, Description:FIELD OF THE INVENTION
The present invention relates to an intelligent cum autonomous system for monitoring, control, forecasting and operation of a dust cleaning mechanism for solar photovoltaic panels.
BACKGROUND OF THE INVENTION
Background description includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art.
Solar photovoltaic (SPV) systems are the most popular renewable energy power generation systems. Solar panels have been installed in large scale all around the world, at both homes and businesses, with generation capacity ranging from a few kilowatts (kW) to Gigawatts (GW). SPV is considered as a non-schedulable and unreliable power source due to its dependence on various meteorological conditions like solar irradiance, cloud cover, wind speed, humidity etc. Another important factor which affects power generation is the clearness of the protective glass above the solar cells. Since the solar panels are placed in open atmosphere, layer of dust and debris or other environmental materials like airborne particles, water droplets, bird droppings etc. frequently get deposited on the surface of these panels. Humidity in the atmosphere causes these particles to stick on the surface. The foreign particles form a layer or film which makes the impact of the solar rays on the surface of the solar panel difficult. This causes shading effect on the solar cells and reduces the intensity of light actually transmitted down to the solar cells. Since, the power generation depends on the intensity of light falling on the cells, the power generation comes down considerably in these conditions.
Only solution to reduce shading effect on solar panels is to frequently clean the glass surface of the panels. Most commonly employed methodology is manually spraying water over the surface and then wiping off. However, manual cleaning is cumbersome and does not give the required results. In some cases, pressurized water jet is employed through a semi-automatic system. In all methodologies, water is the primary component. However, water in itself is a critical and valuable resource. All cleaning methodologies employed are manual with no control over the quantity of water used or the duration of cleaning or the periodicity of cleaning.
This problem can be overcome by employing an artificially intelligent system which decides when to clean and how long to clean based on real time empirical data. The present invention addresses this need.
DESCRIPTION OF PRIOR ART
In the prior arts, cleaning of solar panel surface is achieved by a pre-programmed cleaning system. These systems employ various cleaning media like water, brushes, cleaning solutions etc. They are either permanently mounted in proximity to the panels or can be independent and installed as and when required. However, in all cases, the periodicity and methodology are predetermined. They do not respond to stochastic inputs like environmental parameters.
Now, reference may be made to the following patents: -
The US patent US 2010/0043851 A1 is granted to Mitch Levy and Emanuel Edward Levy for their invention of an automated system for cleaning a plurality of Solar energy generation modules. The invention dispenses a cleaning solution onto the modules in a predetermined and periodical fashion, whereas the invention is silent about the non-predictable environmental conditions like wind and their effect on thickness of dust and debris layers which will result in improper cleaning and thereby reduction in power generation.
The European patent EP 2 048 455 A2 is granted to Castellano Diaz and Juan Jose for their invention of an automatic solar panel cleaning system. The invention utilizes cleaning brushes mounted on a rotary actuator. This actuator drives along longitudinal rails fixed on the sides of the panel. The invention is dependent on the amount of rainfall in the installed area with additional cleaning during summers. However, the invention does not take into account the actual generation drop due to dust accumulation and depends on an unreliable parameter like rainfall. The invention has no practical application in desert areas with minimal or no rainfall. Major solar PV installations are found in those areas and have huge amount of dust accumulation.
The US patent US 8,500,918 B1 is granted to Moshe Meller and Eran Meller for a solar panel cleaning system and method. The invention employs a similar brush cleaning mechanism like in patent EP 2 048 455 A2. While the cleaning operation is done by a dedicated control system, starting the process is manually done. This invention does not respond automatically to accumulation of dust/dirt or to the drop in power generation due to the same.
Thus, none of the above can fulfill the requirements of the present invention, for which it is designed.
OBJECTS OF THE INVENTION
It is therefore, the principal object of the present invention to provide a system for autonomous and intelligent control and operation of a dust cleaning mechanism for Solar photovoltaic panels.
