Life prediction method for single-axis linkage sun-tracking steel support equipment

By collecting and analyzing the timing characteristic data of the photovoltaic stent and establishing a life prediction model, the accuracy of the life judgment of the photovoltaic stent in the existing technology is solved, prediction without manual interference is achieved, and maintenance is carried out in advance, reducing the risk of equipment damage.

CN118656566BActive Publication Date: 2024-12-06JIANGSU ZHENJIANG NEW ENERGY EQUIP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411131779.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-12-06
Estimated Expiration
2044-08-19

AI Technical Summary

Technical Problem

The existing technology is difficult to timely and accurately judge the life of the photovoltaic bracket, resulting in the failure of the equipment to work normally, and there are problems of misjudgment and misjudgment in manual inspection.

Method used

By collecting the timing feature data of the scaffold, selecting the correlation features using logistic regression algorithm, calculating the damage intensity index and constructing stress frequency response functions, establishing a life load function, and finally building a life prediction model to predict the predicted life of the scaffold.

Benefits of technology

It realizes a life expectancy without manual interference, avoids misjudgment, conducts maintenance in advance, and reduces industrial losses caused by equipment damage.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118656566B_ABST
    Figure CN118656566B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of bracket life prediction, and discloses a life prediction method for a single-axis linkage sun-chasing steel bracket equipment, collects the time series characteristic data of the bracket, and uses a logistic regression algorithm to select the associated features that affect the bracket life; calculates the damage intensity index through the bracket structure dynamic coefficient, and constructs a stress frequency response function based on the damage intensity index, thereby constructing a life load function of the associated features; constructs a life prediction model based on the life load function, and brings the existing life of the bracket into the life prediction model to obtain the predicted life of the bracket. The present invention timely and pre-judges the bracket life situation to avoid the impact of bracket damage on the normal operation of photovoltaic equipment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of support life prediction, and in particular to a life prediction method for a single-axis linkage sun-chasing steel support equipment. Background Art

[0002] For example, the utility model with announcement number CN207232769U discloses a push rod type multi-row linkage flat single-axis photovoltaic bracket installation structure, which includes a push rod, a flat single-axis photovoltaic bracket, a driving rocker arm, etc., involving several steel brackets, and the photovoltaic bracket automatically adjusts the angle of the photovoltaic bracket according to the position of the sun by rotating. These brackets are usually installed in areas with sufficient light and high altitudes, but long-term load-bearing and external environmental factors may cause deformation, corrosion and other damage to the brackets, making the photovoltaic equipment unable to work normally or unable to work with maximum efficiency. Usually, manual field inspections are relied on, but manual observation through the naked eye to see if there is any damage may result in misjudgment and omission, resulting in the failure to obtain the bracket in time. Therefore, there is an urgent need for a method to timely and pre-judge the life of the bracket. Summary of the invention

[0003] The purpose of the present invention is to timely and pre-judge the life of the bracket, avoid the impact of bracket damage on the normal operation of the photovoltaic equipment, and provide a life prediction method for a single-axis linkage sun-chasing steel bracket equipment.

[0004] In order to achieve the above-mentioned object of the invention, the embodiment of the present invention provides the following technical solutions:

[0005] The life prediction method of the single-axis linkage sun-chasing steel support equipment includes the following steps:

[0006] Step 1, collect the temporal characteristic data of the stent, and use the logistic regression algorithm to select the associated features that affect the stent life;

[0007] Step 2, calculating the damage intensity index through the dynamic coefficient of the bracket structure, constructing the stress frequency response function based on the damage intensity index, and thus constructing the life load function of the associated characteristics;

[0008] Step 3: construct a life prediction model based on the life load function, bring the existing life of the bracket into the life prediction model, and obtain the predicted life of the bracket.

[0009] In step 1, the collected time series characteristic data of the bracket include: shear friction, temperature, humidity, rainfall, snowfall, wind force, light intensity, bracket gravity, shaft rotation speed, shaft rotation angle, shaft rotation frequency, bracket pH, and bracket salt content.

[0010] In step 2, the dynamic coefficient of the support structure is:

[0011]

[0012] Among them, Kr represents the dynamic coefficient of the support structure; Cr represents the stress concentration coefficient; b represents the support material constant; and r represents the support radius.

[0013] In step 2, the damage intensity index calculated by the dynamic coefficient of the support structure is:

[0014]

[0015] Wherein, Zr represents the damage intensity index.

[0016] In step 2, the stress frequency response function constructed based on the damage intensity index is:

[0017]

[0018] Where L0 represents the stress frequency response function; Represents the stress amplitude.

