JP2024044661A - Contamination determination system - Google Patents

Abstract

To provide a contamination determination system that can optimally determine occurrence of contamination of a solar instrument.SOLUTION: A contamination determination system 1, which can determine occurrence of contamination of a solar instrument (photovoltaic power generation panel 2) utilizing sun light to obtain energy, comprises: a prediction model creation unit that creates a prediction model on the basis of measured learning data on the solar instrument in a learning period; an estimation value calculation unit that calculates an estimation value of an amount of energy (amount of power generation) of the solar instrument in a determination period on the basis of measured determination data on the solar instrument in the determination period after the learning period goes by, using the prediction model; an error calculation unit that can calculate information on an error based on a measured actual measurement value of the amount of energy on the solar instrument in the determination period and the estimation value; and a detection unit that detects occurrence of the contamination of the solar instrument on the basis of the number of continuous times of the determination period in which the information on the error exceeds a prescribed threshold.SELECTED DRAWING: Figure 1

Description

The present invention relates to technology for a system that determines whether equipment that utilizes sunlight has become soiled.

Conventionally, techniques for determining the state of devices that utilize sunlight, such as solar panels, have become publicly known. For example, as described in Patent Document 1.

Patent Document 1 describes a system that can determine the occurrence of a decrease in power generation due to a malfunction using data such as the power generation amount of a solar power generation system. In the system described in Patent Document 1, estimated parameters are created by learning data such as power generation amount, and on a certain day, the estimated power generation amount estimated by the estimated parameters and the measured power generation amount of the solar power generation system are compared. , it is determined that a decrease in the amount of power generation has occurred when the value based on the difference between is equal to or greater than the threshold value.

Here, since solar panels and the like are installed outdoors, it is assumed that dirt will gradually accumulate on the surface as time passes, resulting in staining of the solar panels and the like. In such a case, the amount of power generated by the solar panel may gradually decrease as dirt accumulates. Therefore, there is a need for a system that can determine the occurrence of contamination based on the condition of solar panels and the like.

However, the invention described in Patent Document 1 makes a judgment based only on the information on the day of judgment, so it is difficult to judge the occurrence of stains that gradually accumulate over a predetermined period (for example, several days). is difficult to apply.

Patent No. 6608619

The present invention has been made in view of the above circumstances, and an object thereof is to provide a stain determination system that can suitably determine the occurrence of staining of solar equipment.

The problem to be solved by the present invention is as described above, and next, means for solving this problem will be explained.

That is, in claim 1, there is provided a contamination determination system capable of determining the occurrence of contamination of a solar device that obtains energy using sunlight, wherein learning data regarding the solar device measured during a learning period is used. a prediction model creation unit that creates a prediction model based on the prediction model; an estimated value calculation unit that calculates an estimated value of the amount of energy of the solar device; information regarding an error is calculated based on the actual value of the amount of energy of the solar device measured during the determination period and the estimated value; The present invention includes a possible error calculation section, and a detection section that detects occurrence of contamination of the solar equipment based on the number of consecutive determination periods in which information regarding the error exceeds a predetermined threshold value.

In claim 2, the learning period is the period from immediately after the solar power device starts operating until a predetermined period has elapsed.

In claim 3, the solar power device is a solar power generation device capable of generating power using sunlight, and the amount of energy is the amount of power generated.

In claim 4, the solar device is a solar heat collecting device capable of collecting solar heat, and the energy amount is a heat amount.

In claim 5, the detection unit detects occurrence of contamination of the solar equipment using a plurality of conditions in which the threshold value and the number of times are set, and the plurality of conditions are set in accordance with a plurality of set conditions. The threshold value and the plurality of times are different from each other, and are set such that as the absolute value of the threshold value increases, the number of times decreases.

The present invention has the following effects.

In claim 1, the occurrence of soiling of solar equipment can be appropriately determined.