Another objective of the invention is to ensure that the panels are cleaned for maximum power generation without any manual intervention.
Yet another objective of the invention is to forecast present day’s solar power generation using machine learning and compare the same with actual generation.
Further objective of the invention is to determine the periodicity and duration of cleaning the panels from a many-valued mathematical model using degrees of truth.
Another objective is to tandemly operate either the jet of water or compressed air or both in tandem and ensure pre- and post-cleaning is accomplished along with proper drying of water droplets.
Yet another objective of the invention is to judicially utilize water, a valuable and scarce natural resource.
These and other objects and advantages of the present invention will be apparent to those skilled in the art after a consideration of the following detailed description taken in conjunction with the accompanying drawings in which a preferred form of the present invention is illustrated.
SUMMARY OF THE INVENTION
One or more drawbacks of conventional systems and process are overcome, and additional advantages are provided through the apparatus and a method as claimed in the present disclosure. Additional features and advantages are realized through the technicalities of the present disclosure. Other embodiments and aspects of the disclosure are described in detail herein and are considered to be part of the claimed disclosure.
An artificially intelligent system for monitoring, control, forecasting and operation of a dust cleaning mechanism for solar photovoltaic panels comprising of mainly the following parts: -
a control system that operates the mechanism for lifetime without any manual intervention;
artificial intelligence programs comprising of an artificial neural network for forecasting and a fuzzy logic for determining the cleaning schedules;
a pressurized air cum water jet header with nozzles for spraying air and water;
pump, compressor, tanks and solenoid valves to supply the header with compressed air or water through respective dedicated pipelines.
According to this invention, there is provided an autonomous system for monitoring, forecasting and operation of a dust cleaning device for photovoltaic panels comprising an automatic data processing system operating artificial intelligence program for determining as to when and how long to clean solar panel by solar panel surface cleaning device, wherein the automatic data processing system operates the panel cleaning device through the artificial intelligence program comprising an artificial neural network (ANN) for forecasting and a fuzzy logic (FL) for determining the cleaning schedules.
The automatic data processing system (18) includes computer system; the solar panel includes a plurality of solar cells and is inclined at an angle ? with respect to the horizontal surface that sun rays fall perpendicular to the panel, in which the angle ? is according to the latitude of the location.
The solar cells are protected from environmental factors by a transparent glass installed on the top surface thereof, in which the glass has high light transmittance values that ensures all the available light falls on the cells with maximum intensity.
The solar panel surface cleaning device includes a pressurized air cum water jet header installed close to the top surface of the panels, in which multitude of nozzles provided on the header supply water and air for cleaning the surface of the panel.
The header comprises of two separate and concentric pipelines, in which first pipeline carries water and the other pipeline carries compressed air.
Water required for this system is stored in a water tank and water is filled into this tank by a water pump which supplies the water from the main water supply of the plant/factory through a pipeline.
Compressed air at required pressure (> 5 bar) is stored in an air tank and pressurized air is fed into the tank through another pipeline from the factory/plant compressed air system, alternatively an air compressor feeds the tank.
Water and air from their respective tanks are sent forward towards the jet header via another set of pipelines, in which water and air solenoid valves restrict the flow of water/air.
The ANN forecasts the next day’s solar power generation values based on historical generation values with which it is trained and the program refers fuzzy tables of the FL to determine the cleaning schedules, wherein input data to the ANN comprises of daily power generation data captured on hourly basis for the prior couple of years.
The system activates the water and air solenoid valves which allow the flow of water and air to the jet header via multiple pipelines, in which the system activates water solenoid valve/air solenoid valve for the duration determined by the program’s fuzzy table.
