Monitoring method, device and equipment of flexible photovoltaic array and storage medium

Abstract

The invention discloses a monitoring method, device and equipment of a flexible photovoltaic array and a storage medium, and relates to the technical field of flexible photovoltaics, the method carries out linear regression analysis on an upper chord cable and a lower chord cable of a flexible photovoltaic support through physical parameters and environmental parameters, because the upper chord cable and the lower chord cable are located in the same support and the same environment, the upper chord cable and the lower chord cable are located in the same support and the same environment; the two chord cables are subjected to linear regression, but the two linear regression have relevance, future tensile stress obtained through follow-up prediction is related, data deviation cannot be generated, finally, one judgment condition is selected by defining, and if at least one of the two judgment conditions is met, the two chord cables are subjected to linear regression. And if so, determining that the flexible photovoltaic support will generate excessive stress at the future moment. The whole process is automatically calculated by a computer, manual participation is not needed, subjective experience errors are avoided, the prediction function of the tensile stress is achieved, the predicted tensile stress has relevance with physical parameters and environmental parameters, and data accuracy is guaranteed.

Description

Technical Field

[0001] The present application relates to the field of flexible photovoltaic technology, and particularly to a monitoring method, device, equipment and storage medium for a flexible photovoltaic array. Background Art

[0002] A flexible photovoltaic power station is an integrated power station based on a flexible photovoltaic support. The flexible photovoltaic power station has higher installation flexibility and terrain adaptability compared with a conventional photovoltaic power station, which has attracted more and more attention in recent years.

[0003] The flexible photovoltaic support adopted by the flexible photovoltaic power station can be easily bent and folded, so it can well adapt to the installation environment of various irregular or curved mountainous areas. The above characteristics not only expand the construction scope of the photovoltaic power station, but also improve the land utilization rate, can flexibly adapt to various complex terrains, and provide more possibilities for the construction of mountain photovoltaic power stations; in addition, the flexible photovoltaic support adopts high-strength but lightweight materials, so that while the support remains stable, it has better adaptability and ductility, enabling the photovoltaic panels to be more flexibly installed under different terrains and climatic conditions.

[0004] At present, the flexible photovoltaic power station as a whole is still in the initial and experimental stage. The daily monitoring of various components and facilities of the flexible photovoltaic power station usually uses the monitoring means of conventional photovoltaic power stations, such as manual inspection and judgment and manual meter reading analysis, which causes certain subjective experience errors. Moreover, since the array part of the flexible photovoltaic power station is usually set on mountains and slopes, it also causes certain difficulties in manual inspection. And manual meter reading analysis usually only targets the electrical data of the photovoltaic power station and cannot further understand the structural stability of the flexible photovoltaic. Summary of the Invention

[0005] The main purpose of the present application is to provide a monitoring method, device, equipment and storage medium for a flexible photovoltaic array, so as to solve the problems in the prior art that the monitoring of the flexible photovoltaic array is basically manual experience judgment and manual meter reading analysis, which causes certain subjective experience errors, and since the array part of the flexible photovoltaic power station is usually set on mountains and slopes, it also causes certain difficulties in manual inspection, and manual meter reading analysis usually only targets the electrical data of the photovoltaic power station and cannot further understand the structural stability of the flexible photovoltaic.

[0006] To achieve the above purpose, the present application provides the following technical solutions:

[0007] A monitoring method for a flexible photovoltaic array, the flexible photovoltaic array including a flexible photovoltaic support erected in a preset area, the flexible photovoltaic support including two steel beam frames fixed to the ground, an upper chord cable and a lower chord cable laid on the two steel beam frames, and a plurality of photovoltaic panels installed on the upper chord cable and the lower chord cable, the monitoring method including:

[0008] Step S1, obtaining a plurality of upper chord cable tensile stresses and a plurality of lower chord cable tensile stresses of the flexible photovoltaic support, as well as the span height difference between the two steel beam frames of the flexible photovoltaic support and the number of photovoltaic panels, based on a plurality of preset time periods;

[0009] Step S2, obtaining the wind speed probability distribution and the light intensity distribution in the area where the flexible photovoltaic support is located;

[0010] Step S3, defining the tensile stress of the upper chord cable of the current flexible photovoltaic support as a first dependent variable and the tensile stress of the lower chord cable of the current flexible photovoltaic support as a second dependent variable;

[0011] Step S4, defining the wind speed probability distribution, the light intensity distribution, the span height difference, and the number of photovoltaic panels in the area where the current flexible photovoltaic support is located as a set of independent variables;

[0012] Step S5, analyzing the first linear regression relationship between the first dependent variable of the current flexible photovoltaic support and all independent variables, and the second linear regression relationship between the second dependent variable of the current flexible photovoltaic support and all independent variables through multiple linear regression;

[0013] Step S6, predicting the future tensile stress of the upper chord cable of the flexible photovoltaic support through the first linear regression relationship and predicting the future tensile stress of the lower chord cable of the flexible photovoltaic support through the second linear regression relationship based on a preset number of prediction steps;

[0014] Step S7, obtaining the maximum allowable tensile stress of the upper chord cable and the maximum allowable tensile stress of the lower chord cable;

[0015] Step S8, defining a first judgment condition as judging whether there is a future tensile stress of the upper chord cable greater than or equal to the maximum allowable tensile stress of the upper chord cable, and defining a second judgment condition as judging whether there is a future tensile stress of the lower chord cable greater than or equal to the maximum allowable tensile stress of the lower chord cable;

[0016] Step S9, if at least one of the first judgment condition and the second judgment condition is satisfied, determining that the flexible photovoltaic support has a risk of stress exceeding the standard.

[0017] As a further improvement of the present application, in step S9, if at least one of the first judgment condition and the second judgment condition is satisfied, determining that the flexible photovoltaic support has a risk of stress exceeding the standard, and then, including:

[0018] Step S10, determine whether the stress over - standard risk is triggered by the first judgment condition or the second judgment condition;

[0019] Step S20, if it is only triggered by the first judgment condition, then execute Step S30; if it is only triggered by the second judgment condition, then execute Step S40; if it is triggered by both the first judgment condition and the second judgment condition, then execute Step S50;

[0020] Step S30, obtain the future tensile stress of the upper chord cable that is greater than or equal to the maximum allowable tensile stress of the upper chord cable, and mark it as the future abnormal signal of the upper chord cable;

[0021] Step S40, obtain the future tensile stress of the lower chord cable that is greater than or equal to the maximum allowable tensile stress of the lower chord cable, and mark it as the future abnormal signal of the lower chord cable;

[0022] Step S50, execute Step S30 and Step S40 simultaneously to obtain the future abnormal signal of the upper chord cable and the future abnormal signal of the lower chord cable simultaneously;

[0023] Step S60, respectively obtain the first future timestamp corresponding to each future abnormal signal of the upper chord cable and the second future timestamp corresponding to each future abnormal signal of the lower chord cable;

[0024] Step S70, send all the first future timestamps and all the second future timestamps to an external monitoring terminal.

[0025] As a further improvement of the present application, in Step S2, obtaining the wind speed probability distribution and the light intensity distribution of the area where the flexible photovoltaic bracket is located includes:

[0026] Step S21, collect the wind speed data of several random points in the area where the flexible photovoltaic bracket is located;

[0027] Step S22, define the probability distribution function and the probability density function according to the two - parameter Weibull distribution, and both the probability distribution function and the probability density function include a scale parameter and a shape parameter;

[0028] Step S23, substitute all the wind speed data of the random points as known quantities into the probability distribution function and the probability density function respectively;

[0029] Step S24, define the logarithmic likelihood function of the scale parameter and the shape parameter;

[0030] Step S25, solve the scale parameter and the shape parameter based on the logarithmic likelihood function;

[0031] Step S26: Substitute the solved scale parameter and the solved shape parameter into the probability distribution function and the probability density function respectively to obtain the wind speed probability distribution.

[0032] Step S27: Query the solar radiation distribution of the preset area through a preset strategy.

[0033] As a further improvement of this application, in step S5, analyze the first linear regression relationship between the first dependent variable and all independent variables of the current flexible photovoltaic support, and the second linear regression relationship between the second dependent variable and all independent variables of the current flexible photovoltaic support through multiple linear regression, including:

[0034] Step S51: Normalize all the first dependent variables, all the second dependent variables, and all the independent variables.

[0035] Step S52: Define the first linear regression relationship between all the first dependent variables and all the independent variables through multiple linear regression.

[0036] Step S53: Solve all the first linear regression coefficients of the first linear regression relationship by the least squares method.

[0037] Step S54: Substitute all the solved first linear regression coefficients into the first linear regression relationship to obtain the upper chord cable tensile stress prediction model.

[0038] Step S55: Define the second linear regression relationship between all the second dependent variables and all the independent variables through multiple linear regression.

[0039] Step S56: Solve all the second linear regression coefficients of the second linear regression relationship by the least squares method.

[0040] Step S57: Substitute all the solved second linear regression coefficients into the second linear regression relationship to obtain the lower chord cable tensile stress prediction model.