According to the second aspect of the present invention, it is possible to more appropriately determine the occurrence of contamination of solar equipment.

In claim 3, the occurrence of contamination of the photovoltaic power generation equipment can be suitably determined.

In claim 4, the occurrence of contamination of the solar heat collecting equipment can be suitably determined.

In claim 5, the occurrence of soiling of solar equipment can be more appropriately determined.

1 is a schematic diagram showing the configuration of a stain determination system according to an embodiment of the present invention. 5 is a flowchart showing processing executed by the stain determination system. A graph showing an example of the verification results of the measured power generation amount, estimated power generation amount, and error rate when it is determined that no contamination has occurred. A graph showing an example of the verification results of the measured power generation amount, estimated power generation amount, and error rate when it is determined that contamination has occurred.

The following describes the configuration of a contamination determination system 1 according to one embodiment of the present invention, using Figure 1.

The contamination determination system 1 according to this embodiment is capable of determining whether contamination has occurred on a solar power generation panel 2. The contamination determination system 1 and the solar power generation panel 2 are installed in a facility (e.g., a factory) of a specified business operator (hereinafter also referred to as the "business operator").

The solar power generation panel 2 is capable of generating electricity using sunlight. The electricity obtained by the solar power generation panel 2 is derived from sunlight, which is renewable energy (RE). The solar power generation panel 2 is installed in a sunny location, such as the roof of a facility (factory, etc.). The solar power generation panel 2 is installed using appropriate supports so that it is at an inclination angle that makes it easy to receive sunlight.

The facility of the operator is equipped with a storage battery that can charge and discharge the electricity obtained from the photovoltaic power generation panel 2, a power conditioner that can convert the above electricity as appropriate, and an EMS (energy management system) that can control the operation of the storage battery and the power conditioner. Note that the storage battery, power conditioner, and EMS are not shown in Figure 1. The EMS can obtain information such as the output (power generation amount) of the photovoltaic power generation panel 2 using various sensors not shown.

It is expected that the solar power generation panel 2 will become soiled over time. Here, "soil" refers to the surface of the solar power generation panel 2 becoming dirty, for example, due to the adhesion of factory exhaust smoke or dust. If dirt adheres to the surface of the solar power generation panel 2, there is a risk that the power generation output will gradually decrease as the dirt accumulates. Furthermore, the soiling can be eliminated by cleaning the surface of the solar power generation panel 2.

The stain determination system 1 according to the present embodiment can determine whether the solar power generation panel 2 has been contaminated. Thereby, by taking measures such as cleaning when staining occurs, it is possible to prevent the surface of the solar power generation panel 2 from being left in a contaminated state.

The soiling determination system 1 includes a control device 10. The control device 10 is capable of processing various types of information. A general personal computer, server, or the like can be used as the control device 10. The control device 10 includes a memory unit 11, a control unit 12, a communication unit 13, an input unit 14, and a display unit 15.

The storage unit 11 stores various programs (such as the prediction model described below) and various acquired information. The storage unit 11 is composed of a HDD, RAM, ROM, etc.

The control unit 12 executes the programs stored in the memory unit 11. The control unit 12 is configured by a CPU.

The communication unit 13 is capable of communicating with external devices. The communication unit 13 can exchange information with external devices via various communication means such as the Internet. By communicating using the communication unit 13, the control device 10 can access, for example, an EMS or an external server. This allows the control device 10 to obtain information obtained by the EMS, information from various websites stored on the server, etc.

The input unit 14 is for inputting various information. The input unit 14 includes a keyboard, a mouse, and the like.

The display section 15 displays various information. The display section 15 is composed of, for example, a liquid crystal display.

By communicating using the communication unit 13, the control device 10 can acquire data necessary for determining the occurrence of contamination. The data necessary for determining the occurrence of pollution include "solar radiation amount", "temperature", and "power generation amount".