The entire duration is divided into 3 sections, namely T1, T2, and T3 and the ratio T1: T2: T3 is predetermined; the system switches on the air solenoid valve for T1 duration. which sends pressurized jet of air over the panels through the nozzles which cleans them of superficial dust layers; for the next T2 duration, both solenoid valves are switched on and pressurized water jet cleans the panels during this phase, for T3 of the time, the air solenoid valve is operated, in which compressed air jet flowing over the panels during this phase removes the residual water droplets and dries the surface.
Various objects, features, aspects, and advantages of the inventive subject matter will become more apparent from the following detailed description of preferred embodiments, along with the accompanying drawing figures in which like numerals represent like components.
It is to be understood that the aspects and embodiments of the disclosure described above may be used in any combination with each other. Several of the aspects and embodiments may be combined to form a further embodiment of the disclosure.
The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.
BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWINGS
The illustrated embodiments of the subject matter will be best understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and processes that are consistent with the subject matter as claimed herein, wherein: -
Figure 1 illustrates the general schematic of an autonomous system for monitoring, forecasting and operation of a dust cleaning mechanism for photovoltaic panels according to present invention.
Figure 2 illustrates the process flow diagram of training the artificial neural network with historical power data in accordance with invention.
Figure 3 illustrates the process flow diagram of forecasting day’s power generation using neural network and operating the intelligent panel cleaning mechanism using fuzzy tables of present invention.
The figures depict embodiments of the disclosure for purposes of illustration only. One skilled in the art will readily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.
DETAIL DESCRIPTION OF THE PRESENT INVENTION WITH REFERENCE TO THE ACCOMPANYING DRAWINGS OF PREFERRED EMBODIMENTS
While the embodiments of the disclosure are subject to various modifications and alternative forms, specific embodiment thereof have been shown by way of example in the figures and will be described below. It should be understood, however, that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternative falling within the scope of the disclosure.
The subject matter disclosed herein pertains to a technology in respect of a novel system for autonomous control and operation of solar panel surface cleaning device.
Now, reference may be made to Figure 1 illustrating the general schematic of the proposed system with its various components. Solar panels (1) can be installed on the ground or over rooftops. A solar panel (1) includes many solar cells (2) which generate power when sun rays fall on them. Solar panels (1) are inclined at an angle f with the horizontal surface to ensure that sun’s rays fall perpendicular to the panel. The angle f depends on the latitude of the location. The number of solar cells (2) depend on the power rating of the panel (1). The solar cells (2) are protected from environmental factors by a transparent glass (3) installed on the top surface of solar panels. The glass (3) has high light transmittance values to ensure that all the available light falls on the cells (2) with maximum intensity. A pressurized air cum water jet header (4) is installed close to the top surface of the panels (1). Multitude of Nozzles (5) provided on the header (4) supply water and air for cleaning the surface of the panels (1). The header (4) comprises of two separate, but concentric pipelines (6 and 7). First pipeline (6) carries water and the other pipeline (7) carries compressed air. Necessary water required for this system is stored in a water tank (8) of appropriate capacity. Water is filled into this tank (8) by a water pump (9) which supplies the water from the main water supply of the plant/factory through a dedicated pipeline (10). Similarly, compressed air at required pressure (> 5 bar) is stored in an air tank (11). Pressurized air is fed into the tank (11) through another pipeline (12) from the factory/plant compressed air system. In the absence of a compressed air system, a dedicated air compressor (13) of suitable capacity feeds the tank (11). Water and air from their respective tanks (8 and 11) are sent forward towards the jet header (4) via another set of pipelines (14 and 15 respectively).
In addition to the above, dedicated water and air solenoid valves (16 and 17) restrict the flow of water/air further. The solenoid valves (16 and 17) act as a switch and allow flow of water or air only when their coils receive control signals to switch on. A computer system (18) runs the artificial intelligence program (19) for determining when to clean and how long to clean the solar panels (1).