[0041] As a further improvement of this application, in step S6, predict the future tensile stress of the upper chord cable of the flexible photovoltaic support through the first linear regression relationship and predict the future tensile stress of the lower chord cable of the flexible photovoltaic support through the second linear regression relationship based on a preset prediction step, including:

[0042] Step S61: Obtain the future wind speed probability distribution of the preset area based on the preset prediction step.

[0043] Step S62: Obtain the future light intensity distribution of the preset area based on the preset prediction step.

[0044] Step S63: Substitute the future wind speed probability distribution, the future light intensity distribution, the cross - span height difference, and the number of photovoltaic panels into the upper chord cable tensile stress prediction model to obtain the future tensile stress of the upper chord cable based on the preset number of prediction steps.

[0045] Step S64: Substitute the future wind speed probability distribution, the future light intensity distribution, the cross - span height difference, and the number of photovoltaic panels into the lower chord cable tensile stress prediction model to obtain the future tensile stress of the lower chord cable based on the preset number of prediction steps.

[0046] As a further improvement of the present application, step S61: Obtaining the future wind speed probability distribution of the preset area based on the preset number of prediction steps includes:

[0047] Step S611: Obtain several wind speed probability distributions of the preset area based on several preset time periods.

[0048] Step S612: Integrate the wind speed data at all random points in one wind speed probability distribution into one wind speed data set.

[0049] Step S613: Perform vector normalization processing on all wind speed data sets to obtain one normalized data set based on one wind speed data set.

[0050] Step S614: Divide one normalized data set into a training set and a validation set according to a preset ratio.

[0051] Step S615: Define a neural network model with signal connections between the input layer, the hidden layer, and the output layer in sequence.

[0052] Step S616: Input all training sets into the input layer in sequence and perform several trainings through the neural network model.

[0053] Step S617: Obtain the root - mean - square error of the training results corresponding to the current validation set and the current training set respectively for each training.

[0054] Step S618: Obtain the minimum error among all root - mean - square errors, and the training result corresponding to the minimum error as the wind speed probability distribution prediction model.

[0055] Step S619: Predict the future wind speed probability distribution based on the preset number of prediction steps through the wind speed probability distribution prediction model.

[0056] As a further improvement of the present application, step S62: Obtaining the future light intensity distribution of the preset area based on the preset number of prediction steps includes:

[0057] Step S621: Obtain several light intensity distributions of the preset area based on several preset time periods;

[0058] Step S622: Integrate all the light intensity data of random points in one light intensity distribution into one light intensity data set;

[0059] Step S623: Perform standard normalization processing on all the light intensity data sets, and obtain one normalized data set based on one light intensity data set;

[0060] Step S624: Divide one normalized data set into one training set and one validation set according to a preset ratio;

[0061] Step S625: Define a neural network model with signal connections in sequence of an input layer, a hidden layer, and an output layer;

[0062] Step S626: Input all the training sets into the input layer in sequence, and perform several trainings through the neural network model;

[0063] Step S627: Obtain the root mean square error of the training results corresponding to the current validation set and the current training set respectively based on each training;

[0064] Step S628: Obtain the minimum error among all the root mean square errors, and the training result corresponding to the minimum error as the light intensity distribution prediction model;

[0065] Step S629: Predict the future light intensity distribution based on the preset prediction steps through the light intensity distribution prediction model.

[0066] To achieve the above object, the present application also provides the following technical solutions:

[0067] A monitoring device for a flexible photovoltaic array, the monitoring device is applied to the monitoring method as described above, and the monitoring device includes:

[0068] A bracket physical parameter acquisition module, configured to obtain several upper chord cable tensile stresses and several lower chord cable tensile stresses of the flexible photovoltaic bracket, as well as the span height difference between two steel beam frames of the flexible photovoltaic bracket and the number of photovoltaic panels based on several preset time periods;

[0069] A bracket environment parameter acquisition module, configured to obtain the wind speed probability distribution and the light intensity distribution of the area where the flexible photovoltaic bracket is located;

[0070] An independent variable definition module, configured to define the upper chord cable tensile stress of the current flexible photovoltaic bracket as a first independent variable, and the lower chord cable tensile stress of the current flexible photovoltaic bracket as a second independent variable;

[0071] An independent variable definition module, configured to define the wind speed probability distribution, light intensity distribution, span height difference, and number of photovoltaic panels in the area where the current flexible photovoltaic support is located as a set of independent variables;

[0072] A linear regression relationship analysis module, configured to analyze the first linear regression relationship between the first dependent variable of the current flexible photovoltaic support and all independent variables, and the second linear regression relationship between the second dependent variable of the current flexible photovoltaic support and all independent variables through multiple linear regression;

[0073] An upper and lower chord cable tensile stress prediction module, configured to predict the future tensile stress of the upper chord cable of the flexible photovoltaic support through the first linear regression relationship and predict the future tensile stress of the lower chord cable of the flexible photovoltaic support through the second linear regression relationship based on a preset number of prediction steps;

[0074] A maximum allowable tensile stress acquisition module, configured to acquire the maximum allowable tensile stress of the upper chord cable and the maximum allowable tensile stress of the lower chord cable;

[0075] A judgment condition definition module, configured to define the first judgment condition as judging whether the future tensile stress of the upper chord cable is greater than or equal to the maximum allowable tensile stress of the upper chord cable, and define the second judgment condition as judging whether the future tensile stress of the lower chord cable is greater than or equal to the maximum allowable tensile stress of the lower chord cable;

[0076] A judgment condition determination module, configured to determine that the flexible photovoltaic support has a risk of excessive stress if at least one of the first judgment condition and the second judgment condition is satisfied.

[0077] To achieve the above object, the present application also provides the following technical solutions:

[0078] An electronic device, including a processor and a memory coupled to the processor, where the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, the above-mentioned monitoring method is implemented.

[0079] To achieve the above object, the present application also provides the following technical solutions:

[0080] A storage medium, in which program instructions are stored, and when the program instructions are executed by a processor, the above-mentioned monitoring method can be implemented.

[0081] In this application, several tensile stresses of the upper chord cables and several tensile stresses of the lower chord cables of a flexible photovoltaic support are obtained based on several preset time periods, as well as the elevation difference between the two steel girders of the flexible photovoltaic support and the number of photovoltaic panels; several wind speed probability distributions and several light intensity distributions in the area where the flexible photovoltaic support is located are obtained based on several preset time periods; the tensile stress of the upper chord cable of the current flexible photovoltaic support is defined as a first dependent variable, and the tensile stress of the lower chord cable of the current flexible photovoltaic support is defined as a second dependent variable; the wind speed probability distribution, light intensity distribution, elevation difference between the two steel girders, and the number of photovoltaic panels in the area where the current flexible photovoltaic support is located are defined as a set of independent variables; the first linear regression relationship between the first dependent variable of the current flexible photovoltaic support and all independent variables, and the second linear regression relationship between the second dependent variable of the current flexible photovoltaic support and all independent variables are analyzed through multiple linear regression; the future tensile stress of the upper chord cable of the flexible photovoltaic support is predicted through the first linear regression relationship, and the future tensile stress of the lower chord cable of the flexible photovoltaic support is predicted through the second linear regression relationship based on a preset prediction step; the maximum allowable tensile stress of the upper chord cable and the maximum allowable tensile stress of the lower chord cable are obtained; the first judgment condition is defined as judging whether there is a future tensile stress of the upper chord cable greater than or equal to the maximum allowable tensile stress of the upper chord cable, and the second judgment condition is defined as judging whether there is a future tensile stress of the lower chord cable greater than or equal to the maximum allowable tensile stress of the lower chord cable; if at least one of the first judgment condition and the second judgment condition is satisfied, it is determined that the flexible photovoltaic support has a risk of excessive stress. In this application, the upper chord cable and the lower chord cable of the flexible photovoltaic support are linearly regressed and analyzed with physical parameters and environmental parameters respectively. Since the upper chord cable and the lower chord cable are in the same support and in the same environment, although the two chord cables are linearly regressed separately, the two linear regressions are related to each other, making the future tensile stresses obtained by subsequent predictions related to each other and not generating data deviation. Finally, by defining an alternative judgment condition, and if at least one of the two judgment conditions is satisfied, it is determined that the flexible photovoltaic support will have excessive stress at a future time. The whole process of this application is automatically calculated by a computer without manual participation, avoiding subjective experience errors, and this application realizes the prediction function of tensile stress. The predicted tensile stress is related to physical parameters and environmental parameters, ensuring the accuracy of the data. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 It is a schematic flow chart of the steps of an embodiment of the monitoring method for the flexible photovoltaic array of this application;

[0083] Figure 2 It is a schematic diagram of the functional modules of an embodiment of the monitoring device for the flexible photovoltaic array of this application;

[0084] Figure 3 It is a schematic structural diagram of an embodiment of the electronic device of this application;

[0085] Figure 4 Schematic structural diagram of an embodiment of the storage medium of the present application. Specific embodiments

[0086] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0087] The terms "first", "second", and "third" in the present application are only used for descriptive purposes, and cannot be construed as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first", "second", and "third" may explicitly or implicitly include at least one of such features. In the description of the present application, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present application are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0088] Referring to "embodiments" herein means that the specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of the present application. The phrase appears in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0089] As Figure 1 shown, this embodiment provides an embodiment of a method for monitoring a flexible photovoltaic array. In this embodiment, the flexible photovoltaic array includes a flexible photovoltaic support erected in a preset area. The flexible photovoltaic support includes two steel beam frames fixed to the ground, an upper chord cable and a lower chord cable laid on the two steel beam frames, and a plurality of photovoltaic panels installed on the upper chord cable and the lower chord cable.