The “solar radiation amount” is the solar radiation amount at the location where the solar power generation panel 2 is installed. As the "solar radiation amount", total solar radiation amount, direct solar radiation amount, etc. can be adopted. The “solar radiation amount” is obtained, for example, by a pyranometer installed near the solar power generation panel 2.

"Temperature" is the temperature at the location where the solar panel 2 is installed. "Temperature" is obtained, for example, by a thermometer installed near the solar panel 2.

The “power generation amount” is the amount of power (kWh) generated by the solar power generation panel 2. The “power generation amount” is obtained, for example, by EMS.

As described above, in this embodiment, the occurrence of contamination is determined using data on the "power generation amount" of the solar panel 2 and the weather conditions related to power generation, namely "solar radiation" and "temperature."

The control device 10 communicates using the communication unit 13 to acquire data on "solar radiation," "air temperature," and "power generation" acquired by devices such as a solar radiation meter, thermometer, and EMS.

Instead of the control device 10 directly acquiring the data from devices such as a pyranometer, thermometer, EMS, etc., it is also possible to adopt a configuration in which the control device 10 indirectly acquires the data from, for example, a website published by the business operator. Also, instead of acquiring the "amount of solar radiation" and "temperature" from devices such as a pyranometer, thermometer, etc. installed in the business operator's facility, it is also possible to adopt a configuration in which the control device 10 acquires the "amount of solar radiation" and "temperature" from weather forecast information (weather forecast, etc.) transmitted from a public meteorological institution.

The above-described contamination determination system 1 (control device 10) can execute a contamination determination process that determines whether or not contamination has occurred on the photovoltaic power generation panel 2 using the above-described "solar radiation amount," "air temperature," and "power generation amount" data, and a predictive model creation process that creates a predictive model used in the contamination determination process. The process (control) executed by the control device 10 will be described below with reference to FIG. 2.

First, the predictive model creation process will be explained. The predictive model creation process is a process that creates a predictive model using data on "solar radiation," "temperature," and "power generation" (hereinafter referred to as "learning data") acquired during a predetermined learning period. Yes (step S10). The predictive model creation process is executed, for example, in response to a user's operation using the input unit 14. Further, the predictive model creation process may be automatically executed by the control device 10, for example, when a predetermined amount or a predetermined period of learning data is acquired.

The prediction model predicts (estimates) the amount of power generated by the photovoltaic panel 2 using the "judgment data" described below. The prediction model is created by machine learning. Various methods such as decision trees and neural networks can be used for machine learning.

In this embodiment, the learning period is set to a period of one year from immediately after the solar power generation panel 2 starts operating. In the predictive model creation process, the control device 10 creates a predictive model using learning data acquired every predetermined period (for example, 1 hour) over a learning period (1 year).

In the prediction model creation process, the control device 10 creates a prediction model by learning the relationship between the "power generation amount" during the learning period and the weather conditions related to power generation, namely "solar radiation" and "temperature." Here, it is estimated that no contamination has yet occurred on the solar power generation panel 2 during the learning period. Therefore, the prediction model is created based on data from a period when it is estimated that no contamination has occurred. For this reason, the prediction model is formed so that it can estimate the power generation amount when no contamination has occurred.

After completing the creation of the prediction model, the control device 10 stores the prediction model in the memory unit 11 and terminates the prediction model creation process.

Next, the contamination determination process will be described. The contamination determination process is a process for determining whether contamination has occurred on the photovoltaic panel 2 using data on "solar radiation," "temperature," and "power generation" (hereinafter referred to as "determination data") acquired during a specified determination period.

Here, "occurrence of contamination" refers to the accumulation of contamination on the solar power generation panel 2 to the extent that the amount of power generation (output) of the solar power generation panel 2 is reduced to a certain extent. The degree of reduction in power generation that is recognized as the occurrence of contamination can be set arbitrarily, for example, by an administrator of the contamination determination system 1. The contamination determination process is executed (started) at any timing after the prediction model is created (after the prediction model creation process is completed). The contamination determination process is started, for example, by a user's operation via the input unit 14. The contamination determination process may also be started automatically by the control device 10, for example, when the prediction model creation process is completed.

