New energy power station-oriented equipment residual life prediction method

Abstract

The invention relates to the technical field of life prediction, and discloses an equipment residual life prediction method for a new energy power station, and the method comprises the following steps: collecting first comprehensive information at a current moment, the first comprehensive information comprising all photovoltaic power generation equipment operation data, marine environment information, all inverter operation data, and electromagnetic field data; respectively calculating the corrected salt spray corrosion rate, the corrected dynamic stress and the corrected temperature rise based on the electromagnetic interference factor; generating second comprehensive information based on the first comprehensive information, the corrected salt spray corrosion rate, the corrected dynamic stress and the corrected temperature rise amount; generating plane data based on the second comprehensive information; and inputting the plane data into the life prediction model, and outputting the residual life of all photovoltaic power generation equipment. According to the method, the influence of electromagnetic interference on life prediction is considered, and the residual life of the photovoltaic power generation equipment is predicted more accurately in combination with the collected data.

Description

Technical Field

[0001] The present invention relates to the technical field of life prediction, and more specifically, to a method for predicting the remaining life of equipment in a new energy power station. Background Art

[0002] As the global demand for renewable energy continues to grow, the development of photovoltaic power generation systems, as an important component of clean energy, has also attracted increasing attention for its information-based operation and maintenance technology. As the vast ocean surface is relatively less blocked by clouds, it can receive more sufficient solar radiation, and the ocean area is vast, does not occupy valuable land resources such as arable land and forests, is far away from densely populated areas, and has less visual impact on residents' lives, for all these reasons, photovoltaic power generation equipment at this stage tends to be built at sea.

[0003] In recent years, as photovoltaic power stations have entered a period of high incidence of equipment failure and aging, in order to effectively avoid failures or even the risk of cascading failures, improve the power generation efficiency of power stations and reduce operation and maintenance costs, it is of great significance to study the remaining life prediction method of photovoltaic power generation systems.

[0004] Due to frequent shipping and communication activities in the marine environment, there may be high-intensity electromagnetic fields, especially interference from radar or communication equipment. This interference may affect the electronic components in the photovoltaic system, especially the inverter, causing their performance to deteriorate or accelerate aging.

[0005] Because it is located on the ocean, the protective layer of the metal frame, bracket and inverter casing of the photovoltaic equipment is gradually corroded, and tiny rust spots and pits appear on the metal surface, accelerating the aging of the equipment structure and threatening the mechanical stability and electrical insulation performance.

[0006] The key connection parts and supporting structures of the equipment are subjected to alternating stress, which causes the initiation and propagation of metal fatigue cracks, especially at welding points and bolted connections, increasing the risk of structural fracture and endangering the overall physical structural integrity of the equipment.

[0007] Electromagnetic interference may cause false triggering or wrong switching timing when the internal components of the inverter are subjected to electromagnetic interference. These erroneous switching actions may lead to increased switching losses, because the switching process cannot be completed under the expected current or voltage conditions, resulting in more energy being lost in the form of heat. The high temperature environment not only aggravates the thermal aging of the electronic components inside the equipment, causing the performance parameters of semiconductor devices to drift, the leakage of capacitors to increase, and the resistance value to change, but also affects the heat dissipation performance of the inverter, reduces the heat dissipation efficiency, and further increases the operating temperature of the equipment, forming a vicious cycle, which seriously affects the electrical performance and service life of the equipment. Summary of the invention

[0008] The present invention provides a method for predicting the remaining life of equipment in a new energy power station, which solves the technical problem of difficulty in life prediction due to electromagnetic interference in related technologies.

[0009] The present invention provides a method for predicting the remaining life of equipment in a new energy power station, comprising the following steps:

[0010] Step 100, collecting the first comprehensive information at the current moment, the first comprehensive information includes: all photovoltaic power generation equipment operation data, marine environment information, all inverter operation data, electromagnetic field data;

[0011] The data collection time is: collect data once at a fixed time interval, and the default time interval is 1 hour.

