Heat dissipation fan blade life assessment method based on big data analysis

Through big data analysis and machine learning algorithms, combined with the speed, temperature and vibration frequency data of offshore fan blades, the accuracy of fan blade life evaluation in offshore environment is solved, and more reliable life prediction is achieved.

CN118643748BActive Publication Date: 2024-11-19SUZHOU ZHONGZHI XINHUAN COOLING EQUIP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411103152.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-13
Publication Date
2024-11-19
Estimated Expiration
2044-08-13

AI Technical Summary

Technical Problem

The blade life evaluation of offshore heat dissipation fan blade life. Weight changes and aging wear caused by moisture condensation in high humidity environments affect the rotation speed, resulting in low accuracy of traditional methods and it is difficult to accurately predict the life of the blade.

Method used

Using a method based on big data analysis, the possibility of abnormal data and the reliability of temperature changes is calculated by obtaining the speed, temperature and vibration frequency data of the fan blades, and combining with machine learning algorithms, the impact of water vapor condensation is corrected and the blade life is accurately predicted.

Benefits of technology

It improves the accuracy of fan blade life prediction, reduces the impact of water vapor condensation on data, and makes the prediction results more reliable.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118643748B_ABST
    Figure CN118643748B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of data processing technology, and in particular to a method for evaluating the life of a heat dissipation fan blade based on big data analysis, comprising: obtaining a fan data sequence of a fan blade to be detected and a temperature data sequence of fan blades around the fan blade to be detected; obtaining the initial possibility that each fan data is abnormal data and the instantaneous temperature change rate of each fan data, and then obtaining the second possibility that each fan data is abnormal data; obtaining the temperature change credibility of each fan data based on the temperature data in the temperature data sequence of fan blades around the fan blade to be detected; thereby obtaining the final possibility that each fan data is abnormal data, and obtaining the life of the fan blade to be detected. The present invention aims to solve the problem of treating the data of normal fan blades as the data of fan blade aging when obtaining the data of fan blade aging based on speed data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method for evaluating the life of a heat dissipation fan blade based on big data analysis. Background Art

[0002] A cooling fan is a device used for heat dissipation, usually used in electronic or mechanical equipment. Its main function is to reduce the temperature inside the equipment through air flow to prevent the equipment from overheating. The life assessment of cooling fan blades is a key link in ensuring the reliability of the fan. In recent years, with the development of big data analysis technology, this method has changed from traditional experience-based evaluation to data-based quantitative analysis. By collecting and analyzing the operating data of the fan, a more accurate prediction of the service life of the blades can be made.

[0003] Due to the harsh working environment of offshore cooling fans, high temperature, high humidity, high salt fog, and difficulty in maintenance, the life assessment requirements for fan blades are relatively high. In the process of using the fan's SCADA system to collect data, it is often encountered that due to the high humidity of the air at sea, the moisture in the air condenses and adsorbs on the fan blades, causing the weight of the fan blades to increase, thereby affecting the normal speed of the fan and causing the fan speed to change. The normal aging and wear of the fan blades will also slow down the fan speed, resulting in a low accuracy rate of the normal aging and wear data of the fan blades obtained based on the fan blade speed. Summary of the invention

[0004] The present invention provides a heat dissipation fan blade life assessment method based on big data analysis to solve the existing problems.

[0005] The heat dissipation fan blade life assessment method based on big data analysis of the present invention adopts the following technical solutions:

[0006] The present invention proposes a method for evaluating the life of a heat dissipation fan blade based on big data analysis, the method comprising the following steps:

[0007] Acquire a fan data sequence of a fan blade to be detected, and acquire a temperature data sequence of fan blades around the fan blade to be detected; the fan data in the fan data sequence includes speed data, temperature data and vibration frequency data, and each fan data in the fan data sequence and each temperature data in the temperature data sequence corresponds to a collection time;

[0008] According to the change of the vibration frequency data and the speed data of each fan data in the fan data sequence, the initial possibility of each fan data being abnormal data is obtained;

[0009] According to the speed data in each fan data, the corresponding data of each fan data is obtained; according to the temperature data in the adjacent fan data, the instantaneous temperature change rate of each fan data is obtained; according to the difference between the instantaneous temperature change rate of each fan data and the corresponding data, and the initial possibility that each fan data is abnormal data, the second possibility that each fan data is abnormal data is obtained;

