and driving the modulator; the modulator can be used to modulate the continuous light signal output by the ultra-narrow light source into a light pulse signal; the pulsed EDFA (Pulsed Erbium-Doped Fiber Amplifier, Erbium-doped fiber amplifier) can be used to amplify the light pulse signal; the circulator (3-port optical circulator) can be used for directional transmission of the light pulse signal; the WDM (Wavelength Division Multiplexing, Wavelength Division Multiplexing) can be used to improve the channel capacity when transmitting or receiving light signals; the isolator can be used for one-way transmission of light signals and blocking of reverse reflected light; the DWDM (Dense Wavelength Division Multiplexing, Dense Wavelength Division Multiplexing) can be used to transmit multiple light signals of different wavelengths in a single sensing optical fiber; the Raman amplifier can be used to amplify the light signal; the polarimeter can be used to detect the polarization state of the light signal and convert the polarization state of the light into a quantifiable signal; and the optical detector can be used to convert the weak scattered light signal in the sensing optical fiber into a quantifiable signal.

[0050] Referring to Figure 2 , Figure 2 A flowchart of a main cable monitoring method of a flexible photovoltaic power station provided by the embodiment is shown in FIG. 1. Figure 2 The main cable monitoring method of the flexible photovoltaic power station provided by the embodiment can include steps S10 to S13, which will be described in detail below.

[0051] S10, collect the scattered echo signals of the sensing optical fiber within a period of time, the scattered echo signals being the signals returned by the sensing optical fiber after transmitting the light pulse signals.

[0052] The scattered echo signals of the sensing optical fiber can be the light signals scattered and returned by the sensing optical fiber after transmitting the light pulse signals.

[0053] The process of transmitting the light pulse signals from the distributed optical fiber sensing host to the sensing optical fiber can be that the ultra-narrow light source transmits continuous light signals, the modulator modulates the continuous light signals output by the ultra-narrow light source into light pulse signals, the pulsed EDFA amplifies the light pulse signals, the light pulse signals enter from port 1 of the circulator, are output to the WDM from port 2, and the light pulse signals enter the sensing optical fiber through the WDM.

[0054] The optical pulse signal is transmitted in the sensing optical fiber, and the process of collecting the scattering echo signal returned by the sensing optical fiber by the distributed optical fiber sensing host can be: the scattering echo signal of the sensing optical fiber enters the WDM, the scattering echo signal enters from the 2 port of the circulator through the WDM, the 3 port of the circulator outputs the scattering echo signal to the polarization detector, the polarization state of the scattering echo signal passing through the DWDM is detected, the optical detector converts the scattering echo signal into an electrical signal, realizes digital signal acquisition, and facilitates subsequent signal processing.

[0055] S11, acquiring vibration frequency data of the main cable according to the frequency change of the Rayleigh scattering light signal in the scattering echo signal;

[0056] S12, acquiring strain force data and temperature data of the main cable according to the frequency shift of the Brillouin scattering light signal in the scattering echo signal, the frequency shift of the Brillouin scattering of the scattering echo signal is linearly related to the temperature of the main cable and the strain force of the main cable.

[0057] Wherein, the steps S11 and S12 can not have an execution sequence, in an optional embodiment, the step S11 can be executed first, and then the step S12 is executed, of course, in another optional embodiment, the step S12 can be executed first, and then the step S11 is executed.

[0058] The vibration frequency of the main cable can be the vibration frequency of the main cable under the influence of external excitation or its own dynamic characteristics, the strain force of the main cable can be the interaction force of the adjacent parts of the main cable due to external force, and the temperature of the main cable can be the temperature value of the main cable under specific environment or working condition.

[0059] Rayleigh scattering refers to an optical phenomenon, when light waves encounter tiny particles (such as gas molecules, nanoscale particles) with a size much smaller than the wavelength, the light waves are scattered by the tiny particles. Therefore, when the external vibration wave (such as sound wave) acts on the sensing optical fiber, the glass lattice inside the optical fiber can vibrate at the same frequency, and the vibration of the glass lattice causes Rayleigh scattering of the optical pulse signal propagating in the sensing optical fiber, forming a back Rayleigh echo carrying vibration information, and the polarization state of the back Rayleigh echo can vibrate with the vibration frequency of the glass lattice.