[0012] Step 200, respectively calculating a corrected salt spray corrosion rate, a corrected dynamic stress, and a corrected temperature rise based on electromagnetic interference factors;

[0013] Step 300, generating second comprehensive information based on the first comprehensive information and the corrected salt spray corrosion rate, the corrected dynamic stress and the corrected temperature rise;

[0014] Step 400, generating plane data based on the second comprehensive information, the plane data including facets for storing data, one facet indexing a serial data stream of a data object, the serial data stream of a data object including n data units ordered by time, the tth data unit representing the second comprehensive information collected at the tth moment of the data object;

[0015] Step 500, input the plane data into the life prediction model, the life prediction model includes a first encoder, a second encoder, and a first fully connected layer, wherein the first encoder is used to input the serial data stream and output the first identification feature to the second encoder, the second encoder outputs the second identification feature to the first fully connected layer, and the first fully connected layer outputs the remaining life of all photovoltaic power generation equipment.

[0016] In a preferred embodiment, the photovoltaic power generation equipment operation information includes: output power, voltage, current, temperature, mass, damping coefficient, and stiffness coefficient of the photovoltaic power generation equipment;

[0017] Marine environmental information includes: salinity, humidity, wave height, wave period, wind speed, and wind direction;

[0018] The inverter operation data includes: inverter input power, output power, input current, output current, input voltage, and output voltage;

[0019] Electromagnetic field data include: electromagnetic field strength and electromagnetic field frequency.

[0020] In a preferred embodiment, the corrected salt spray corrosion rate is calculated based on the electromagnetic interference factor, and the calculation formula is as follows:

[0021] ;

[0022] ;

[0023] ;

[0024] in, represents the salinity at time t, represents the humidity at time t, represents the salt spray corrosion rate at time t, represents the synergy factor at time t, represents the electromagnetic field strength at time t, represents the electromagnetic field frequency at time t, represents the corrected salt spray corrosion rate at time t, , , , , , They represent the first, second, third, fourth, fifth and sixth experimental coefficients respectively.

[0025] In a preferred embodiment, the corrected dynamic stress caused by the wave sloshing is calculated based on the electromagnetic interference factor, and the calculation formula is as follows:

[0026] ;

[0027] ;

[0028] ;

[0029] in, represents the wave height at time t, represents the wave period at time t, Indicates the quality of photovoltaic power generation equipment. represents the damping coefficient, represents the stiffness coefficient, represents the dynamic stress at time t, represents the electromagnetic field strength at time t, represents the electromagnetic field frequency at time t, represents the fatigue damage acceleration factor at time t, represents the modified dynamic stress at time t, , , They represent the seventh, eighth and ninth experimental coefficients respectively.

[0030] In a preferred embodiment, the corrected temperature rise is calculated based on the electromagnetic interference factor, and the calculation formula is as follows:

[0031] ;

[0032] ;

[0033] ;

[0034] ;

[0035] in, represents the humidity at time t, represents the temperature rise at time t, represents the electromagnetic field strength at time t, represents the electromagnetic field frequency at time t, represents the electromagnetic interference rate loss at time t, represents the thermal effect superposition factor at time t, represents the corrected temperature rise at time t, , , , , They represent the tenth, eleventh, twelfth, thirteenth and fourteenth experimental coefficients respectively.

[0036] In a preferred embodiment, the plane data further includes a relationship list for storing the association relationship between the data objects indexed by the facets, and the element value in the i-th row and j-th column of the relationship list represents the quantitative value of the association relationship between the data objects indexed by the i-th and j-th facets;

[0037] The association relationships include high and low, corresponding to two quantitative values;

[0038] Data objects include: photovoltaic power generation equipment, environment, inverter, electromagnetic field;

[0039] The data objects with high correlation are defined as: all photovoltaic power generation equipment and inverters and their environment, all inverters and their photovoltaic power generation equipment, photovoltaic power generation equipment affected by electromagnetic fields and their corresponding inverters.

[0040] In a preferred embodiment, the electromagnetic field data in the second comprehensive information includes: electromagnetic field intensity, electromagnetic field frequency, corrected salt spray corrosion rate, corrected dynamic stress and corrected temperature rise.

[0041] In a preferred embodiment, the loss function during life prediction model training adopts mean square error loss function, and the calculation formula is as follows:

[0042] ;

[0043] in represents the loss value, represents the total number of training samples, represents the actual remaining life of the qth sample, Represents the predicted life expectancy of the qth sample output by the model.