[0010] According to the adjacent temperature data in the temperature data sequence of the fan blades around the fan blade to be detected, the instantaneous temperature change rate of each temperature data of each fan blade is obtained; according to the instantaneous temperature change rate of each temperature data of each fan blade and the instantaneous temperature change rate of each fan data, the temperature change credibility of each fan data is obtained; combined with the second possibility that each fan data is abnormal data, the final possibility that each fan data is abnormal data is obtained, and then the aging time is obtained, and finally the life of the fan blade to be detected is obtained.

[0011] Furthermore, the method of obtaining the fan data sequence of the fan blade to be detected includes:

[0012] Collect the fan blades to be tested The rotation speed data, temperature data and vibration frequency data of the fan blade to be detected within a year; the rotation speed data, temperature data and vibration frequency data of the fan blade to be detected obtained at any collection time are used as elements of the fan data of the fan blade to be detected at the collection time, and the fan data of the fan blade to be detected at the collection time are obtained, and then the fan data sequence of the fan blade to be detected is obtained;

[0013] in Indicates the preset collection duration, the collection interval is Hour.

[0014] Furthermore, the method of obtaining the temperature data sequence of the fan blades around the fan blade to be detected includes:

[0015] Get the information around the fan blade to be detected The fan blades Temperature data of the year are used to obtain a temperature data sequence of each fan blade around the fan blade to be tested;

[0016] in Indicates the preset collection duration, the collection interval is Hour, Indicates the number of fan blades surrounding the preset fan blade to be detected.

[0017] Furthermore, the initial possibility of each fan data being abnormal data is obtained according to the change of the vibration frequency data and the change of the speed data of each fan data in the fan data sequence, including the specific method of:

[0018]

[0019] In the formula, Indicates The initial probability that the wind turbine data is abnormal data, Indicates The vibration frequency data in the fan data, Indicates The vibration frequency data in the fan data, Indicates The speed data in the fan data, Indicates The speed data in the fan data, Indicates the number of fan data contained in the fan data sequence. represents the absolute value function, To prevent hyperparameters with denominators equal to zero, Represents the sigmoid function.

[0020] Furthermore, the method of obtaining corresponding data of each fan data according to the speed data in each fan data includes the following specific methods:

[0021] The speed data and The fan data with the same speed data in the fan data is recorded as The corresponding data of each fan data.

[0022] Furthermore, the instantaneous temperature change rate of each fan data is obtained according to the temperature data in the adjacent fan data, including the specific method of:

[0023] The first The temperature data in the fan data is subtracted from the The absolute value of the difference in temperature data within the fan data is recorded as The instantaneous temperature change rate of each fan data.

[0024] Further, the second possibility that each fan data is abnormal data is obtained according to the difference between the instantaneous temperature change rate of each fan data and the corresponding data, and the initial possibility that each fan data is abnormal data, including the specific method of:

[0025]

[0026] In the formula, Indicates The second possibility is that the wind turbine data is abnormal data. Indicates The initial probability that the wind turbine data is abnormal data, Indicates The instantaneous temperature change rate of each fan data, Indicates The mean of the instantaneous temperature change rate of all corresponding data of the fan data, is an exponential function with a natural constant as its base.

[0027] Furthermore, the instantaneous temperature change rate of each temperature data of each fan blade is obtained according to the adjacent temperature data in the temperature data sequence of the fan blades around the fan blade to be detected, including the specific method of:

[0028] Place the first The temperature data series of the fan blades minus the temperature data The absolute value of the difference between the temperature data is recorded as The fan blade The instantaneous temperature change rate of a temperature data.

[0029] Further, the temperature change credibility of each fan data is obtained according to the instantaneous temperature change rate of each temperature data of each fan blade and the instantaneous temperature change rate of each fan data, including the specific method of:

[0030]

[0031] In the formula, Indicates The reliability of the temperature change of each fan data, Indicates The instantaneous temperature change rate of each fan data, Indicates The fan blade The instantaneous temperature change rate of the temperature data, Indicates the number of fan blades around the fan blade to be detected, is an exponential function with a natural constant as its base.