[0019] In step 2, the life load function of the associated feature is constructed as follows:

[0020]

[0021] Where F represents the life load function; G represents the stiffness matrix; R represents the elastic modulus; p i represents the probability distribution of the i-th associated feature; E i represents the power response matrix of the i-th associated feature, i=1,2,...,n, and n represents the number of associated features.

[0022] The power response matrix E i Calculated using the following formula:

[0023]

[0024] in, represents the output power of the photovoltaic device in the kth prediction period; Represents the associated feature x in the kth prediction period i The factor affecting the photovoltaic output power, k∈{1,2,...,s f},have:

[0025]

[0026] Among them, y(k) represents the meteorological characteristic value; x i (k) represents the associated feature x i The responsiveness to the meteorological characteristic value indicates the correlation characteristic x i The degree of weather influence; Represents the resolution coefficient.

[0027] In step 3, the life prediction model constructed based on the life load function is:

[0028]

[0029] in, represents the predicted life of the stent; represents the damage intensity coefficient; N represents the current life of the bracket; represents the extended life of the bracket; a represents the life extension coefficient;

[0030] The existing life N of the stent is brought into the life prediction model to obtain the predicted life of the stent.

[0031] Compared with the prior art, the present invention has the following beneficial effects: when predicting the life of a bracket, the current life N of the bracket is brought into the life prediction model to obtain the predicted life of the bracket. The predicted life is obtained through a large amount of historical data and algorithms, and is not interfered by human judgment, and can avoid the misjudgment caused by human observation through naked eyes. However, the predicted life is only used as manual auxiliary data, and does not represent the actual service life of the bracket. It is used to help humans to maintain the equipment in time before the predicted life is approaching, so as to avoid industrial losses caused by damage to the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present invention.

[0035] It should be noted that similar numbers and letters represent similar items in the following figures, so once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance, or implying any such actual relationship or order between these entities or operations. In addition, the terms "connected", "connected", etc. can be directly connected between elements, or indirectly connected via other elements.

[0036] The present invention is achieved through the following technical solutions: Figure 1 As shown, the life prediction method of the single-axis linkage sun-chasing steel support equipment includes the following steps:

[0037] Step 1: Collect the temporal characteristic data of the stent and use the logistic regression algorithm to select the associated features that affect the stent life.

[0038] Collect the time series characteristic data of the bracket at the same time in history. For example, the time series characteristic data collected at time t may include: shear friction, temperature, humidity, rainfall, snowfall, wind, light intensity, bracket gravity, shaft rotation speed, shaft rotation angle, shaft rotation frequency, bracket pH, bracket salt content, etc. This scheme only gives examples of time series characteristic data and is not limited to this. The time series characteristic data to be collected can be adjusted according to actual conditions. However, it is easy to understand that the collected time series characteristic data is related to the bracket and factors that may affect the life of the bracket.

[0039] The linear relationship between the time series feature data and the stent injury results was established using the logistic regression algorithm. The input time series feature data was mapped to the range of [0,1] through the sigmoid function to obtain the probability distribution p of each time series feature data. i , p i represents the probability distribution of the i-th time series feature data. By setting the strong correlation threshold, the time series feature data with a probability distribution greater than the strong correlation threshold is selected as the correlation feature. Assume that after the logistic regression algorithm and screening, the final set of correlation features is X(t)={x1,x2,...,x n}, where x i represents the i-th associated feature, p i For x i The probability distribution of , i=1,2,...,n.

[0040] In different seasons or climate conditions, such as temperature, humidity, rainfall, wind speed, light intensity, etc., there are no strict rules of change. At the same time, the shaft rotation speed, shaft rotation angle, and shaft rotation frequency caused by light intensity will also change. Therefore, when collecting historical time series feature data, it is necessary to collect time series feature data at multiple moments. Only with a large amount of data support can more accurate correlation features be obtained.

[0041] Step 2: Calculate the damage intensity index through the dynamic coefficient of the support structure, construct the stress frequency response function based on the damage intensity index, and thus construct the life load function of the associated characteristics.

[0042] The dynamic coefficient of the support structure is an important parameter related to structural dynamics. It is usually used to describe the response characteristics of the support structure under dynamic loads. This scheme takes into account the material and structure of the support and uses the following formula to express the dynamic coefficient of the support structure:

[0043]

[0044] Among them, Kr represents the dynamic coefficient of the bracket structure; Cr represents the stress concentration coefficient; b represents the bracket material constant; r represents the bracket radius. If the bracket is circular, r is directly the radius of the circular aperture; if the bracket is square, r is half the length of the side of the square aperture.