[0044] The beneficial effect of the present invention is that the present invention corrects the salt spray corrosion rate, dynamic stress and temperature rise by giving priority to the influence of electromagnetic interference, and then makes a more accurate prediction of the remaining life of the photovoltaic power generation equipment based on the corrected data combined with the collected data. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flow chart of a method for predicting the remaining life of equipment for a new energy power station according to the present invention. DETAILED DESCRIPTION

[0046] The subject matter described herein will now be discussed with reference to example implementations. It should be understood that the discussion of these implementations is only to enable those skilled in the art to better understand and implement the subject matter described herein, and the functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the present specification. Various examples may omit, replace, or add various processes or components as needed. In addition, the features described in some examples may also be combined in other examples.

[0047] At least one embodiment of the present invention discloses a method for predicting the remaining life of equipment in a new energy power station. Figure 1 As shown, the following steps are included:

[0048] Step 100, collecting the first comprehensive information at the current moment, the first comprehensive information includes: all photovoltaic power generation equipment operation data, marine environment information, all inverter operation data, electromagnetic field data;

[0049] The operation information of photovoltaic power generation equipment includes: output power, voltage, current, temperature, mass, damping coefficient, and stiffness coefficient of photovoltaic power generation equipment;

[0050] Marine environmental information includes: salinity, humidity, wave height, wave period, wind speed, and wind direction;

[0051] The inverter operation data includes: inverter input power, output power, input current, output current, input voltage, and output voltage;

[0052] Electromagnetic field data include: electromagnetic field strength, electromagnetic field frequency;

[0053] In one embodiment of the present invention, data is collected once at fixed time intervals, and the default value of the time interval is 1 hour.

[0054] Step 200, respectively calculating a corrected salt spray corrosion rate, a corrected dynamic stress, and a corrected temperature rise based on electromagnetic interference factors;

[0055] In one embodiment of the present invention, the corrected salt spray corrosion rate is calculated based on the electromagnetic interference factor, and the calculation formula is as follows:

[0056] ;

[0057] ;

[0058] ;

[0059] in, represents the salinity at time t, represents the humidity at time t, represents the salt spray corrosion rate at time t, represents the synergy factor at time t, represents the electromagnetic field strength at time t, represents the electromagnetic field frequency at time t, represents the corrected salt spray corrosion rate at time t, , , , , , They represent the first, second, third, fourth, fifth and sixth experimental coefficients respectively.

[0060] In one embodiment of the present invention, the corrected dynamic stress caused by the wave sloshing is calculated based on the electromagnetic interference factor, and the calculation formula is as follows:

[0061] ;

[0062] ;

[0063] ;

[0064] in, represents the wave height at time t, represents the wave period at time t, Indicates the quality of photovoltaic power generation equipment. represents the damping coefficient, represents the stiffness coefficient, represents the dynamic stress at time t, represents the electromagnetic field strength at time t, represents the electromagnetic field frequency at time t, represents the fatigue damage acceleration factor at time t, represents the modified dynamic stress at time t, , , They represent the seventh, eighth and ninth experimental coefficients respectively.

[0065] In one embodiment of the present invention, the corrected temperature rise is calculated based on the electromagnetic interference factor, and the calculation formula is as follows:

[0066] ;

[0067] ;

[0068] ;

[0069] ;

[0070] in, represents the humidity at time t, represents the temperature rise at time t, represents the electromagnetic field strength at time t, represents the electromagnetic field frequency at time t, represents the electromagnetic interference rate loss at time t, represents the thermal effect superposition factor at time t, represents the corrected temperature rise at time t, , , , , They represent the tenth, eleventh, twelfth, thirteenth and fourteenth experimental coefficients respectively.

[0071] Step 300, generating second comprehensive information based on the first comprehensive information and the corrected salt spray corrosion rate, the corrected dynamic stress and the corrected temperature rise;

[0072] It should be noted that the electromagnetic field data in the No. 2 comprehensive information include: electromagnetic field intensity, electromagnetic field frequency, corrected salt spray corrosion rate, corrected dynamic stress and corrected temperature rise;

[0073] Step 400, generating plane data based on the second comprehensive information, the plane data including facets for storing data, a serial data stream in which one facet indexes a data object, and a relationship list for storing association relationships between data objects indexed by the facets, wherein the element value in the i-th row and j-th column of the relationship list represents a quantitative value of the association relationship between the data objects indexed by the i-th and j-th facets;

[0074] The association relationships include high and low, corresponding to two quantitative values;

[0075] Data objects include: photovoltaic power generation equipment, environment, inverter, electromagnetic field;

[0076] The data objects with high association are defined as: all photovoltaic power generation equipment and inverters and their environment, all inverters and their photovoltaic power generation equipment, photovoltaic power generation equipment affected by electromagnetic fields and their corresponding inverters;

[0077] The serial data stream of a data object includes n data units ordered by time, and the t-th data unit represents the second comprehensive information collected at the t-th moment of the data object.