When the contamination determination process is started, the control device 10 determines whether or not contamination has occurred on the solar power generation panel 2 each time a predetermined determination period has elapsed (performing the process of step S14 described below). In this embodiment, the predetermined determination period is set to one day. That is, in this embodiment, the control device 10 determines whether or not contamination has occurred on the solar power generation panel 2 every day (on the day of determination), for example, at midnight.

In step S11, the control device 10 acquires data for judgment ("solar radiation", "temperature", and "power generation"). Specifically, the control device 10 acquires data for judgment for a predetermined period (e.g., one hour) on the day of judgment. The judgment data may be acquired at least during the time period when the solar power generation panel 2 is generating power (e.g., the time period from sunrise to sunset). After performing the process of step S11, the control device 10 proceeds to the process of step S12. The timing of acquiring the data for judgment is not limited to the timing (24:00) when the process of step S14 is executed, and can be any timing.

In step S12, the control device 10 calculates an estimate of the amount of power generated by the photovoltaic panel 2 on the day of the determination (hereinafter referred to as the "estimated amount of power generation") based on the determination data and the prediction model. The estimated amount of power generation is the amount of power generation in the absence of contamination, estimated by the prediction model based on the "amount of solar radiation" and "air temperature" on the day of the determination contained in the determination data.

In this embodiment, the estimated power generation amount is the amount of power generation per day (see Figures 3 and 4). After performing the process of step S12, the control device 10 proceeds to the process of step S13.

In step S13, the control device 10 calculates the error rate of the actual power generation amount relative to the estimated power generation amount. Here, the actual power generation amount is the amount of power generation per day actually measured on the day of the judgment (see Figures 3 and 4). The actual power generation amount is calculated based on the judgment data acquired in step S11 (the amount of power generation per hour).

The error rate is the ratio of the difference between the estimated power generation amount and the actual power generation amount (the value obtained by subtracting the estimated power generation amount from the actual power generation amount) for a certain power generation amount (estimated power generation amount). If the actual power generation amount is smaller than the estimated power generation amount, the error rate is shown as a negative value (e.g., -10%) (see FIG. 4). The error rate is calculated for each day. After performing the process of step S13, the control device 10 proceeds to the process of step S14.

In step S14, the control device 10 determines whether or not the solar power generation panel 2 is contaminated. In the present embodiment, the control device 10 is based on the calculation result of the error rate on the day of determination, the calculation result of the error rate in the past (before yesterday) stored in the storage unit 11, and a preset condition group. Detection (judgment) of occurrence of contamination of the solar power generation panel 2 is performed.

The condition group includes multiple conditions (conditions A to C). Each condition is set by an error rate threshold and the number of consecutive days (determination period) during which the error rate exceeds the threshold. Here, in this embodiment, "the error rate exceeds the threshold" refers to a case in which the error rate is a negative value and the absolute value of the error rate is greater than the absolute value of the threshold.

In this embodiment, condition A is that the error rate exceeds -5% (error rate < -5%) for 10 or more consecutive days. Condition B is that there are five or more consecutive days in which the error rate exceeds -7% (error rate < -7%). Condition C is that there are three or more consecutive days in which the error rate exceeds -10% (error rate < -10%).

As described above, in this embodiment, each condition is set so that as the absolute value of the threshold value increases, the number of days in which the error rate exceeds the threshold value decreases. Note that conditions A to C are just examples, and the conditions are not limited to the above-mentioned examples. The contents of the conditions described above can be changed as appropriate, and new conditions may be added to the condition group.

In the present embodiment, the control device 10 determines that the solar power generation panel 2 is contaminated if the calculation result of the error rate on the determination day satisfies any of conditions A to C. Note that the manner of determination in step S14 is not limited to the example described above. For example, it may be determined that staining has occurred if two or more or all of conditions A to C are satisfied.