[0090] Preferably, the upper and lower chords also need two anchor cables for fixing, one end of each anchor cable is passed around the steel beam frame and anchored to the ground, and the other end of each anchor cable is fixedly connected to the upper or lower chord cable. The upper, lower and anchor cables all use steel strands with a diameter of 15.2 mm. The photovoltaic panels are then installed on the upper and lower chords. The two steel beam frames are "1 span". The site selection methods in this embodiment below are all based on the midpoint of "1 span" for site selection. Generally, 16 photovoltaic panels are installed in each span, with a spacing of 30 mm between photovoltaic panels, and a spacing of 300 mm between photovoltaic panels in the mid-span position. A single photovoltaic panel is 2278 mm long, 1134 mm wide and 30 mm thick.

[0091] Specifically, the monitoring method comprises the following steps:

[0092] Step S1, based on a number of preset time periods, obtain a number of upper chord tensile stresses and a number of lower chord tensile stresses of the flexible photovoltaic support, as well as the height difference between the spans of two steel beams of the flexible photovoltaic support and the number of photovoltaic panels.

[0093] Preferably, the tensile stress of the upper and lower chords of the flexible photovoltaic support can be directly measured by an instrument or calculated by a calculation formula. The tensile stress calculation formula is: σ = F / A, where σ represents tensile stress, F represents force, and A represents cross-sectional area. This formula is applicable to the stress calculation of steel cables under tension. For example, for a steel cable of a specific diameter, when subjected to a certain tensile force, the tensile stress σ can be calculated by measuring its force F and cross-sectional area A, and then substituting them into the formula.

[0094] Preferably, the forces acting on the upper and lower chords come from the gravity and deadweight of the photovoltaic panels, and the gravity between the two steel beams can be uniformly calculated.

[0095] Step S2, obtaining a plurality of wind speed probability distributions and a plurality of light intensity distributions in the area where the flexible photovoltaic support is located based on a plurality of preset time periods.

[0096] Preferably, the wind speed probability distribution of this embodiment adopts a two-parameter Weibull distribution, and the light intensity distribution can be directly queried from public channels or can also be measured by itself.

[0097] For example, the light intensity distribution of this embodiment can be obtained by a variety of methods, including using professional equipment, software, and meteorological data platforms.

[0098] Among them, professional measurement equipment can use pyroelectric detectors, CCD / CMOS cameras, linear detector arrays, thermal imagers, illuminometers and other professional equipment to measure the light intensity distribution. These devices have their own characteristics and are suitable for different measurement scenarios and requirements. For example, pyroelectric detectors have a fast response speed and are suitable for measuring pulsed lasers; CCD / CMOS cameras can capture the intensity distribution image when the laser beam passes through a specific plane.

[0099] Among them, software-assisted analysis can be carried out on the basis of using professional equipment for measurement, and can be combined with specialized software for analysis and processing to obtain more accurate light intensity distribution information. These software usually have functions such as data processing, image analysis and visualization.

[0100] Among them, obtaining through the meteorological data platform is for the light intensity distribution of a large area, and is obtained through data released by the meteorological data platform or authoritative institutions. These platforms usually integrate solar radiation data from multiple international institutions and provide data query services on a monthly, daily or even hourly basis.

[0101] Among them, for the light intensity distribution of a small range with low precision, a smartphone and software can be used for measurement. The front camera and light sensor of the mobile phone are used to measure the light intensity and display the current light intensity value. Although this method is relatively simple and easy to operate, its measurement accuracy and range may be affected by the mobile phone configuration and measurement environment.

[0102] Step S3, define the tensile stress of the upper chord cable of the current flexible photovoltaic support as a first dependent variable, and the tensile stress of the lower chord cable of the current flexible photovoltaic support as a second dependent variable.

[0103] Step S4, define the wind speed probability distribution, light intensity distribution, span height difference, and number of photovoltaic panels in the area where the current flexible photovoltaic support is located as a set of independent variables.

[0104] Step S5, analyze the first linear regression relationship between the first dependent variable of the current flexible photovoltaic support and all independent variables, and the second linear regression relationship between the second dependent variable of the current flexible photovoltaic support and all independent variables through multiple linear regression.

[0105] Preferably, LASSO linear regression is adopted in this embodiment.

[0106] It should be noted that during the use of the flexible photovoltaic support, the span height difference and the number of photovoltaic panels generally do not change. Therefore, the same independent variable data can be used for the two columns corresponding to the span height difference and the number of photovoltaic panels in the above expressions. The upper chord cable and the lower chord cable are respectively substituted into the above formula for calculation, and the upper chord cable and the lower chord cable cannot be substituted into the same expression.

[0107] This embodiment takes into account the situation where the elevation difference between bays and the number of photovoltaic panels change, so a variable form of expression is adopted.

[0108] Step S6, based on the preset prediction steps, predict the future tensile stress of the upper chord cable of the flexible photovoltaic support through the first linear regression relationship, and predict the future tensile stress of the lower chord cable of the flexible photovoltaic support through the second linear regression relationship.

[0109] Step S7, obtain the maximum allowable tensile stress of the upper chord cable and the maximum allowable tensile stress of the lower chord cable.

[0110] Preferably, the maximum allowable tensile stresses of the upper chord cable and the lower chord cable can be directly queried from the manufacturer or measured by oneself.

[0111] Specifically, the measurement methods of tensile stress mainly include static bending test, fatigue test, and tensile test using specific test equipment such as a universal testing machine.

[0112] Among them, the static bending test is mainly used to evaluate the tensile strength of the steel cable. The specific operation is to fix one end of the steel cable on the force measuring device of the fixture, and then slowly apply a load to deflect the pointer of the force measuring device by a certain angle and then stop loading, and record the number of turns of the pointer deflection. If the elongation of the steel cable exceeds the specified range, it is regarded as broken and this test needs to be carried out again.

[0113] Among them, the fatigue test is used to evaluate the performance of the steel cable under repeated stress. The specific operation is to place the steel cable on a fixed pulley and perform reciprocating motion until the steel cable breaks. Usually, after several (such as about 10 times) reciprocating motions, the steel cable will break.

[0114] Among them, using a universal testing machine to conduct a tensile test is an important method to evaluate the mechanical properties of materials. Fix the steel cable sample on the universal testing machine and gradually increase the tensile force until the sample breaks. By measuring the force and elongation during the tensile process, key indicators such as the tensile strength of the steel cable can be obtained. This method needs to follow corresponding test standards, such as GB / T228.1 - 2010 or GB / T 5224 - 2014, etc., to ensure the accuracy and repeatability of the test.

[0115] Step S8, define the first judgment condition as judging whether the future tensile stress of the upper chord cable is greater than or equal to the maximum allowable tensile stress of the upper chord cable, and define the second judgment condition as judging whether the future tensile stress of the lower chord cable is greater than or equal to the maximum allowable tensile stress of the lower chord cable.

[0116] Step S9, if at least one of the first judgment condition and the second judgment condition is satisfied, it is determined that the flexible photovoltaic support has a risk of stress exceeding the standard.

[0117] Further, in step S9, if at least one of the first judgment condition and the second judgment condition is satisfied, it is determined that the flexible photovoltaic support has a risk of excessive stress. After that, the following steps are further included:

[0118] Step S10, determine whether the risk of excessive stress is triggered by the first judgment condition or the second judgment condition.

[0119] Step S20, if it is only triggered by the first judgment condition, then execute step S30; if it is only triggered by the second judgment condition, then execute step S40; if it is triggered by both the first judgment condition and the second judgment condition at the same time, then execute step S50.

[0120] Step S30, obtain the future tensile stress of the upper chord cable that is greater than or equal to the maximum allowable tensile stress of the upper chord cable, and mark it as the future abnormal signal of the upper chord cable.

[0121] Step S40, obtain the future tensile stress of the lower chord cable that is greater than or equal to the maximum allowable tensile stress of the lower chord cable, and mark it as the future abnormal signal of the lower chord cable.

[0122] Step S50, execute step S30 and step S40 simultaneously to obtain the future abnormal signal of the upper chord cable and the future abnormal signal of the lower chord cable at the same time.

[0123] Step S60, respectively obtain the first future timestamp corresponding to each future abnormal signal of the upper chord cable and the second future timestamp corresponding to each future abnormal signal of the lower chord cable.

[0124] Step S70, send all the first future timestamps and all the second future timestamps to the external monitoring terminal.

[0125] Further, in step S2, based on several preset time periods, obtain several wind speed probability distributions and several light intensity distributions in the area where the flexible photovoltaic support is located. The specific steps are as follows:

[0126] Step S21, collect the wind speed data at several random points in the area where the flexible photovoltaic support is located.

[0127] Preferably, the wind speed data at random points can be directly measured and obtained, or can be obtained by querying the meteorological bureau.

[0128] Step S22, define the probability distribution function and the probability density function according to the two-parameter Weibull distribution. Both the probability distribution function and the probability density function include a scale parameter and a shape parameter.