[0032] Furthermore, the second possibility that each wind turbine data is abnormal data is combined to obtain the final possibility that each wind turbine data is abnormal data, and then obtain the aging time, including the specific method of:

[0033]

[0034] In the formula, Indicates The final possibility that the wind turbine data is abnormal data, Indicates The second possibility is that the wind turbine data is abnormal data. Indicates The reliability of the temperature change of each fan data, Represents the sigmoid function;

[0035] Preset likelihood threshold , the final probability is greater than the probability threshold The collection time corresponding to the fan data is recorded as the aging time.

[0036] The beneficial effects of the technical solution of the present invention are: in the process of predicting the life of a fan blade, based on the characteristics that when water condenses on the fan blade, the fan speed and the fan vibration frequency decrease simultaneously; and when the fan blade is aged, the fan speed decreases and the fan vibration frequency decreases, according to the changes in the vibration frequency data and the speed data of each fan data in the fan data sequence, the initial possibility of each fan data being abnormal data is obtained, so that the fan data corresponding to the aging of the blade and the fan data corresponding to the condensation of water vapor on the blade have a more obvious difference; according to the characteristic that the specific heat capacity of water is large, according to the temperature data in each fan data, the initial possibility of each fan data being abnormal data is corrected to obtain the second possibility of each fan data being abnormal data; the difference between the second possibility of the fan data corresponding to the aging of the blade and the second possibility of the fan data corresponding to the condensation of water vapor on the blade is more obvious; according to the temperature data of the fan blades around each fan blade to be detected, the influence of temperature on the second possibility of the fan data is removed, so that the acquired aging time is more accurate, and the predicted life of the fan blade is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 This is a flow chart of the steps of the heat dissipation fan blade life assessment method based on big data analysis of the present invention. DETAILED DESCRIPTION

[0039] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation method, structure, characteristics and effects of the heat dissipation fan blade life assessment method based on big data analysis proposed by the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0040] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0041] The specific scheme of the heat dissipation fan blade life assessment method based on big data analysis provided by the present invention is described in detail below with reference to the accompanying drawings.

[0042] See also Figure 1 , which shows a flowchart of a method for evaluating the life of a heat dissipation fan blade based on big data analysis provided by an embodiment of the present invention, the method comprising the following steps:

[0043] Step S001: Acquire a fan data sequence of a fan blade to be detected, and acquire a temperature data sequence of fan blades around the fan blade to be detected.

[0044] This embodiment estimates the life of the heat dissipation fan blades, thereby obtaining the fan blade data.

[0045] Specifically, the SCADA system is installed on the wind turbine blades to be tested to collect the information of the wind turbine blades to be tested. The speed data, temperature data, and vibration frequency data of the fan blade to be tested obtained at any collection time are used as elements in the fan data of the fan blade to be tested at the collection time, and the corresponding fan data of the fan blade to be tested at the collection time are obtained, and then the fan data sequence of the fan blade to be tested is obtained. Among them, the power of the fan blade will not change during the collection time. Among them, the first The fan data corresponding to the acquisition time is the fan data sequence of the fan blade to be detected. According to the surrounding area of ​​the fan blade to be tested The SCADA system installed on each wind turbine blade collects information about the wind turbine blade to be inspected. The fan blades The temperature data of the year are used to obtain the temperature data sequence of each fan blade around the fan blade to be detected.

[0046] Furthermore, each fan data in the fan data sequence of the fan blade to be detected corresponds to a collection time; and the temperature data in the temperature data sequence of the fan blades around the fan blade to be detected corresponds to a collection time. The fan data is compared with the temperature data of the fan blades around the fan blade to be detected. The collection time corresponding to each temperature data is the same. Among them, the collection interval of the SCADA system is The collection time preset in this embodiment is , collection interval , which is described as an example, and other implementations may be set to other values. The number of fan blades around the fan blade to be detected is preset in this embodiment. , which is described by taking this as an example, and other implementations may be set to other values. The full name of the SCADA system is a supervisory control and data acquisition system, which is a well-known technology and will not be described in detail in this embodiment.

[0047] Step S002: According to the change of the vibration frequency data and the speed data of each fan data in the fan data sequence, the initial possibility of each fan data being abnormal data is obtained.