The artificial intelligence program (19) comprises of an artificial neural network (ANN) program and a fuzzy logic (FL) program. ANN forecasts the next day’s solar power generation values based on historical generation values with which it is trained. The program (19) subsequently refers fuzzy tables of the FL to determine the cleaning schedules. The system (18), then, activates the water and air solenoid valves (16 and 17 respectively) which allow the flow of water and air further to the jet header (4) via a set of pipelines (20 and 21 respectively). The system (18) activates water solenoid valve (16) or air solenoid valve (17) for the duration determined by the program’s (19) fuzzy table. The entire duration is divided into 3 sections, namely T1, T2, and T3. The ratio T1: T2: T3 is predetermined. First, the system (18) switches on the air solenoid valve (17) alone for T1 duration. This sends pressurized jet of air over the panels (1) through the nozzles (5) which cleans them of superficial dust layers. For the next T2 duration, both solenoid valves (16 and 17) are switched on. Pressurized water jet cleans the panels (1) during this phase. Finally, for the remaining T3 of the time, only the air solenoid valve (17) is operated. Compressed air jet flowing over the panels (1) during this phase removes the residual water droplets and dries the surface.
Figure 2 illustrates the process flow diagram of training the artificial neural network with historical power generation data. Input data to the ANN comprises of daily power generation data captured on hourly basis two years prior. The periodicity of data capture can be varied according to the system requirements. Output to the ANN for training comprises of daily power generation data captured on hourly basis one year prior (or the next year corresponding to the input year). For example, the generation data from the year 2017 will serve as initial training input and data from the year 2018 will be the corresponding training output. The forecasting accuracy of the ANN improves with more data. The current year’s data can be fed similarly in future to improve the training process. The trained ANN is then employed for forecasting the day’s power generation and operating the cleaning mechanism if required.
Figure 3 illustrates the process flow diagram of forecasting day’s power generation using neural network and operating the intelligent panel cleaning mechanism using fuzzy tables. ANN forecasts the present day’s power generation pattern on an hourly basis. The actual generation is monitored in the same time period. At the end of the day, actual and forecasted power generation values are compared and Mean Absolute Percentage Error (MAPE) is calculated as per the following formula: MAPE=(100%)/n ?_(t=1)^n¦|(A_t-F_t)/A_t | , where A_t is the actual value, F_t is the forecast value, and n is the number of fitted points. Acceptable value of MAPE is defined as P %. Within N number of days, if the value of MAPE is more than P for M days, where M is the acceptable number of days when MAPE > P, the panel cleaning system is initiated. After N days, even if M is not reached, the cleaning is initiated. This ensures that continuous dust accumulation does not occur even if the MAPE values are within acceptable limit for many consecutive days. Once cleaning is initiated, the system refers fuzzy logic table F to determine the duration T for which cleaning is to be carried out. The fuzzy table F is defined between Tmax for Upper Acceptable Limit of MAPE (MAPE Upper Limit) and Tmin for Lower Acceptable Limit of MAPE (MAPE Lower Limit), with the values normalized between 0 and 1. The logic chooses the value of T from the fuzzy table F based on the degree of truth as a mathematical model of vagueness. The duration of cleaning T is split into the predetermined ratio T1: T2: T3.
This present invention guarantees automatic cleaning of the solar panels to ensure no loss in power generation due to dust/dirt or foreign particles accumulation. This invention proactively responds to significant changes in dust accumulation due to environment and operates automatically with no manual intervention during its lifetime. Artificial intelligence of the system improves its response as time progresses due to its machine learning feature applied on historical generation data. Consequently, the buildup of dust and debris are prevented thereby allowing the solar modules to generate power at full capacity.
Each of the appended claims defines a separate invention, which for infringement purposes is recognized as including equivalents to the various elements or limitations specified in the claims. Depending on the context, all references below to the "invention" may in some cases refer to certain specific embodiments only. In other cases, it will be recognized that references to the "invention" will refer to subject matter recited in one or more, but not necessarily all, of the claims.