[0078] Step 500, input the plane data into the life prediction model, the life prediction model includes a first encoder, a second encoder, and a first fully connected layer, the first encoder is used to input the serial data stream and output the first identification feature to the second encoder, the second encoder outputs the second identification feature to the first fully connected layer, and the first fully connected layer outputs the remaining life of all photovoltaic power generation equipment.

[0079] In one embodiment of the present invention, the calculation formula of the first encoder is as follows:

[0080] ;

[0081] ;

[0082] ;

[0083] ;

[0084] ;

[0085] ;

[0086] in represents the tth data unit of the serial data stream corresponding to the vth bin of the plane data, and They represent the t-th and t-1-th first identification features of the serial data stream corresponding to the v-th bin of the plane data, respectively. , , , and They represent the tth first, second, third, fourth and fifth intermediate features of the vth facet of the plane data, respectively. represents the t-1th fourth intermediate feature of the vth face element of the plane data, → represents the cycle direction, , , , , , , , Respectively represent the first, second, third, fourth, fifth, sixth, seventh, and eighth serial recognition weight parameters, , , , Respectively represent the first, second, third, and fourth serial identification bias parameters represents the Hadamard product, , n represents the total number of data units in the serial data stream, when t=1 , tanh is the tanh function, Represents the Sigmoid function.

[0087] In one embodiment of the present invention, the calculation formula of the second encoder is as follows:

[0088] ;

[0089] in represents the panel feature of the vth panel in the lth layer, represents the set of facets with high correlation with facet v, represents the first plane recognition weight matrix of layer l, is the attention weight of facet u on facet v at layer l, calculated by the following formula:

[0090] ;

[0091] in is a learnable attention vector, represents the vector concatenation operation, represents the second plane recognition weight matrix of layer l, represents transpose, express Activation function;

[0092] and They represent the panel features of the vth panel and the uth panel of the l-1th layer respectively, , E represents the total number of layers, when l=1 , , when l=E is equal to the second identification feature of the face element v, where and They respectively represent the t-th first identification feature of the serial data stream corresponding to the v-th bin and the u-th bin of the plane data, and n represents the total number of data units of the serial data stream.

[0093] In one embodiment of the present invention, the calculation formula of the first fully connected layer is as follows:

[0094] ;

[0095] Where out represents a vector, and the cth component of the vector represents the remaining life of the cth photovoltaic power generation equipment. It represents the second identification feature of the vth facet of the Eth layer of the plane data, M represents the set of facets of all the plane data, and FC represents full connectivity.

[0096] In one embodiment of the present invention, the loss function during life prediction model training adopts mean square error loss function, and the calculation formula is as follows:

[0097] ;

[0098] in represents the loss value, represents the total number of training samples, represents the actual remaining life of the qth sample, Represents the predicted life expectancy of the qth sample output by the model.

[0099] The above describes an embodiment of the present invention, but this embodiment is not limited to the above-mentioned specific implementation mode. The above-mentioned specific implementation mode is merely illustrative and not restrictive. Under the guidance of this embodiment, ordinary technicians in this field can also make more forms of equivalent embodiments, all of which are within the protection of this embodiment.

Claims

1. A method for predicting the remaining life of equipment in a new energy power station, characterized in that: The following steps are involved: Step 100, collecting the first comprehensive information at the current moment, the first comprehensive information includes: all photovoltaic power generation equipment operation data, marine environment information, all inverter operation data, electromagnetic field data; The data collection time is: collect data once at a fixed time interval, and the default time interval is 1 hour; Step 200, respectively calculating a corrected salt spray corrosion rate, a corrected dynamic stress, and a corrected temperature rise based on electromagnetic interference factors; Step 300, generating second comprehensive information based on the first comprehensive information and the corrected salt spray corrosion rate, the corrected dynamic stress and the corrected temperature rise; Step 400, generating plane data based on the second comprehensive information, the plane data including facets for storing data, one facet indexing a serial data stream of a data object, the serial data stream of a data object including n data units ordered by time, the tth data unit representing the second comprehensive information collected at the tth moment of the data object; Step 500, input the plane data into the life prediction model, the life prediction model includes a first encoder, a second encoder, and a first fully connected layer, wherein the first encoder is used to input the serial data stream and output the first identification feature to the second encoder, the second encoder outputs the second identification feature to the first fully connected layer, and the first fully connected layer outputs the remaining life of all photovoltaic power generation equipment.