[0129] Preferably, the probability distribution function is shown as the following formula:

[0130]

[0131] Among them, F(V) is the probability distribution function, and the value of the probability distribution function is in the interval [0, 1]; c is the scale parameter of the Weibull distribution; k is the shape parameter of the Weibull distribution; V is the wind speed data of the current random point.

[0132] Preferably, the probability density function is as shown in the following formula:

[0133]

[0134] Among them, f(V) is the probability density function.

[0135] Step S23, substitute all the wind speed data of the random points into the probability distribution function and the probability density function respectively as known quantities.

[0136] Step S24, define the log-likelihood function of the scale parameter and the shape parameter.

[0137] Preferably, the log-likelihood function is as shown in the following formula:

[0138]

[0139] Among them, L(k, c) is the log-likelihood function.

[0140] Step S25, solve the scale parameter and the shape parameter based on the log-likelihood function.

[0141] Preferably, this embodiment provides a solution process for the log-likelihood function:

[0142] Let: And Then:

[0143]

[0144] Modify the above formula to obtain the matrix equation:

[0145]

[0146] Iterate the above matrix equation by the Jacobi iteration method until the spectral radius ρ(G) of the matrix equation is less than 1, then it is determined to converge.

[0147] After convergence, the scale parameter and the shape parameter of the Weibull distribution can be obtained.

[0148] It should be noted that the formulas in the above additional content are for principle explanations, and the symbol meanings of the formulas are not interoperable with other formulas.

[0149] Step S26, substitute the solved scale parameter and the solved shape parameter into the probability distribution function and the probability density function respectively to obtain the wind speed probability distribution.

[0150] Step S27: Query the solar radiation distribution in the preset area through a preset strategy.

[0151] Preferably, the light intensity distribution in this embodiment can be directly queried from public channels or measured independently.

[0152] For example, the light intensity distribution in this embodiment can be obtained through various methods, including using professional equipment, software, and meteorological data platforms, etc.

[0153] Among them, professional measurement equipment can use pyroelectric detectors, CCD / CMOS cameras, linear detector arrays, thermal imagers, and illuminometers and other professional equipment to measure the light intensity distribution. These devices have their own characteristics and are suitable for different measurement scenarios and requirements. For example, pyroelectric detectors have a fast response speed and are suitable for measuring pulsed lasers; CCD / CMOS cameras can capture the intensity distribution image when the laser beam passes through a specific plane.

[0154] Among them, software-assisted analysis can be carried out on the basis of measuring with professional equipment, and can be combined with specialized software for analysis and processing to obtain more accurate light intensity distribution information. These software usually have functions such as data processing, image analysis, and visualization.

[0155] Among them, obtaining through a meteorological data platform is for the light intensity distribution of a large area, and is obtained through data released by a meteorological data platform or an authoritative institution. These platforms usually integrate solar radiation data from multiple international institutions and provide data query services on a monthly, daily, or even hourly basis.

[0156] Among them, for the light intensity distribution of a small area with low precision, a smartphone and software can be used for measurement. The front camera and light sensor of the mobile phone are used to measure the light intensity and display the current light intensity value. Although this method is relatively simple and easy to operate, its measurement accuracy and range may be affected by the mobile phone configuration and measurement environment.

[0157] Further, in step S5, analyze the first linear regression relationship between the first dependent variable and all independent variables of the current flexible photovoltaic support, and the second linear regression relationship between the second dependent variable and all independent variables of the current flexible photovoltaic support, including:

[0158] Step S51: Normalize all first dependent variables, all second dependent variables, and all independent variables.

[0159] Step S52: Define the first linear regression relationship between all first dependent variables and all independent variables through multiple linear regression.

[0160] Preferably, the multiple linear regression is shown as the following formula:

[0161]

[0162] Among them, is the first dependent variable of the i-th preset time period, n is the total number of all first dependent variables, and β 0 is the intercept of the linear regression relationship, and β j is the linear regression coefficient of the j-th independent variable, m is the total number of independent variables in a set of independent variables, and x j,i is the j-th independent variable of the i-th preset time period, and δ is the random error of the linear regression relationship.

[0163] It should be noted that the above additional content is only for principle explanation, and the symbolic meanings of the above additional content are not interoperable with the symbolic meanings in other positions of this embodiment. If there are repeated symbols in the additional content in different positions, please understand them separately and do not associate them with each other.

[0164] Step S53, solve all the first linear regression coefficients of the first linear regression relationship by the least squares method.

[0165] Preferably, all the linear regression coefficients of the multiple linear regression can be solved by the least squares method, and the least squares method is shown as follows:

[0166]

[0167] Among them, is the estimated value of β j , j = 1, 2,..., m, X is the matrix of all independent variables, X T is the transpose matrix of the matrix X.

[0168] Preferably, since this embodiment lists four independent variables, then m = 4, and if additional independent variables need to be added, they can be directly added.

[0169] It should be noted that the above additional content is only for principle explanation, and the symbolic meanings of the above additional content are not interoperable with the symbolic meanings in other positions of this embodiment. If there are repeated symbols in the additional content in different positions, please understand them separately and do not associate them with each other.

[0170] Step S54, substitute all the first linear regression coefficients obtained by the solution into the first linear regression relationship to obtain the upper chord cable tensile stress prediction model.

[0171] Preferably, the residual sum of squares of the linear regression can be used to judge the fitting effect of the model by comparing its magnitude. The residual sum of squares (RSS) is the sum of the squares of the differences between the actual observed values and the values predicted by the regression equation, and is used to quantify the difference between the model predicted value and the actual value.

[0172] Preferably, the judgment criterion for the sum of squared residuals is that the smaller the better. That is, the smaller the sum of squared residuals, the closer the predicted value of the model is to the actual observed value, and the better the fitting effect of the model. On the contrary, if the sum of squared residuals is large, it indicates that there is a large deviation between the predicted value of the model and the actual observed value, and the fitting effect of the model is poor.

[0173] Step S55, define the second linear regression relationship between all second dependent variables and all independent variables through multiple linear regression.

[0174] Step S56, solve all second linear regression coefficients of the second linear regression relationship by the least squares method.

[0175] Step S57, substitute all the obtained second linear regression coefficients into the second linear regression relationship to obtain the lower chord cable tensile stress prediction model.

[0176] Preferably, the calculation methods of steps S55 to S57 can be calculated by the above expressions, and the calculation principles are the same, so they will not be elaborated here.

[0177] Furthermore, in step S6, based on the preset prediction steps, predict the future tensile stress of the upper chord cable of the flexible photovoltaic support through the first linear regression relationship and predict the future tensile stress of the lower chord cable of the flexible photovoltaic support through the second linear regression relationship, which specifically includes the following steps:

[0178] Step S61, obtain the future wind speed probability distribution of the preset area based on the preset prediction steps.

[0179] Preferably, the future wind speed probability distribution can be directly obtained by querying the meteorological bureau, or can be obtained through machine learning and training in the following text of this embodiment.

[0180] Step S62, obtain the future light intensity distribution of the preset area based on the preset prediction steps.

[0181] Preferably, the future light intensity distribution can be directly obtained by querying the meteorological bureau, or can be obtained through machine learning and training in the following text of this embodiment.

[0182] Step S63, substitute the future wind speed probability distribution, the future light intensity distribution, the span height difference, and the number of photovoltaic panels into the upper chord cable tensile stress prediction model to obtain the future tensile stress of the upper chord cable based on the preset prediction steps.

[0183] Step S64, substitute the future wind speed probability distribution, the future light intensity distribution, the span height difference, and the number of photovoltaic panels into the lower chord cable tensile stress prediction model to obtain the future tensile stress of the lower chord cable based on the preset prediction steps.

[0184] Preferably, the elevation difference between bays and the number of photovoltaic panels generally do not change.

[0185] Further, in step S61, obtaining the future wind speed probability distribution of a preset area based on a preset prediction step number specifically includes the following steps:

[0186] Step S611, obtaining several wind speed probability distributions of a preset area based on several preset time periods.

[0187] Preferably, the preset time period and the preset prediction step number can be set to the same magnitude, such as one natural hour.

[0188] Step S612, integrating all the wind speed data at random points in one wind speed probability distribution into one wind speed data set.

[0189] Step S613, performing vector normalization processing on all the wind speed data sets, and obtaining one normalized data set based on one wind speed data set.

[0190] Preferably, vector normalization processing is a method of scaling a vector proportionally to a unit vector. The main purpose is to only consider the direction of the vector without affecting its magnitude. The mathematical principle of vector normalization is to divide the vector by its modulus length to obtain a unit vector.

[0191] Step S614, dividing one normalized data set into one training set and one validation set according to a preset ratio.

[0192] Preferably, the preset ratio usually adopts the ratio of 80%:20% to divide the image data into a training set and a validation set, that is, 80% of the data is the training set and 20% of the data is the validation set.

[0193] Step S615, defining a neural network model with signal connections between the input layer, the hidden layer, and the output layer in sequence.