[0048] It should be noted that when the fan blades are adsorbed by water vapor, the weight of the fan blades increases, so that the speed of the fan blades slows down when the power is constant, and the vibration frequency of the fan blades decreases; that is, when the fan blades are adsorbed by water vapor, the speed of the fan blades slows down, and the vibration frequency of the fan blades decreases. When the fan blades are aged, metal passivation occurs on the fan blades or rust or stains appear on the surface of the fan blades, causing the surface of the fan blades to become uneven, causing the resistance of the fan blades during rotation to increase, so that the speed of the fan blades slows down when the power is constant, and the vibration frequency increases; that is, when the fan blades are aged, the speed of the fan blades slows down, and the vibration frequency increases. Therefore, according to the changes in the vibration frequency data and the speed data in each fan data in the fan data sequence, the initial possibility of each fan data being abnormal data is obtained.

[0049] Specifically, get the The calculation formula for the initial probability that the data of a wind turbine is abnormal data is as follows:

[0050]

[0051] In the formula, Indicates The initial probability that the wind turbine data is abnormal data, Indicates The vibration frequency data in the fan data, Indicates The vibration frequency data in the fan data, Indicates The speed data in the fan data, Indicates The speed data in the fan data, Indicates the number of fan data contained in the fan data sequence. represents the absolute value function, To prevent the hyperparameter from having a denominator of 0, this embodiment sets the hyperparameter , can be set to other values ​​in other implementation modes; represents a sigmoid function, which is used for normalization processing in this embodiment.

[0052] It should be noted that The larger the value, the The more the data of the fan is in line with the characteristics that the fan speed decreases but the vibration frequency increases when the fan blades are worn, the further explanation is that the The greater the possibility that the data of a wind turbine is abnormal data.

[0053] At this point, the initial possibility that each wind turbine data is abnormal data is obtained.

[0054] Step S003: Obtain corresponding data of each fan data based on the rotational speed data in each fan data; obtain the instantaneous temperature change rate of each fan data based on the temperature data in the adjacent fan data; obtain the second possibility that each fan data is abnormal data based on the difference between the instantaneous temperature change rate of each fan data and the corresponding data, and the initial possibility that each fan data is abnormal data.

[0055] It should be noted that when the fan blades are adsorbed by water vapor, the specific heat capacity of water is greater than that of the fan blades, so when the fan blades rotate at the same speed, the temperature change of the fan blades adsorbed by water vapor is smaller than that of the aged fan blades. Therefore, according to the temperature data in each fan data, the initial possibility that the fan data collected at each collection time is abnormal data is corrected to obtain the second possibility that each fan data is abnormal data.

[0056] Specifically, the speed data is compared with the The fan data with the same speed data in the fan data is recorded as The corresponding data of the fan data. The temperature data in the fan data is subtracted from the The absolute value of the difference in temperature data within the fan data is recorded as Furthermore, the first fan data has no instantaneous temperature change rate, that is, the second possibility that the first fan data is abnormal data is not calculated.

[0057] Furthermore, according to the instantaneous temperature change rate of each fan data and the initial possibility of being abnormal data, the specific calculation formula for obtaining the second possibility of each fan data being abnormal data is as follows:

[0058]

[0059] In the formula, Indicates The second possibility is that the wind turbine data is abnormal data. Indicates The initial probability that the wind turbine data is abnormal data, Indicates The instantaneous temperature change rate of each fan data, Indicates The mean of the instantaneous temperature change rate of all corresponding data of the fan data, is an exponential function with a natural constant as the base, used to prevent Is a negative number.

[0060] It should be noted that The larger the value, the The faster the fan temperature rises at the first collection moment, the The smaller the specific heat capacity of the fan at the first collection moment, The greater the possibility that the data of a wind turbine is abnormal data.

[0061] Step S004: Obtain the instantaneous temperature change rate of each temperature data of each fan blade based on the adjacent temperature data in the temperature data sequence of the fan blades around the fan blade to be detected; obtain the temperature change credibility of each fan data based on the instantaneous temperature change rate of each temperature data of each fan blade and the instantaneous temperature change rate of each fan data; obtain the final possibility that each fan data is abnormal data by combining the second possibility that each fan data is abnormal data, and then obtain the aging time, and finally obtain the life of the fan blade to be detected.