[0060] Since the sensing optical fiber is fixed with the main cable, the embodiment can demodulate the vibration information of the glass lattice in the sensing optical fiber by detecting the polarization state or phase change of the Rayleigh scattering light signal in the scattering echo signal returned by the sensing optical fiber, so as to determine the vibration of the main cable. Specifically, the embodiment can demodulate the polarization vibration energy difference of the Rayleigh scattering light signal in the scattering echo signal to obtain the vibration frequency data of the main cable. Wherein, the polarization vibration energy difference can refer to the uneven energy distribution phenomenon of the light wave in a specific polarization state due to the difference in the interaction between the vibration direction and the medium.

[0061] The Brillouin scattering refers to an optical phenomenon that when an optical wave propagates in a medium, interacts with acoustic phonons (elastic waves generated by thermal vibration or external excitation) in the medium, resulting in a frequency shift of the scattered light. Therefore, when the optical pulse signal is transmitted in the sensing optical fiber, the photons collide inelastically with the acoustic phonons generated by the thermal motion of the molecules of the optical fiber material, resulting in a frequency shift of the scattered light. In the present embodiment, the frequency shift of the Brillouin scattering of the scattered echo signal is approximately linearly related to the temperature of the main cable and the strain force of the main cable within a conventional change range. For example, when the temperature rises, the thermal expansion of the sensing optical fiber causes the density to decrease, the acoustic velocity to decrease, and the frequency shift to decrease. For another example, when the strain force increases, the compression of the material causes the acoustic velocity to increase, and the frequency shift to increase.

[0062] Since the sensing optical fiber is in close contact with the main cable, the temperature and strain force of the sensing optical fiber are highly related to the main cable. Therefore, the present embodiment can determine the temperature and strain force of the main cable by detecting the frequency shift of the Brillouin scattering light signal in the scattered echo signal returned by the sensing optical fiber and the approximate linear relationship between the frequency shift and the temperature and strain force. Of course, in another optional embodiment, the present embodiment can also determine the temperature and strain force of the main cable by the power change of the Brillouin scattering light signal in the scattered echo signal. In spontaneous Brillouin scattering or stimulated Brillouin scattering, the power change of the Brillouin scattering light signal is also linearly related to the temperature of the main cable and the strain force of the main cable. For example, when the temperature rises, the molecular vibration is enhanced, resulting in an increase in scattering efficiency. For another example, when the strain force increases, the molecular order is destroyed, resulting in a decrease in scattering efficiency.

[0063] When the present embodiment obtains the vibration frequency data, strain force data and temperature data of the main cable at each time, the multi-dimensional information trend graph of the main cable within a period of time can be obtained when visualized, which is convenient for observing the change trend of each information of the main cable and early warning.

[0064] S13, input the vibration frequency data, strain force data, temperature data, inherent parameters of the main cable and environmental parameters at the same time into a preset classification model for classification to obtain an event category result of the main cable output by the preset classification model.

[0065] The inherent parameters of the main cable can refer to physical parameters related to the main cable itself, such as length, load bearing, etc. The environmental parameters can refer to related parameters of the current environment in which the main cable is located, such as weather, latitude and longitude, season, wind speed, wind direction, etc. The preset classification model is a classification model obtained by the present embodiment through training of the vibration frequency data, strain force data, temperature data of the main cable, inherent parameters of the main cable and environmental parameters. Of course, in another optional embodiment, the inherent parameters of the main cable can be pre-set in the preset classification model as fixed parameters.

[0066] The event category result output by the preset classification model can refer to the predicted event type and event level of the main cable, the event type being, for example, strong wind, heavy rain, fatigue, short fiber, etc., and the event level being, for example, level one, level two, level three, etc., and thus the event category result output by the preset classification model is, for example, rain event / fourth level, wind-induced vibration / third level, etc. When visualized, a 3D health heat map of the main cable can be generated according to the output result of the preset classification model, and the hidden danger position of the main cable, the identification corresponding to the event type, and the event level (different event levels can correspond to different identification colors) are marked, and when a hidden danger of the main cable is monitored, an alarm is given to the operation and maintenance personnel through a PC terminal or a mobile terminal.

[0067] The embodiment converts the abstract main cable monitoring data into an event type and an event level, solves the problems that the data associated with the hidden danger of the main cable is difficult to quantify and the judgment standard is difficult to unify, and displays the related data of the main cable in an intuitive visual manner, facilitating the operation and maintenance personnel to quickly determine the current state and hidden danger position of the main cable.