The following describes how to determine whether contamination has occurred, using the graphs in Figures 3 and 4. The graphs show an example of the verification results of the estimated power generation, the measured power generation, and the error rate for each day over a certain period. The horizontal axis of the graph shows the period. One vertical axis of the graph shows the amount of power per day (kWh/d), and the other vertical axis shows the error rate (%).

In the example shown in the graph in Figure 3, there are no consecutive days on which the error rate is a negative value, and none of conditions A to C are met. In this case, the control device 10 determines that the solar panel 2 is not soiled.

In the example shown in the graph of FIG. 4, as shown in the area surrounded by the dashed line, there are three or more consecutive days in which the error rate exceeds -10% (error rate < -10%). Condition C is satisfied. In this case, the control device 10 determines that the solar power generation panel 2 is contaminated in the process of step S14 on January 6th.

The control device 10 causes the storage unit 11 to store the determination result in step S14. Further, after performing the process in step S14, the control device 10 proceeds to the process in step S15.

In step S15, the control device 10 outputs the determination result in step S14. In this embodiment, the control device 10 causes the display unit 15 to display the determination result. After performing the process of step S15, the control device 10 ends the stain determination process.

According to the stain determination system 1 as described above, by determining the occurrence of staining of the solar power generation panel 2 and outputting the determination result, it is possible to urge the business operator to clean the solar power generation panel 2, etc. can. As a result, it is possible to prevent the surface of the solar power generation panel 2 from being contaminated and the amount of power generated by the solar power generation panel 2 from continuing to decrease.

Further, according to the stain determination system 1, it is possible to perform a determination taking into consideration the number of consecutive periods (determination periods) in which the error rate exceeds a threshold value. Thereby, it is possible to suitably determine the staining of the solar power generation panel 2, which is assumed to gradually accumulate dirt as time passes.

Furthermore, in this embodiment, the conditions A to C for determination are set such that as the absolute value of the threshold value increases, the number of days in which the error rate exceeds the threshold value decreases. As a result, when the degree of contamination is estimated to be large, such as when the error rate exceeds a threshold with a large absolute value, it is possible to determine the occurrence of contamination in fewer days. In this way, the occurrence of staining can be determined in a number of days depending on the estimated degree of staining.

The above describes the soiling determination system 1. Note that the control according to this embodiment is an example, and the control executed by the soiling determination system 1 is not limited to the above example, and any processing may be added or changed. Also, the specific numerical values exemplified in the above description are an example, and can be changed as desired.

Furthermore, in the example described above, the stain determination system 1 that can determine the occurrence of staining of the solar power generation panel 2 has been described, but the system is not limited to the example described above. For example, the contamination determination system 1 can also be applied to a solar heat collection panel (not shown) that can collect solar heat. That is, the contamination determination system 1 can also determine the occurrence of contamination of a solar heat collection panel instead of the solar power generation panel 2.

In this case, the contamination determination system 1 can execute the predictive model creation process and the contamination determination process based on the amount of heat of the solar heat collection panel instead of the amount of power generated by the solar power generation panel 2. Note that the contents of each process when the stain determination system 1 is applied to a solar heat collection panel are generally the same except that the amount of heat is used instead of the amount of power generation, so a detailed explanation will be omitted.

As described above, the stain determination system 1 according to the present embodiment is
A contamination determination system 1 capable of determining the occurrence of contamination of a solar power device (solar power generation panel 2) that obtains energy using sunlight,
A prediction model creation unit (control device 10) that creates a prediction model based on learning data regarding the solar power device (solar power generation panel 2) measured during the learning period (step S10);
Using the prediction model, based on the determination data regarding the solar power device (solar power generation panel 2) measured in the determination period after the elapse of the learning period, an estimated value calculation unit (control device 10) that calculates an estimated value of the energy amount (power generation amount) of the power generation panel 2) (step S12);
Information regarding the error (error rate) can be calculated based on the actual value of the energy amount (power generation amount) of the solar power device (solar power generation panel 2) measured during the determination period and the estimated value ( Step S13) Error calculation unit (control device 10);
detecting occurrence of contamination of the solar power equipment (solar power generation panel 2) based on the number of consecutive determination periods in which the information regarding the error (error rate) exceeds a predetermined threshold (step S14); a control device 10);
It is equipped with the following.