[0045] The damage intensity index is calculated by the dynamic coefficient of the support structure. The damage intensity index (or damage degree, damage index) is a quantitative indicator to measure the degree of damage to an object or structure under force or external factors. The damage intensity index is expressed by the following formula:

[0046]

[0047] Wherein, Zr represents the damage intensity index.

[0048] The change of stress frequency response function can reflect the damage of the structure. By comparing the stress frequency response function of the structure in different states, real-time monitoring and evaluation of the health status of the structure can be achieved. This scheme constructs the stress frequency response function based on the damage intensity index and uses the following formula to express the stress frequency response function:

[0049]

[0050] Where L0 represents the stress frequency response function; Represents the stress amplitude.

[0051] Construct a life load function for the associated feature:

[0052]

[0053] Where F represents the life load function; G represents the stiffness matrix; R represents the elastic modulus; p i represents the probability distribution of the i-th associated feature; E i represents the power response matrix of the i-th associated feature, i=1,2,...,n, and n represents the number of associated features.

[0054] The power response matrix E i Reflects the i-th associated feature x i Impact on photovoltaic output power, power response matrix E i Calculated using the following formula:

[0055]

[0056] in, represents the output power of the photovoltaic device in the kth prediction period; Represents the associated feature x in the kth prediction period i The factor affecting the photovoltaic output power, k∈{1,2,...,s f},have:

[0057]

[0058] Among them, y(k) represents the meteorological characteristic value; x i (k) represents the associated feature x i The responsiveness to the meteorological characteristic value indicates the correlation characteristic x i The degree of weather influence; It represents the resolution coefficient and takes 0.5.

[0059] Step 3: construct a life prediction model based on the life load function, bring the existing life of the bracket into the life prediction model, and obtain the predicted life of the bracket.

[0060]

[0061] in, represents the predicted life of the stent; represents the damage intensity coefficient; N represents the current life of the bracket; represents the extended life of the bracket; a represents the life extension coefficient.

[0062] When predicting the life of the bracket, the current life N of the bracket is brought into the life prediction model to obtain the predicted life of the bracket. The predicted life is not interfered by human judgment and can avoid misjudgment caused by human observation through naked eyes. However, the predicted life is only used as manual auxiliary data and does not represent the actual service life of the bracket. It is used to help humans maintain the equipment in time before the predicted life is approaching to avoid industrial losses caused by equipment damage.

[0063] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. Life prediction method for single-axis linkage sun-chasing steel support equipment, Features: The following steps are involved: Step 1, collect the temporal characteristic data of the stent, and use the logistic regression algorithm to select the associated features that affect the stent life; Step 2, calculating the damage intensity index through the dynamic coefficient of the bracket structure, constructing the stress frequency response function based on the damage intensity index, and thus constructing the life load function of the associated characteristics; In step 2, the dynamic coefficient of the support structure is: Among them, Kr represents the dynamic coefficient of the bracket structure; Cr represents the stress concentration coefficient; b represents the bracket material constant; r represents the bracket radius; In step 2, the damage intensity index calculated by the dynamic coefficient of the support structure is: Where Zr represents the damage intensity index; In step 2, the stress frequency response function constructed based on the damage intensity index is: Among them, L 0 represents the stress frequency response function; represents the stress amplitude; In step 2, the life load function of the associated feature is constructed as follows: Where F represents the life load function; G represents the stiffness matrix; R represents the elastic modulus; p i represents the probability distribution of the i-th associated feature; E i represents the power response matrix of the i-th correlation feature, i=1,2,...,n, n represents the number of correlation features; Step 3: construct a life prediction model based on the life load function, bring the existing life of the bracket into the life prediction model, and obtain the predicted life of the bracket.

2. The life prediction method of the single-axis linkage sun-chasing steel support equipment according to claim 1, Features: In step 1, the collected time series characteristic data of the bracket include: shear friction, temperature, humidity, rainfall, snowfall, wind force, light intensity, bracket gravity, shaft rotation speed, shaft rotation angle, shaft rotation frequency, bracket pH, and bracket salt content.

3. According to the life prediction method of a single-axis linkage sun-chasing steel support equipment described in claim 1, Features: In step 3, the life prediction model constructed based on the life load function is: in, represents the predicted life of the stent; represents the damage intensity coefficient; N represents the current life of the bracket; represents the extended life of the bracket; a represents the life extension coefficient; The existing life N of the stent is brought into the life prediction model to obtain the predicted life of the stent.