[0068] Further, in the embodiment, a plurality of measuring points can be provided on the main cable, and for each measuring point on the main cable, the scattered echo signals of the sensing optical fiber at the measuring point within a period of time can be collected, and the vibration frequency data, the strain force data, and the temperature data of the main cable at each measuring point can be obtained through the above processing process.

[0069] The embodiment can locate the plurality of measuring points on the main cable through optical time domain reflectometry (OTDR). The principle can be that a light pulse signal is transmitted to the sensing optical fiber of the measured main cable, and scattering phenomena occur in the sensing optical fiber, so that backscattered light and forward scattered light are formed in the sensing optical fiber. Among them, the backscattered light can propagate to the starting end (light pulse signal injection end) of the sensing optical fiber. Since each backscattered light can correspond to a scattering point on the sensing optical fiber, the distance between the scattering point position and the starting end of the sensing optical fiber can be calculated according to the travel time of the backscattered light, so that the position of the scattering point on the sensing optical fiber can be determined, and the position of the scattering point on the sensing optical fiber can correspond to the position of a measuring point on the main cable. The formula for calculating the distance between the scattering point position and the starting end of the sensing optical fiber can be as follows:

[0070] ;

[0071] Among them, may represent the distance between the scattering point position and the starting end of the sensing optical fiber; may represent the speed of light in vacuum; may represent the total time from the emission of the light signal to the reception of the light signal (double trip). It can represent the refractive index of the sensing fiber.

[0072] The accuracy of measuring points on the main cable can be related to the frequency of optical signals captured by the host optical switch and detector that generate the optical pulse signal. In this embodiment, the positioning accuracy of the measuring points is set to 1-2 meters, that is, a measuring point is set every 1-2 meters on the main cable. During the deployment of the sensing fiber, the corresponding sensing fiber range of each main cable length is determined, so the continuous measuring points on each main cable can be determined.

[0073] This embodiment can obtain data from multiple measuring points on the main cable through a single sensing optical fiber, thereby achieving full-length coverage and detection of the main cable. Compared with the cost of deploying a large number of point sensors, the cost of deploying the sensing optical fiber is significantly lower.

[0074] Specifically, the process of obtaining the preset classification model includes steps 1 to 3:

[0075] Step 1: Collect the three-dimensional data of the main cable, the inherent parameters of the main cable, and the environmental parameters. The three-dimensional data of the main cable includes the vibration frequency data, strain data, and temperature data of the main cable;

[0076] Step 2: Obtain multiple sets of training data under different working conditions. Each set of training data under different working conditions consists of three-dimensional data of the main cable, inherent parameters of the main cable, and environmental parameters with different values.

[0077] Step 3: Obtain labeled training data after event labeling of the training data, and train the convolutional neural network classification model with the labeled training data to obtain a preset classification model. The types of labels of the labeled training data include: various normal events and various abnormal events.

[0078] Among them, a normal event may mean that the main cable is in a normal state under this event. For example, in a strong wind or heavy rain event, the vibration frequency of the main cable is abnormal compared to usual. However, since the event in which the main cable is located is a strong wind or heavy rain, the vibration frequency of the main cable is a normal change under the influence of this event, and it is not a problem with the main cable itself. An abnormal event may mean that the main cable is in an abnormal state under this event. For example, in a calm state, the vibration frequency of the main cable is abnormal compared to usual. However, since the event in which the main cable is located is calm, the abnormal vibration frequency of the main cable is not affected by this event, but is caused by its own problems. Therefore, this embodiment takes environmental factors into consideration when labeling the training data, so that the training model can determine whether the abnormal parameters of the main cable are caused by the environment in which the main cable is located or by problems with the main cable itself based on environmental factors, effectively reducing the interference of environmental factors on main cable monitoring.

[0079] Since the training data under each group of working conditions is composed of three-dimensional data of the main cable with different values, inherent parameters of the main cable and environmental parameters, when data labeling is performed, the actual situation and experience can be comprehensively considered to determine whether each group of working conditions belongs to a normal event or an abnormal event, and the event type is labeled, and of course the event level can also be labeled. In addition to obtaining sample data of abnormal events by labeling abnormal events for training data, more sample data of abnormal events can be obtained through simulation of abnormal physical injection, simulation of abnormal generation, fault library migration labeling, etc.

[0080] The training data under each group of working conditions is labeled according to the actual situation in this embodiment, which is divided into normal events and abnormal events, and the abstract main cable monitoring data is converted into events, which can effectively improve the adaptability of the training model to the actual application scene, improve the classification precision, and through various ways to expand the sample data of abnormal events, the response and recognition ability of the training model to abnormal events can be effectively improved.