With this configuration, it is possible to suitably determine whether the solar power equipment (solar power generation panel 2) is contaminated. That is, the prediction model is created based on learning data measured during a learning period in which it is estimated that there is relatively little contamination. By using the above prediction model, the estimated value calculation unit (control device 10) can calculate the estimated value of the energy amount (power generation amount) when there is little contamination, and the detection unit (control device 10) can determine Detection can be performed using information regarding the error (error rate) between the actual measured value and the estimated value during the period. Furthermore, by using the above detection results, it is possible to determine whether the solar power equipment (solar power generation panel 2) has been contaminated. Further, according to the detection unit (control device 10), for example, even if the period in which the error rate exceeds the threshold value is a single period (one day), it is determined that the condition is satisfied, and the period in which the error rate exceeds the threshold is continuous. It is possible to make a judgment taking into consideration the number of times the process has been performed. Thereby, it is possible to suitably determine whether the solar power equipment (solar power generation panel 2) is contaminated, where it is assumed that dirt will gradually accumulate over time.

In addition, the learning period is
This is a period from immediately after the solar power equipment (solar power generation panel 2) starts operating until a predetermined period of time has elapsed.

This configuration allows for a more appropriate determination of whether or not the solar device (solar power generation panel 2) is soiled. In other words, the learning period is set to a period starting immediately after the solar device (solar power generation panel 2) starts operating, which is presumed to be free of soiling, so that an estimate of the amount of energy (amount of power generation) when there is less soiling can be calculated, and thus the occurrence of soiling of the solar device (solar power generation panel 2) can be more appropriately determined.

Further, the solar power device is a solar power generation device (solar power generation panel 2) that can generate electricity using sunlight,
The amount of energy is the amount of power generated.

By configuring it in this way, it is possible to appropriately determine whether or not the solar power generation equipment (solar power generation panel 2) has become soiled.

The solar power device is a solar heat collecting device capable of collecting solar heat,
The amount of energy is a heat amount.

This configuration makes it possible to appropriately determine whether or not the solar heat collection equipment has become soiled.

Further, the detection unit (control device 10)
Detecting occurrence of contamination of the solar power device (solar power generation panel 2) using a plurality of conditions in which the threshold value and the number of times are set,
The plurality of conditions are:
The plural threshold values and the plural number of times are set to be different from each other, and the number of times is set to decrease as the absolute value of the threshold value becomes larger.

By configuring in this way, it is possible to more appropriately determine whether the solar power device (solar power generation panel 2) is contaminated. That is, the conditions for determination are set so that as the absolute value of the threshold value increases, the number of consecutive periods in which the error rate exceeds the threshold value decreases. As a result, if the degree of contamination is estimated to be large, for example, when the information regarding the error (error rate) exceeds a threshold with a large absolute value, the contamination can be detected in a smaller number of consecutive periods (number of days). Occurrence can be determined. In this way, the occurrence of contamination can be determined by the number of consecutive periods corresponding to the estimated degree of contamination.

The control device 10 according to this embodiment is an embodiment of the prediction model creation unit, the estimated value calculation unit, the error calculation unit, and the detection unit according to the present invention.
Moreover, the solar power generation panel 2 according to this embodiment is one embodiment of a solar device and a solar power generation device according to the present invention.
The solar heat collecting panel according to this embodiment is one embodiment of the solar light device and the solar heat collecting device according to the present invention.