Groupings of alternative elements or embodiments of the invention disclosed herein are not to be construed as limitations. Each group member can be referred to and claimed individually or in any combination with other members of the group or other elements found herein. One or more members of a group can be included in, or deleted from, a group for reasons of convenience and/or patentability. When any such inclusion or deletion occurs, the specification is herein deemed to contain the group as modified thus fulfilling the written description of all groups used in the appended claims.
It will be understood by those within the art that, in general, terms used herein, and especially in the appended claims (e.g., bodies of the appended claims) are generally intended as “open” terms (e.g., the term “including” should be interpreted as “including but not limited to,” the term “having” should be interpreted as “having at least,” the term “includes” should be interpreted as “includes but is not limited to,” etc.). It will be further understood by those within the art that if a specific number of an introduced claim recitation is intended, such an intent will be explicitly recited in the claim, and in the absence of such recitation no such intent is present. For example, as an aid to understanding, the following appended claims may contain usage of the introductory phrases “at least one” and “one or more” to introduce claim recitations. However, the use of such phrases should not be construed to imply that the introduction of a claim recitation by the indefinite articles “a” or “an” limits any particulars claim containing such introduced claim recitation to inventions containing only one such recitation, even when the same claim includes the introductory phrases “one or more” or “at least one” and indefinite articles such as “a” or “an” (e.g., “a” and/or “an” should typically be interpreted to mean “at least one” or “one or more”); the same holds true for the use of definite articles used to introduce claim recitations. In addition, even if a specific number of an introduced claim recitation is explicitly recited, those skilled in the art will recognize that such recitation should typically be interpreted to mean at least the recited number (e.g., the bare recitation of “two recitations,” without other modifiers, typically means at least two recitations, or two or more recitations). Furthermore, in those instances where a convention analogous to “at least one of A, B and C, etc.” is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., “a system having at least one of A, B and C” would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and/or A, B, and C together, etc.). In those instances, where a convention analogous to “at least one of A, B, or C, etc.” is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., “a system having at least one of A, B, or C” would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and/or A, B, and C together, etc.). It will be further understood by those within the art that virtually any disjunctive word and/or phrase presenting two or more alternative terms, whether in the description, claims, or drawings, should be understood to contemplate the possibilities of including one of the terms, either of the terms, or both terms. For example, the phrase “A or B” will be understood to include the possibilities of “A” or “B” or “A and B”.
The above description does not provide specific details of manufacture or design of the various components. Those of skill in the art are familiar with such details, and unless departures from those techniques are set out, techniques, known, related art or later developed designs and materials should be employed. Those in the art are capable of choosing suitable manufacturing and design details.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the present disclosure. It will be appreciated that several of the above-disclosed and other features and functions, or alternatives thereof, may be combined into other systems or applications. Various presently unforeseen or unanticipated alternatives, modifications, variations, or improvements therein may subsequently be made by those skilled in the art without departing from the scope of the present disclosure as encompassed by the following claims.
The claims, as originally presented and as they may be amended, encompass variations, alternatives, modifications, improvements, equivalents, and substantial equivalents of the embodiments and teachings disclosed herein, including those that are presently unforeseen or unappreciated, and that, for example, may arise from applicants/patentees and others.
While various aspects and embodiments have been disclosed herein, other aspects and embodiments will be apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, with the true scope and spirit being indicated by the following claims.

Claims:1. An autonomous system for monitoring, forecasting and operation of a dust cleaning device for photovoltaic panels comprising an automatic data processing system (18) operating artificial intelligence program (19) for determining as to when and how long to clean solar panel (1) by solar panel surface cleaning device, wherein the automatic data processing system (18) operates the panel cleaning device through the artificial intelligence program (19) comprising an artificial neural network (ANN) for forecasting and a fuzzy logic (FL) for determining the cleaning schedules.