[0081] When collecting training data, the vibration frequency data, strain force data, temperature data, inherent parameters and environmental parameters of the main cable at each measuring point within a period of time can be collected, and the time series data of each measuring point can be formed in combination with the sampling time interval, and subsequent data labeling can be performed, and the vibration frequency data, strain force data and temperature data of the main cable can be segmented according to the main cable positioning.

[0082] When data preprocessing is performed, not only can the collected data be filtered and reconstructed, but also the collected data can be enhanced. For example, noise filtering can separate the vibration signal of the main cable and the mechanical noise of the photovoltaic panel based on envelope analysis, or can compare and learn based on wind vibration, rain strike and other noise characteristic templates to suppress false positives. For example, data enhancement can generate synthetic data such as fracture and fatigue of the main cable based on wave equation, or can synchronize the strain force data and vibration data of the main cable with the wind speed in the external environment in time sequence.

[0083] The training model selected in this embodiment can be a deep learning model, which can be a convolutional neural network classification model, or can be a long short-term memory network (LSTM) and its variants. Specifically, the structure of the model in this embodiment can include an input layer, a multi-modal data fusion layer, an output layer, a constraint condition, etc. When training the model, the model can be cross-validated, and after labeling the false positives and false negatives, the model can be automatically triggered for fine-tuning.

[0084] The method provided by the embodiment of the present application can monitor the main cable by using the sensing optical fiber, the sensing optical fiber can easily cover the whole length of the main cable, and when analyzing, the method adds not only the internal parameters and inherent parameters of the main cable but also the environmental parameters, so that the preset classification model can cope with the abnormal parameters of the main cable under environmental interference and can identify the environmental interference events that are not abnormal to the main cable itself, and can effectively reduce the interference of the outdoor environment on the monitoring of the main cable, and therefore, the method can effectively improve the monitoring effect of the main cable.

[0085] The above introduces the method for monitoring the main cable of the flexible photovoltaic power station provided by the embodiment of the present application, and the system applying the above method for monitoring the main cable of the flexible photovoltaic power station will be introduced below.

[0086] Please refer to Figure 3 , Figure 3 The structure diagram of the system for monitoring the main cable of the flexible photovoltaic power station provided by the embodiment of the present application is shown in FIG. 1. Figure 3 As shown in the figure, the system for monitoring the main cable of the photovoltaic power station has a sensing optical fiber fixed along the main cable, and the system can include:

[0087] The acquisition unit 100 is configured to acquire the scattering echo signal of the sensing optical fiber within a period of time, and the scattering echo signal is the signal returned by the sensing optical fiber after emitting the optical pulse signal to the sensing optical fiber.

[0088] The first acquisition unit 110 is configured to acquire the vibration frequency data of the main cable according to the frequency change of the Rayleigh scattering light signal in the scattering echo signal.

[0089] The second acquisition unit 120 is configured to acquire the strain force data and the temperature data of the main cable according to the frequency shift of the Brillouin scattering light signal in the scattering echo signal, and the frequency shift of the Brillouin scattering of the scattering echo signal is linearly related to the temperature of the main cable and the strain force of the main cable.

[0090] The classification unit 130 is configured to input the vibration frequency data, the strain force data, the temperature data, the inherent parameters of the main cable and the environmental parameters at the same time into the preset classification model for classification to obtain the event category result of the main cable output by the preset classification model.

[0091] In a possible implementation, the main cable is provided with a plurality of measuring points, and the acquisition unit can be specifically configured to:

[0092] For each measuring point on the main cable, the scattered echo signals of the sensing optical fiber are collected within a period of time.

[0093] In a possible implementation, the first obtaining unit can be specifically configured to:

[0094] The polarization vibration energy difference of the Rayleigh scattering light signal in the scattered echo signal is demodulated to obtain the vibration frequency data of the main cable.

[0095] In a possible implementation, the main cable monitoring system of the photovoltaic power station can further include a construction unit of the preset classification model, and the construction unit is specifically configured to:

[0096] The three-dimensional data of the main cable, the inherent parameters of the main cable and the environmental parameters are collected, the three-dimensional data of the main cable includes the vibration frequency data, the strain force data and the temperature data of the main cable, the training data under multiple groups of different working conditions is obtained, the training data under each group of working conditions is composed of the three-dimensional data of the main cable, the inherent parameters of the main cable and the environmental parameters with different values, the labeled training data obtained after the event labeling of the training data is obtained, and the labeled training data is used to train the convolutional neural network classification model to obtain the preset classification model, and the types of the labeled training data include various normal events and various abnormal events. In this embodiment, the training data under each group of working conditions is labeled and divided into normal events and abnormal events according to the actual situation, the classification ability of the training model for events can be effectively improved, and the adaptability of the training model to the actual application scene and the classification precision are improved.