Although one embodiment of the present invention has been described above, the present invention is not limited to the above configuration, and various modifications are possible within the scope of the invention described in the claims.

For example, in this embodiment, an example is shown in which the contamination determination system 1 includes only the control device 10, but the present invention is not limited to this. For example, in addition to the control device 10, an actinometer, a thermometer, a solar power generation panel 2, and a solar heat collection panel may be included.

Further, in this embodiment, an example is shown in which "solar radiation amount", "temperature", and "power generation amount (calorific amount)" are used as data used to determine the occurrence of contamination, but the present invention is not limited to this. . For example, other data may be used instead of or in addition to "solar radiation amount," "temperature," and "power generation amount (heat amount)."

Further, in this embodiment, an example has been shown in which the error rate is calculated for each day in the stain determination process (step S13), but the present invention is not limited to this. For example, the error rate may be calculated hourly. In this case, the estimated power generation amount and the measured power generation amount are also calculated every hour. Further, in this case, the number of times (number of hours) in which the error rate exceeds the threshold value in the condition group for the determination using the error rate (step S14) can be set as appropriate. Further, the error rate can also be calculated after a relatively long period of time, such as every two days or every week.

Furthermore, in this embodiment, one day is set as the predetermined determination period (that is, the timing for determining the occurrence of contamination is set to be the same as the period for calculating the error rate). The present invention is not limited to this. Specifically, the predetermined determination period is 10 days (for example, 10 days from January 1st to January 10th, as shown in FIG. 4), and the control device 10 determines the timing when 10 days have passed. The occurrence of contamination may be determined by comparing the daily error rates from January 1st to January 10th. In this way, by collectively determining trends for 10 days, it is possible to reduce the burden on the control device 10.

In addition, in this embodiment, an example is shown in which an error rate is used in the contamination determination process (step S13), but the present invention is not limited to this. For example, instead of the error rate, the difference (error) between the estimated power generation amount and the actually measured power generation amount may be used directly to determine the occurrence of contamination.

In addition, in this embodiment, an example is shown in which the contamination determination system 1 and the photovoltaic power generation panel 2 (solar heat collection panel) are applied to a facility of a business operator such as a factory, but the present invention is not limited to this. For example, the contamination determination system 1 and the photovoltaic power generation panel 2 (solar heat collection panel) may be applied to a house, etc.

1 Contamination determination system 2 Solar power generation panel 10 Control device

Claims (5)

A contamination determination system capable of determining the occurrence of contamination of solar equipment that obtains energy using sunlight,
a prediction model creation unit that creates a prediction model based on learning data regarding the solar equipment measured during a learning period;
Estimating using the prediction model to calculate an estimated value of the energy amount of the solar device in the determination period based on determination data regarding the solar device measured in the determination period after the learning period has elapsed. A value calculation unit,
an error calculation unit capable of calculating information regarding an error based on the estimated value and an actual value of the energy amount of the solar device measured in the determination period;
a detection unit that detects occurrence of contamination of the solar device based on the number of consecutive determination periods in which the information regarding the error exceeds a predetermined threshold;
Equipped with
Contamination determination system. The learning period is
It is a period from immediately after the start of operation of the solar equipment until a predetermined period has elapsed,
The stain determination system according to claim 1. The solar device is a solar power generation device that can generate electricity using sunlight,
The amount of energy is the amount of power generation,
The stain determination system according to claim 1. The solar device is a solar heat collecting device capable of collecting solar heat,
The amount of energy is a heat amount.
The contamination determination system according to claim 1 . The detection unit includes:
Detecting occurrence of contamination of the solar equipment using a plurality of conditions in which the threshold value and the number of times are set,
The plurality of conditions are:
The plurality of set threshold values and the plural number of times are set to be different from each other, and the number of times is set to decrease as the absolute value of the threshold value becomes larger.
A stain determination system according to any one of claims 1 to 4.

Images