2. The autonomous system for monitoring, forecasting and operation of a dust cleaning mechanism for photovoltaic panels as claimed in claim 1, wherein the automatic data processing system (18) includes computer system; the solar panel (1) includes a plurality of solar cells (2) and is inclined at an angle ? with respect to the horizontal surface that sun rays fall perpendicular to the panel (1), in which the angle ? is according to the latitude of the location.
3. The autonomous system for monitoring, forecasting and operation of a dust cleaning mechanism for photovoltaic panels as claimed in the claims 1 or 2, wherein the solar cells (2) are protected from environmental factors by a transparent glass (3) installed on the top surface thereof, in which the glass (3) has high light transmittance values that all the available light falls on the cells (2) with maximum intensity.
<
4. The autonomous system for monitoring, forecasting and operation of a dust cleaning mechanism for photovoltaic panels as claimed in the claims 1-3, wherein the solar panel surface cleaning device includes a pressurized air cum water jet header (4) installed close to the top surface of the panels (1), in which multitude of nozzles (5) provided on the header (4) supply water and air for cleaning the surface of the panel (1).
5. The autonomous system for monitoring, forecasting and operation of a dust cleaning mechanism for photovoltaic panels as claimed in the claims 1-4, wherein the header (4) comprises of two separate and concentric pipelines (6 and 7), in which first pipeline (6) carries water and the other pipeline (7) carries compressed air.
6. The autonomous system for monitoring, forecasting and operation of a dust cleaning mechanism for photovoltaic panels as claimed in the claims 1-5, wherein water required for this system is stored in a water tank (8) and water is filled into this tank (8) by a water pump (9) which supplies the water from the main water supply of the plant/factory through a pipeline (10).
7. The autonomous system for monitoring, forecasting and operation of a dust cleaning mechanism for photovoltaic panels as claimed in the claims 1-6, wherein compressed air at required pressure (> 5 bar) is stored in an air tank (11) and pressurized air is fed into the tank (11) through another pipeline (12) from the factory/plant compressed air system, alternatively an air compressor (13) feeds the tank (11).
8. The autonomous system for monitoring, forecasting and operation of a dust cleaning mechanism for photovoltaic panels as claimed in the claims 1-7, wherein water and air from their respective tanks (8 and 11) are sent forward towards the jet header (4) via another set of pipelines (14 and 15 respectively), in which water and air solenoid valves (16 and 17) restrict the flow of water/air.
9. The autonomous system for monitoring, forecasting and operation of a dust cleaning mechanism for photovoltaic panels as claimed in the claims 1-8, wherein the ANN forecasts the next day’s solar power generation values based on historical generation values with which it is trained and the program (19) refers fuzzy tables of the FL to determine the cleaning schedules, wherein input data to the ANN comprises of daily power generation data captured on hourly basis for the prior couple of years.
10. The autonomous system for monitoring, forecasting and operation of a dust cleaning mechanism for photovoltaic panels as claimed in the claims 1-9, wherein the system (18) activates the water and air solenoid valves (16 and 17 respectively) which allow the flow of water and air to the jet header (4) via multiple pipelines (20 and 21 respectively), in which the system (18) activates water solenoid valve (16)/air solenoid valve (17) for the duration determined by the program’s (19) fuzzy table.
11. The autonomous system for monitoring, forecasting and operation of a dust cleaning mechanism for photovoltaic panels as claimed in the claims 1-10, wherein the entire duration is divided into 3 sections, namely T1, T2, and T3 and the ratio T1: T2: T3 is predetermined; the system (18) switches on the air solenoid valve (17) for T1 duration, which sends pressurized jet of air over the panels (1) through the nozzles (5) which cleans them of superficial dust layers; for the next T2 duration, both solenoid valves (16 and 17) are switched on and pressurized water jet cleans the panels (1) during this phase, for T3 of the time, the air solenoid valve (17) is operated, in which compressed air jet flowing over the panels (1) during this phase removes the residual water droplets and dries the surface.