[0097] The application also provides an electronic device. Referring to Figure 4 Fig. 1 shows a structural schematic diagram of an electronic device suitable for implementing the electronic device in the embodiments of the application. The electronic device in the embodiments of the application can include, but is not limited to, a fixed terminal such as a mobile phone, a notebook computer, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), a desktop computer, etc. Figure 4 The electronic device shown is only an example, and should not impose any limitation on the functions and use range of the embodiments of the application.

[0098] As shown in Figure 4 The electronic device can include a processing device (for example, a central processor, a graphics processor, etc.) 401, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 402 or loaded from a storage device 408 into a random access memory (RAM) 403. In the state that the electronic device is powered on, the RAM 403 also stores various programs and data required for the operation of the electronic device. The processing device 401, the ROM 402 and the RAM 403 are connected to each other through a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0099] In general, the following devices can be connected to the I / O interface 405: input devices 406 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, and the like; output devices 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, and the like; storage devices 408 including, for example, a memory card, a hard disk, and the like; and communication devices 409. The communication devices 409 can allow the electronic device to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 The electronic device is shown with various devices, but it is understood that all of the shown devices are not required to be implemented or present. More or fewer devices can alternatively be implemented or present.

[0100] The embodiment of the present application further provides a computer program product comprising computer readable instructions, which, when executed on an electronic device, cause the electronic device to implement any of the main cable monitoring methods of the flexible photovoltaic power station provided by the embodiments of the present application.

[0101] The embodiment of the present application further provides a computer readable storage medium, which carries one or more computer programs, when the one or more computer programs are executed by an electronic device, can enable the electronic device to implement any of the main cable monitoring methods of the flexible photovoltaic power station provided by the embodiments of the present application.

[0102] In addition, it should be noted that the system embodiments described above are only schematic, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e. they can be located in one place or distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments. In addition, the connection between the modules in the system embodiments provided by the present application indicates that there is a communication connection between them, which can be implemented as one or more communication buses or signal lines.

[0103] Those skilled in the art can clearly understand that the application can be implemented by means of software plus necessary universal hardware, and of course can also be implemented by means of dedicated hardware including special-purpose integrated circuits, special-purpose CPUs, special-purpose memories, special-purpose components, etc. Generally, any function completed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure for implementing the same function can also be various, such as analog circuits, digital circuits, or special-purpose circuits, etc. However, for the present application, software program implementation is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a readable storage medium, such as a floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk, etc., and includes a plurality of instructions for causing a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in various embodiments of the present application.

[0104] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product.

[0105] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another, for example, the computer instructions can be transmitted from one website, computer, training device or data center to another website, computer, training device or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be stored by a computer or a data storage device such as a training device, a data center, etc. integrated with one or more available media. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)), etc.

[0106] Each of the embodiments in the specification is described in a relevant manner, and the same or similar parts between the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiments.

[0107] It can be understood that, before using the technical solutions disclosed in the embodiments of the present disclosure, the type of personal information involved in the present disclosure, the use range, the use scenario, etc. should be informed to the user and the authorization of the user should be obtained through appropriate means according to relevant laws and regulations.

[0108] The above only shows the embodiments of the present application and is not used to limit the present application. The present application can have various changes and modifications for those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A main cable monitoring method for a flexible photovoltaic power station, characterized in that: A sensing optical fiber is fixed along the main cable. The main cable monitoring method of the photovoltaic power station includes: Collecting a scattered echo signal of the sensing optical fiber over a period of time, wherein the scattered echo signal is a signal transmitted back by the sensing optical fiber after an optical pulse signal is emitted to the sensing optical fiber; acquiring vibration frequency data of the main cable according to a frequency change of the Rayleigh scattered light signal in the scattered echo signal; acquiring strain data and temperature data of the main cable according to a frequency shift of a Brillouin scattered light signal in the scattered echo signal, wherein the frequency shift of the Brillouin scattered light signal in the scattered echo signal is linearly related to the temperature of the main cable and the strain of the main cable; The vibration frequency data, the strain force data, the temperature data, the inherent parameters of the main cable and the environmental parameters at the same time are input into a preset classification model for classification, and an event category result of the main cable output by the preset classification model is obtained.