2. The method for predicting the remaining life of equipment for a new energy power station according to claim 1 is characterized in that: The operation information of photovoltaic power generation equipment includes: output power, voltage, current, temperature, mass, damping coefficient, and stiffness coefficient of photovoltaic power generation equipment; Marine environmental information includes: salinity, humidity, wave height, wave period, wind speed, and wind direction; The inverter operation data includes: inverter input power, output power, input current, output current, input voltage, and output voltage; Electromagnetic field data include: electromagnetic field strength and electromagnetic field frequency.

3. The method for predicting the remaining life of equipment for a new energy power station according to claim 1 is characterized in that: The corrected salt spray corrosion rate is calculated based on the electromagnetic interference factor. The calculation formula is as follows: ； ； ； in, represents the salinity at time t, represents the humidity at time t, represents the salt spray corrosion rate at time t, represents the synergy factor at time t, represents the electromagnetic field strength at time t, represents the electromagnetic field frequency at time t, represents the corrected salt spray corrosion rate at time t, , , , , , They represent the first, second, third, fourth, fifth and sixth experimental coefficients respectively.

4. The method for predicting the remaining life of equipment for a new energy power station according to claim 1 is characterized in that: The corrected dynamic stress caused by wave sloshing is calculated based on the electromagnetic interference factor. The calculation formula is as follows: ； ； ； in, represents the wave height at time t, represents the wave period at time t, Indicates the quality of photovoltaic power generation equipment. represents the damping coefficient, represents the stiffness coefficient, represents the dynamic stress at time t, represents the electromagnetic field strength at time t, represents the electromagnetic field frequency at time t, represents the fatigue damage acceleration factor at time t, represents the modified dynamic stress at time t, , , They represent the seventh, eighth and ninth experimental coefficients respectively.

5. The method for predicting the remaining life of equipment for a new energy power station according to claim 1 is characterized in that: The corrected temperature rise is calculated based on the electromagnetic interference factor. The calculation formula is as follows: ； ； ； ； in, represents the humidity at time t, represents the temperature rise at time t, represents the electromagnetic field strength at time t, represents the electromagnetic field frequency at time t, represents the electromagnetic interference rate loss at time t, represents the thermal effect superposition factor at time t, represents the corrected temperature rise at time t, , , , , They represent the tenth, eleventh, twelfth, thirteenth and fourteenth experimental coefficients respectively.

6. The method for predicting the remaining life of equipment for a new energy power station according to claim 1 is characterized in that: The plane data also includes a relationship list for storing the association relationship between the data objects indexed by the facet, wherein the element value of the i-th row and j-th column of the relationship list represents the quantitative value of the association relationship between the data objects indexed by the i-th and j-th facets; The association relationships include high and low, corresponding to two quantitative values; Data objects include: photovoltaic power generation equipment, environment, inverter, electromagnetic field; The data objects with high correlation are defined as: all photovoltaic power generation equipment and inverters and their environment, all inverters and their photovoltaic power generation equipment, photovoltaic power generation equipment affected by electromagnetic fields and their corresponding inverters.

7. The method for predicting the remaining life of equipment for a new energy power station according to claim 1, characterized in that: The electromagnetic field data in the No. 2 comprehensive information include: electromagnetic field intensity, electromagnetic field frequency, corrected salt spray corrosion rate, corrected dynamic stress and corrected temperature rise.

8. The method for predicting the remaining life of equipment for a new energy power station according to claim 1 is characterized in that: The loss function used in training the life prediction model is the mean square error loss function, and the calculation formula is as follows: ； in represents the loss value, represents the total number of training samples, represents the actual remaining life of the qth sample, Represents the predicted life expectancy of the qth sample output by the model.

9. A system for predicting the remaining life of equipment for a new energy power station, characterized in that: It is used to execute a method for predicting the remaining life of equipment for a new energy power station as described in any one of claims 1-8.

Images