[0194] Preferably, the neural network model is characterized by the following formula:

[0195]

[0196] where y is the neural network model; x n is the nth input node of the input layer, and each input node corresponds to one normalized data set in the training set, is the weight from the mth input node of the input layer to the nth input node of the hidden layer; is the bias connected to the nth input node of the hidden layer; is the bias of the output layer; tansig(·) is the activation function; the number in the parentheses of the symbolic subscript is the layer number, the subscript (1) is the first layer, that is, the input layer, and the subscript (1, 2) is from the first layer to the second layer, that is, from the input layer to the hidden layer.

[0197] It should be noted that the above formulas and formula symbols are only for principle explanation, and their meanings are not interoperable with those in other positions.

[0198] Step S616: Input all training sets into the input layer in sequence and perform several trainings through the neural network model.

[0199] Step S617: Obtain the root mean square error of the training results corresponding to the current validation set and the current training set respectively based on each training.

[0200] Step S618: Obtain the minimum error among all root mean square errors, and the training result corresponding to the minimum error as the wind speed probability distribution prediction model.

[0201] Step S619: Predict the future wind speed probability distribution based on the wind speed probability distribution prediction model with a preset prediction step.

[0202] Preferably, training a neural network model usually requires a large amount of data, that is, a data set; the data set is generally divided into three categories, namely the above-mentioned training set (training set), validation set (validation set), and test set (test set).

[0203] Among them, one epoch is equal to the process of training once with all samples in the training set. By training once, it means performing one forward pass and one back pass; when the number of samples (i.e., the training set) in one epoch is too large, training once may consume too much time, and it is not entirely necessary to use all the data in the training set for each training. Then, the entire training set needs to be divided into multiple small pieces, that is, divided into multiple batches for training; one epoch consists of one or more batches. A batch is a part of the training set, and only a part of the data, that is, one batch, is used in each training process. The process of training one batch is one iteration.

[0204] Preferably, neural network training specifically includes the perceptron (Perceptron). The perceptron consists of two layers of neurons. The input layer receives external input signals and then transmits them to the output layer. The output layer is an M-P neuron, and the step function is y j = f(∑ i w i ·xi -θ i )。

[0205] Preferably, given a training data set, the weights w i (i = 1, 2,..., n) and the training bias θ i can be obtained through learning, and θ i can be understood as the weight w corresponding to a fixed value with fixed inputs of -1 and 0 i+1 。

[0206] It should be noted that the step function here does not have the same symbolic meaning as the other formulas in the embodiments. This step function is only for illustrative purposes and does not participate in the calculations of other formulas.

[0207] Preferably, the number of neural network training times in this embodiment can be set to 10,000 times.

[0208] Preferably, the learning rate for the 1st to 5000th epochs can be set to 0.01, the learning rate for the 5001st to 7500th epochs can be set to 0.001, and the learning rate for the 7501st to 10000th epochs can be set to 0.0001.

[0209] It can be understood that the neural network training in this embodiment mainly includes the following ideas:

[0210] ① Initialize the weights and bias terms in the network.

[0211] Initializing the parameter values (the weights and bias terms of the output units, and the weights and bias terms of the hidden units are all parameters of the model) is to activate the forward propagation, obtain the output values of each layer of elements, and then obtain the value of the loss function.

[0212] ② Activate the forward propagation to obtain the output values of each layer and the expected values of the loss functions of each layer.

[0213] ③ Calculate the error terms of the output units and the error terms of the hidden units according to the loss function.

[0214] Calculate each error, calculate the gradient of the parameter with respect to the loss function or calculate the partial derivative according to the calculus chain rule. For the partial derivative of a vector or matrix in a composite function, the partial derivative of the inner function of the composite function always chooses to multiply on the left; for the partial derivative of a scalar in a composite function, the partial derivative of the inner function of the composite function can choose to multiply on the left or on the right.

[0215] ④ Update the weights and bias terms in the neural network.

[0216] ⑤ Repeat steps ② to ④ until the loss function is less than the preset bias or the number of iterations is used up, and output the parameters at this time as the current best parameters.

[0217] Further, in step S62, obtaining the future light intensity distribution of a preset area based on a preset prediction step number includes:

[0218] Step S621, obtaining several light intensity distributions of the preset area based on several preset time periods.

[0219] Step S622, integrating the light intensity data of all random points in one light intensity distribution into one light intensity data set.

[0220] Step S623, performing standard normalization processing on all light intensity data sets, and obtaining one normalized data set based on one light intensity data set.

[0221] Step S624, dividing one normalized data set into one training set and one validation set according to a preset ratio.

[0222] Step S625, defining a neural network model with signal connections in sequence of an input layer, a hidden layer, and an output layer.

[0223] Step S626, sequentially inputting all training sets into the input layer, and performing several trainings through the neural network model.

[0224] Step S627, respectively obtaining the root mean square error of the training results corresponding to the current validation set and the current training set for each training.

[0225] Step S628, obtaining the minimum error among all root mean square errors, and the training result corresponding to the minimum error as the light intensity distribution prediction model.

[0226] Step S629, predicting the future light intensity distribution based on the preset prediction step number through the light intensity distribution prediction model.

[0227] Preferably, the calculation principles of steps S621 to S629 are the same as those of steps S611 to S619 above. Refer to the above preferred content, and details are not repeated here.

[0228] In this embodiment, several tensile stresses of the upper chord cables and several tensile stresses of the lower chord cables of the flexible photovoltaic support are obtained based on several preset time periods, as well as the elevation difference between the two steel girders of the flexible photovoltaic support and the number of photovoltaic panels; several wind speed probability distributions and several light intensity distributions in the area where the flexible photovoltaic support is located are obtained based on several preset time periods; the tensile stress of the upper chord cable of the current flexible photovoltaic support is defined as a first dependent variable, and the tensile stress of the lower chord cable of the current flexible photovoltaic support is defined as a second dependent variable; the wind speed probability distribution, light intensity distribution, elevation difference between the two steel girders, and the number of photovoltaic panels in the area where the current flexible photovoltaic support is located are defined as a set of independent variables; the first linear regression relationship between the first dependent variable of the current flexible photovoltaic support and all independent variables, and the second linear regression relationship between the second dependent variable of the current flexible photovoltaic support and all independent variables are analyzed through multiple linear regression; the future tensile stress of the upper chord cable of the flexible photovoltaic support is predicted based on the first linear regression relationship, and the future tensile stress of the lower chord cable of the flexible photovoltaic support is predicted based on the second linear regression relationship with a preset prediction step; the maximum allowable tensile stress of the upper chord cable and the maximum allowable tensile stress of the lower chord cable are obtained; a first judgment condition is defined to judge whether the future tensile stress of the upper chord cable is greater than or equal to the maximum allowable tensile stress of the upper chord cable, and a second judgment condition is defined to judge whether the future tensile stress of the lower chord cable is greater than or equal to the maximum allowable tensile stress of the lower chord cable; if at least one of the first judgment condition and the second judgment condition is satisfied, it is determined that the flexible photovoltaic support has a risk of excessive stress. In this embodiment, the upper chord cable and the lower chord cable of the flexible photovoltaic support are linearly regressed and analyzed with physical parameters and environmental parameters respectively. Since the upper chord cable and the lower chord cable are in the same support and the same environment, although the two chord cables are linearly regressed separately, the two linear regressions are related to each other, so that the future tensile stresses obtained by subsequent prediction are related to each other and no data deviation will occur. Finally, by defining an alternative judgment condition, and if at least one of the two judgment conditions is satisfied, it is determined that the flexible photovoltaic support will have excessive stress at a future time. The whole process of this embodiment is automatically calculated by a computer without manual participation, avoiding subjective experience errors. Moreover, this embodiment realizes the prediction function of tensile stress, and the predicted tensile stress is related to physical parameters and environmental parameters, ensuring the accuracy of the data.

[0229] As Figure 2 shown, this embodiment provides an embodiment of a monitoring device for a flexible photovoltaic array. In this embodiment, the monitoring device is applied to the monitoring method in the above embodiment.

[0230] Specifically, the monitoring device includes a support physical parameter acquisition module 1, a support environmental parameter acquisition module 2, a dependent variable definition module 3, an independent variable definition module 4, a linear regression relationship analysis module 5, an upper and lower chord cable tensile stress prediction module 6, a maximum allowable tensile stress acquisition module 7, a judgment condition definition module 8, and a judgment condition determination module 9, which are electrically connected in sequence.