2. The main cable monitoring method of a flexible photovoltaic power station according to claim 1, characterized in that: A plurality of measuring points are provided on the main cable, and the collecting of scattered echo signals of the sensing optical fiber over a period of time includes: For each measuring point on the main cable, the scattered echo signal of the sensing optical fiber is collected over a period of time.

3. The main cable monitoring method of a flexible photovoltaic power station according to claim 1, characterized in that: The obtaining of the vibration frequency data of the main cable according to the frequency change of the Rayleigh scattered light signal in the scattered echo signal comprises: The polarization vibration energy difference of the Rayleigh scattered light signal in the scattered echo signal is demodulated to obtain the vibration frequency data of the main cable.

4. The main cable monitoring method of a flexible photovoltaic power station according to claim 1, characterized in that: The process of obtaining the preset classification model includes: Collecting three-dimensional data of the main cable, inherent parameters of the main cable, and environmental parameters, wherein the three-dimensional data of the main cable includes vibration frequency data, strain force data, and temperature data of the main cable; Acquire multiple sets of training data under different working conditions, wherein each set of training data under the working condition is composed of three-dimensional data of the main cable, inherent parameters of the main cable, and environmental parameters with different values; Obtain labeled training data after event labeling of the training data, and train a convolutional neural network classification model with the labeled training data to obtain the preset classification model, wherein the types of labeling of the labeled training data include: various normal events and various abnormal events.

5. A main cable monitoring system for a flexible photovoltaic power station, characterized in that: A sensing optical fiber is fixed along the main cable. The main cable monitoring system of the photovoltaic power station includes: A collection unit, configured to collect a scattered echo signal of the sensing optical fiber over a period of time, wherein the scattered echo signal is a signal transmitted back from the sensing optical fiber after an optical pulse signal is emitted to the sensing optical fiber; a first acquiring unit, configured to acquire vibration frequency data of the main cable according to a frequency change of a Rayleigh scattered light signal in the scattered echo signal; a second acquiring unit, configured to acquire strain data and temperature data of the main cable according to a frequency shift of a Brillouin scattered light signal in the scattered echo signal, wherein the frequency shift of the Brillouin scattering of the scattered echo signal is linearly related to the temperature of the main cable and the strain of the main cable; The classification unit is used to input the vibration frequency data, the strain force data, the temperature data, the inherent parameters of the main cable and the environmental parameters at the same time into a preset classification model for classification, and obtain the event category result of the main cable output by the preset classification model.

6. The main cable monitoring system of the flexible photovoltaic power station according to claim 5, characterized in that: The main cable is provided with a plurality of measuring points, and the acquisition unit is specifically configured as follows: For each measuring point on the main cable, the scattered echo signal of the sensing optical fiber is collected over a period of time.

7. The main cable monitoring system of the flexible photovoltaic power station according to claim 5, characterized in that: The first acquiring unit is specifically configured as follows: The polarization vibration energy difference of the Rayleigh scattered light signal in the scattered echo signal is demodulated to obtain the vibration frequency data of the main cable.

8. The main cable monitoring system of the flexible photovoltaic power station according to claim 5, characterized in that: The main cable monitoring system of the photovoltaic power station further includes a construction unit of the preset classification model, and the construction unit is specifically configured as follows: Collecting three-dimensional data of the main cable, inherent parameters of the main cable, and environmental parameters, wherein the three-dimensional data of the main cable includes vibration frequency data, strain force data, and temperature data of the main cable; Acquire multiple sets of training data under different working conditions, wherein each set of training data under the working condition is composed of three-dimensional data of the main cable, inherent parameters of the main cable, and environmental parameters with different values; Obtain labeled training data after event labeling of the training data, and train a convolutional neural network classification model with the labeled training data to obtain the preset classification model, wherein the types of labeling of the labeled training data include: various normal events and various abnormal events.

9. An electronic device, characterized in that: comprising at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is configured to execute the computer program so that the electronic device can implement the main cable monitoring method for a flexible photovoltaic power station according to any one of claims 1 to 4.

10. A computer program product, characterized in that The method comprises computer-readable instructions, which, when executed on an electronic device, enable the electronic device to implement the main cable monitoring method of a flexible photovoltaic power station according to any one of claims 1 to 4.

Images