[0062] It should be noted that the instantaneous temperature change rate of a fan data is not only related to the water vapor on the fan blades at the collection time corresponding to the fan data, but also to the outdoor temperature corresponding to the collection time. Since the outdoor temperature at each collection time may be different from the outdoor temperature at other collection times, the second possibility that each fan data is abnormal data is affected by the outdoor temperature. Therefore, the influence of the outdoor temperature at each collection time on the second possibility that each fan data is abnormal data is removed.

[0063] It should be further explained that since the distance between the fan blades to be detected and the surrounding fan blades is relatively close, the second possibility that the outdoor temperature at each collection time affects the abnormal data of each fan is eliminated according to the temperature changes of the fan blades around the fan blades to be detected.

[0064] Specifically, the first The temperature data series of the fan blades minus the temperature data The absolute value of the difference between the temperature data is recorded as The fan blade The instantaneous temperature change rate of each temperature data is not calculated.

[0065] Further, get the The specific calculation formula for the temperature change credibility of each fan data is as follows:

[0066]

[0067] In the formula, Indicates The reliability of the temperature change of each fan data, Indicates The instantaneous temperature change rate of each fan data, Indicates The fan blade The instantaneous temperature change rate of the temperature data, Indicates the number of fan blades around the fan blade to be detected, is an exponential function with a natural constant as the base. This embodiment is used to prevent .

[0068] It should be noted that The larger the value, the The greater the difference between the temperature change of the fan blade to be detected and the temperature change of the surrounding fan blades at the first acquisition time, the greater the difference between the temperature change of the fan blade to be detected and the temperature change of the surrounding fan blades. The less credible the instantaneous temperature change rate of the fan blade to be detected is at each acquisition time, that is, The lower the credibility of the temperature change of the fan data.

[0069] Furthermore, according to The second possibility that the wind turbine data is abnormal data is The reliability of the temperature change of the fan data is obtained. The specific calculation formula for the final probability that the wind turbine data is abnormal data is as follows:

[0070]

[0071] In the formula, Indicates The final possibility that the wind turbine data is abnormal data, Indicates The second possibility is that the wind turbine data is abnormal data. Indicates The reliability of the temperature change of each fan data, represents a sigmoid function, which is used for normalization processing in this embodiment.

[0072] Furthermore, a preset possibility threshold , the possibility threshold preset in this embodiment . The final probability is greater than the probability threshold The collection time corresponding to the fan data is recorded as the aging time. Function, according to the final possibility that the fan data corresponding to each aging time is abnormal data, obtains the influence weight of the data collected at each aging time. The input of the function is the final possibility that the fan data corresponding to each aging time is abnormal data.

[0073] Furthermore, the machine learning algorithm in the big data analysis model is used to take the data of the standby fan blades collected at all aging times as a training set, and the aging degree of the fan blades to be tested is obtained based on the influence weight of the data collected at each aging time, so as to obtain the life of the fan blades to be tested; this process relies on the machine learning algorithm as a prior art and will not be repeated in this embodiment.

[0074] At this point, this embodiment is completed.