[0231] Among them, the support physical parameter acquisition module 1 is used to acquire a plurality of upper chord cable tensile stresses and a plurality of lower chord cable tensile stresses of the flexible photovoltaic support, as well as the span height difference between two steel beam frames of the flexible photovoltaic support and the number of photovoltaic panels based on a plurality of preset time periods; the support environmental parameter acquisition module 2 is used to acquire a plurality of wind speed probability distributions and a plurality of light intensity distributions in the area where the flexible photovoltaic support is located based on a plurality of preset time periods; the dependent variable definition module 3 is used to define the upper chord cable tensile stress of the current flexible photovoltaic support as a first dependent variable and the lower chord cable tensile stress of the current flexible photovoltaic support as a second dependent variable; the independent variable definition module 4 is used to define the wind speed probability distribution, light intensity distribution, span height difference, and number of photovoltaic panels in the area where the current flexible photovoltaic support is located as a set of independent variables; the linear regression relationship analysis module 5 is used to analyze the first linear regression relationship between the first dependent variable of the current flexible photovoltaic support and all independent variables and the second linear regression relationship between the second dependent variable of the current flexible photovoltaic support and all independent variables through multiple linear regression; the upper and lower chord cable tensile stress prediction module 6 is used to predict the future tensile stress of the upper chord cable of the flexible photovoltaic support through the first linear regression relationship and predict the future tensile stress of the lower chord cable of the flexible photovoltaic support through the second linear regression relationship based on a preset number of prediction steps; the maximum allowable tensile stress acquisition module 7 is used to acquire the maximum allowable tensile stress of the upper chord cable and the maximum allowable tensile stress of the lower chord cable; the judgment condition definition module 8 is used to define the first judgment condition as judging whether there is a future tensile stress of the upper chord cable greater than or equal to the maximum allowable tensile stress of the upper chord cable, and define the second judgment condition as judging whether there is a future tensile stress of the lower chord cable greater than or equal to the maximum allowable tensile stress of the lower chord cable; the judgment condition determination module 9 is used to determine that the flexible photovoltaic support has a risk of stress exceeding the standard if at least one of the first judgment condition and the second judgment condition is satisfied.

[0232] Furthermore, the monitoring device further includes a judgment condition trigger source acquisition module and a trigger source distribution module that are electrically connected in sequence. The trigger source distribution module is electrically connected to an upper chord cable future abnormal signal marking module, a lower chord cable future abnormal signal marking module, and an upper and lower chord cable future abnormal signal simultaneous marking module respectively. The upper chord cable future abnormal signal marking module, the lower chord cable future abnormal signal marking module, and the upper and lower chord cable future abnormal signal simultaneous marking module are electrically connected to an abnormal signal future timestamp acquisition module respectively. The abnormal signal future timestamp acquisition module is electrically connected to an abnormal signal future timestamp sending module.

[0233] Among them, the determination condition trigger source acquisition module is used to determine whether the stress exceeding standard risk is triggered by the first determination condition or the second determination condition; the trigger source allocation module is used to execute the upper chord future abnormal signal marking module if only triggered by the first determination condition, execute the lower chord future abnormal signal marking module if only triggered by the second determination condition, and execute the upper and lower chord future abnormal signal simultaneous marking module if triggered by both the first determination condition and the second determination condition.

[0234] Among them, the upper chord future abnormal signal marking module is used to obtain the upper chord future tensile stress greater than or equal to the maximum allowable tensile stress of the upper chord and mark it as the upper chord future abnormal signal; the lower chord future abnormal signal marking module is used to obtain the lower chord future tensile stress greater than or equal to the maximum allowable tensile stress of the lower chord and mark it as the lower chord future abnormal signal; the upper and lower chord future abnormal signal simultaneous marking module is used to simultaneously execute the upper chord future abnormal signal marking module and the lower chord future abnormal signal marking module to simultaneously obtain the upper chord future abnormal signal and the lower chord future abnormal signal.

[0235] Among them, the abnormal signal future timestamp acquisition module is used to respectively obtain the first future timestamp corresponding to each upper chord future abnormal signal and the second future timestamp corresponding to each lower chord future abnormal signal; the abnormal signal future timestamp sending module is used to send all the first future timestamps and all the second future timestamps to the external monitoring end.

[0236] Furthermore, the bracket environment parameter acquisition module 2 specifically includes a first bracket environment parameter acquisition sub-module, a second bracket environment parameter acquisition sub-module, a third bracket environment parameter acquisition sub-module, a fourth bracket environment parameter acquisition sub-module, a fifth bracket environment parameter acquisition sub-module, a sixth bracket environment parameter acquisition sub-module, and a seventh bracket environment parameter acquisition sub-module that are electrically connected in sequence; the first bracket environment parameter acquisition sub-module is electrically connected to the bracket physical parameter acquisition module 1, and the seventh bracket environment parameter acquisition sub-module is electrically connected to the dependent variable definition module 3.

[0237] Among them, the first support environmental parameter acquisition sub-module is used to collect wind speed data at several random points in the area where the flexible photovoltaic support is located; the second support environmental parameter acquisition sub-module is used to define the probability distribution function and the probability density function according to the two-parameter Weibull distribution, and both the probability distribution function and the probability density function include a scale parameter and a shape parameter; the third support environmental parameter acquisition sub-module is used to substitute all the random point wind speed data as known quantities into the probability distribution function and the probability density function respectively; the fourth support environmental parameter acquisition sub-module is used to define the logarithmic likelihood function of the scale parameter and the shape parameter; the fifth support environmental parameter acquisition sub-module is used to solve the scale parameter and the shape parameter based on the logarithmic likelihood function; the sixth support environmental parameter acquisition sub-module is used to substitute the solved scale parameter and the solved shape parameter into the probability distribution function and the probability density function respectively to obtain the wind speed probability distribution; the seventh support environmental parameter acquisition sub-module is used to query the solar radiation distribution in the preset area through a preset strategy.

[0238] Further, the linear regression relationship analysis module 5 specifically includes a first linear regression relationship analysis sub-module, a second linear regression relationship analysis sub-module, a third linear regression relationship analysis sub-module, a fourth linear regression relationship analysis sub-module, a fifth linear regression relationship analysis sub-module, a sixth linear regression relationship analysis sub-module, and a seventh linear regression relationship analysis sub-module that are electrically connected in sequence; the first linear regression relationship analysis sub-module is electrically connected to the independent variable definition module 4, and the seventh linear regression relationship analysis sub-module is electrically connected to the upper and lower chord cable tensile stress prediction module 6.

[0239] Among them, the first linear regression relationship analysis sub-module is used to perform normalization processing on all the first dependent variables, all the second dependent variables, and all the independent variables; the second linear regression relationship analysis sub-module is used to define the first linear regression relationship between all the first dependent variables and all the independent variables through multiple linear regression; the third linear regression relationship analysis sub-module is used to solve all the first linear regression coefficients of the first linear regression relationship by the least squares method; the fourth linear regression relationship analysis sub-module is used to substitute all the obtained first linear regression coefficients into the first linear regression relationship to obtain the upper chord cable tensile stress prediction model; the fifth linear regression relationship analysis sub-module is used to define the second linear regression relationship between all the second dependent variables and all the independent variables through multiple linear regression; the sixth linear regression relationship analysis sub-module is used to solve all the second linear regression coefficients of the second linear regression relationship by the least squares method; the seventh linear regression relationship analysis sub-module is used to substitute all the obtained second linear regression coefficients into the second linear regression relationship to obtain the lower chord cable tensile stress prediction model.

[0240] Furthermore, the upper and lower cable tensile stress prediction module 6 specifically includes a first upper and lower cable tensile stress prediction sub-module, a second upper and lower cable tensile stress prediction sub-module, a third upper and lower cable tensile stress prediction sub-module, and a fourth upper and lower cable tensile stress prediction sub-module that are electrically connected in sequence; the first upper and lower cable tensile stress prediction sub-module is electrically connected to the seventh linear regression relationship analysis sub-module, and the fourth upper and lower cable tensile stress prediction sub-module is electrically connected to the maximum allowable tensile stress acquisition module 7.

[0241] Among them, the first upper and lower cable tensile stress prediction sub-module is used to obtain the future wind speed probability distribution in a preset area based on a preset prediction step; the second upper and lower cable tensile stress prediction sub-module is used to obtain the future light intensity distribution in a preset area based on a preset prediction step; the third upper and lower cable tensile stress prediction sub-module is used to substitute the future wind speed probability distribution, the future light intensity distribution, the span height difference, and the number of photovoltaic panels into the upper cable tensile stress prediction model to obtain the future tensile stress of the upper cable based on a preset prediction step; the fourth upper and lower cable tensile stress prediction sub-module is used to substitute the future wind speed probability distribution, the future light intensity distribution, the span height difference, and the number of photovoltaic panels into the lower cable tensile stress prediction model to obtain the future tensile stress of the lower cable based on a preset prediction step.

[0242] Furthermore, the first upper and lower cable tensile stress prediction sub-module specifically includes a first upper and lower cable tensile stress prediction unit, a second upper and lower cable tensile stress prediction unit, a third upper and lower cable tensile stress prediction unit, a fourth upper and lower cable tensile stress prediction unit, a fifth upper and lower cable tensile stress prediction unit, a sixth upper and lower cable tensile stress prediction unit, a seventh upper and lower cable tensile stress prediction unit, an eighth upper and lower cable tensile stress prediction unit, and a ninth upper and lower cable tensile stress prediction unit that are electrically connected in sequence; the first upper and lower cable tensile stress prediction unit is electrically connected to the seventh linear regression relationship analysis sub-module, and the ninth upper and lower cable tensile stress prediction unit is electrically connected to the second upper and lower cable tensile stress prediction sub-module.