[0075] To sum up, in the embodiments of the present invention, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A heat dissipation fan blade life assessment method based on big data analysis, characterized in that: The method comprises the following steps: Acquire a fan data sequence of a fan blade to be detected, and acquire a temperature data sequence of fan blades around the fan blade to be detected; the fan data in the fan data sequence includes speed data, temperature data and vibration frequency data, and each fan data in the fan data sequence and each temperature data in the temperature data sequence corresponds to a collection time; According to the change of the vibration frequency data and the speed data of each fan data in the fan data sequence, the initial possibility of each fan data being abnormal data is obtained; According to the speed data in each fan data, the corresponding data of each fan data is obtained; according to the temperature data in the adjacent fan data, the instantaneous temperature change rate of each fan data is obtained; according to the difference between the instantaneous temperature change rate of each fan data and the corresponding data, and the initial possibility that each fan data is abnormal data, the second possibility that each fan data is abnormal data is obtained; According to the adjacent temperature data in the temperature data sequence of the fan blades around the fan blade to be detected, the instantaneous temperature change rate of each temperature data of each fan blade is obtained; according to the instantaneous temperature change rate of each temperature data of each fan blade and the instantaneous temperature change rate of each fan data, the temperature change credibility of each fan data is obtained; combined with the second possibility that each fan data is abnormal data, the final possibility that each fan data is abnormal data is obtained, and then the aging time is obtained, and finally the life of the fan blade to be detected is obtained; The method of obtaining the initial possibility that each fan data is abnormal data according to the change of the vibration frequency data and the change of the speed data of each fan data in the fan data sequence includes the following specific methods: In the formula, Indicates The initial probability that the wind turbine data is abnormal data, Indicates The vibration frequency data in the fan data, Indicates The vibration frequency data in the fan data, Indicates The speed data in the fan data, Indicates The speed data in the fan data, Indicates the number of fan data contained in the fan data sequence. represents the absolute value function, To prevent hyperparameters with denominators equal to zero, Represents the sigmoid function; The specific method of obtaining corresponding data of each fan data according to the speed data in each fan data is as follows: The speed data and The fan data with the same speed data in the fan data is recorded as The corresponding data of each fan data; The specific method of obtaining the instantaneous temperature change rate of each fan data according to the temperature data in the adjacent fan data is as follows: The first The temperature data in the fan data is subtracted from the The absolute value of the difference in temperature data within the fan data is recorded as The instantaneous temperature change rate of each fan data; The second possibility that each fan data is abnormal data is obtained based on the difference between the instantaneous temperature change rate of each fan data and the corresponding data, and the initial possibility that each fan data is abnormal data, including the specific method of: In the formula, Indicates The second possibility is that the wind turbine data is abnormal data. Indicates The initial probability that the wind turbine data is abnormal data, Indicates The instantaneous temperature change rate of each fan data, Indicates The mean of the instantaneous temperature change rate of all corresponding data of the fan data, is an exponential function with a natural constant as base; The method of obtaining the instantaneous temperature change rate of each temperature data of each fan blade according to the adjacent temperature data in the temperature data sequence of the fan blades around the fan blade to be detected includes the following specific methods: Place the first The temperature data series of the fan blades minus the temperature data The absolute value of the difference between the temperature data is recorded as The fan blade The instantaneous temperature change rate of each temperature data; The specific method of obtaining the temperature change credibility of each fan data according to the instantaneous temperature change rate of each temperature data of each fan blade and the instantaneous temperature change rate of each fan data is as follows: In the formula, Indicates The reliability of the temperature variation of each fan data, Indicates The instantaneous temperature change rate of each fan data, Indicates The fan blade The instantaneous temperature change rate of the temperature data, Indicates the number of fan blades around the fan blade to be detected, is an exponential function with a natural constant as base; The method of combining the second possibility that each fan data is abnormal data to obtain the final possibility that each fan data is abnormal data and then obtaining the aging time includes the following specific methods: In the formula, Indicates The final possibility that the wind turbine data is abnormal data, Indicates The second possibility is that the wind turbine data is abnormal data. Indicates The reliability of the temperature variation of each fan data, Represents the sigmoid function; Preset likelihood threshold , the final probability is greater than the probability threshold The collection time corresponding to the fan data is recorded as the aging time.

2. The heat dissipation fan blade life assessment method based on big data analysis according to claim 1 is characterized in that: The specific method of obtaining the fan data sequence of the fan blade to be detected includes: Collect the fan blades to be tested The rotation speed data, temperature data and vibration frequency data of the fan blade to be detected within a year; the rotation speed data, temperature data and vibration frequency data of the fan blade to be detected obtained at any collection time are used as elements of the fan data of the fan blade to be detected at the collection time, and the fan data of the fan blade to be detected at the collection time are obtained, and then the fan data sequence of the fan blade to be detected is obtained; in Indicates the preset collection duration, the collection interval is Hour.

3. The heat dissipation fan blade life assessment method based on big data analysis according to claim 1 is characterized in that: The specific method of obtaining the temperature data sequence of the fan blades around the fan blade to be detected includes: Get the information around the fan blade to be detected The fan blades Temperature data of the year are used to obtain a temperature data sequence of each fan blade around the fan blade to be tested; in Indicates the preset collection duration, the collection interval is Hour, Indicates the number of fan blades surrounding the preset fan blade to be detected.