[0243] Among them, the first upper and lower chord cable tensile stress prediction unit is used to obtain the wind speed probability distributions of a preset area based on a number of preset time periods; the second upper and lower chord cable tensile stress prediction unit is used to integrate the wind speed data of all random points in a wind speed probability distribution into a wind speed data set; the third upper and lower chord cable tensile stress prediction unit is used to perform vector normalization processing on all wind speed data sets and obtain a normalized data set based on a wind speed data set; the fourth upper and lower chord cable tensile stress prediction unit is used to divide a normalized data set into a training set and a validation set according to a preset ratio; the fifth upper and lower chord cable tensile stress prediction unit is used to define a neural network model with signal connections in sequence of an input layer, a hidden layer, and an output layer; the sixth upper and lower chord cable tensile stress prediction unit is used to input all training sets into the input layer in sequence and perform several trainings through the neural network model; the seventh upper and lower chord cable tensile stress prediction unit is used to obtain the root mean square error of the training results corresponding to the current validation set and the current training set respectively based on each training; the eighth upper and lower chord cable tensile stress prediction unit is used to obtain the minimum error among all root mean square errors and the training result corresponding to the minimum error as the wind speed probability distribution prediction model; the ninth upper and lower chord cable tensile stress prediction unit is used to predict the future wind speed probability distribution based on the wind speed probability distribution prediction model according to a preset prediction step number.

[0244] Further, the second upper and lower chord cable tensile stress prediction sub-module specifically includes a tenth upper and lower chord cable tensile stress prediction unit, an eleventh upper and lower chord cable tensile stress prediction unit, a twelfth upper and lower chord cable tensile stress prediction unit, a thirteenth upper and lower chord cable tensile stress prediction unit, a fourteenth upper and lower chord cable tensile stress prediction unit, a fifteenth upper and lower chord cable tensile stress prediction unit, a sixteenth upper and lower chord cable tensile stress prediction unit, a seventeenth upper and lower chord cable tensile stress prediction unit, and an eighteenth upper and lower chord cable tensile stress prediction unit that are electrically connected in sequence; the tenth upper and lower chord cable tensile stress prediction unit is electrically connected to the ninth upper and lower chord cable tensile stress prediction unit, and the eighteenth upper and lower chord cable tensile stress prediction unit is electrically connected to the third upper and lower chord cable tensile stress prediction sub-module.

[0245] Among them, the tenth upper and lower chord cable tensile stress prediction unit is used to obtain several light intensity distributions in a preset area based on several preset time periods; the eleventh upper and lower chord cable tensile stress prediction unit is used to integrate all the random point light intensity data in a light intensity distribution into a light intensity data set; the twelfth upper and lower chord cable tensile stress prediction unit is used to perform standard normalization processing on all the light intensity data sets and obtain a normalized data set based on a light intensity data set; the thirteenth upper and lower chord cable tensile stress prediction unit is used to divide a normalized data set into a training set and a validation set according to a preset ratio; the fourteenth upper and lower chord cable tensile stress prediction unit is used to define a neural network model with signal connections in sequence of an input layer, a hidden layer, and an output layer; the fifteenth upper and lower chord cable tensile stress prediction unit is used to sequentially input all the training sets into the input layer and perform several trainings through the neural network model; the sixteenth upper and lower chord cable tensile stress prediction unit is used to respectively obtain the root mean square error of the training results corresponding to the current validation set and the current training set based on each training; the seventeenth upper and lower chord cable tensile stress prediction unit is used to obtain the minimum error among all the root mean square errors and the training result corresponding to the minimum error as the light intensity distribution prediction model; the eighteenth upper and lower chord cable tensile stress prediction unit is used to predict the future light intensity distribution based on the light intensity distribution prediction model according to a preset prediction step number.

[0246] It should be noted that this embodiment is a functional module item embodiment based on the above method embodiment. For additional content such as the preference, expansion, limitation, and illustrative examples of this embodiment, refer to the above method embodiment, and this embodiment will not be elaborated herein.

[0247] In this embodiment, by obtaining a plurality of upper chord cable tensile stresses and a plurality of lower chord cable tensile stresses of the flexible photovoltaic support, as well as the span height difference between two steel girders of the flexible photovoltaic support and the number of photovoltaic panels, based on a plurality of preset time periods; obtaining a plurality of wind speed probability distributions and a plurality of light intensity distributions in the area where the flexible photovoltaic support is located, based on a plurality of preset time periods; defining the tensile stress of the upper chord cable of the current flexible photovoltaic support as a first dependent variable, and the tensile stress of the lower chord cable of the current flexible photovoltaic support as a second dependent variable; defining the wind speed probability distribution, light intensity distribution, span height difference, and number of photovoltaic panels in the area where the current flexible photovoltaic support is located as a set of independent variables; analyzing the first linear regression relationship between the first dependent variable of the current flexible photovoltaic support and all independent variables, and the second linear regression relationship between the second dependent variable of the current flexible photovoltaic support and all independent variables, through multiple linear regression; predicting the future tensile stress of the upper chord cable of the flexible photovoltaic support through the first linear regression relationship, and predicting the future tensile stress of the lower chord cable of the flexible photovoltaic support through the second linear regression relationship, based on a preset number of prediction steps; obtaining the maximum allowable tensile stress of the upper chord cable and the maximum allowable tensile stress of the lower chord cable; defining a first judgment condition as determining whether there is a future tensile stress of the upper chord cable greater than or equal to the maximum allowable tensile stress of the upper chord cable, and defining a second judgment condition as determining whether there is a future tensile stress of the lower chord cable greater than or equal to the maximum allowable tensile stress of the lower chord cable; if at least one of the first judgment condition and the second judgment condition is satisfied, it is determined that the flexible photovoltaic support has a risk of excessive stress. In this embodiment, the upper chord cable and the lower chord cable of the flexible photovoltaic support are respectively subjected to linear regression analysis with physical parameters and environmental parameters. Since the upper chord cable and the lower chord cable are in the same support and in the same environment, although the two chord cables are respectively subjected to linear regression, the two linear regressions are related to each other, so that the future tensile stresses predicted subsequently are related to each other and no data deviation will occur. Finally, by defining an alternative judgment condition, and if at least one of the two judgment conditions is satisfied, it is determined that the flexible photovoltaic support will have excessive stress at a future time. The whole process of this embodiment is automatically calculated by a computer without manual participation, avoiding subjective experience errors. Moreover, this embodiment realizes the prediction function of tensile stress, and the predicted tensile stress is related to physical parameters and environmental parameters, ensuring the accuracy of the data.

[0248] As Figure 3 shown, this embodiment provides an embodiment of an electronic device. In this embodiment, the electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101.

[0249] The memory 102 stores program instructions for implementing the monitoring method of the flexible photovoltaic array in any of the above embodiments.

[0250] The processor 101 is configured to execute the program instructions stored in the memory 102 to monitor the flexible photovoltaic array.

[0251] Among them, the processor 101 can also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip with data processing capabilities. The processor 101 can also be a general-purpose processor, a digital data processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0252] Furthermore, Figure 4 It is a schematic structural diagram of a storage medium according to an embodiment of the present application. The storage medium 11 of the embodiment of the present application stores program instructions 111 that can implement all the above methods. Among them, the program instructions 111 can be stored in the above storage medium in the form of a software product, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, or terminal devices such as computers, servers, mobile phones, and tablets.

[0253] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, indirect couplings or communication connections of devices or units, and can be in electrical, mechanical, or other forms.

[0254] In addition, in each embodiment of the present application, each functional unit may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit. The above is only the implementation manner of the present application and does not limit the patent scope of the present application. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be included in the patent protection scope of the present application by the same token.

[0255] The specific implementation manners of the present application have been described in detail above, but they are only examples, and the present application is not limited to the specific implementation manners described above. For those skilled in the art, any equivalent modification or substitution to the present application is also within the scope of the present application. Therefore, all equal transformations, modifications, improvements, etc. made without departing from the spirit and principle of the present application should be covered by the scope of the present application.

Claims

1. A monitoring method for a flexible photovoltaic array, wherein the flexible photovoltaic array comprises a flexible photovoltaic bracket erected in a preset area, wherein the flexible photovoltaic bracket comprises two steel beams fixed to the ground, an upper chord and a lower chord erected on the two steel beams, and a plurality of photovoltaic panels installed on the upper chord and the lower chord, wherein: The monitoring method comprises: Step S1, obtaining a plurality of upper chord tensile stresses and a plurality of lower chord tensile stresses of the flexible photovoltaic support, as well as a span height difference between two steel beams of the flexible photovoltaic support and the number of photovoltaic panels based on a plurality of preset time periods; Step S2, obtaining the wind speed probability distribution and light intensity distribution in the area where the flexible photovoltaic bracket is located; Step S3, defining the tensile stress of the upper chord cable of the current flexible photovoltaic support as a first dependent variable, and defining the tensile stress of the lower chord cable of the current flexible photovoltaic support as a second dependent variable; Step S4, defining the wind speed probability distribution, light intensity distribution, span height difference, and number of photovoltaic panels in the area where the current flexible photovoltaic bracket is located as a set of independent variables; Step S5, analyzing the first linear regression relationship between the first dependent variable of the current flexible photovoltaic support and all independent variables, and the second linear regression relationship between the second dependent variable of the current flexible photovoltaic support and all independent variables through multiple linear regression; Step S6, predicting the future tensile stress of the upper chord of the flexible photovoltaic support through the first linear regression relationship based on a preset number of prediction steps, and predicting the future tensile stress of the lower chord of the flexible photovoltaic support through the second linear regression relationship; Step S7, obtaining the maximum allowable tensile stress of the upper chord of the upper chord and the maximum allowable tensile stress of the lower chord of the lower chord; Step S8, defining a first judgment condition as judging whether the future tensile stress of the upper chord is greater than or equal to the maximum allowable tensile stress of the upper chord, and defining a second judgment condition as judging whether the future tensile stress of the lower chord is greater than or equal to the maximum allowable tensile stress of the lower chord; Step S9: If at least one of the first judgment condition and the second judgment condition is met, it is determined that the flexible photovoltaic bracket has a risk of excessive stress.

2. The monitoring method according to claim 1, characterized in that: Step S9, if at least one of the first judgment condition and the second judgment condition is satisfied, it is determined that the flexible photovoltaic bracket has a risk of excessive stress, and then includes: Step S10, determining whether the stress exceeding risk is triggered by the first judgment condition or the second judgment condition; Step S20, if it is triggered only by the first judgment condition, then execute step S30; if it is triggered only by the second judgment condition, then execute step S40; if it is triggered by both the first judgment condition and the second judgment condition, then execute step S50; Step S30, obtaining a future tensile stress of the upper chord that is greater than or equal to the maximum allowable tensile stress of the upper chord, and marking it as a future abnormal signal of the upper chord; Step S40, obtaining a future tensile stress of the lower chord that is greater than or equal to the maximum allowable tensile stress of the lower chord, and marking it as a future abnormal signal of the lower chord; Step S50, executing step S30 and step S40 simultaneously, so as to simultaneously obtain the future abnormal signal of the upper chord and the future abnormal signal of the lower chord; Step S60, respectively obtaining a first future timestamp corresponding to a future abnormal signal of each upper chord and a second future timestamp corresponding to a future abnormal signal of each lower chord; Step S70: Send all first future timestamps and all second future timestamps to an external monitoring terminal.

3. The monitoring method according to claim 1, characterized in that: Step S2, obtaining the wind speed probability distribution and light intensity distribution in the area where the flexible photovoltaic bracket is located, including: Step S21, collecting wind speed data of several random points in the area where the flexible photovoltaic bracket is located; Step S22, defining a probability distribution function and a probability density function according to a two-parameter Weibull distribution, wherein both the probability distribution function and the probability density function include a scale parameter and a shape parameter; Step S23, substituting all random point wind speed data as known quantities into the probability distribution function and the probability density function respectively; Step S24, defining a log-likelihood function of the scale parameter and the shape parameter; Step S25, solving the scale parameter and the shape parameter based on the log-likelihood function; Step S26, substituting the solved scale parameter and the solved shape parameter into the probability distribution function and the probability density function respectively to obtain the wind speed probability distribution; Step S27, querying the solar radiation distribution of the preset area through a preset strategy.

4. The monitoring method according to claim 3, characterized in that: Step S5, analyzing the first linear regression relationship between the first dependent variable of the current flexible photovoltaic support and all independent variables, and the second linear regression relationship between the second dependent variable of the current flexible photovoltaic support and all independent variables through multiple linear regression, including: Step S51, normalizing all first dependent variables, all second dependent variables, and all independent variables; Step S52, defining the first linear regression relationship between all first dependent variables and all independent variables through multiple linear regression; Step S53, solving all first linear regression coefficients of the first linear regression relationship by least square method; Step S54, substituting all the first linear regression coefficients obtained by solving into the first linear regression relationship to obtain a tensile stress prediction model for the upper chord cable; Step S55, defining the second linear regression relationship between all second dependent variables and all independent variables through multiple linear regression; Step S56, solving all second linear regression coefficients of the second linear regression relationship by least square method; Step S57: Substitute all the solved second linear regression coefficients into the second linear regression relationship to obtain a lower chord tensile stress prediction model.

5. The monitoring method according to claim 4, characterized in that: Step S6, predicting the future tensile stress of the upper chord of the flexible photovoltaic support through the first linear regression relationship based on a preset number of prediction steps, and predicting the future tensile stress of the lower chord of the flexible photovoltaic support through the second linear regression relationship, including: Step S61, obtaining the future wind speed probability distribution of the preset area based on the preset prediction step number; Step S62, obtaining the future light intensity distribution of the preset area based on the preset prediction step number; Step S63, substituting the future wind speed probability distribution, the future light intensity distribution, the span height difference, and the number of photovoltaic panels into the upper chord tensile stress prediction model to obtain the future tensile stress of the upper chord based on the preset prediction step number; Step S64, substituting the future wind speed probability distribution, the future light intensity distribution, the span height difference, and the number of photovoltaic panels into the lower chord tensile stress prediction model to obtain the future tensile stress of the lower chord based on the preset prediction step number.

6. The monitoring method according to claim 5, characterized in that: Step S61, obtaining the future wind speed probability distribution of the preset area based on the preset prediction step number, includes: Step S611, obtaining a plurality of wind speed probability distributions of the preset area based on a plurality of preset time periods; Step S612, integrating all random point wind speed data in a wind speed probability distribution into a wind speed data set; Step S613, performing vector normalization processing on all wind speed data sets, and obtaining a normalized data set based on one wind speed data set; Step S614, dividing a normalized data set into a training set and a validation set according to a preset ratio; Step S615, defining a neural network model in which the input layer, the hidden layer, and the output layer are sequentially connected; Step S616, inputting all training sets into the input layer in sequence, and performing several trainings through the neural network model; Step S617, obtaining a root mean square error of the training results corresponding to the current validation set and the current training set based on each training; Step S618, obtaining the minimum error value among all root mean square errors, and the training result corresponding to the minimum error value as a wind speed probability distribution prediction model; Step S619: predicting the future wind speed probability distribution based on the preset prediction step number by using the wind speed probability distribution prediction model.

7. The monitoring method according to claim 5, characterized in that: Step S62, obtaining the future illumination intensity distribution of the preset area based on the preset prediction step number, includes: Step S621, obtaining a plurality of light intensity distributions of the preset area based on a plurality of preset time periods; Step S622, integrating all random point illumination intensity data in an illumination intensity distribution into an illumination intensity data set; Step S623, performing standard normalization processing on all illumination intensity data sets, and obtaining a normalized data set based on one illumination intensity data set; Step S624, dividing a normalized data set into a training set and a validation set according to a preset ratio; Step S625, defining a neural network model in which the input layer, the hidden layer, and the output layer are sequentially connected; Step S626, input all training sets into the input layer in sequence, and perform several trainings through the neural network model; Step S627, obtaining a root mean square error of the training results corresponding to the current validation set and the current training set based on each training; Step S628, obtaining the minimum error value among all root mean square errors, and the training result corresponding to the minimum error value as a light intensity distribution prediction model; Step S629: predicting the future illumination intensity distribution based on the preset number of prediction steps by using the illumination intensity distribution prediction model.

8. A monitoring device for a flexible photovoltaic array, the monitoring device being applied to the monitoring method according to any one of claims 1 to 7, characterized in that: The monitoring device comprises: A support physical parameter acquisition module, used to acquire a plurality of upper chord tensile stresses and a plurality of lower chord tensile stresses of the flexible photovoltaic support, as well as a span height difference between two steel beams of the flexible photovoltaic support and the number of photovoltaic panels based on a plurality of preset time periods; A support environmental parameter acquisition module is used to obtain the wind speed probability distribution and light intensity distribution in the area where the flexible photovoltaic support is located; A dependent variable definition module, used to define the tensile stress of the upper chord of the current flexible photovoltaic support as a first dependent variable, and define the tensile stress of the lower chord of the current flexible photovoltaic support as a second dependent variable; The independent variable definition module is used to define the wind speed probability distribution, light intensity distribution, span height difference, and number of photovoltaic panels in the area where the current flexible photovoltaic bracket is located as a set of independent variables; A linear regression relationship analysis module is used to analyze the first linear regression relationship between the first dependent variable of the current flexible photovoltaic support and all independent variables, and the second linear regression relationship between the second dependent variable of the current flexible photovoltaic support and all independent variables through multiple linear regression; An upper and lower chord tensile stress prediction module, used to predict the future tensile stress of the upper chord of the flexible photovoltaic support through the first linear regression relationship based on a preset prediction step number, and predict the future tensile stress of the lower chord of the flexible photovoltaic support through the second linear regression relationship; A maximum allowable tensile stress acquisition module, used to acquire the maximum allowable tensile stress of the upper chord of the upper chord and the maximum allowable tensile stress of the lower chord of the lower chord; A judgment condition definition module is used to define a first judgment condition for determining whether the future tensile stress of an upper chord is greater than or equal to the maximum allowable tensile stress of the upper chord, and a second judgment condition for determining whether the future tensile stress of a lower chord is greater than or equal to the maximum allowable tensile stress of the lower chord; The judgment condition determination module is used to determine whether the flexible photovoltaic bracket has a risk of excessive stress if at least one of the first judgment condition and the second judgment condition is met.

9. An electronic device, characterized in that: It comprises a processor and a memory coupled to the processor, wherein the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, the monitoring method as described in any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores program instructions, and when the program instructions are executed by the processor, the monitoring method according to any one of claims 1 to 7 can be implemented.

Images